diff --git a/module-1/Advanced-Regex/your-code/.ipynb_checkpoints/main-checkpoint.ipynb b/module-1/Advanced-Regex/your-code/.ipynb_checkpoints/main-checkpoint.ipynb new file mode 100644 index 00000000..432397b4 --- /dev/null +++ b/module-1/Advanced-Regex/your-code/.ipynb_checkpoints/main-checkpoint.ipynb @@ -0,0 +1,455 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Advanced Regular Expressions Lab\n", + "\n", + "Complete the following set of exercises to solidify your knowledge of regular expressions." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import re" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 1. Use a regular expression to find and extract all vowels in the following text." + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "text = \"This is going to be a sentence with a good number of vowels in it.\"" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['i', 'i', 'o', 'i', 'o', 'e', 'a', 'e', 'e', 'e', 'i', 'a', 'o', 'o', 'u', 'e', 'o', 'o', 'e', 'i', 'i']\n" + ] + } + ], + "source": [ + "regex = re.findall('[aeiou]', text)\n", + "print(regex)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 2. Use a regular expression to find and extract all occurrences and tenses (singular and plural) of the word \"puppy\" in the text below." + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": {}, + "outputs": [], + "source": [ + "text2 = \"The puppy saw all the rest of the puppies playing and wanted to join them. I saw this and wanted a puppy of my own!\"" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "None\n", + "\n", + "None\n", + "\n" + ] + } + ], + "source": [ + "puppy_list = ['Puppy', 'puppy', 'Puppies', 'Puppies']\n", + "\n", + "a = re.search('Puppy',text2)\n", + "b = re.search('puppy',text2)\n", + "c = re.search('Puppies',text2)\n", + "d = re.search('puppies',text2)\n", + "\n", + "print(a)\n", + "print(b)\n", + "print(c)\n", + "print(d)\n", + "\n", + "#There are two occurences. 'puppy' and 'puppies'\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 3. Use a regular expression to find and extract all tenses (present and past) of the word \"run\" in the text below." + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [], + "source": [ + "text3 = \"I ran the relay race the only way I knew how to run it.\"" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "None\n", + "\n" + ] + } + ], + "source": [ + "\n", + "a = re.search('run',text3)\n", + "b = re.search('running',text3)\n", + "c = re.search('ran',text3)\n", + "\n", + "print(a)\n", + "print(b)\n", + "print(c)\n", + "\n", + "#there is an occurance of 'run' and 'ran'" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['I', 'ran', 'the', 'relay', 'race', 'the', 'only', 'way', 'I', 'knew', 'how', 'to', 'run', 'it.']\n" + ] + } + ], + "source": [ + "text3_split = text3.split(' ')\n", + "print(text3_split)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 4. Use a regular expression to find and extract all words that begin with the letter \"r\" from the previous text." + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "None\n" + ] + } + ], + "source": [ + "r_words_regex = re.compile('^r\\W')\n", + "match = r_words_regex.search(text3)\n", + "\n", + "print(match)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 5. Use a regular expression to find and substitute the letter \"i\" for the exclamation marks in the text below." + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": {}, + "outputs": [], + "source": [ + "text4 = \"Th!s !s a sentence w!th spec!al characters !n !t.\"" + ] + }, + { + "cell_type": "code", + "execution_count": 74, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Th!s !s a sentence w!th spec!al characters !n !t.\n" + ] + } + ], + "source": [ + "print(re.sub('i', '!', text4))\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 6. Use a regular expression to find and extract words longer than 4 characters in the text below." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "text = \"This sentence has words of varying lengths.\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 7. Use a regular expression to find and extract all occurrences of the letter \"b\", some letter(s), and then the letter \"t\" in the sentence below." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "text = \"I bet the robot couldn't beat the other bot with a bat, but instead it bit me.\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 8. Use a regular expression to find and extract all words that contain either \"ea\" or \"eo\" in them." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "text = \"During many of the peaks and troughs of history, the people living it didn't fully realize what was unfolding. But we all know we're navigating breathtaking history: Nearly every day could be — maybe will be — a book.\"\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 9. Use a regular expression to find and extract all the capitalized words in the text below individually." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "text = \"Teddy Roosevelt and Abraham Lincoln walk into a bar.\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 10. Use a regular expression to find and extract all the sets of consecutive capitalized words in the text above." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 11. Use a regular expression to find and extract all the quotes from the text below.\n", + "\n", + "*Hint: This one is a little more complex than the single quote example in the lesson because there are multiple quotes in the text.*" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "text = 'Roosevelt says to Lincoln, \"I will bet you $50 I can get the bartender to give me a free drink.\" Lincoln says, \"I am in!\"'\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 12. Use a regular expression to find and extract all the numbers from the text below." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "text = \"There were 30 students in the class. Of the 30 students, 14 were male and 16 were female. Only 10 students got A's on the exam.\"\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 13. Use a regular expression to find and extract all the social security numbers from the text below." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "text = \"\"\"\n", + "Henry's social security number is 876-93-2289 and his phone number is (847)789-0984.\n", + "Darlene's social security number is 098-32-5295 and her phone number is (987)222-0901.\n", + "\"\"\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 14. Use a regular expression to find and extract all the phone numbers from the text below." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 15. Use a regular expression to find and extract all the formatted numbers (both social security and phone) from the text below." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.3" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/module-1/Advanced-Regex/your-code/main.ipynb b/module-1/Advanced-Regex/your-code/main.ipynb index b898da50..9a348c00 100644 --- a/module-1/Advanced-Regex/your-code/main.ipynb +++ b/module-1/Advanced-Regex/your-code/main.ipynb @@ -11,7 +11,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 78, "metadata": {}, "outputs": [], "source": [ @@ -27,7 +27,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 79, "metadata": {}, "outputs": [], "source": [ @@ -36,10 +36,21 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] + "execution_count": 80, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['i', 'i', 'o', 'i', 'o', 'e', 'a', 'e', 'e', 'e', 'i', 'a', 'o', 'o', 'u', 'e', 'o', 'o', 'e', 'i', 'i']\n" + ] + } + ], + "source": [ + "regex = re.findall('[aeiou]', text)\n", + "print(regex)" + ] }, { "cell_type": "markdown", @@ -50,19 +61,44 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 81, "metadata": {}, "outputs": [], "source": [ - "text = \"The puppy saw all the rest of the puppies playing and wanted to join them. I saw this and wanted a puppy of my own!\"" + "text2 = \"The puppy saw all the rest of the puppies playing and wanted to join them. I saw this and wanted a puppy of my own!\"" ] }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] + "execution_count": 82, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "None\n", + "\n", + "None\n", + "\n" + ] + } + ], + "source": [ + "puppy_list = ['Puppy', 'puppy', 'Puppies', 'Puppies']\n", + "\n", + "a = re.search('Puppy',text2)\n", + "b = re.search('puppy',text2)\n", + "c = re.search('Puppies',text2)\n", + "d = re.search('puppies',text2)\n", + "\n", + "print(a)\n", + "print(b)\n", + "print(c)\n", + "print(d)\n", + "\n", + "#There are two occurences. 'puppy' and 'puppies'\n" + ] }, { "cell_type": "markdown", @@ -73,19 +109,59 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 94, "metadata": {}, "outputs": [], "source": [ - "text = \"I ran the relay race the only way I knew how to run it.\"" + "text3 = \"I ran the relay race the only way I knew how to run it.\"" ] }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] + "execution_count": 85, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "None\n", + "\n" + ] + } + ], + "source": [ + "\n", + "a = re.search('run',text3)\n", + "b = re.search('running',text3)\n", + "c = re.search('ran',text3)\n", + "\n", + "print(a)\n", + "print(b)\n", + "print(c)\n", + "\n", + "#there is an occurance of 'run' and 'ran'\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 86, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['I', 'ran', 'the', 'relay', 'race', 'the', 'only', 'way', 'I', 'knew', 'how', 'to', 'run', 'it.']\n" + ] + } + ], + "source": [ + "text3_split = text3.split(' ')\n", + "print(text3_split)" + ] }, { "cell_type": "markdown", @@ -96,10 +172,24 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] + "execution_count": 95, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['r', 'r', 'r', 'r']" + ] + }, + "execution_count": 95, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#error\n", + "re.findall('r+', text3)\n" + ] }, { "cell_type": "markdown", @@ -110,19 +200,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 72, "metadata": {}, "outputs": [], "source": [ - "text = \"Th!s !s a sentence w!th spec!al characters !n !t.\"" + "text4 = \"Th!s !s a sentence w!th spec!al characters !n !t.\"" ] }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] + "execution_count": 74, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Th!s !s a sentence w!th spec!al characters !n !t.\n" + ] + } + ], + "source": [ + "print(re.sub('i', '!', text4))\n" + ] }, { "cell_type": "markdown", @@ -349,7 +449,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.0" + "version": "3.8.3" } }, "nbformat": 4, diff --git a/module-1/List-Comprehension/your-code/.ipynb_checkpoints/main-checkpoint.ipynb b/module-1/List-Comprehension/your-code/.ipynb_checkpoints/main-checkpoint.ipynb new file mode 100644 index 00000000..c8dad81f --- /dev/null +++ b/module-1/List-Comprehension/your-code/.ipynb_checkpoints/main-checkpoint.ipynb @@ -0,0 +1,215 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# List Comprehensions\n", + "\n", + "Complete the following set of exercises to solidify your knowledge of list comprehensions." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "import os;" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 1. Use a list comprehension to create and print a list of consecutive integers starting with 1 and ending with 50." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 2. Use a list comprehension to create and print a list of even numbers starting with 2 and ending with 200." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 3. Use a list comprehension to create and print a list containing all elements of the 10 x 4 array below." + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "a = [[0.84062117, 0.48006452, 0.7876326 , 0.77109654],\n", + " [0.44409793, 0.09014516, 0.81835917, 0.87645456],\n", + " [0.7066597 , 0.09610873, 0.41247947, 0.57433389],\n", + " [0.29960807, 0.42315023, 0.34452557, 0.4751035 ],\n", + " [0.17003563, 0.46843998, 0.92796258, 0.69814654],\n", + " [0.41290051, 0.19561071, 0.16284783, 0.97016248],\n", + " [0.71725408, 0.87702738, 0.31244595, 0.76615487],\n", + " [0.20754036, 0.57871812, 0.07214068, 0.40356048],\n", + " [0.12149553, 0.53222417, 0.9976855 , 0.12536346],\n", + " [0.80930099, 0.50962849, 0.94555126, 0.33364763]];" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 4. Add a condition to the list comprehension above so that only values greater than or equal to 0.5 are printed." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 5. Use a list comprehension to create and print a list containing all elements of the 5 x 2 x 3 array below." + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [], + "source": [ + "b = [[[0.55867166, 0.06210792, 0.08147297],\n", + " [0.82579068, 0.91512478, 0.06833034]],\n", + "\n", + " [[0.05440634, 0.65857693, 0.30296619],\n", + " [0.06769833, 0.96031863, 0.51293743]],\n", + "\n", + " [[0.09143215, 0.71893382, 0.45850679],\n", + " [0.58256464, 0.59005654, 0.56266457]],\n", + "\n", + " [[0.71600294, 0.87392666, 0.11434044],\n", + " [0.8694668 , 0.65669313, 0.10708681]],\n", + "\n", + " [[0.07529684, 0.46470767, 0.47984544],\n", + " [0.65368638, 0.14901286, 0.23760688]]];" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 6. Add a condition to the list comprehension above so that the last value in each subarray is printed, but only if it is less than or equal to 0.5." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 7. Use a list comprehension to select and print the names of all CSV files in the */data* directory." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Bonus" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Try to solve these katas using list comprehensions." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**Easy**\n", + "- [Insert values](https://www.codewars.com/kata/invert-values)\n", + "- [Sum Square(n)](https://www.codewars.com/kata/square-n-sum)\n", + "- [Digitize](https://www.codewars.com/kata/digitize)\n", + "- [List filtering](https://www.codewars.com/kata/list-filtering)\n", + "- [Arithmetic list](https://www.codewars.com/kata/541da001259d9ca85d000688)\n", + "\n", + "**Medium**\n", + "- [Multiples of 3 or 5](https://www.codewars.com/kata/514b92a657cdc65150000006)\n", + "- [Count of positives / sum of negatives](https://www.codewars.com/kata/count-of-positives-slash-sum-of-negatives)\n", + "- [Categorize new member](https://www.codewars.com/kata/5502c9e7b3216ec63c0001aa)\n", + "\n", + "**Advanced**\n", + "- [Queue time counter](https://www.codewars.com/kata/queue-time-counter)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.3" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/module-1/List-Comprehension/your-code/main.ipynb b/module-1/List-Comprehension/your-code/main.ipynb index cf7d3ad4..aea15e07 100644 --- a/module-1/List-Comprehension/your-code/main.ipynb +++ b/module-1/List-Comprehension/your-code/main.ipynb @@ -27,10 +27,21 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1, 6, 7, 8, 9, 9, 23, 44, 45, 50]\n" + ] + } + ], + "source": [ + "int_list = [1,6,7,8,9,9,23,44,45,50]\n", + "print(list1)" + ] }, { "cell_type": "markdown", @@ -207,7 +218,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.2" + "version": "3.8.3" } }, "nbformat": 4, diff --git a/module-1/String-Operations/your-code/.ipynb_checkpoints/main-checkpoint.ipynb b/module-1/String-Operations/your-code/.ipynb_checkpoints/main-checkpoint.ipynb new file mode 100644 index 00000000..b5ab0825 --- /dev/null +++ b/module-1/String-Operations/your-code/.ipynb_checkpoints/main-checkpoint.ipynb @@ -0,0 +1,300 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Before your start:\n", + "- Read the README.md file\n", + "- Comment as much as you can and use the resources in the README.md file\n", + "- Happy learning!" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import re " + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Challenge 1 - Combining Strings\n", + "\n", + "Combining strings is an important skill to acquire. There are multiple ways of combining strings in Python, as well as combining strings with variables. We will explore this in the first challenge. In the cell below, combine the strings in the list and add spaces between the strings (do not add a space after the last string). Insert a period after the last string." + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Durante un tiempo no estuvo segura de si su marido era su marido.\n" + ] + } + ], + "source": [ + "str_list = ['Durante', 'un', 'tiempo', 'no', 'estuvo', 'segura', 'de', 'si', 'su', 'marido', 'era', 'su', 'marido']\n", + "# Your code here:\n", + "\n", + "#creating a new variable the joins the list element sinto a string using the join function\n", + "str_foods = ' '.join(str_list) \n", + "\n", + "#Add a '.' at the end of the string list\n", + "str_foods = str_foods + \".\"\n", + "\n", + "\n", + "print(str_foods) #printing the new string\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "In the cell below, use the list of strings to create a grocery list. Start the list with the string `Grocery list: ` and include a comma and a space between each item except for the last one. Include a period at the end. Only include foods in the list that start with the letter 'b' and ensure all foods are lower case." + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['bananas', 'chocolate', 'bread', 'diapers', 'ice cream', 'brownie mix', 'broccoli']\n", + "bananas, bread, brownie mix, broccoli\n", + "Grocery List: bananas, bread, brownie mix, broccoli.\n" + ] + } + ], + "source": [ + "food_list = ['Bananas', 'Chocolate', 'bread', 'diapers', 'Ice Cream', 'Brownie Mix', 'broccoli']\n", + "# Your code here:\n", + "\n", + "#convert list to lower case using .lower() function on each element using a for loop\n", + "lower_list = [x.lower() for x in food_list]\n", + "print(lower_list) #print to test\n", + "\n", + "\n", + "#only include foods in the list that start with the letter 'b'\n", + "food_list_b = []\n", + "for food in lower_list:\n", + " if food.startswith('b'): \n", + " food_list_b.append(food)\n", + "\n", + "\n", + "#creating a new variable the joins the list elements into a string using the join function, whilst putting commas between them\n", + "str_food_list = ', '.join(food_list_b)\n", + "print(str_food_list) #print to test\n", + "\n", + "#Add/concatenatethe 'Grocery List:' part of the string at the beggining and '.' at the end\n", + "final_str_list = 'Grocery List:' + ' ' + str_food_list + '.' \n", + "\n", + "\n", + "\n", + "print(final_str_list)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "In the cell below, write a function that computes the area of a circle using its radius. Compute the area of the circle and insert the radius and the area between the two strings. Make sure to include spaces between the variable and the strings. \n", + "\n", + "Note: You can use the techniques we have learned so far or use f-strings. F-strings allow us to embed code inside strings. You can read more about f-strings [here](https://www.python.org/dev/peps/pep-0498/)." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "import math\n", + "\n", + "string1 = \"The area of the circle with radius:\"\n", + "string2 = \"is:\"\n", + "radius = 4.5\n", + "\n", + "def area(x, pi = math.pi):\n", + " \"\"\"\n", + " This function takes a radius and returns the area of a circle. \n", + " We also pass a default value for pi.\n", + " \n", + " Input: Float (and default value for pi)\n", + " Output: Float\n", + " \n", + " Sample input: 5.0\n", + " Sample Output: 78.53981633\n", + " \"\"\"\n", + " \n", + " # Your code here:\n", + " \n", + " \n", + "# Your output string here:" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Challenge 2 - Splitting Strings\n", + "\n", + "We have first looked at combining strings into one long string. There are times where we need to do the opposite and split the string into smaller components for further analysis. \n", + "\n", + "In the cell below, split the string into a list of strings using the space delimiter. Count the frequency of each word in the string in a dictionary. Strip the periods, line breaks and commas from the text. Make sure to remove empty strings from your dictionary." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "poem = \"\"\"Some say the world will end in fire,\n", + "Some say in ice.\n", + "From what I’ve tasted of desire\n", + "I hold with those who favor fire.\n", + "But if it had to perish twice,\n", + "I think I know enough of hate\n", + "To say that for destruction ice\n", + "Is also great\n", + "And would suffice.\"\"\"\n", + "\n", + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "In the cell below, find all the words that appear in the text and do not appear in the blacklist. You must parse the string but can choose any data structure you wish for the words that do not appear in the blacklist. Remove all non letter characters and convert all words to lower case." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "blacklist = ['and', 'as', 'an', 'a', 'the', 'in', 'it']\n", + "\n", + "poem = \"\"\"I was angry with my friend; \n", + "I told my wrath, my wrath did end.\n", + "I was angry with my foe: \n", + "I told it not, my wrath did grow. \n", + "\n", + "And I waterd it in fears,\n", + "Night & morning with my tears: \n", + "And I sunned it with smiles,\n", + "And with soft deceitful wiles. \n", + "\n", + "And it grew both day and night. \n", + "Till it bore an apple bright. \n", + "And my foe beheld it shine,\n", + "And he knew that it was mine. \n", + "\n", + "And into my garden stole, \n", + "When the night had veild the pole; \n", + "In the morning glad I see; \n", + "My foe outstretched beneath the tree.\"\"\"\n", + "\n", + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Challenge 3 - Regular Expressions\n", + "\n", + "Sometimes, we would like to perform more complex manipulations of our string. This is where regular expressions come in handy. In the cell below, return all characters that are upper case from the string specified below." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "poem = \"\"\"The apparition of these faces in the crowd;\n", + "Petals on a wet, black bough.\"\"\"\n", + "\n", + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "In the cell below, filter the list provided and return all elements of the list containing a number. To filter the list, use the `re.search` function. Check if the function does not return `None`. You can read more about the `re.search` function [here](https://docs.python.org/3/library/re.html)." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "data = ['123abc', 'abc123', 'JohnSmith1', 'ABBY4', 'JANE']\n", + "\n", + "# Your code here:\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Bonus Challenge - Regular Expressions II\n", + "\n", + "In the cell below, filter the list provided to keep only strings containing at least one digit and at least one lower case letter. As in the previous question, use the `re.search` function and check that the result is not `None`.\n", + "\n", + "To read more about regular expressions, check out [this link](https://developers.google.com/edu/python/regular-expressions)." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "data = ['123abc', 'abc123', 'JohnSmith1', 'ABBY4', 'JANE']\n", + "# Your code here:\n" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.3" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/module-1/String-Operations/your-code/main.ipynb b/module-1/String-Operations/your-code/main.ipynb index 87c99646..e013e42e 100644 --- a/module-1/String-Operations/your-code/main.ipynb +++ b/module-1/String-Operations/your-code/main.ipynb @@ -12,11 +12,11 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ - "import re" + "import re " ] }, { @@ -30,13 +30,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 50, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Durante un tiempo no estuvo segura de si su marido era su marido.\n" + ] + } + ], "source": [ "str_list = ['Durante', 'un', 'tiempo', 'no', 'estuvo', 'segura', 'de', 'si', 'su', 'marido', 'era', 'su', 'marido']\n", "# Your code here:\n", - "\n" + "\n", + "#creating a new variable the joins the list element sinto a string using the join function\n", + "str_foods = ' '.join(str_list) \n", + "\n", + "#Add a '.' at the end of the string list\n", + "str_foods = str_foods + \".\"\n", + "\n", + "\n", + "print(str_foods) #printing the new string\n" ] }, { @@ -48,13 +64,45 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 49, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['bananas', 'chocolate', 'bread', 'diapers', 'ice cream', 'brownie mix', 'broccoli']\n", + "bananas, bread, brownie mix, broccoli\n", + "Grocery List: bananas, bread, brownie mix, broccoli.\n" + ] + } + ], "source": [ "food_list = ['Bananas', 'Chocolate', 'bread', 'diapers', 'Ice Cream', 'Brownie Mix', 'broccoli']\n", "# Your code here:\n", - "\n" + "\n", + "#convert list to lower case using .lower() function on each element using a for loop\n", + "lower_list = [x.lower() for x in food_list]\n", + "print(lower_list) #print to test\n", + "\n", + "\n", + "#only include foods in the list that start with the letter 'b'\n", + "food_list_b = []\n", + "for food in lower_list:\n", + " if food.startswith('b'): \n", + " food_list_b.append(food)\n", + "\n", + "\n", + "#creating a new variable the joins the list elements into a string using the join function, whilst putting commas between them\n", + "str_food_list = ', '.join(food_list_b)\n", + "print(str_food_list) #print to test\n", + "\n", + "#Add/concatenatethe 'Grocery List:' part of the string at the beggining and '.' at the end\n", + "final_str_list = 'Grocery List:' + ' ' + str_food_list + '.' \n", + "\n", + "\n", + "\n", + "print(final_str_list)" ] }, { @@ -63,14 +111,23 @@ "source": [ "In the cell below, write a function that computes the area of a circle using its radius. Compute the area of the circle and insert the radius and the area between the two strings. Make sure to include spaces between the variable and the strings. \n", "\n", - "Note: You can use the techniques we have learned so far or use f-strings. F-strings allow us to embed code inside strings. You can read more about f-strings [here](https://www.python.org/dev/peps/pep-0498/)." + "Note: You can use the techniques we have learned so far or use f-strings. F-strings allow us to embed code inside strings. You can read more about f-strings [here](https://www.python.org/dev/peps/pep-049/)8." ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 93, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Enter float radius value:5\n", + "['The area of the circle with radius:', 5.0, 'is:', 246.74011002723395]\n" + ] + } + ], "source": [ "import math\n", "\n", @@ -91,9 +148,22 @@ " \"\"\"\n", " \n", " # Your code here:\n", + " # calc pi * radius ** 2\n", + " \n", + " #take input from the user and convert it into a float data type\n", + " x = float(input(\"Enter float radius value:\"))\n", + " \n", + " #to calculate the area of a circle, multiply the user input (x in this case) by pi and then square it\n", + " circ_area = (x * pi) ** 2\n", + " output_list = [string1, x, string2, circ_area]\n", + " print(output_list)\n", + " \n", " \n", + " return\n", " \n", - "# Your output string here:" + "# Your output string here:\n", + "\n", + "area(5.0)\n" ] }, { @@ -244,7 +314,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.2" + "version": "3.8.3" } }, "nbformat": 4, diff --git a/module-2/Descriptive-Stats/your-code/.ipynb_checkpoints/main-checkpoint.ipynb b/module-2/Descriptive-Stats/your-code/.ipynb_checkpoints/main-checkpoint.ipynb new file mode 100644 index 00000000..1febdff1 --- /dev/null +++ b/module-2/Descriptive-Stats/your-code/.ipynb_checkpoints/main-checkpoint.ipynb @@ -0,0 +1,609 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Understanding Descriptive Statistics\n", + "\n", + "Import the necessary libraries here:" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "# Libraries\n", + "\n", + "import random" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Challenge 1\n", + "#### 1.- Define a function that simulates rolling a dice 10 times. Save the information in a dataframe.\n", + "**Hint**: you can use the *choices* function from module *random* to help you with the simulation." + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[3]" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# your code here\n", + "\n", + "\n", + "def dice(n):\n", + " rolls = []\n", + " for i in range(n):\n", + " two_dice = random.randint(1, 6) + random.randint(1, 6)\n", + " rolls.append(two_dice)\n", + " return rolls\n", + "\n", + "dice(1)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[8, 7]" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dice(2)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 2.- Plot the results sorted by value." + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here\n", + "\n", + "\n", + "def dicesort(n):\n", + " rolls = []\n", + " for i in range(n):\n", + " two_dice = random.randint(1, 6) + random.randint(1, 6)\n", + " rolls.append(two_dice)\n", + " return sorted(rolls)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[5, 5, 7, 7, 8]" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dicesort(5)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 3.- Calculate the frequency distribution and plot it. What is the relation between this plot and the plot above? Describe it with words." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here\n", + "\n", + "###prev matplotlib code from lab to try\n", + "x = np.arange(0,100)\n", + "y = x*2\n", + "z = x**2\n", + "\n", + "fig, [ax1, ax2] = plt.subplots(nrows=1, ncols=2) \n", + "ax1.plot(x,y, color='red', linewidth=3)\n", + "ax1.set_title('XY') \n", + "\n", + "\n", + "ax2.plot(x,z, color='red', linewidth=3)\n", + "ax2.set_title('XZ') \n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "your comments here\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Challenge 2\n", + "Now, using the dice results obtained in *challenge 1*, your are going to define some functions that will help you calculate the mean of your data in two different ways, the median and the four quartiles. \n", + "\n", + "#### 1.- Define a function that computes the mean by summing all the observations and dividing by the total number of observations. You are not allowed to use any methods or functions that directly calculate the mean value. " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 2.- First, calculate the frequency distribution. Then, calculate the mean using the values of the frequency distribution you've just computed. You are not allowed to use any methods or functions that directly calculate the mean value. " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 3.- Define a function to calculate the median. You are not allowed to use any methods or functions that directly calculate the median value. \n", + "**Hint**: you might need to define two computation cases depending on the number of observations used to calculate the median." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 4.- Define a function to calculate the four quartiles. You can use the function you defined above to compute the median but you are not allowed to use any methods or functions that directly calculate the quartiles. " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Challenge 3\n", + "Read the csv `roll_the_dice_hundred.csv` from the `data` folder.\n", + "#### 1.- Sort the values and plot them. What do you see?" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "your comments here\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 2.- Using the functions you defined in *challenge 2*, calculate the mean value of the hundred dice rolls." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 3.- Now, calculate the frequency distribution.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 4.- Plot the histogram. What do you see (shape, values...) ? How can you connect the mean value to the histogram? " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "your comments here\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 5.- Read the `roll_the_dice_thousand.csv` from the `data` folder. Plot the frequency distribution as you did before. Has anything changed? Why do you think it changed?" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "your comments here\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Challenge 4\n", + "In the `data` folder of this repository you will find three different files with the prefix `ages_population`. These files contain information about a poll answered by a thousand people regarding their age. Each file corresponds to the poll answers in different neighbourhoods of Barcelona.\n", + "\n", + "#### 1.- Read the file `ages_population.csv`. Calculate the frequency distribution and plot it as we did during the lesson. Try to guess the range in which the mean and the standard deviation will be by looking at the plot. " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 2.- Calculate the exact mean and standard deviation and compare them with your guesses. Do they fall inside the ranges you guessed?" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "your comments here\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 3.- Now read the file `ages_population2.csv` . Calculate the frequency distribution and plot it." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 4.- What do you see? Is there any difference with the frequency distribution in step 1?" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "your comments here\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 5.- Calculate the mean and standard deviation. Compare the results with the mean and standard deviation in step 2. What do you think?" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "your comments here\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Challenge 5\n", + "Now is the turn of `ages_population3.csv`.\n", + "\n", + "#### 1.- Read the file `ages_population3.csv`. Calculate the frequency distribution and plot it." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 2.- Calculate the mean and standard deviation. Compare the results with the plot in step 1. What is happening?" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "your comments here\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 3.- Calculate the four quartiles. Use the results to explain your reasoning for question in step 2. How much of a difference is there between the median and the mean?" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "your comments here\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 4.- Calculate other percentiles that might be useful to give more arguments to your reasoning." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "your comments here\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Bonus challenge\n", + "Compare the information about the three neighbourhoods. Prepare a report about the three of them. Remember to find out which are their similarities and their differences backing your arguments in basic statistics." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# your code here" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "your comments here\n", + "\"\"\"" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.3" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/module-2/Descriptive-Stats/your-code/main.ipynb b/module-2/Descriptive-Stats/your-code/main.ipynb index a0a5b669..580d62ce 100644 --- a/module-2/Descriptive-Stats/your-code/main.ipynb +++ b/module-2/Descriptive-Stats/your-code/main.ipynb @@ -11,11 +11,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ - "# Libraries" + "# Libraries\n", + "\n", + "import random" ] }, { @@ -29,11 +31,90 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "[3]" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "# your code here\n", + "\n", + "##need to multiple no of rolls by 10\n", + "def dice(n):\n", + " rolls = []\n", + " for i in range(n):\n", + " two_dice = random.randint(1, 6) + random.randint(1, 6)\n", + " rolls.append(two_dice)\n", + " return rolls\n", + "\n", + "dice(1)" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Number is: 6\n", + "Number is: 6\n", + "Number is: 5\n", + "Number is: 2\n", + "Number is: 2\n", + "Number is: 1\n", + "Number is: 2\n", + "Number is: 6\n", + "Number is: 6\n", + "Number is: 1\n", + "Number is: 1\n" + ] + } + ], + "source": [ + "from random import randint\n", + "\n", + "def roll_dice():\n", + " print(f\"Number is: {randint(1,6)}\")\n", + "\n", + "# Do this to simulate once\n", + "roll_dice() \n", + "\n", + "# Do this to simulate multiple times\n", + "whatever = 10 # Put the number of times you want to simulate here\n", + "for number in range(0,whatever):\n", + " roll_dice()" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[8, 7]" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dice(2)" ] }, { @@ -45,11 +126,39 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ - "# your code here" + "# your code here\n", + "\n", + "\n", + "def dicesort(n):\n", + " rolls = []\n", + " for i in range(n):\n", + " two_dice = random.randint(1, 6) + random.randint(1, 6)\n", + " rolls.append(two_dice)\n", + " return sorted(rolls)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[5, 5, 7, 7, 8]" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dicesort(5)" ] }, { @@ -65,7 +174,23 @@ "metadata": {}, "outputs": [], "source": [ - "# your code here" + "# your code here\n", + "\n", + "###prev matplotlib code from lab to try\n", + "x = np.arange(0,100)\n", + "y = x*2\n", + "z = x**2\n", + "\n", + "fig, [ax1, ax2] = plt.subplots(nrows=1, ncols=2) \n", + "ax1.plot(x,y, color='red', linewidth=3)\n", + "ax1.set_title('XY') \n", + "\n", + "\n", + "ax2.plot(x,z, color='red', linewidth=3)\n", + "ax2.set_title('XZ') \n", + "\n", + "\n", + "plt.show()" ] }, { @@ -91,11 +216,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, - "outputs": [], + "outputs": [ + { + "ename": "TypeError", + "evalue": "unsupported operand type(s) for *: 'NoneType' and 'int'", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 6\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mrolls\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 7\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 8\u001b[1;33m \u001b[0mdice\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[1;32m\u001b[0m in \u001b[0;36mdice\u001b[1;34m(n)\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mn\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0mtwo_dice\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mrandom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrandint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m6\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mrandom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrandint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m6\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 5\u001b[1;33m \u001b[0mrolls\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtwo_dice\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m*\u001b[0m \u001b[1;36m10\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 6\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mrolls\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 7\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mTypeError\u001b[0m: unsupported operand type(s) for *: 'NoneType' and 'int'" + ] + } + ], "source": [ - "# your code here" + "\n", + "def dice(n):\n", + " rolls = []\n", + " for i in range(n):\n", + " two_dice = random.randint(1, 6) + random.randint(1, 6)\n", + " rolls.append(two_dice)\n", + " return rolls\n", + "\n", + "dice(1)" ] }, { @@ -500,9 +646,9 @@ ], "metadata": { "kernelspec": { - "display_name": "ironhack-3.7", + "display_name": "Python 3", "language": "python", - "name": "ironhack-3.7" + "name": "python3" }, "language_info": { "codemirror_mode": { @@ -514,7 +660,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.8.3" } }, "nbformat": 4, diff --git a/module-2/Intro-Scipy/your-code/.ipynb_checkpoints/main-checkpoint.ipynb b/module-2/Intro-Scipy/your-code/.ipynb_checkpoints/main-checkpoint.ipynb new file mode 100644 index 00000000..b8bd2f21 --- /dev/null +++ b/module-2/Intro-Scipy/your-code/.ipynb_checkpoints/main-checkpoint.ipynb @@ -0,0 +1,345 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Before your start:\n", + "- Read the README.md file\n", + "- Comment as much as you can and use the resources (README.md file)\n", + "- Happy learning!" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "#import numpy and pandas\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Challenge 1 - The `stats` Submodule\n", + "\n", + "This submodule contains statistical functions for conducting hypothesis tests, producing various distributions and other useful tools. Let's examine this submodule using the KickStarter dataset. Load the data using Ironhack's database (db: kickstarter, table: projects)." + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Now print the `head` function to examine the dataset." + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Import the `mode` function from `scipy.stats` and find the mode of the `country` and `currency` column." + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The trimmed mean is a function that computes the mean of the data with observations removed. The most common way to compute a trimmed mean is by specifying a percentage and then removing elements from both ends. However, we can also specify a threshold on both ends. The goal of this function is to create a more robust method of computing the mean that is less influenced by outliers. SciPy contains a function called `tmean` for computing the trimmed mean. \n", + "\n", + "In the cell below, import the `tmean` function and then find the 75th percentile of the `goal` column. Compute the trimmed mean between 0 and the 75th percentile of the column. Read more about the `tmean` function [here](https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.tmean.html#scipy.stats.tmean)." + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### SciPy contains various statistical tests. One of the tests is Fisher's exact test. This test is used for contingency tables. \n", + "\n", + "The test originates from the \"Lady Tasting Tea\" experiment. In 1935, Fisher published the results of the experiment in his book. The experiment was based on a claim by Muriel Bristol that she can taste whether tea or milk was first poured into the cup. Fisher devised this test to disprove her claim. The null hypothesis is that the treatments do not affect outcomes, while the alternative hypothesis is that the treatment does affect outcome. To read more about Fisher's exact test, see:\n", + "\n", + "* [Wikipedia's explanation](http://b.link/test61)\n", + "* [A cool deep explanation](http://b.link/handbook47)\n", + "* [An explanation with some important Fisher's considerations](http://b.link/significance76)\n", + "\n", + "Let's perform Fisher's exact test on our KickStarter data. We intend to test the hypothesis that the choice of currency has an impact on meeting the pledge goal. We'll start by creating two derived columns in our dataframe. The first will contain 1 if the amount of money in `usd_pledged_real` is greater than the amount of money in `usd_goal_real`. We can compute this by using the `np.where` function. If the amount in one column is greater than the other, enter a value of 1, otherwise enter a value of zero. Add this column to the dataframe and name it `goal_met`." + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Next, create a column that checks whether the currency of the project is in US Dollars. Create a column called `usd` using the `np.where` function where if the currency is US Dollars, assign a value of 1 to the row and 0 otherwise." + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Now create a contingency table using the `pd.crosstab` function in the cell below to compare the `goal_met` and `usd` columns." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Import the `fisher_exact` function from `scipy.stats` and conduct the hypothesis test on the contingency table that you have generated above. You can read more about the `fisher_exact` function [here](https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.fisher_exact.html#scipy.stats.fisher_exact). The output of the function should be the odds ratio and the p-value. The p-value will provide you with the outcome of the test." + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Challenge 2 - The `interpolate` submodule\n", + "\n", + "This submodule allows us to interpolate between two points and create a continuous distribution based on the observed data.\n", + "\n", + "In the cell below, import the `interp1d` function and first take a sample of 10 rows from `kickstarter`. " + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Next, create a linear interpolation of the backers as a function of `usd_pledged_real`. Create a function `f` that generates a linear interpolation of backers as predicted by the amount of real pledged dollars." + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Now create a new variable called `x_new`. This variable will contain all integers between the minimum number of backers in our sample and the maximum number of backers. The goal here is to take the dataset that contains few obeservations due to sampling and fill all observations with a value using the interpolation function. \n", + "\n", + "Hint: one option is the `np.arange` function." + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Plot function f for all values of `x_new`. Run the code below." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# Run this code:\n", + "\n", + "%matplotlib inline\n", + "import matplotlib.pyplot as plt\n", + "\n", + "plt.plot(x_new, f(x_new))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Next create a function that will generate a cubic interpolation function. Name the function `g`." + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# Run this code:\n", + "\n", + "plt.plot(x_new, g(x_new))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Bonus Challenge - The Binomial Distribution\n", + "\n", + "The binomial distribution allows us to calculate the probability of k successes in n trials for a random variable with two possible outcomes (which we typically label success and failure). \n", + "\n", + "The probability of success is typically denoted by p and the probability of failure is denoted by 1-p.\n", + "\n", + "The `scipy.stats` submodule contains a `binom` function for computing the probabilites of a random variable with the binomial distribution. You may read more about the binomial distribution [here](http://b.link/binomial55)\n", + "\n", + "* In the cell below, compute the probability that a dice lands on 5 exactly 3 times in 8 tries.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "* Do a simulation for the last event: do a function that simulate 8 tries and return a 1 if the result is 5 exactly 3 times and 0 if not. Now launch your simulation." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "* Launch 10 simulations and represent the result in a bar plot. Now launch 1000 simulations and represent it. What do you see?" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.3" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/module-2/Intro-Scipy/your-code/main.ipynb b/module-2/Intro-Scipy/your-code/main.ipynb index d08aab8e..b8bd2f21 100644 --- a/module-2/Intro-Scipy/your-code/main.ipynb +++ b/module-2/Intro-Scipy/your-code/main.ipynb @@ -337,7 +337,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.2" + "version": "3.8.3" } }, "nbformat": 4, diff --git a/module-3/Data-Cleaning-Challenge/.ipynb_checkpoints/1- Scikit-Learn Clean and transform - Lecture Live code along-checkpoint.ipynb b/module-3/Data-Cleaning-Challenge/.ipynb_checkpoints/1- Scikit-Learn Clean and transform - Lecture Live code along-checkpoint.ipynb new file mode 100644 index 00000000..a4f1a569 --- /dev/null +++ b/module-3/Data-Cleaning-Challenge/.ipynb_checkpoints/1- Scikit-Learn Clean and transform - Lecture Live code along-checkpoint.ipynb @@ -0,0 +1,1943 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Intro to Data Cleaning & Preprocessing with Scikit Learn Transformers" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Data splitting" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [], + "source": [ + "iris = pd.read_csv(\"iris_codealong.csv\", index_col=0)" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmColorStemLengthCmSpecies
Id
15.13.51.40.2purple3.636364Iris-setosa
24.93.01.40.2yellowNaNIris-setosa
34.73.21.30.2blue2.727273Iris-setosa
44.63.11.50.2purpleNaNIris-setosa
55.03.61.40.2blue1.919192Iris-setosa
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Color \\\n", + "Id \n", + "1 5.1 3.5 1.4 0.2 purple \n", + "2 4.9 3.0 1.4 0.2 yellow \n", + "3 4.7 3.2 1.3 0.2 blue \n", + "4 4.6 3.1 1.5 0.2 purple \n", + "5 5.0 3.6 1.4 0.2 blue \n", + "\n", + " StemLengthCm Species \n", + "Id \n", + "1 3.636364 Iris-setosa \n", + "2 NaN Iris-setosa \n", + "3 2.727273 Iris-setosa \n", + "4 NaN Iris-setosa \n", + "5 1.919192 Iris-setosa " + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "150" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(iris)" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "SepalLengthCm 0\n", + "SepalWidthCm 0\n", + "PetalLengthCm 0\n", + "PetalWidthCm 0\n", + "Color 0\n", + "StemLengthCm 50\n", + "Species 0\n", + "dtype: int64" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris.isna().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Id\n", + "1 3.636364\n", + "2 NaN\n", + "3 2.727273\n", + "4 NaN\n", + "5 1.919192\n", + " ... \n", + "146 0.101010\n", + "147 NaN\n", + "148 3.434343\n", + "149 8.181818\n", + "150 NaN\n", + "Name: StemLengthCm, Length: 150, dtype: float64" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris['StemLengthCm']" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "SepalLengthCm float64\n", + "SepalWidthCm float64\n", + "PetalLengthCm float64\n", + "PetalWidthCm float64\n", + "Color object\n", + "StemLengthCm float64\n", + "Species object\n", + "dtype: object" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris.dtypes" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris['StemLengthCm'].hist(bins=100)" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris['StemLengthCm'].plot.box()" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "4.999999999999999" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris['StemLengthCm'].mean()" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmStemLengthCm
count150.000000150.000000150.000000150.000000100.000000
mean5.8433333.0540003.7586671.1986675.000000
std0.8280660.4335941.7644200.7631612.930454
min4.3000002.0000001.0000000.1000000.000000
25%5.1000002.8000001.6000000.3000002.500000
50%5.8000003.0000004.3500001.3000005.000000
75%6.4000003.3000005.1000001.8000007.500000
max7.9000004.4000006.9000002.50000010.000000
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm StemLengthCm\n", + "count 150.000000 150.000000 150.000000 150.000000 100.000000\n", + "mean 5.843333 3.054000 3.758667 1.198667 5.000000\n", + "std 0.828066 0.433594 1.764420 0.763161 2.930454\n", + "min 4.300000 2.000000 1.000000 0.100000 0.000000\n", + "25% 5.100000 2.800000 1.600000 0.300000 2.500000\n", + "50% 5.800000 3.000000 4.350000 1.300000 5.000000\n", + "75% 6.400000 3.300000 5.100000 1.800000 7.500000\n", + "max 7.900000 4.400000 6.900000 2.500000 10.000000" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.model_selection import train_test_split\n", + "train_set, test_set = train_test_split(iris, test_size=0.2, random_state=123)" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmColorStemLengthCmSpecies
Id
1317.42.86.11.9purpleNaNIris-virginica
1206.02.25.01.5purple4.141414Iris-virginica
304.73.21.60.2blue5.757576Iris-setosa
15.13.51.40.2purple3.636364Iris-setosa
636.02.24.01.0red8.989899Iris-versicolor
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Color \\\n", + "Id \n", + "131 7.4 2.8 6.1 1.9 purple \n", + "120 6.0 2.2 5.0 1.5 purple \n", + "30 4.7 3.2 1.6 0.2 blue \n", + "1 5.1 3.5 1.4 0.2 purple \n", + "63 6.0 2.2 4.0 1.0 red \n", + "\n", + " StemLengthCm Species \n", + "Id \n", + "131 NaN Iris-virginica \n", + "120 4.141414 Iris-virginica \n", + "30 5.757576 Iris-setosa \n", + "1 3.636364 Iris-setosa \n", + "63 8.989899 Iris-versicolor " + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_set.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmStemLengthCm
count120.000000120.000000120.000000120.00000080.000000
mean5.8691673.0408333.8208331.2233334.830808
std0.8129000.4404921.7288410.7425522.980444
min4.4000002.0000001.0000000.1000000.000000
25%5.1000002.8000001.6000000.4000002.297980
50%5.8000003.0000004.3500001.3000004.696970
75%6.4000003.3000005.1000001.8000007.601010
max7.9000004.4000006.9000002.50000010.000000
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm StemLengthCm\n", + "count 120.000000 120.000000 120.000000 120.000000 80.000000\n", + "mean 5.869167 3.040833 3.820833 1.223333 4.830808\n", + "std 0.812900 0.440492 1.728841 0.742552 2.980444\n", + "min 4.400000 2.000000 1.000000 0.100000 0.000000\n", + "25% 5.100000 2.800000 1.600000 0.400000 2.297980\n", + "50% 5.800000 3.000000 4.350000 1.300000 4.696970\n", + "75% 6.400000 3.300000 5.100000 1.800000 7.601010\n", + "max 7.900000 4.400000 6.900000 2.500000 10.000000" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_set.describe()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Do you see anything rare?" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "Int64Index: 120 entries, 131 to 110\n", + "Data columns (total 7 columns):\n", + "SepalLengthCm 120 non-null float64\n", + "SepalWidthCm 120 non-null float64\n", + "PetalLengthCm 120 non-null float64\n", + "PetalWidthCm 120 non-null float64\n", + "Color 120 non-null object\n", + "StemLengthCm 80 non-null float64\n", + "Species 120 non-null object\n", + "dtypes: float64(5), object(2)\n", + "memory usage: 7.5+ KB\n" + ] + } + ], + "source": [ + "train_set.info()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Now we will drop the text column so all of them are numerical." + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmColorStemLengthCm
Id
1317.42.86.11.9purpleNaN
1206.02.25.01.5purple4.141414
304.73.21.60.2blue5.757576
15.13.51.40.2purple3.636364
636.02.24.01.0red8.989899
.....................
185.13.51.40.3purple4.545455
995.12.53.01.1red9.898990
675.63.04.51.5blue4.949495
1276.22.84.81.8yellowNaN
1107.23.66.12.5purple0.606061
\n", + "

120 rows × 6 columns

\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Color \\\n", + "Id \n", + "131 7.4 2.8 6.1 1.9 purple \n", + "120 6.0 2.2 5.0 1.5 purple \n", + "30 4.7 3.2 1.6 0.2 blue \n", + "1 5.1 3.5 1.4 0.2 purple \n", + "63 6.0 2.2 4.0 1.0 red \n", + ".. ... ... ... ... ... \n", + "18 5.1 3.5 1.4 0.3 purple \n", + "99 5.1 2.5 3.0 1.1 red \n", + "67 5.6 3.0 4.5 1.5 blue \n", + "127 6.2 2.8 4.8 1.8 yellow \n", + "110 7.2 3.6 6.1 2.5 purple \n", + "\n", + " StemLengthCm \n", + "Id \n", + "131 NaN \n", + "120 4.141414 \n", + "30 5.757576 \n", + "1 3.636364 \n", + "63 8.989899 \n", + ".. ... \n", + "18 4.545455 \n", + "99 9.898990 \n", + "67 4.949495 \n", + "127 NaN \n", + "110 0.606061 \n", + "\n", + "[120 rows x 6 columns]" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_labels = iris[\"Species\"]\n", + "train_set.drop(\"Species\", axis = 1)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Fill missing values\n", + "\n", + "**Exercise**: read https://scikit-learn.org/stable/modules/generated/sklearn.impute.SimpleImputer.html and figure out how to impute the mean or the median to missing values in \"StemLengthCm\"" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "\u001b[0;31mInit signature:\u001b[0m\n", + "\u001b[0mSimpleImputer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mmissing_values\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mnan\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mstrategy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'mean'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mfill_value\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mverbose\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mcopy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0madd_indicator\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mDocstring:\u001b[0m \n", + "Imputation transformer for completing missing values.\n", + "\n", + "Read more in the :ref:`User Guide `.\n", + "\n", + "Parameters\n", + "----------\n", + "missing_values : number, string, np.nan (default) or None\n", + " The placeholder for the missing values. All occurrences of\n", + " `missing_values` will be imputed.\n", + "\n", + "strategy : string, optional (default=\"mean\")\n", + " The imputation strategy.\n", + "\n", + " - If \"mean\", then replace missing values using the mean along\n", + " each column. Can only be used with numeric data.\n", + " - If \"median\", then replace missing values using the median along\n", + " each column. Can only be used with numeric data.\n", + " - If \"most_frequent\", then replace missing using the most frequent\n", + " value along each column. Can be used with strings or numeric data.\n", + " - If \"constant\", then replace missing values with fill_value. Can be\n", + " used with strings or numeric data.\n", + "\n", + " .. versionadded:: 0.20\n", + " strategy=\"constant\" for fixed value imputation.\n", + "\n", + "fill_value : string or numerical value, optional (default=None)\n", + " When strategy == \"constant\", fill_value is used to replace all\n", + " occurrences of missing_values.\n", + " If left to the default, fill_value will be 0 when imputing numerical\n", + " data and \"missing_value\" for strings or object data types.\n", + "\n", + "verbose : integer, optional (default=0)\n", + " Controls the verbosity of the imputer.\n", + "\n", + "copy : boolean, optional (default=True)\n", + " If True, a copy of X will be created. If False, imputation will\n", + " be done in-place whenever possible. Note that, in the following cases,\n", + " a new copy will always be made, even if `copy=False`:\n", + "\n", + " - If X is not an array of floating values;\n", + " - If X is encoded as a CSR matrix;\n", + " - If add_indicator=True.\n", + "\n", + "add_indicator : boolean, optional (default=False)\n", + " If True, a `MissingIndicator` transform will stack onto output\n", + " of the imputer's transform. This allows a predictive estimator\n", + " to account for missingness despite imputation. If a feature has no\n", + " missing values at fit/train time, the feature won't appear on\n", + " the missing indicator even if there are missing values at\n", + " transform/test time.\n", + "\n", + "Attributes\n", + "----------\n", + "statistics_ : array of shape (n_features,)\n", + " The imputation fill value for each feature.\n", + "\n", + "indicator_ : :class:`sklearn.impute.MissingIndicator`\n", + " Indicator used to add binary indicators for missing values.\n", + " ``None`` if add_indicator is False.\n", + "\n", + "See also\n", + "--------\n", + "IterativeImputer : Multivariate imputation of missing values.\n", + "\n", + "Examples\n", + "--------\n", + ">>> import numpy as np\n", + ">>> from sklearn.impute import SimpleImputer\n", + ">>> imp_mean = SimpleImputer(missing_values=np.nan, strategy='mean')\n", + ">>> imp_mean.fit([[7, 2, 3], [4, np.nan, 6], [10, 5, 9]])\n", + "... # doctest: +NORMALIZE_WHITESPACE\n", + "SimpleImputer(add_indicator=False, copy=True, fill_value=None,\n", + " missing_values=nan, strategy='mean', verbose=0)\n", + ">>> X = [[np.nan, 2, 3], [4, np.nan, 6], [10, np.nan, 9]]\n", + ">>> print(imp_mean.transform(X))\n", + "... # doctest: +NORMALIZE_WHITESPACE\n", + "[[ 7. 2. 3. ]\n", + " [ 4. 3.5 6. ]\n", + " [10. 3.5 9. ]]\n", + "\n", + "Notes\n", + "-----\n", + "Columns which only contained missing values at `fit` are discarded upon\n", + "`transform` if strategy is not \"constant\".\n", + "\u001b[0;31mFile:\u001b[0m ~/opt/anaconda3/lib/python3.7/site-packages/sklearn/impute/_base.py\n", + "\u001b[0;31mType:\u001b[0m type\n", + "\u001b[0;31mSubclasses:\u001b[0m \n" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "from sklearn.impute import SimpleImputer\n", + "\n", + "# Function for the value replacements\n", + "\n", + "?SimpleImputer" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "4.830808080808081" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_num['StemLengthCm'].mean()" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "SepalLengthCm float64\n", + "SepalWidthCm float64\n", + "PetalLengthCm float64\n", + "PetalWidthCm float64\n", + "Color object\n", + "StemLengthCm float64\n", + "Species object\n", + "dtype: object" + ] + }, + "execution_count": 39, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_set.dtypes" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmStemLengthCm
Id
1317.42.86.11.94.830808
1206.02.25.01.54.141414
304.73.21.60.25.757576
15.13.51.40.23.636364
636.02.24.01.08.989899
945.02.33.31.01.717172
1327.93.86.42.04.343434
65.43.91.70.42.828283
175.43.91.30.40.505051
835.82.73.91.25.656566
615.02.03.51.00.808081
365.03.21.20.24.830808
1446.83.25.92.34.830808
1466.73.05.22.30.101010
1435.82.75.11.94.830808
1155.82.85.12.44.830808
1376.33.45.62.44.830808
545.52.34.01.30.404040
205.13.81.50.32.020202
394.43.01.30.25.858586
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm StemLengthCm\n", + "Id \n", + "131 7.4 2.8 6.1 1.9 4.830808\n", + "120 6.0 2.2 5.0 1.5 4.141414\n", + "30 4.7 3.2 1.6 0.2 5.757576\n", + "1 5.1 3.5 1.4 0.2 3.636364\n", + "63 6.0 2.2 4.0 1.0 8.989899\n", + "94 5.0 2.3 3.3 1.0 1.717172\n", + "132 7.9 3.8 6.4 2.0 4.343434\n", + "6 5.4 3.9 1.7 0.4 2.828283\n", + "17 5.4 3.9 1.3 0.4 0.505051\n", + "83 5.8 2.7 3.9 1.2 5.656566\n", + "61 5.0 2.0 3.5 1.0 0.808081\n", + "36 5.0 3.2 1.2 0.2 4.830808\n", + "144 6.8 3.2 5.9 2.3 4.830808\n", + "146 6.7 3.0 5.2 2.3 0.101010\n", + "143 5.8 2.7 5.1 1.9 4.830808\n", + "115 5.8 2.8 5.1 2.4 4.830808\n", + "137 6.3 3.4 5.6 2.4 4.830808\n", + "54 5.5 2.3 4.0 1.3 0.404040\n", + "20 5.1 3.8 1.5 0.3 2.020202\n", + "39 4.4 3.0 1.3 0.2 5.858586" + ] + }, + "execution_count": 41, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# I'll show how we'd do it for all numerical features\n", + "train_num = train_set.select_dtypes(include=[\"float64\"])\n", + "\n", + "# we 'initiate' the transformer\n", + "imputer = SimpleImputer(strategy=\"mean\")\n", + "\n", + "# we use its 'fit_transform' method on the selected features of the training set\n", + "# 'fit' in this case means looking for the mean in each selected feature\n", + "# 'transform' means actually replacing NANs with the mean\n", + "X = imputer.fit_transform(train_num)\n", + "# transform output back to dataframe \n", + "# (not needed for modelling, but it might help if you have to keep exploring)\n", + "train_num = pd.DataFrame(X,\n", + " columns=train_num.columns,\n", + " index=train_num.index)\n", + "train_num.head(20)" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "4.830808080808081" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_num['StemLengthCm'].mean()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Now we do it on the test set. Important to understand that we don't want to 'fit' the transformer again! We just want to replace the NAN's with the value we already decidid (in this case the mean). We'll make sure everyone understands why! \n", + "\n", + "Optional reading: https://medium.com/@chipk215/are-you-unknowingly-data-snooping-when-training-your-ml-models-7d6a70bdff1b\n", + "\n", + "Extra example: in a 'production' setting, it's likely you won't have to make predictions on any 'set' of observations, you'll make predictions on individual observations (you can't take the mean to fill NAN's there). We're trying to replicate the conditions we'll have in 'production' to see whether or not we can produce a model capable of making good generalizations." + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmStemLengthCm
Id
736.32.54.91.58.383838
1136.83.05.52.16.868687
1336.42.85.62.27.474747
895.63.04.11.33.535354
384.93.11.50.16.969697
1396.03.04.81.87.272727
886.32.34.41.34.830808
434.43.21.30.20.303030
94.42.91.40.28.787879
915.52.64.41.20.909091
1426.93.15.12.36.060606
345.54.21.40.24.830808
605.22.73.91.44.830808
1176.53.05.51.84.444444
1367.73.06.12.34.830808
1056.53.05.82.29.696970
375.53.51.30.26.161616
144.33.01.10.14.830808
646.12.94.71.44.830808
464.83.01.40.36.767677
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm StemLengthCm\n", + "Id \n", + "73 6.3 2.5 4.9 1.5 8.383838\n", + "113 6.8 3.0 5.5 2.1 6.868687\n", + "133 6.4 2.8 5.6 2.2 7.474747\n", + "89 5.6 3.0 4.1 1.3 3.535354\n", + "38 4.9 3.1 1.5 0.1 6.969697\n", + "139 6.0 3.0 4.8 1.8 7.272727\n", + "88 6.3 2.3 4.4 1.3 4.830808\n", + "43 4.4 3.2 1.3 0.2 0.303030\n", + "9 4.4 2.9 1.4 0.2 8.787879\n", + "91 5.5 2.6 4.4 1.2 0.909091\n", + "142 6.9 3.1 5.1 2.3 6.060606\n", + "34 5.5 4.2 1.4 0.2 4.830808\n", + "60 5.2 2.7 3.9 1.4 4.830808\n", + "117 6.5 3.0 5.5 1.8 4.444444\n", + "136 7.7 3.0 6.1 2.3 4.830808\n", + "105 6.5 3.0 5.8 2.2 9.696970\n", + "37 5.5 3.5 1.3 0.2 6.161616\n", + "14 4.3 3.0 1.1 0.1 4.830808\n", + "64 6.1 2.9 4.7 1.4 4.830808\n", + "46 4.8 3.0 1.4 0.3 6.767677" + ] + }, + "execution_count": 44, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# select only numerical features\n", + "test_num = test_set.select_dtypes(include=[\"float64\"])\n", + "\n", + "# the imputer's already created and fitted. we just need to use the .transform() method \n", + "# to fill Nan's with the mean\n", + "test_X = imputer.transform(test_num)\n", + "# transform output back to dataframe \n", + "# (not needed for modelling, but it might help if you have to keep exploring)\n", + "test_num = pd.DataFrame(test_X,\n", + " columns=test_num.columns,\n", + " index=test_num.index)\n", + "\n", + "test_num.head(20)" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "4.830808080808081" + ] + }, + "execution_count": 45, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_num['StemLengthCm'].mean()" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "5.394781144781145" + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "test_num['StemLengthCm'].mean()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Summary\n", + "\n", + "Beware with nans. The replacement decision will impact for sure the outcome of the analysis. Most common reactions;\n", + "+ delete all rows with nans.\n", + "+ Replace by zeroes.\n", + "+ Replace by the average or median (Imputer).\n", + "\n", + "If the replacement is done based on actual data distribution, make sure not to cheat yourself. You shouldn't use test data for that. If you then need to extrapolate the replacement to the test dataset then you must use the value concluded as per the training dataset.\n", + "\n", + "## What about if we didn't want to replace by the mean?" + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "SepalLengthCm 0\n", + "SepalWidthCm 0\n", + "PetalLengthCm 0\n", + "PetalWidthCm 0\n", + "Color 0\n", + "StemLengthCm 50\n", + "Species 0\n", + "dtype: int64" + ] + }, + "execution_count": 47, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris = pd.read_csv(\"iris_codealong.csv\", index_col=0)\n", + "iris.isna().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[,\n", + " ],\n", + " [,\n", + " ],\n", + " [,\n", + " ]],\n", + " dtype=object)" + ] + }, + "execution_count": 48, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA2wAAANeCAYAAABu3o33AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAgAElEQVR4nOzdfZyldX3f/9ebu7ABFSM4XYG4NpJU41awE2JKaiZoEiJVsDWphipU81iTX2z0kY0J2lbxJg22QdNYa7oGhUaqEtCCgiaoTJDGYEDRBddUxY0CK3jD3RBLOvj5/XGuIYed2Z0zM+ec65ozr+fjcR57zve6+1zfuc5+z+e6vtf3SlUhSZIkSeqeA9oOQJIkSZK0NBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNm04SbYkqSQHtR1LvySzSX657TgkSRqGtba3SW5OMrOPaTNJbh3VtqUuMWFTpyTZneS7SeaS3JHk3UkOX2aZs5Jcu4Ztjj1RSnJOkvescJlDmuW+lOT+pq7elWTLaKKUJE2qcbe3SV6Y5At7lV21j7KzAarqR6tqdsD1707yrBXG9MNJ/iTJt5Lck+TzSX4jyYErWY80aiZs6qLnVNXhwNOAHwP+fcvxdMUlwHOBXwIeBTwVuAF4ZptBSZLWrXG2t38OPCnJUQDNla+nAt+/V9lPANeMMA6abf0QcB3wdWBrVT0K+AVgGnjEqLcvrYQJmzqrqm4DPgI8JcmjkpyfZE+S25K8KcmBSZ4E/CHwE81ZwrsBkpya5LNJ7k3y9STnrCaGJE9P8hdJ7k7yuf6uGc2VuTcm+d9J7kvyZ0mO7Jv+4iR/k+TbSf7Dwtm/JKcArwH+VRPz5/o2+fil1tecNfwZ4LSq+quqmq+qe6rq7VV1fl88b2rinUvyoSSPSXJRUw9/5dU4SdLextHeVtXtwC3AM5qipwE300vk+ssOAK5v1v3QVbMkm5JckOSu5qrcjy2sO8kfAz8IfKiJ7bf6Nn1Gkq81V9H+XV/564G/qKrfqKo9TYx/XVW/VFV393Wp/DfNft2V5FeS/FhzJe7uJP91dTUurYwJmzorybHAs4HPAhcC88ATgROAnwV+uap2Ab8CfKqqDq+qI5rF7wdeDBwBnAr8apLTV7j9o4ErgDcBPwD8JnDpwpnAxi8B/wZ4LHBIMw9Jngz8N+AMYDO9K2JHA1TVR4H/CLy/ifmpy60PeBbw6ar6+jJhvwB4UbOtHwI+Bby7iX8X8LqV1IEkafKNsb29hr9Pzp4BfBK4dq+yv6yqv1ti2dfRa9d+CPg54MyFCVX1IuBrNFcMq+o/9S33k8CP0OuN8tom8YReu3rJ/uql8ePAccC/An4f+HfNsj8K/GKSnxpgHdKamLCpi/5Xc+buWnpn3v4I+HnglVV1f1XdCbyVXnKypKqaraqdVfW9qvo88F5gpf+p/mvgyqq6slnPVfTO+j27b553V9X/qarvAhcDxzflzwc+VFXXNg3Pa4EaYJv7Wt9jgD0DLv+VqrqH3tnSr1TVx6pqHvgTeo2vJEkw/va2/2raP6OXsH1yr7I/38eyvwj8TlV9pzl5+QcD7uPrq+q7VfU54HP0umHC4O3qG6vq/1bVn9FLTt9bVXc2VyU/ie2qxsCRc9RFp1fVxxY+JDkROBjYk2Sh+AB6/c6XlOTHgXOBp9C7UvV99BKWlXg88AtJntNXdjBwdd/nb/S9/1tg4Ybtx/XHV1V/m+TbA2xzX+v7NvDDAyx/R9/77y7xeb83lEuSNpRxt7fXAOcneTTwdOCMqppLsrkp+0l6V7GW8rB2FfibZfZtwf7a1c0DLG+7qtZ5hU3rwdeBB4Ajq+qI5vXIqvrRZvpSV67+J3A5cGxzI/EfAllivuW2+8d92zyiqg6rqnMHWHYPcMzChySb6J3NWzDI1bZ+HwNOTHLMsnNKkrQ6I21vq+oW4HZgG/C1qpprJn2qKTsc+Mt9xLYHOLbv8w/uvfr97tliHwP+5QqXkVphwqbOa24G/jPgvCSPTHJAkh/q6zd+B3BMkkP6FnsE8J2q+r/NGcNfWmYzByU5tO91MPAe4DlJfq654frQ9J77MkjSdEmz7D9t4no9D2/A7gC2JBnoO9icAb0K+GCSf5LkoCSPaG6Afskg65AkaX/G1N5+EviN5t8F1zZl1ze3BCzlYuDVSR7dtMP/dq/pdwD/cLl97PM64J8m+c9J/gFAkicmeU+SI5ZZVhorEzatFy+m19XiC8Bd9BKiha4Mn6A30tQ3knyrKfv/gDckuY/e/WMXL7P+d9Dr2rDwenfTR/40eiM6fpPemcdXMcD3pqpupteYvI/eWcH7gDvpnbmEv+8u8u0kn1lufY3nA1cC7wfuAW6iN/zwx/a3kCRJKzDq9vbP6Q2s1f88t082Zfsbzv/19LpBfpVeUvnHe03/XeDfN6M3/ubeC++tqr5C7xECW4Cbk9wDXErvXvX7llteGqdUrfQKsqSVSu9hpHcDx1XVV9uOR5IkSeuDV9ikEUnynCTfn+Qw4PeAncDudqOSJEnSemLCJo3OafRurr6d3jNcXlBe0pYkSdIK2CVSkiRJkjrKK2ySJEmS1FFjfXD2kUceWVu2bFn18vfffz+HHXbY8ALqoEnfR/dvfXP/1reV7N8NN9zwrao6asQhaYj629hJP5ZXwzpZzDpZzDp5OOtjsWHUyUrb2LEmbFu2bOH6669f9fKzs7PMzMwML6AOmvR9dP/WN/dvfVvJ/iX5m9FGo2Hrb2Mn/VheDetkMetkMevk4ayPxYZRJyttY+0SKUmSJEkdZcImSZIkSR1lwiZJkiRJHWXCJkmSJEkdZcImSZIkSR1lwiZJkiRJHWXCJkmSJEkdZcImSZIkSR1lwiZJkiRJHXVQ2wGsxM7b7uGss69oOwx2n3tq2yFIkjR0W2xjJalzvMImSZIkSR1lwiZJUsuSHJjks0k+3Hx+QpLrknwpyfuTHNJ2jJKkdpiwSZLUvlcAu/o+vxl4a1UdB9wFvLSVqCRJrTNhkySpRUmOAU4F/qj5HOBk4JJmlguB09uJTpLUtnU16IgkSRPo94HfAh7RfH4McHdVzTefbwWOXmrBJNuAbQBTU1PMzs4CMDc399D7ldi+dX75mUZsNXEPYrV1Msmsk8Wsk4ezPhZro05M2CRJakmSfw7cWVU3JJlZKF5i1lpq+araAewAmJ6erpmZ3ipmZ2dZeL8SnRiJ+YyZkax3tXUyyayTxayTh7M+FmujTkzYJElqz0nAc5M8GzgUeCS9K25HJDmoucp2DHB7izFKklrkPWySJLWkql5dVcdU1RbgBcAnquoM4Grg+c1sZwKXtRSiJKllyyZsSQ5N8ukkn0tyc5LXN+UXJPlqkhub1/GjD1eSpA3ht4HfSPJleve0nd9yPJKklgzSJfIB4OSqmktyMHBtko80015VVZfsZ1lJkjSAqpoFZpv3twAnthmPJKkblk3YqqqAuebjwc1ryZufJUmSJEnDM9CgI0kOBG4Angi8vaquS/KrwO8keS3wceDsqnpgiWWXHHJ4NaY2TfaQwzD5w6e6f+ub+7e+Tfr+SZI0iQZK2KrqQeD4JEcAH0zyFODVwDeAQ+gNKfzbwBuWWHbJIYdX420XXcZ5O9sf2HJUQw7D5A+f6v6tb+7f+jbp+ydJ0iRa0SiRVXU3vf71p1TVnup5AHg39rWXJEmSpKEaZJTIo5orayTZBDwL+GKSzU1ZgNOBm0YZqCRJkiRtNIP0L9wMXNjcx3YAcHFVfTjJJ5IcBQS4EfiVEcYpSZIkSRvOIKNEfh44YYnyk0cSkSRJkiQJWOE9bJIkSZKk8TFhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJKklSQ5N8ukkn0tyc5LXN+UXJPlqkhub1/FtxypJasdBbQcgSdIG9gBwclXNJTkYuDbJR5ppr6qqS1qMTZLUASZskiS1pKoKmGs+Hty8qr2IJEldY8ImSVKLkhwI3AA8EXh7VV2X5FeB30nyWuDjwNlV9cASy24DtgFMTU0xOzsLwNzc3EPvV2L71vlV7sXwrCbuQay2TiaZdbKYdfJw1sdibdSJCZskSS2qqgeB45McAXwwyVOAVwPfAA4BdgC/DbxhiWV3NNOZnp6umZkZoJf0LLxfibPOvmJV+zBMu8+YGcl6V1snk8w6Wcw6eTjrY7E26sRBRyRJ6oCquhuYBU6pqj3V8wDwbuDEVoOTJLXGhE2SpJYkOaq5skaSTcCzgC8m2dyUBTgduKm9KCVJbbJLpCRJ7dkMXNjcx3YAcHFVfTjJJ5IcBQS4EfiVNoOUJLXHhE2SpJZU1eeBE5YoP7mFcCRJHbRsl8j9PNTzCUmuS/KlJO9Pcsjow5UkSZKkjWOQe9gWHur5VOB44JQkTwfeDLy1qo4D7gJeOrowJUmSJGnjWTZha0apWuqhnicDlzTlF9K7KVqSJEmSNCQD3cO290M9ga8Ad1fVwhM2bwWO3seySz7UczWmNk32Qz1h8h9Q6P6tb+7f+jbp+ydJ0iQaKGHb+6GewJOWmm0fyy75UM/VeNtFl3HezvbHSRnVQz1h8h9Q6P6tb+7f+jbp+ydp8mwZ88Pct2+dX/QA+d3nnjrWGKS9reg5bH0P9Xw6cESShezpGOD24YYmSZIkSRvbIKNELvVQz13A1cDzm9nOBC4bVZCSJEmStBEN0r9wXw/1/ALwviRvAj4LnD/COCVJkiRpw1k2YdvPQz1vAU4cRVCSJEmSpAEHHZHUbeO6KXupm7EXeFO2JEnS8K1o0BFJkiRJ0viYsEmSJElSR5mwSZIkSVJHmbBJkiRJUkeZsEmSJElSR5mwSZIkSVJHmbBJkiRJUkeZsEmS1JIkhyb5dJLPJbk5yeub8ickuS7Jl5K8P8khbccqSWqHCZskSe15ADi5qp4KHA+ckuTpwJuBt1bVccBdwEtbjFGS1CITNkmSWlI9c83Hg5tXAScDlzTlFwKntxCeJKkDDmo7AEmSNrIkBwI3AE8E3g58Bbi7quabWW4Fjt7HstuAbQBTU1PMzs4CMDc399D7ldi+dX75mUZsNXEPYrV1MsnWQ52M+5ic2rR4m12vo1FaD8fIuLVRJyZskiS1qKoeBI5PcgTwQeBJS822j2V3ADsApqena2ZmBuj9wFx4vxJnnX3FipcZtt1nzIxkvautk0m2Hupk3Mfk9q3znLfz4T+PR3VMrgfr4RgZtzbqxC6RkiR1QFXdDcwCTweOSLLwq/EY4Pa24pIktcuETZKkliQ5qrmyRpJNwLOAXcDVwPOb2c4ELmsnQklS2+wSKUlSezYDFzb3sR0AXFxVH07yBeB9Sd4EfBY4v80gJUntMWGTJKklVfV54IQlym8BThx/RJKkrjFhk9ZoS98N0du3znfipn1JkiRNBu9hkyRJkqSOMmGTJEmSpI5aNmFLcmySq5PsSnJzklc05eckuS3Jjc3r2aMPV5IkSZI2jkHuYZsHtlfVZ5I8ArghyVXNtLdW1e+NLjxJkiRJ2riWTdiqag+wp3l/X5JdwNGjDkySJEmSNroVjRKZZAu94YevA04CXp7kxcD19K7C3bXEMtuAbQBTU1PMzs6uOtipTb1R+Nq2ln1Yztzc3EjX37ZJ3L/+Y7Irx+io7G//JuHvOonHZ79J3z9JkibRwAlbksOBS4FXVtW9Sd4BvBGo5t/zgJfsvVxV7QB2AExPT9fMzMyqg33bRZdx3s72n0Sw+4yZka17dnaWtdRR103i/p2117D+XThGR2V/+zfK78W4TOLx2W/S90+SpEk00CiRSQ6ml6xdVFUfAKiqO6rqwar6HvBOfMCnJEmSJA3VIKNEBjgf2FVVb+kr39w32/OAm4YfniRJkiRtXIP03ToJeBGwM8mNTdlrgBcmOZ5el8jdwMtGEqEkSZIkbVCDjBJ5LZAlJl05/HAkSZIkSQsGuodNkiRJkjR+JmySJEmS1FEmbJIkSZLUUSZskiRJktRRJmySJEmS1FEmbJIktSTJsUmuTrIryc1JXtGUn5PktiQ3Nq9ntx2rJKkdgzyHTZIkjcY8sL2qPpPkEcANSa5qpr21qn6vxdgkSR1gwiZJUkuqag+wp3l/X5JdwNHtRiVJ6hITNkmSOiDJFuAE4DrgJODlSV4MXE/vKtxdSyyzDdgGMDU1xezsLABzc3MPvV+J7VvnVxX7MK0m7kGstk4m2Xqok3Efk1ObFm+z63U0SuvhGBm3NurEhE2SpJYlORy4FHhlVd2b5B3AG4Fq/j0PeMney1XVDmAHwPT0dM3MzAC9H5gL71firLOvWN0ODNHuM2ZGst7V1skkWw91Mu5jcvvWec7b+fCfx6M6JteD9XCMjFsbdeKgI5IktSjJwfSStYuq6gMAVXVHVT1YVd8D3gmc2GaMkqT2mLBJktSSJAHOB3ZV1Vv6yjf3zfY84KZxxyZJ6ga7REqS1J6TgBcBO5Pc2JS9BnhhkuPpdYncDbysnfAkSW0zYZMkqSVVdS2QJSZdOe5YJEndZJdISZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6ihHiZQkSZI6bMvZV7Sy3e1b5zmr2fbuc09tJQYNcIUtybFJrk6yK8nNSV7RlP9AkquSfKn599GjD1eSJEmSNo5BukTOA9ur6knA04FfS/Jk4Gzg41V1HPDx5rMkSZIkaUiWTdiqak9VfaZ5fx+wCzgaOA24sJntQuD0UQUpSZIkSRvRiu5hS7IFOAG4Dpiqqj3QS+qSPHYfy2wDtgFMTU0xOzu76mCnNvX60rZtLfuwnLm5uZGuv22TuH/9x2RXjtFR2d/+TcLfdRKPz36Tvn+SJE2igRO2JIcDlwKvrKp7kwy0XFXtAHYATE9P18zMzCrC7HnbRZdx3s72x0nZfcbMyNY9OzvLWuqo6yZx/87quxF4+9b5Thyjo7K//Rvl92JcJvH47Dfp+ydJ0iQaaFj/JAfTS9YuqqoPNMV3JNncTN8M3DmaECVJkiRpYxpklMgA5wO7quotfZMuB85s3p8JXDb88CRJkiRp4xqk79ZJwIuAnUlubMpeA5wLXJzkpcDXgF8YTYiSJEmStDEtm7BV1bXAvm5Ye+Zww5EkSZIkLRjoHjZJkiRJ0viZsEmSJElSR5mwSZLUkiTHJrk6ya4kNyd5RVP+A0muSvKl5t9Htx2rJKkdJmySJLVnHtheVU8Cng78WpInA2cDH6+q44CPN58lSRuQCZskSS2pqj1V9Znm/X3ALuBo4DTgwma2C4HT24lQktQ2EzZJkjogyRbgBOA6YKqq9kAvqQMe215kkqQ2DfIcNkla1pazr2g7BHafe2rbIUirkuRw4FLglVV1b7Kvp+ksWm4bsA1gamqK2dlZAObm5h56vxLbt86veJlhW03cg1htnUyy9VAn4z4mpzYt3mYX6qit72Z/fXShHrqgje+NCZskSS1KcjC9ZO2iqvpAU3xHks1VtSfJZuDOpZatqh3ADoDp6emamZkBej+sFt6vxFldOPFyxsxI1rvaOplk66FOxn1Mbt86z3k7H/7zeFTH5Eq09d3sr48u1EMXtPG9sUukJEktSe9S2vnArqp6S9+ky4Ezm/dnApeNOzZJUjd4hU2SpPacBLwI2JnkxqbsNcC5wMVJXgp8DfiFluKTJLXMhE2SpJZU1bXAvm5Ye+Y4Y5EkdZNdIiVJkiSpo0zYJEmSJKmjTNgkSZIkqaNM2CRJkiSpo0zYJEmSJKmjTNgkSZIkqaNM2CRJkiSpo0zYJEmSJKmjTNgkSZIkqaOWTdiSvCvJnUlu6is7J8ltSW5sXs8ebZiSJEmStPEMcoXtAuCUJcrfWlXHN68rhxuWJEmSJGnZhK2qrgG+M4ZYJEmSJEl9DlrDsi9P8mLgemB7Vd211ExJtgHbAKamppidnV31Bqc2wfat86tefljWsg/LmZubG+n62zaJ+9d/THblGB2Vru/fWo+tSTw++036/kmSNIlWm7C9A3gjUM2/5wEvWWrGqtoB7ACYnp6umZmZVW4S3nbRZZy3cy055nDsPmNmZOuenZ1lLXXUdZO4f2edfcVD77dvne/EMToqXd+/tX43J/H47Dfp+ydJ0iRa1SiRVXVHVT1YVd8D3gmcONywJEmSJEmrStiSbO77+Dzgpn3NK0mSJElanWX7NiV5LzADHJnkVuB1wEyS4+l1idwNvGyEMUqSJEnShrRswlZVL1yi+PwRxCJJkiRJ6rOqLpGSJGntkrwryZ1JbuorOyfJbUlubF7PbjNGSVK7TNgkSWrPBcApS5S/taqOb15XjjkmSVKHmLBJktSSqroG+E7bcUiSuqu7D1SSJGnjenmSFwPXA9ur6q6lZkqyDdgGMDU19dCD0Vf7kPTtW+dXGe7wjOrh7j44frH1UCfjPianNi3eZhfqqK3vZn99dKEeuqCN740JmyRJ3fIO4I30RmJ+I3Ae8JKlZqyqHcAOgOnp6Vp4MPpqH5J+1tlXrCbeodp9xsxI1uuD4xdbD3Uy7mNy+9Z5ztv58J/HozomV6Kt72Z/fXShHrqgje+NXSIlSeqQqrqjqh6squ8B7wRObDsmSVJ7vMK2CltGeJZj+9b5gc6i7D731JHFIElqT5LNVbWn+fg84Kb9zS9JmmwmbJIktSTJe4EZ4MgktwKvA2aSHE+vS+Ru4GWtBShJap0JmyRJLamqFy5RfP7YA5GkdWCUvdwGdcEph419m97DJkmSJEkdZcImSZIkSR1lwiZJkiRJHWXCJkmSJEkdZcImSZIkSR1lwiZJkiRJHWXCJkmSJEkdZcImSZIkSR1lwiZJkiRJHXVQ2wFI0rBsOfuKNS2/fes8Z61xHbvPPXVNy0uSJPXzCpskSZIkddSyCVuSdyW5M8lNfWU/kOSqJF9q/n30aMOUJEmSpI1nkCtsFwCn7FV2NvDxqjoO+HjzWZIkSZI0RMsmbFV1DfCdvYpPAy5s3l8InD7kuCRJkiRpw1vtPWxTVbUHoPn3scMLSZIkSZIEYxglMsk2YBvA1NQUs7Ozq17X1KbeKG6TbNB9XEs9tmlubm7dxr4v/X+vST9G3b/ldfn4nsTvnyRJk261CdsdSTZX1Z4km4E79zVjVe0AdgBMT0/XzMzMKjcJb7voMs7bOdlPIti+dX6gfdx9xszogxmB2dlZ1nIMdFH/MPCD/v3WK/dveV3+bk7i90+SpEm32i6RlwNnNu/PBC4bTjiSJG0sjsYsSdqfQYb1fy/wKeBHktya5KXAucDPJPkS8DPNZ0mStHIX4GjMkqR9WLbvT1W9cB+TnjnkWCRJ2nCq6pokW/YqPg2Yad5fCMwCvz22oCRJnTG5N6NIkrR+PWw05iRLjsa8r4G9VjvATBcGFRrVwDgOurPYeqiTcR+TSw0+1YU6auu72V8fG7ke+rXxvTFhkyRpndrXwF6rHWCmfxCltoxq4B4H3VlsPdTJuI/JpQaf6sJgUm19N/vrYyPXQ78LTjls7N+b1Q46IkmSRueOZhRmlhuNWZI02UzYJEnqHkdjliQBJmySJLXK0ZglSfvjPWySJLXI0ZglSftjwqZ1bUsHbj6VJEmadP7mao9dIiVJkiSpo0zYJEmSJKmjTNgkSZIkqaNM2CRJkiSpoxx0RJIkdcaoBjbYvnWeswZc9+5zTx1JDOuNg0xI3eAVNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKAcdkSRJ6phxDPixkoFYJLXHK2ySJEmS1FEmbJIkSZLUUSZskiRJktRRJmySJEmS1FFrGnQkyW7gPuBBYL6qpocRlCRJktQF4xgARtqfYYwS+dNV9a0hrEeSJEmS1Mdh/SVJ6iB7sUiSYO0JWwF/lqSA/15VO/aeIck2YBvA1NQUs7Ozq97Y1KbeM0Mm2aD7uJZ6bNPc3NxQY+/a8TDpx6j7t7y3XXTZkKJZva1HP2rJ8mF//zQW9mKRpA1urQnbSVV1e5LHAlcl+WJVXdM/Q5PE7QCYnp6umZmZVW/sbRddxnk7J/ui4Pat8wPt4+4zZkYfzAjMzs6ylmNgb1174Oegf7/1yv1bH/b1/8Owv3+SJGn01jRKZFXd3vx7J/BB4MRhBCVJkh7qxXJD01tFkrQBrfpUcpLDgAOq6r7m/c8CbxhaZJIkbWzL9mLZ120Hq+3+apfnni50HR7H32LSu7mvhnXycNbHYm3cXrCWvj9TwAeTLKznf1bVR4cSlSRJG1x/L5YkC71YBrrtYLXdX7vWzXyYVtLluQu3HYzjbzEp3cCHyTp5OOtjsQtOOWzstxes+i9QVbcATx1iLJIkCXuxSJL+nimzJEndYy8WSRJgwiZJUufYi0WStGBNo0RKkiRJkkbHhE2SJEmSOsqETZIkSZI6ynvYtGpbVjHk8Pat8xM9bLQkSZI0TF5hkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjqo7QAkSZK6ZMvZV7QdgiQ9xCtskiRJktRRa0rYkpyS5K+TfDnJ2cMKSpKkjc42VpIEa0jYkhwIvB34eeDJwAuTPHlYgUmStFHZxkqSFqzlCtuJwJer6paq+jvgfcBpwwlLkqQNzTZWkgRAqmp1CybPB06pql9uPr8I+PGqevle820DtjUffwT469WHy5HAt9aw/How6fvo/q1v7t/6tpL9e3xVHTXKYLRvQ2hjJ/1YXg3rZDHrZDHr5OGsj8WGUScramPXMkpklihblP1V1Q5gxxq28/cbTK6vqulhrKurJn0f3b/1zf1b3yZ9/ybMmtpY/9aLWSeLWSeLWScPZ30s1kadrKVL5K3AsX2fjwFuX1s4kiQJ21hJUmMtCdtfAccleUKSQ4AXAJcPJyxJkjY021hJErCGLpFVNZ/k5cCfAgcC76qqm4cW2dKG0rWy4yZ9H92/9c39W98mff8mxrXn4DMAACAASURBVBDaWP/Wi1kni1kni1knD2d9LDb2Oln1oCOSJEmSpNFa04OzJUmSJEmjY8ImSZIkSR21LhK2JO9KcmeSm9qOZRSSHJvk6iS7ktyc5BVtxzRMSQ5N8ukkn2v27/VtxzQKSQ5M8tkkH247lmFLsjvJziQ3Jrm+7XiGLckRSS5J8sXme/gTbcc0TEl+pPnbLbzuTfLKtuPS2iU5JclfJ/lykrOXmP59Sd7fTL8uyZbxRzk+A9THWUm+2fdd+OU24hyn5X5DpecPmjr7fJKnjTvGcRugTmaS3NN3nLx23DGO0yC/QzfacTJgnYztOFnLc9jG6QLgvwL/o+U4RmUe2F5Vn0nyCOCGJFdV1RfaDmxIHgBOrqq5JAcD1yb5SFX9ZduBDdkrgF3AI9sOZER+uqom9eGZ/wX4aFU9vxmR7/vbDmiYquqvgeOhd2IBuA34YKtBac2av+XbgZ+h9xiAv0py+V5tx0uBu6rqiUleALwZ+Ffjj3b0BqwPgPfv/QDyCXcB+/8N9fPAcc3rx4F3NP9OsgtY/nflJ6vqn48nnNYN8jt0ox0ng/42H8txsi6usFXVNcB32o5jVKpqT1V9pnl/H70f/Ue3G9XwVM9c8/Hg5jVRo90kOQY4FfijtmPRyiR5JPAM4HyAqvq7qrq73ahG6pnAV6rqb9oORGt2IvDlqrqlqv4OeB9w2l7znAZc2Ly/BHhmkqUeyj0JBqmPDWeA31CnAf+jaav/EjgiyebxRNeOSf9duVID/g7dUMdJ136br4uEbSNpuqucAFzXbiTD1XQXvBG4E7iqqiZq/4DfB34L+F7bgYxIAX+W5IYk29oOZsj+IfBN4N1Nl9Y/SnJY20GN0AuA97YdhIbiaODrfZ9vZfEPiofmqap54B7gMWOJbvwGqQ+Af9l06bokybFLTN9oBq23jeYnmls5PpLkR9sOZlz28zt0wx4ny/w2H8txYsLWIUkOBy4FXllV97YdzzBV1YNVdTxwDHBikqe0HdOwJPnnwJ1VdUPbsYzQSVX1NHpdIn4tyTPaDmiIDgKeBryjqk4A7gcW3fsyCZruns8F/qTtWDQUS10p27v3wiDzTIpB9vVDwJaq+sfAx/j7q48b2UY6Rgb1GeDxVfVU4G3A/2o5nrFY5nfohjxOlqmTsR0nJmwd0dzbdSlwUVV9oO14RqXpajYLnNJyKMN0EvDcJLvpdcE5Ocl72g1puKrq9ubfO+nd+3RiuxEN1a3ArX1XfS+hl8BNop8HPlNVd7QdiIbiVqD/CtExwO37mifJQcCjmNyuYMvWR1V9u6oeaD6+E/gnY4qtywY5jjaUqrp34VaOqroSODjJkS2HNVID/A7dcMfJcnUyzuPEhK0DmvsJzgd2VdVb2o5n2JIcleSI5v0m4FnAF9uNaniq6tVVdUxVbaHX3ewTVfWvWw5raJIc1txwS9NV8GeBiRmxtaq+AXw9yY80Rc8EJmXAn729ELtDTpK/Ao5L8oTm6ukLgMv3mudy4Mzm/fPp/f80qWfFl62Pve65eS69+1I2usuBFzejAD4duKeq9rQdVJuS/IOFez2TnEjv9/K3241qdAb8HbqhjpNB6mScx8m6GCUyyXuBGeDIJLcCr6uq89uNaqhOAl4E7Gzu8wJ4TZOtT4LNwIXNCF4HABdX1cQNfT/BpoAPNv8nHQT8z6r6aLshDd2/BS5qfuTdAvybluMZuiTfT2/0vJe1HYuGo6rmk7wc+FPgQOBdVXVzkjcA11fV5fR+cPxxki/Tu7L2gvYiHq0B6+PXkzyX3ghw3wHOai3gMVnqNxS9wb+oqj8ErgSeDXwZ+Fsm8P+/vQ1QJ88HfjXJPPBd4AUTfKID9vE7FPhB2LDHySB1MrbjJJN9/EmSJEnS+mWXSEmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNm1oSXYneVbbcfRLck6S97QdhyRJw7KW9jbJHyb5D/uZXkmeOIptS11gwqbOSPKTSf4iyT1JvpPkfyf5sTFuf+yJUpKZJLeuYrlfSnJ9krkke5J8JMlPjiJGSdJkabO9TbK5SbCm+sr+3T7KPgpQVb9SVW8ccP0XJHnTCmN6ZJLfT/K1pl39cvP5yJWsRxoVEzZ1QpJHAh8G3gb8AHA08HrggTbj6qIkvwH8PvAfgSngB4H/BpzWZlySpO5ru72tqj3Al4Fn9BU/A/jiEmXXjDqeJIcAHwd+FDgFeCTwT4FvAyeOevvSIEzY1BU/DFBV762qB6vqu1X1Z1X1eYAkL0myK8ldSf40yeMXFmzOyv16kluSfCvJf05yQDPth5J8Ism3m2kXJTlipcEleVySS5N8M8lXk/x637Rzklyc5H8kuS/JzUmm+6Y/Lclnm2l/kuT9Sd6U5DDgI8DjmjN6c0ke1yx2yFLrS/Io4A3Ar1XVB6rq/qr6f1X1oap6VV88f5LkPc3yO5P8cJJXJ7kzydeT/OxK60CSNBG60N5eQ5OcJTkQOAH4L3uV/UQz36KrZkle1fQuuT3JS/rKtwFnAL/VtKkf6tvm8Uk+31xVfH+SQ5vyF9M78fm8qvpCVX2vqu6sqjdW1ZXNenc32/x8kvuTnJ9kqundcl+SjyV59Kr+GtIATNjUFf8HeDDJhUl+vv8/viSnA68B/gVwFPBJ4L17Lf88YBp4Gr0rTQv/gQf4XeBxwJOAY4FzVhJY0xh9CPgcvTORzwRemeTn+mZ7LvA+4AjgcuC/NsseAnwQuIDemcz3NrFSVfcDPw/cXlWHN6/b97c+eg3Yoc069+c5wB8DjwY+C/wpve/70fQSvv++kjqQJE2MLrS3DyVs9JK1L9K7ytVfdjDw6b0XTHIK8JvAzwDHAQ/dm1ZVO4CLgP/UtKnP6Vv0F+ldQXsC8I+Bs5ryZwEfraq5fcS64F822/xhem3sR+jV1ZH02tdf3/ei0tqYsKkTqupe4CeBAt4JfDPJ5U1/9pcBv1tVu6pqnl5XwOP7z/oBb66q71TV1+h1F3xhs94vV9VVVfVAVX0TeAvwUysM78eAo6rqDVX1d1V1SxPjC/rmubaqrqyqB+klSk9typ8OHAT8QXMl7AMs0QAtYV/rewzwraYe9ueTVfWnzXx/Qq/hPbeq/h+9RHDLaq40SpLWt460t38OPKVJFv8ZvTbrS8CRfWV/WVV/t8Syvwi8u6puak58njPgrv9BVd1eVd+hdxL2+Kb8McCeAZZ/W1XdUVW30Utkr6uqz1bVA/ROop4wYBzSipmwqTOaBuKsqjoGeAq9s3S/Dzwe+C9J7k5yN/Ademfyju5b/Ot97/+mWZYkj03yviS3JbkXeA+9s2Er8Xh63Rbv7ovhNfTuH1vwjb73fwscmuSgJo7bqqr2Eeu+7Gt936bXoB20zPJ39L3/Lr0k78G+zwCHDxCHJGnCtN3eVtVu4FZ6ieMz6CVAAJ/qK9vX/WuPWyKGQezdri60gd8GNg+w/N7t6t6fbVM1MiZs6qSq+iK9boRPofcf88uq6oi+16aq+ou+RY7te/+DwELXwt+ldxbxH1fVI4F/Ta/xWYmvA1/da/uPqKpnD7DsHuDoJP3b7I+1WJlPAf8XOH2Fy0mStEiL7e0n6SVmPwH8xV5lP8m+E7Y9S8TwsF3azzaX8jHg55r7yqVOMmFTJyT5R0m2Jzmm+XwsvW4Wfwn8IfDqJD/aTHtUkl/YaxWvSvLoZrlXAO9vyh8BzAF3JzkaeNUyoRyQ5NC+1/fR68J4b5LfTrIpyYFJnpLBhkD+FPAg8PIkByU5jYePOnUH8JhmMJFlVdU9wGuBtyc5Pcn3Jzm4uQ/hPw2yDknSxtWh9vYaegN+3N500wS4til7FL32cykXA2cleXKS7wdet9f0O4B/uMy2+/0xvUT10qZuDkjymCSvSTLIiVlp5EzY1BX3AT8OXJfkfnoNx03A9qr6IPBm4H1NN4ub6A3W0e8y4AbgRuAK4Pym/PX0boy+pyn/wDJxvJBe14aF11earoTPodff/avAt4A/oteg7FfT//5fAC8F7qZ3xvHDNMMnN2c23wvc0nRBedy+1tW3zrcAvwH8e+Cb9BqalwP/a7llJUkbXlfa2z8HHksvSVtwI7AJuKGq/napharqI/S6b36C3uMBPrHXLOcDT27a1GXbxeYetGfRG/jkKuBeeidqjwSuW255aRzy8FtrpPUnSQHHVdWX245lEEmuA/6wqt7ddiySJA1qvbW30qTwCps0Ykl+Ksk/aLpEnklvOOGPth2XJEmSum+5keYkrd2P0OtzfzjwFeD5VTXIEMKSJEna4OwSKUmSJEkdZZdISZIkSeqosXaJPPLII2vLli3j3OQ+3X///Rx22Pp75IZxj5dxj5dxj9f+4r7hhhu+VVVHjTkkrcEw2tj1eiyPknXycNbHYtbJYtbJYv11stI2dqwJ25YtW7j++uvHucl9mp2dZWZmpu0wVsy4x8u4x8u4x2t/cSf5m/FGo7UaRhu7Xo/lUbJOHs76WMw6Wcw6Way/TlbaxtolUpIkSZI6yoRNkiRJkjrKhE2SJEmSOsqETZIkSZI6yoRNkiRJkjrKhE2SJEmSOsqETZIkSZI6yoRNkiRJkjrKhE2SJEmSOuqgtgPQ+rXl7CsGnnf71nnOWsH8g9p97qlDX6ckSVq6nR9Ve74vtvOSV9gkSZIkqbNM2CRJkiSpo0zYJEmSJKmjTNgkSZIkqaNM2CRJkiSpo0zYJEmSJKmjTNgkSZIkqaN8Dpu0Rit5Ht2o+JwaSZKkyeQVNkmSJEnqKBM2SZIkSeooEzZJkiRJ6qhlE7Ykxya5OsmuJDcneUVTfk6S25Lc2LyePfpwJUmSJGnjGGTQkXlge1V9JskjgBuSXNVMe2tV/d7owpMkaXIlORS4Bvg+em3yJVX1uiQXAD8F3NPMelZV3dhOlJKkNi2bsFXVHmBP8/6+JLuAo0cdmCRJG8ADwMlVNZfkYODaJB9ppr2qqi5pMTZJUges6B62JFuAE4DrmqKXJ/l8knclefSQY5MkaaJVz1zz8eDmVS2GJEnqmIGfw5bkcOBS4JVVdW+SdwBvpNewvBE4D3jJEsttA7YBTE1NMTs7O4Sw125ubq4zsaxEl+LevnV+4HmnNq1s/kGNui4Gqe9R7NdK7R1jl46TlTDu8VqvcU+aJAcCNwBPBN5eVdcl+VXgd5K8Fvg4cHZVPdBmnJKkdqRq+RN5TTeNDwN/WlVvWWL6FuDDVfWU/a1nenq6rr/++tVFOmSzs7PMzMy0HcaKdSnulTwwevvWec7bOfzntI/6gdGD1HcXH5zdpeNkJYx7vPYXd5Ibqmp6vBFtbEmOAD4I/Fvg28A3gEOAHcBXquoNSyzTf1L0n7zvfe9bUwxzc3Mcfvjha1rHpNnIdbLztnsWlU1tgju+O74Yth79qPFtbJU28jGyL9bJYv118tM//dMramOX/QWdJMD5wK7+ZC3J5ub+NoDnATetKGpJkvSQqro7ySxwSt+AXg8keTfwm/tYZge9hI7p6ela64mD9XryYZQ2cp2ctcQJyVGdgN2X3WfMjG1bq7WRj5F9sU4WW0udDPKNOwl4EbAzycIIVa8BXpjkeHpdIncDL1tVBJIkbVBJjgL+X5OsbQKeBbx54aRoc9L0dDwpKkkb1iCjRF4LZIlJVw4/HEmSNpTNwIXNfWwHABdX1YeTfKJJ5gLcCPxKm0FKktozvmvakiTpYarq8/RGX967/OQWwpEkddCKhvWXJEmSJI2PCZskSZIkdZQJmyRJkiR1lAmbJEmSJHWUCZskSZIkdZQJmyRJkiR1lAmbJEmSJHWUCZskSZIkdZQJmyRJkiR1lAmbJEmSJHXUQW0HsB5tOfuK1ra9fes8Z519BbvPPbW1GCRJkiSNh1fYJEmSJKmjTNgkSZIkqaNM2CRJkiSpo0zYJEmSJKmjTNgkSZIkqaNM2CRJkiSpoxzWX5IkSZ3U5qOUFvgoJbXNK2ySJEmS1FEmbJIkSZLUUSZskiS1JMmhST6d5HNJbk7y+qb8CUmuS/KlJO9PckjbsUqS2mHCJklSex4ATq6qpwLHA6ckeTrwZuCtVXUccBfw0hZjlCS1yIRNkqSWVM9c8/Hg5lXAycAlTfmFwOkthCdJ6gBHiZQkqUVJDgRuAJ4IvB34CnB3Vc03s9wKHL2PZbcB2wCmpqaYnZ1dUyxzc3NrXsek2ch1sn3r/KKyqU1Ll0+y5f7+G/kY2RfrZLG11IkJmyRJLaqqB4HjkxwBfBB40lKz7WPZHcAOgOnp6ZqZmVlTLLOzs6x1HZNmI9fJWUsMqb996zzn7dxYPx93nzGz3+kb+RjZF+tksbXUiV0iJUnqgKq6G5gFng4ckWThV/ExwO1txSVJapcJmyRJLUlyVHNljSSbgGcBu4Crgec3s50JXNZOhJKktm2sa9qSJHXLZuDC5j62A4CLq+rDSb4AvC/Jm4DPAue3GaQkqT0mbJIktaSqPg+csET5LcCJ449IktQ1domUJEmSpI5aNmFLcmySq5PsSnJzklc05T+Q5KokX2r+ffTow5UkSZKkjWOQK2zzwPaqehK9kat+LcmTgbOBj1fVccDHm8+SJEmSpCFZNmGrqj1V9Znm/X30Rq86GjgNuLCZ7ULg9FEFKUmSJEkb0YruYUuyhd7N0dcBU1W1B3pJHfDYYQcnSZIkSRvZwKNEJjkcuBR4ZVXdm2TQ5bYB2wCmpqaYnZ1dRZjDNzc3t+pYtm+dH24wKzC1qbf9LtTjSuphIe5hG3U9DHKctHk8LNg7xrUc320y7vFar3FLkrSRDJSwJTmYXrJ2UVV9oCm+I8nmqtqTZDNw51LLVtUOYAfA9PR0zczMrD3qIZidnWW1sZx19hXDDWYFtm+d57ydB7H7jJnWYliwknpYiHvYRl0PgxwnbR4PC/auh7Uc320y7vFar3FLkrSRDDJKZOg9sHNXVb2lb9LlwJnN+zOBy4YfniRJkiRtXINc8jgJeBGwM8mNTdlrgHOBi5O8FPga8AujCVGSJEmSNqZlE7aquhbY1w1rzxxuOJIkSZKkBSsaJVKSJEmSND4mbJIkSZLUUSZskiRJktRRJmySJEmS1FEmbJIkSZLUUSZskiRJktRRJmySJEmS1FEmbJIkSZLUUSZskiRJktRRJmySJLUkybFJrk6yK8nNSV7RlJ+T5LYkNzavZ7cdqySpHQe1HYAkSRvYPLC9qj6T5BHADUmuaqa9tap+r8XYJEkdYMImTYAtZ1/xsM/bt85z1l5lo7b73FPHuj1pElTVHmBP8/6+JLuAo9uNSpLUJSZskiR1QJItwAnAdcBJwMuTvBi4nt5VuLuWWGYbsA1gamqK2dnZNcUwNze35nVMmo1cJ9u3zi8qm9q0dPkkW+7vv5GPkX2xThZbS52YsEmS1LIkhwOXAq+sqnuTvAN4I1DNv+cBL9l7uaraAewAmJ6erpmZmTXFMTs7y1rXMWk2cp0s1VNj+9Z5ztu5sX4+7j5jZr/TN/Ixsi/WyWJrqRMHHZEkqUVJDqaXrF1UVR8AqKo7qurBqvoe8E7gxDZjlCS1x4RNkqSWJAlwPrCrqt7SV765b7bnATeNOzZJUjdsrGvakiR1y0nAi4CdSW5syl4DvDDJ8fS6RO4GXtZOeJKktpmwSZLUkqq6FsgSk64cdyySpG4yYZMkSeqYvR/XImnj8h42SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igfnK11bdQPFt2+dZ6zfHipJEmSWuIVNkmSJEnqKK+wSZIk9envvWFPC0lt8wqbJEmSJHXUsglbkncluTPJTX1l5yS5LcmNzevZow1TkvT/t3f3YZbeZZ3gv7dpkJAGAgZKSBgbr2HiMmR4KxHEdStG3AAOwV1mBxaZxMFtZ1cUnd7V6LWrjrPuMnsZlWFdtQVMHGIiBphERF4G7UV3MWMnMJPEwICQgUBMg5FAmKzQcO8f5zRWqrtTlTqn6vyq6/O5rrrOOc95Xu6++zynzree3/McAGD32cgRtsuTXHiC6b/Y3U+d/rx9vmUBAACwbmDr7vcmuWsbagEAAGCVWc5he2VV/fvpkMlHzq0iAAAAkmz+KpG/kuSfJ+np7WVJ/vGJZqyq/Un2J8nS0lIOHTq0yU3O1z333LPpWg6cd3S+xTwAS6dPtj9CHx9IH47VvdOoe+Pm8ZqcZb9cJHUDAFtlU4Gtu+88dr+qfj3J2+5n3oNJDibJ8vJyr6ysbGaTc3fo0KFstpZFXt73wHlHc9lNe3Lby1YWVsMxD6QPx+readS9cfN4Tc6yXy6SugGArbKpIZFV9dhVD78nyc0nmxcAAIDNWfdP8FV1VZKVJGdV1e1JfjrJSlU9NZMhkbcl+YEtrBEATklV9fgkv5nk65N8JcnB7n5NVT0qyW8n2ZfJ79n/prv/alF1ArA46wa27n7pCSa/fgtqAYDd5miSA919Y1U9LMkNVfXuJJckeU93v7qqLk1yaZIfX2CdACzILFeJBABm0N13dPeN0/ufT3JrkrOTXJTkiulsVyR50WIqBGDRdt7VFADgFFRV+5I8Lcn1SZa6+45kEuqq6jEnWWauV2J25dCJ1VfZ3alXC94qu7Ef6+0T9pvj6cnxZumJwLZD7VvglSoBmK+q2pvkzUl+pLs/V1UbWm7eV2J25dCJ1VdB3qlXC94qu7Ef610F2X5zPD053iw9MSQSABaoqh6USVi7srvfMp1857ErMk9vjyyqPgAWS2ADgAWpyaG01ye5tbt/YdVT1yW5eHr/4iTXbndtAIxhdx3TBoCxPCfJy5PcVFUfmE77ySSvTvKmqnpFko8n+QcLqg+ABRPYAGBBuvuPk5zshLULtrMWAMZkSCQAAMCgBDYAAIBBCWwAAACDEtgAAAAGJbABAAAMSmADAAAYlMAGAAAwKIENAABgUAIbAADAoAQ2AACAQQlsAAAAgxLYAAAABiWwAQAADEpgAwAAGJTABgAAMCiBDQAAYFACGwAAwKAENgAAgEEJbAAAAIMS2ABgQarqDVV1pKpuXjXtZ6rqk1X1genP8xdZIwCLJbABwOJcnuTCE0z/xe5+6vTn7dtcEwADEdgAYEG6+71J7lp0HQCMa8+iCwAAjvPKqvpHSQ4nOdDdf3Wimapqf5L9SbK0tJRDhw7NtNF77rln5nWcCg6cd/Sr95dOv+/j3W439mO9fcJ+czw9Od4sPRHYAGAsv5Lknyfp6e1lSf7xiWbs7oNJDibJ8vJyr6yszLThQ4cOZdZ1nAouufT3vnr/wHlHc9lNPi4dsxv7cdvLVu73efvN8fTkeLP0ZN0hkSc5IfpRVfXuqvrw9PaRm9o6AHAf3X1nd3+5u7+S5NeTPHPRNQGwOBs5h+3yHH9C9KVJ3tPdT0zynuljAGBGVfXYVQ+/J8nNJ5sXgFPfuse0u/u9VbVvzeSLkqxM71+R5FCSH59jXQBwyquqqzL5fXpWVd2e5KeTrFTVUzMZEnlbkh9YWIEALNxmByEvdfcdSdLdd1TVY04247xPiJ6XWU78W+TJtjv1ZF91b69F1D2PfXunnqSsbjaru196gsmv3/ZCABjWlp81Ou8ToudllhP/Vp+MvN126sm+6t5ei6h7vZOyN2KnnqSsbgBgq2z2e9juPDbGfnp7ZH4lAQAAkGw+sF2X5OLp/YuTXDufcgAAADhmI5f1vyrJ+5KcW1W3V9Urkrw6yXOr6sNJnjt9DAAAwBxt5CqRJzohOkkumHMtAAAArLLZIZEAAABsMYENAABgUDvqeuX75ng5/QPnHV3o5fkBAADW4wgbAADAoAQ2AACAQQlsAAAAgxLYAAAABiWwAQAADEpgAwAAGJTABgAAMCiBDQAAYFACGwAAwKD2LLoAAADg5PZd+nuLLiG3vfoFiy5h13KEDQAAYFACGwAsUFW9oaqOVNXNq6Y9qqreXVUfnt4+cpE1ArA4AhsALNblSS5cM+3SJO/p7icmec/0MQC7kMAGAAvU3e9NcteayRcluWJ6/4okL9rWogAYhsAGAONZ6u47kmR6+5gF1wPAgrhKJADsUFW1P8n+JFlaWsqhQ4dmWt8999wz8zpOBQfOO/rV+0un3/fxbrcb+7HePrEd+80IPX8g/0bvJcebpScCGwCM586qemx331FVj01y5EQzdffBJAeTZHl5uVdWVmba6KFDhzLrOk4Fl6y6hPqB847mspt8XDpmN/bjtpet3O/z27HfXDLCZf3X6cNq3kuON0tPDIkEgPFcl+Ti6f2Lk1y7wFoAWCCBDQAWqKquSvK+JOdW1e1V9Yokr07y3Kr6cJLnTh8DsAvtrmPaADCY7n7pSZ66YFsLAWBIAhsAAJzEvnXOHztw3tEhzjHj1GVIJAAAwKAENgAAgEEZEgnMxXpDRjZi1mElt736BTPXMKt59GFWI/QBAJgPR9gAAAAGJbABAAAMSmADAAAYlMAGAAAwqJkuOlJVtyX5fJIvJzna3cvzKAoAAID5XCXy/O7+zBzWAwAAwCqGRAIAAAxq1iNsneRdVdVJfq27D66doar2J9mfJEtLSzl06NCmN3bgvKObXnatkalsNAAAHzxJREFUpdPnu77tou7tpe7tNWvdr73y2jlWs3FLp//Ntg+ct5AS7mOj77P33HPPTO/JAMDWmzWwPae7P1VVj0ny7qr6YHe/d/UM0xB3MEmWl5d7ZWVl0xub5Qt11zpw3tFcdtPO+95wdW8vdW8vdc/HbS9b2dB8hw4dyizvybAVRvjyeYCRzDQksrs/Nb09kuStSZ45j6IAAACYIbBV1RlV9bBj95N8V5Kb51UYAADAbjfLGJ6lJG+tqmPr+a3ufsdcqgIAAGDzga27P5rkKXOsBQAAgFVc1h8AAGBQAhsAAMCgBDYAAIBBjfPFQQDAV1XVbUk+n+TLSY529/JiKwJgEQQ2ABjX+d39mUUXAcDiGBIJAAAwKEfYAGBMneRdVdVJfq27D66doar2J9mfJEtLSzl06NBMG7znnntmXsesDpx3dKHbX2vp9PFqWiT9ON5u6ckDeW8Y4b1kNLP0RGADgDE9p7s/VVWPSfLuqvpgd7939QzTEHcwSZaXl3tlZWWmDR46dCizrmNWl1z6ewvd/loHzjuay27ycekY/TjebunJbS9b2fC8I7yXjGaWnhgSCQAD6u5PTW+PJHlrkmcutiIAFkFgA4DBVNUZVfWwY/eTfFeSmxdbFQCLcOofvwWAnWcpyVurKpn8rv6t7n7HYksCYBEENgAYTHd/NMlTFl0HAIsnsAEASZKbPnn3cBf9ANjtnMMGAAAwKIENAABgUAIbAADAoAQ2AACAQQlsAAAAgxLYAAAABiWwAQAADEpgAwAAGJTABgAAMCiBDQAAYFB7Fl0AAAAwtn2X/t6G5z1w3tFc8gDm30lue/ULtn2bjrABAAAMSmADAAAYlMAGAAAwKIENAABgUAIbAADAoAQ2AACAQQlsAAAAg5opsFXVhVX1oar6SFVdOq+iAGC38zsWgGSGwFZVpyX55STPS/KkJC+tqifNqzAA2K38jgXgmFmOsD0zyUe6+6Pd/cUkVye5aD5lAcCu5ncsAEmS6u7NLVj14iQXdvf3Tx+/PMm3dPcr18y3P8n+6cNzk3xo8+XO1VlJPrPoIjZB3dtL3dtL3dvr/ur+hu5+9HYWw99Y4O/Ynfpa3kp6cl/6cTw9OZ6eHG91Tx7Q79g9M2y0TjDtuPTX3QeTHJxhO1uiqg539/Ki63ig1L291L291L29dmrdu8RCfsd6TRxPT+5LP46nJ8fTk+PN0pNZhkTenuTxqx6fk+RTM6wPAJjwOxaAJLMFtj9N8sSqekJVPTjJS5JcN5+yAGBX8zsWgCQzDIns7qNV9cok70xyWpI3dPctc6ts6w03THOD1L291L291L29dmrdp7wF/o71mjientyXfhxPT46nJ8fbdE82fdERAAAAttZMX5wNAADA1hHYAAAABnXKB7aqOq2q3l9VbzvBc5dU1aer6gPTn+9fRI0nUlW3VdVN07oOn+D5qqp/WVUfqap/X1VPX0Sda22g7pWquntVz39qEXWuVVVnVtU1VfXBqrq1qp695vnh+r2BmofrdVWdu6qeD1TV56rqR9bMM2KvN1L3cP1Okqr60aq6papurqqrquoha57/2qr67Wm/r6+qfYuplO1QVY+vqj+cvmfcUlWvOsE8w+2DW2mDPRly/94qVfWQqvq3VfXvpj35ZyeYZ1e9d2ywJ8N+rtxKdf+ftXfV6+SYdXrygF8ns3wP207xqiS3Jnn4SZ7/7bVfRDqQ87v7ZF86+LwkT5z+fEuSX5nejuD+6k6SP+ru7962ajbmNUne0d0vrskV2R665vkR+71ezclgve7uDyV5ajJ5M0vyySRvXTPbcL3eYN3JYP2uqrOT/HCSJ3X3vVX1pkyuNnj5qtlekeSvuvtvV9VLkvyLJP9w24tluxxNcqC7b6yqhyW5oare3d1/tmqe4fbBLbaRniSD7d9b7K+TfEd331NVD0ryx1X1+939J6vm2W3vHRvpSTL258qtcn+ftXfb6+SYueaPU/oIW1Wdk+QFSV636Fq2wEVJfrMn/iTJmVX12EUXtRNV1cOTfHuS1ydJd3+xuz+7Zrah+r3Bmkd3QZI/7+7/uGb6UL0+gZPVPao9SU6vqj2ZhPq13+V1UZIrpvevSXJBVZ3oS5s5BXT3Hd194/T+5zP5QHH2mtlG3wfnaoM92VWm//f3TB8+aPqz9ip1u+q9Y4M92XU28Fl7V71Okq3JH6d0YEvyS0l+LMlX7mee/3o65OOaqnr8/cy33TrJu6rqhqraf4Lnz07yiVWPb88Yv2DWqztJnj0dUvD7VfV3t7O4k/jGJJ9O8hvTw9evq6oz1swzWr83UnMyXq9Xe0mSq04wfbRer3WyupPB+t3dn0zy80k+nuSOJHd397vWzPbVfnf30SR3J/m67ayTxZgOTXpakuvXPDX6Prhl7qcnyWD791abDun6QJIjSd7d3Sd9neyW944N9CQZ93PlVlnvs/aue51kC/LHKRvYquq7kxzp7hvuZ7bfTbKvu/9ekn+Tv/kLwAie091Pz2Royg9W1bevef5Ef50Y4S8969V9Y5Jv6O6nJHltkn+93QWewJ4kT0/yK939tCRfSHLpmnlG6/dGah6x10mS6RDOFyb5nRM9fYJpI7y216t7uH5X1SMz+evmE5I8LskZVfW9a2c7waJD9JutU1V7k7w5yY909+fWPn2CRU7518Q6PRlu/95q3f3l7n5qknOSPLOqnrxmll33OtlAT0b+XDl3G/ysvateJ1uVP07ZwJbkOUleWFW3Jbk6yXdU1RtXz9Ddf9ndfz19+OtJnrG9JZ5cd39qenskk3NlnrlmltuTrE7k5+T4oU7bbr26u/tzx4YUdPfbkzyoqs7a9kLv6/Ykt6/6S9k1mYShtfOM1O91ax6018c8L8mN3X3nCZ4brdernbTuQfv9nUk+1t2f7u4vJXlLkm9dM89X+z0dNvmIJHdta5Vsq+n5N29OcmV3v+UEs4y8D26J9Xoy6P69LabD7Q8luXDNU7v2veNkPRn5c+UWWfezdnbf62RL8scpG9i6+ye6+5zu3pfJEKY/6O77/GV5zZj8F2Yybn3hquqM6YnPmQ5z+64kN6+Z7bok/6gmnpXJUKc7trnU+9hI3VX19cfGLlfVMzN5Df7ldte6Wnf/RZJPVNW500kXJFl7svlQ/d5IzSP2epWX5uTDCofq9RonrXvQfn88ybOq6qHT2i7I8e9z1yW5eHr/xZm8V56yf/3c7aavg9cnubW7f+Eks428D87dRnoy6P69Zarq0VV15vT+6Zn88eeDa2bbVe8dG+nJqJ8rt8pGPmtnl71Otip/7IarRN5HVf1sksPdfV2SH66qF2Zyhai7klyyyNpWWUry1unvhj1Jfqu731FV/yRJuvtXk7w9yfOTfCTJf0ryfQuqdbWN1P3iJP99VR1Ncm+Slwyy4/5QkiunQ94+muT7dkC/16t5yF5X1UOTPDfJD6yaNnqvN1L3cP3u7uur6ppMhnMdTfL+JAfXvA++Psm/qqqPZPI++JKFFcx2eE6Slye5aXouTpL8ZJK/lYy9D26hjfRkuP17iz02yRU1uSru1yR5U3e/bZe/d2ykJ6N+rtxWu/x1ckKzvk7q1H6/AQAA2LlO2SGRAAAAO53ABgAAMCiBDQAAYFACGwAAwKAENgAAgEEJbAAAAIMS2AAAAAYlsAEAAAxKYAMAABiUwAYAADAogQ0AAGBQAhsAAMCgBDYAAIBBCWwAAACDEtgAAAAGJbABAAAMSmADAAAYlMAGAAAwKIENAABgUAIbAADAoAQ2AACAQQlsAAAAgxLYAAAABiWwAQAADEpgAwAAGJTABgAAMCiBDQAAYFACGwAAwKAENgAAgEEJbAAAAIMS2AAAAAYlsAEAAAxKYAMAABiUwAYAADAogQ0AAGBQAhsAAMCgBDYYSFX9TFW9cdF1AAAwBoGNoVTVt1XV/1tVd1fVXVX1/1TVN1fVJVX1x1u43W0PSlW1UlW3b2K5/7aqDlfVPVV1R1X9flV921bUCADAYglsDKOqHp7kbUlem+RRSc5O8s+S/PUi6xpJVf3TJL+U5H9LspTkbyX5v5JctMi6AADYGgIbI/k7SdLdV3X3l7v73u5+V5IvJfnVJM+eHlX6bJJU1ddW1c9X1cer6s6q+tWqOn363EpV3V5VP1ZVR6ZHol5UVc+vqv8wPXr3kxspqqoeV1VvrqpPV9XHquqHVz33M1X1pqr6zar6fFXdUlXLq55/elW9f/rc71TVb1fV/1pVZyT5/SSPm/6b7qmqx00Xe/CJ1ldVj0jys0l+sLvf0t1f6O4vdffvdvf/tKqe36mqN06Xv6mq/k5V/cS0D5+oqu+a7b8JAIDtIrAxkv+Q5MtVdUVVPa+qHpkk3X1rkn+S5H3dvbe7z5zO/y8yCXlPTfK3Mzki91Or1vf1SR6yavqvJ/neJM9I8p8n+amq+sb7K6iqvibJ7yb5d9P1XJDkR6rqv1w12wuTXJ3kzCTXJfk/p8s+OMlbk1yeyRHDq5J8z/Tf9IUkz0vyqem/aW93f+r+1pfk2dN/z1vvr+Ykfz/Jv0ryyCTvT/LOTPb1szMJfL+2zvIAAAxCYGMY3f25JN+WpDMJV5+uquuqamntvFVVSf67JD/a3Xd19+czGSb4klWzfSnJz3X3lzIJQGcleU13f767b0lyS5K/t05Z35zk0d39s939xe7+6LS21dv54+5+e3d/OZOg9JTp9Gcl2ZPkX06PhL0lyb/dQCtOtr6vS/KZ7j66zvJ/1N3vnM73O0keneTVq/qwr6rOvN81AAAwhD2LLgBWmx5NuyRJquqbkrwxk3O23rlm1kcneWiSGybZLUlSSU5bNc9fTkNPktw7vb1z1fP3Jtm7TknfkMmwxc+umnZakj9a9fgvVt3/T0keUlV7kjwuySe7u1c9/4l1tnd/6/vLJGdV1Z51Qtvaf+NnTtCHvUk+GwAAhuYIG8Pq7g9mMpzwyZkcdVvtM5mEj7/b3WdOfx7R3esFsAfqE0k+tmobZ3b3w7r7+RtY9o4kZ9eqRJnk8avur/03red9Sf6/JC96gMsBALBDCWwMo6q+qaoOVNU508ePT/LSJH+SyVGjc6bnhaW7v5LJ0MRfrKrHTOc/e825ZQ/U11TVQ1b9fG0mQxg/V1U/XlWnV9VpVfXkqvrmDazvfUm+nOSVVbWnqi5K8sxVz9+Z5OumFxNZV3ffncm5eL88vYDKQ6vqQdPz/f6PB/ZPBQBgJxDYGMnnk3xLkuur6guZBLWbkxxI8geZnHP2F1X1men8P57kI0n+pKo+l+TfJDl3hu2/NJOjdsd+/nw6lPDvZ3Jhk49lcmTvdUnWDVnd/cUk/1WSV2Qy/PB7M/nagr+ePv/BTC5E8tGq+uyqq0Te3zp/Ick/TfI/J/l0JkcAX5nkXz+QfygAADtD3ff0GmArVdX1SX61u39j0bUAADA+R9hgC1XVf1FVXz8dEnlxJlelfMei6wIAYGdwlUjYWucmeVMmV2X88yQv7u47FlsSAAA7hSGRAAAAgzIkEgAAYFDbOiTyrLPO6n379m16+S984Qs544wz5lfQDqYXE/owoQ8T+jAxjz7ccMMNn+nuR8+pJABgk7Y1sO3bty+HDx/e9PKHDh3KysrK/ArawfRiQh8m9GFCHybm0Yeq+o/zqQYAmIUhkQAAAIMS2AAAAAYlsAEAAAxKYAMAABiUwAYAADAogQ0AAGBQ6wa2qnpDVR2pqptXTXtUVb27qj48vX3k1pYJAACw+2zkCNvlSS5cM+3SJO/p7icmec/0MQAAAHO0bmDr7vcmuWvN5IuSXDG9f0WSF825LgAAgF2vunv9mar2JXlbdz95+viz3X3mquf/qrtPOCyyqvYn2Z8kS0tLz7j66qs3XeyRu+7OnfduevFTytLp0YvowzH6MKEPE094xGnZu3fvTOs4//zzb+ju5TmVBABs0p6t3kB3H0xyMEmWl5d7ZWVl0+t67ZXX5rKbtrzkHeHAeUf1IvpwjD5M6MPE5ReekVneawGAcWz2KpF3VtVjk2R6e2R+JQEAAJBsPrBdl+Ti6f2Lk1w7n3IAAAA4ZiOX9b8qyfuSnFtVt1fVK5K8Oslzq+rDSZ47fQwAAMAcrXuyR3e/9CRPXTDnWgAAAFhls0MiAQAA2GICGwAAwKAENgAAgEEJbAAAAIMS2AAAAAYlsAEAAAxKYAMAABiUwAYAADAogQ0AAGBQAhsAAMCgBDYAAIBBCWwAAACDEtgAAAAGJbABAAAMSmADAAAYlMAGAAAwKIENAABgUAIbAADAoAQ2AACAQQlsAAAAgxLYAAAABiWwAQAADEpgAwAAGJTABgAAMCiBDQAAYFACGwAAwKAENgAAgEEJbAAAAIMS2AAAAAYlsAEAAAxKYAMAABiUwAYAADAogQ0AAGBQAhsAAMCgZgpsVfWjVXVLVd1cVVdV1UPmVRgAAMBut+nAVlVnJ/nhJMvd/eQkpyV5ybwKAwAA2O1mHRK5J8npVbUnyUOTfGr2kgAAAEiS6u7NL1z1qiQ/l+TeJO/q7pedYJ79SfYnydLS0jOuvvrqTW/vyF135857N734KWXp9OhF9OEYfZjQh4knPOK07N27d6Z1nH/++Td09/KcSgIANmnTga2qHpnkzUn+YZLPJvmdJNd09xtPtszy8nIfPnx4U9tLktdeeW0uu2nPppc/lRw476heRB+O0YcJfZi4/MIzsrKyMtM6qkpgA4ABzDIk8juTfKy7P93dX0ryliTfOp+yAAAAmCWwfTzJs6rqoVVVSS5Icut8ygIAAGDTga27r09yTZIbk9w0XdfBOdUFAACw6810skd3/3SSn55TLQAAAKwy62X9AQAA2CICGwAAwKAENgAAgEEJbAAAAIMS2AAAAAYlsAEAAAxKYAMAABiUwAYAADAogQ0AAGBQAhsAAMCgBDYAAIBBCWwAAACDEtgAAAAGJbABAAAMSmADAAAYlMAGAAAwKIENAABgUAIbAADAoAQ2AACAQQlsAAAAgxLYAAAABiWwAQAADEpgAwAAGJTABgAAMCiBDQAAYFACGwAAwKAENgAAgEEJbAAAAIMS2AAAAAYlsAEAAAxKYAMAABiUwAYAADAogQ0AAGBQAhsAAMCgZgpsVXVmVV1TVR+sqlur6tnzKgwAAGC32zPj8q9J8o7ufnFVPTjJQ+dQEwAAAJkhsFXVw5N8e5JLkqS7v5jki/MpCwAAgOruzS1Y9dQkB5P8WZKnJLkhyau6+wtr5tufZH+SLC0tPePqq6/edLFH7ro7d9676cVPKUunRy+iD8fow4Q+TDzhEadl7969M63j/PPPv6G7l+dUEgCwSbMEtuUkf5LkOd19fVW9Jsnnuvt/Odkyy8vLffjw4c1VmuS1V16by26adRTnqeHAeUf1IvpwjD5M6MPE5ReekZWVlZnWUVUCGwAMYJaLjtye5Pbuvn76+JokT5+9JAAAAJIZAlt3/0WST1TVudNJF2QyPBIAAIA5mHXs0A8luXJ6hciPJvm+2UsCAAAgmTGwdfcHkjjHAQAAYAvM9MXZAAAAbB2BDQAAYFACGwAAwKAENgAAgEEJbAAAAIMS2AAAAAYlsAEAAAxKYAMAABiUwAYAADAogQ0AAGBQAhsAAMCgBDYAAIBBCWwAAACDEtgAAAAGJbABAAAMSmADAAAYlMAGAAAwKIENAABgUAIbAADAoAQ2AACAQQlsAAAAgxLYAAAABiWwAQAADEpgAwAAGJTABgAAMCiBDQAAYFACGwAAwKAENgAAgEEJbAAAAIMS2AAAAAYlsAEAAAxKYAMAABiUwAYAADAogQ0AAGBQMwe2qjqtqt5fVW+bR0EAAABMzOMI26uS3DqH9QAAALDKTIGtqs5J8oIkr5tPOQAAABwz6xG2X0ryY0m+ModaAAAAWKW6e3MLVn13kud39/9QVStJ/sfu/u4TzLc/yf4kWVpaesbVV1+96WKP3HV37rx304ufUpZOj15EH47Rhwl9mHjCI07L3r17Z1rH+eeff0N3L8+pJABgk2YJbP97kpcnOZrkIUkenuQt3f29J1tmeXm5Dx8+vKntJclrr7w2l920Z9PLn0oOnHdUL6IPx+jDhD5MXH7hGVlZWZlpHVUlsAHAADY9JLK7f6K7z+nufUlekuQP7i+sAQAA8MD4HjYAAIBBzWXsUHcfSnJoHusCAABgwhE2AACAQQlsAAAAgxLYAAAABiWwAQAADEpgAwAAGJTABgAAMCiBDQAAYFACGwAAwKAENgAAgEEJbAAAAIMS2AAAAAYlsAEAAAxKYAMAABiUwAYAADAogQ0AAGBQAhsAAMCgBDYAAIBBCWwAAACDEtgAAAAGJbABAAAMSmADAAAYlMAGAAAwKIENAABgUAIbAADAoAQ2AACAQQlsAAAAgxLYAAAABiWwAQAADEpgAwAAGJTABgAAMCiBDQAAYFACGwAAwKAENgAAgEEJbAAAAIPadGCrqsdX1R9W1a1VdUtVvWqehQEAAOx2e2ZY9miSA919Y1U9LMkNVfXu7v6zOdUGAACwq236CFt339HdN07vfz7JrUnOnldhAAAAu91czmGrqn1Jnpbk+nmsDwAAgKS6e7YVVO1N8n8n+bnufssJnt+fZH+SLC0tPePqq6/e9LaO3HV37rx304ufUpZOj15EH47Rhwl9mHjCI07L3r17Z1rH+eeff0N3L8+pJABgk2YKbFX1oCRvS/LO7v6F9eZfXl7uw4cPb3p7r73y2lx20yyn3Z06Dpx3VC+iD8fow4Q+TFx+4RlZWVmZaR1VJbABwABmuUpkJXl9kls3EtYAAAB4YGY5h+05SV6e5Duq6gPTn+fPqS4AAIBdb9Njh7r7j5PUHGsBAABglblcJRIAAID5E9gAAAAGJbABAAAMSmADAAAYlMAGAAAwKIENAABgUAIbAADAoAQ2AACAQQlsAAAAgxLYAAAABiWwAQAADEpgAwAAGJTABgAAMCiBDQAAYFACGwAAwKAENgAAgEEJbAAAAIMS2AAAAAYlsAEAAAxKYAMAABiUwAYAADAogQ0AAGBQAhsAAMCgBDYAAIBBCWwAAACDEtgAAAAGJbABAAAMSmADAAAYlMAGAAAwKIENAABgUAIbAADAoAQ2AACAQQlsAAAAgxLYAAAABiWwAQAADGqmwFZVF1bVh6rqI1V16byKAgAAYIbAVlWnJfnlJM9L8qQkL62qJ82rMAAAgN1uliNsz0zyke7+aHd/McnVSS6aT1kAAABUd29uwaoXJ7mwu79/+vjlSb6lu1+5Zr79SfZPH56b5EObLzdnJfnMDMufSvRiQh8m9GFCHybm0Ydv6O5Hz6MYAGDz9sywbJ1g2nHpr7sPJjk4w3b+ZoNVh7t7eR7r2un0YkIfJvRhQh8m9AEATh2zDIm8PcnjVz0+J8mnZisHAACAY2YJbH+a5IlV9YSqenCSlyS5bj5lAQAAsOkhkd19tKpemeSdSU5L8obuvmVulZ3YXIZWniL0YkIfJvRhQh8m9AEAThGbvugIAAAAW2umL84GAABg6whsAAAAg9oxga2qLqyqD1XVR6rq0kXXswhV9fiq+sOqurWqbqmqVy26pkWqqtOq6v1V9bZF17JIVXVmVV1TVR+cvjaeveiaFqGqfnS6X9xcVVdV1UMWXdN2qKo3VNWRqrp51bRHVdW7q+rD09tHLrJGAGDzdkRgq6rTkvxykucleVKSl1bVkxZb1UIcTXKgu/+zJM9K8oO7tA/HvCrJrYsuYgCvSfKO7v6mJE/JLuxJVZ2d5IeTLHf3kzO5ENJLFlvVtrk8yYVrpl2a5D3d/cQk75k+BgB2oB0R2JI8M8lHuvuj3f3FJFcnuWjBNW277r6ju2+c3v98Jh/Mz15sVYtRVeckeUGS1y26lkWqqocn+fYkr0+S7v5id392sVUtzJ4kp1fVniQPzS75Xsjufm+Su9ZMvijJFdP7VyR50bYWBQDMzU4JbGcn+cSqx7dnlwaVY6pqX5KnJbl+sZUszC8l+bEkX1l0IQv2jUk+neQ3psNDX1dVZyy6qO3W3Z9M8vNJPp7kjiR3d/e7FlvVQi119x3J5A89SR6z4HoAgE3aKYGtTjBt134fQVXtTfLmJD/S3Z9bdD3braq+O8mR7r5h0bUMYE+Spyf5le5+WpIvZBcOf5ueo3VRkickeVySM6rqexdbFQDA7HZKYLs9yeNXPT4nu2S401pV9aBMwtqV3f2WRdezIM9J8sKqui2T4bHfUVVvXGxJC3N7ktu7+9iR1msyCXC7zXcm+Vh3f7q7v5TkLUm+dcE1LdKdVfXYJJneHllwPQDAJu2UwPanSZ5YVU+oqgdncjGB6xZc07arqsrkXKVbu/sXFl3PonT3T3T3Od29L5PXwh909648mtLdf5HkE1V17nTSBUn+bIElLcrHkzyrqh463U8uyC68+Moq1yW5eHr/4iTXLrAWAGAGexZdwEZ099GqemWSd2Zy9bc3dPctCy5rEZ6T5OVJbqqqD0yn/WR3v32BNbF4P5TkyukfMz6a5PsWXM+26+7rq+qaJDdmcjXV9yc5uNiqtkdVXZVkJclZVXV7kp9O8uokb6qqV2QSZv/B4ioEAGZR3bv2VDAAAICh7ZQhkQAAALuOwAYAADAogQ0AAGBQAhsAAMCgBDYAAIBBCWwAAACDEtgAAAAG9f8Di2YeAdRf0bYAAAAASUVORK5CYII=\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris.hist(figsize = (15,15))" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 49, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA2cAAAEvCAYAAADB37lNAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAd20lEQVR4nO3de7hdZ10n8O+PJi3phYI2ys0QRQZTU4qYQS4ZIAh91KoMM3VqK6OVPGa8BRnlkUAcoYMZg3ekAhbSoc7QIDcVWwaLmAIpt6bQe1QQU6hUCYKhlEADfeePtQ49DSc5pzn7nL3OOZ/P8+znrL322mv9ztnvWXt/13rXu6u1FgAAAMbrfuMuAAAAAOEMAABgEIQzAACAARDOAAAABkA4AwAAGADhDAAAYACWzefGTjvttLZ69er53CQAAMBgXHvttZ9tra2c6rF5DWerV6/Onj175nOTAAAAg1FVtx7pMd0aAQAABkA4AwAAGADhDAAAYACEMwAAgAEQzgAAAAZAOAMAABgA4QwAAGAApg1nVXVJVX2mqm6aNO+bqupdVfWx/ueD5rZMAACAxW0mZ85en+QHDpu3Jcm7W2uPSvLu/j4AAADHaNpw1lp7b5LPHTb7WUku7acvTfIfR1wXAADAkrLsGJ/3ra2125OktXZ7VX3LkRasqk1JNiXJqlWrjnFzAADAdKpq3CXMWGtt3CUMzpwPCNJau7i1tq61tm7lypVzvTkAAFiyWmsjvz3ihZfPyXr5Rscazv6lqh6SJP3Pz4yuJAAAgKXnWMPZ25P8VD/9U0n+YjTlAAAALE0zGUp/Z5IPJHl0Vd1WVRuTbE/yzKr6WJJn9vcBAAA4RtMOCNJaO+8ID33/iGsBAABYsuZ8QBAAAACmJ5wBAAAMgHAGAAAwAMIZAADAAAhnAAAAAyCcAQAADIBwBgAAMADCGQAAwAAIZwAAAAMgnAEAAAyAcAYAADAAwhkAAMAACGcAAAADIJwBAAAMgHAGAAAwAMIZAADAAAhnAAAAAyCcAQAADIBwBgAAMADCGQAAwAAIZwAAAAMgnAEAAAyAcAYAADAAwhkAAMAACGcAAAADIJwBAAAMgHAGAAAwAMIZAADAAAhnAAAAAyCcAQAADIBwBgAAMADCGQAAwAAIZwAAAAMgnAEAAAyAcAYAADAAwhkAAMAACGcAAAADIJwBAAAMgHAGAAAwAMIZAADAAMwqnFXVf6+qm6vqpqraWVX3H1VhAAAAS8kxh7OqeliS5yVZ11pbm+S4JD8+qsIAAACWktl2a1yWZEVVLUtyYpJPz74kAACApeeYw1lr7Z+S/E6STya5PcmB1tqVoyoMAABgKZlNt8YHJXlWkm9P8tAkJ1XVc6ZYblNV7amqPfv37z/2SgEAABax2XRrfEaSf2yt7W+tHUrytiRPOnyh1trFrbV1rbV1K1eunMXmAAAAFq9ls3juJ5M8oapOTHIwyfcn2TOSqhahqhp3CTPSWht3CQAAsCTN5pqzDyV5S5KPJLmxX9fFI6pr0Wmtjfz2iBdePvJ1AgAA4zGbM2dprb0kyUtGVAsAAMCSNduh9AEAABgB4QwAAGAAhDMAAIABEM4AAAAGQDgDAAAYAOEMAABgAIQzAACAAZjV95wBAADH5swLr8yBg4fGXcaMrN5yxbhLmNapK5bn+pecNe4yZkU4AwCAMThw8FD2bT973GUsGgshQE5Ht0YAAIABEM4AAAAGQDgDAAAYAOEMAABgAIQzAACAARDOAAAABkA4AwAAGADhDAAAYACEMwAAgAEQzgAAAAZAOAMAABgA4QwAAGAAhDMAAIABWDbuAgBgKlU17hJmrLU27hIAWAScOQNgkFprI7894oWXz8l6AWAUhDMAAIABEM4AAAAGQDgDAAAYAOEMAABgAIQzAACAARDOAAAABkA4AwAAGADhDAAAYACEMwAAgAEQzgAAAAZg2bgLGKIzL7wyBw4eGncZM7J6yxXjLuGoTl2xPNe/5KxxlwEAAIMnnE3hwMFD2bf97HGXsSgMPTwCAMBQ6NYIAAAwAMIZAADAAAhnAAAAAyCcAQAADMCswllVPbCq3lJVf1tVe6vqiaMqDAAAYCmZ7WiNr0jyztbaOVV1fJITR1ATAADAknPM4ayqHpDkKUkuSJLW2l1J7hpNWQAAAEvLbLo1fkeS/Un+d1V9tKpeV1UnjaguAACAJWU24WxZkscleXVr7XuS3Jlky+ELVdWmqtpTVXv2798/i80BAAAsXrMJZ7clua219qH+/lvShbV7aa1d3Fpb11pbt3LlyllsDgAAYPE65nDWWvvnJJ+qqkf3s74/yS0jqQoAAGCJme1ojZuTvKEfqfETSX569iUBAAAsPbMKZ62165KsG1EtAAAAS9Zsz5wtSqes2ZIzLv2GsU04BqesSZKzx10GAAAMnnA2hTv2bs++7QLFKKzecsW4SwAAgAVhNqM1AgAAMCLCGQAAwAAIZwAAAAMgnAEAAAyAcAYAADAAwhkAAMAACGcAAAADIJwBAAAMgHAGAAAwAMIZAADAAAhnAAAAAyCcAQAADIBwBgAAMADCGQAAwAAIZwAAAAOwbNwFDNXqLVeMu4RF4dQVy8ddAjAPzrzwyhw4eGjcZczIQti/n7piea5/yVnjLgOAeSacTWHf9rPHXcKMrN5yxYKpFVjcDhw8ZH80QgshQAIwero1AgAADIAzZwAAMAanrNmSMy7dMu4yFo1T1iTJwu7FIZwBAMAY3LF3uy7hI7QYuoTr1ggAADAAwhkAAMAACGcAAAADIJwBAAAMgHAGAAAwAMIZAADAAAhnAAAAAyCcAQAADIBwBgAAMADCGQAAwAAIZ8DI7Ny5M2vXrs1xxx2XtWvXZufOneMuCQBgwVg27gKAxWHnzp3ZunVrduzYkfXr12f37t3ZuHFjkuS8884bc3UAAMPnzBkwEtu2bcuOHTuyYcOGLF++PBs2bMiOHTuybdu2cZcGALAgCGfASOzduzfr16+/17z169dn7969Y6oIAGBh0a0RGIk1a9Zk9+7d2bBhw9fn7d69O2vWrBljVcyXU9ZsyRmXbhl3GYvGKWuS5OxxlwHAPBPO5klVzc16Xz7a9bXWRrtCloytW7fm3HPPzUknnZRPfvKTWbVqVe6888684hWvGHdpzIM79m7Pvu3CxKis3nLFuEsAYAyEs3ki9LCUaO8AAPeda86Akdi2bVs2bdqUk046KVWVk046KZs2bTIgCADADDlzBozELbfckjvvvDOXXHLJ14fSf+5zn5tbb7113KUBACwIsz5zVlXHVdVHq+ryURQELEzHH398Nm/efK+h9Ddv3pzjjz9+3KUBACwIo+jW+EtJjJUNS9xdd92Viy66KLt27cqhQ4eya9euXHTRRbnrrrvGXRoAwIIwq3BWVQ9PN9bv60ZTDrBQnX766Tn//POzefPm3P/+98/mzZtz/vnn5/TTTx93aQAAC8Jsz5z9QZJfTXL3CGoBFrCtW7fmsssuyytf+cp8+ctfzitf+cpcdtll2bp167hLAwBYEI55QJCq+uEkn2mtXVtVTzvKcpuSbEqSVatWHevmgDky6u/ge/rTn36v++eff37OP//8kazbEP0AwGI2mzNnT07yo1W1L8kbkzy9qv7v4Qu11i5ura1rra1buXLlLDYHzIXW2shvj3jh5XOyXgCAxeyYw1lr7UWttYe31lYn+fEkf9Nae87IKgMAAFhCfAk1AADAAIzkS6hba1cluWoU6wIAAFiKnDkDAAAYAOEMAABgAIQzAACAARDOAAAABkA4AwAAGADhDAAAYACEMwAAgAEQzgAAAAZAOAMAABgA4QwAAGAAhDMAAIABEM4AAAAGYNm4CwBm7swLr8yBg4fGXcaMrN5yxbhLmNapK5bn+pecNe4yAACSCGewoBw4eCj7tp897jIWjYUQIAGApUO3RgAAgAEQzgAAAAZAOAMAABgA4QwAAGAAhDMAAIABMFojLCCnrNmSMy7dMu4yFo1T1iSJ0S8BgGEQzmABuWPvdkPpj5Ch9AGAIdGtEQAAYACEMwAAgAEQzgAAAAbANWewwLhOanROXbF83CUAAHydcAYLyEIZDGT1lisWTK0AAEOhWyMAAMAACGcAAAADIJwBAAAMgHAGAAAwAMIZAADAAAhnAAAAA2AofQCA+6iqxl3CjLXWxl0CR+H7S0dnMXx/qXAGAHAfzUXg8R2RS89Ceb21zfmjWyMAAMAACGcAAAADIJwBAAAMgHAGAAAwAMIZAADAABitEZa4uRoOul4++nUaDhoAWMyOOZxV1bcl+ZMkD05yd5KLW2uvGFVhwPwQeAAAhmE23Rq/muRXWmtrkjwhyS9U1emjKQtYiHbu3Jm1a9fmuOOOy9q1a7Nz585xlwQAsGAc85mz1trtSW7vp++oqr1JHpbklhHVBiwgO3fuzNatW7Njx46sX78+u3fvzsaNG5Mk55133pirAwAYvpEMCFJVq5N8T5IPjWJ9wMKzbdu27NixIxs2bMjy5cuzYcOG7NixI9u2bRt3aQAAC8Ksw1lVnZzkrUme31r7whSPb6qqPVW1Z//+/bPdHDBQe/fuzfr16+81b/369dm7d++YKgIAWFhmFc6qanm6YPaG1trbplqmtXZxa21da23dypUrZ7M5YMDWrFmT3bt332ve7t27s2bNmjFVBACwsBxzOKtu/O0dSfa21n5vdCUBC9HWrVuzcePG7Nq1K4cOHcquXbuycePGbN26ddylAQAsCLP5nrMnJ/mvSW6squv6eS9urb1j9mUBC83EoB+bN2/O3r17s2bNmmzbts1gIAAAMzSb0Rp3J5mbb68FFqTzzjtPGAMAOEazOXMGADB4Z154ZQ4cPDTuMmZk9ZYrxl3CtE5dsTzXv+SscZcBi5JwBgAsagcOHsq+7WePu4xFYyEESFioRvI9ZwAAAMyOcAYAADAAwhkAAMAAuOYMgJFwHcronLpi+bhLAGAMhDMAZm2hDLawessVC6ZWAJYe3RoBAAAGQDgDAAAYAOEMAABgAIQzAACAARDOAAAABsBojQDAonbKmi0549It4y5j0ThlTZIY9RTmgnAGACxqd+zd7isURsh3GsLc0a0RAABgAIQzAACAARDOAAAABkA4AwAAGADhDAAAYACEMwAAgAEwlD4Ag1RVc7Pel49+na210a8UgCVHOANgkAQeAJYa3RoBAAAGQDgDAAAYAOEMAABgAIQzAACAARDOAAAABkA4AwAAGADhDAAAYACEMwAAgAEQzgAAAAZAOAMAABgA4QwAAGAAhDMAAIABEM4AAAAGQDgDAAAYAOEMAABgAJaNuwAAgLm2essV4y5h0Th1xfJxlwCLlnAGACxq+7afPe4SZmT1lisWTK3A3NCtEQAAYACEMwAAgAGYVTirqh+oqr+rqo9X1ZZRFQUAALDUHPM1Z1V1XJI/SvLMJLcluaaq3t5au2VUxQEADFFVzc16Xz76dbbWRr9SYE7MZkCQxyf5eGvtE0lSVW9M8qwkwhkAsKgJPMBcmE04e1iST026f1uS7zt8oaralGRTkqxatWoWmwMAAI7GWd2FbTbhbKpX/hv+wq21i5NcnCTr1q3zCgAAwBwReBa22QwIcluSb5t0/+FJPj27cgAAAJam2YSza5I8qqq+vaqOT/LjSd4+mrIAAACWlmPu1tha+2pV/WKSv0pyXJJLWms3j6wyAACAJWQ215yltfaOJO8YUS0AAABL1qy+hBoAAIDREM4AAAAGQDgDAAAYAOEMAABgAIQzAACAARDOAAAABkA4AwAAGIBqrc3fxqr2J7l13ja4+J2W5LPjLgKmoG0yVNomQ6Z9MlTa5mg9orW2cqoH5jWcMVpVtae1tm7cdcDhtE2GSttkyLRPhkrbnD+6NQIAAAyAcAYAADAAwtnCdvG4C4Aj0DYZKm2TIdM+GSptc5645gwAAGAAnDkDAAAYAOFsBqpqa1XdXFU3VNV1VfV9I1z306rq8n76gqq6aFTrnmJbD6yqn59q21Msu7yqtlfVx6rqpqr6cFX94FzVxuzNRzutzmer6kH9/IdUVauq9ZOW3V9V31xVP1tVPznFulZX1U399GOr6ocmPfbSqnrBEWp4cFW9sar+oapuqap3VNW/G9XvyOhV1df6tnhTVb25qk6cZvkXz3C9+6rqtH76i6Oo9SjbuqCqHjrVtqdY9gerak9V7a2qv62q35nL2hiNuW6nVfX7VfX8SfP/qqpeN+n+71bVL1fVQ6vqLUdY11VVte7w7U/enx7heS/o2+JNVXX9VPtkhmeq9/Oqev50bfM+rP+o7WZE27hXvUfbV1fVT/Zt9Ob+/X3KzwFLhXA2jap6YpIfTvK41tpjkjwjyafGW9Uxe2CSn592qc7LkjwkydrW2tokP5LklLkqjNmZr3baun7QH0ryxH7Wk5J8tP+Zqnp0ks+21v61tfaa1tqfTLPKxyb5oWmWSVVVkj9LclVr7ZGttdOTvDjJtx7bb8I8Odhae2y/D7kryc9Os/yMPvTOswuSPHS6hapqbZKLkjyntbYmydokn5jb0hiRuW6n7889+8j7pfu+qO+e9PiTklzdWvt0a+2cGaxvpuHwZ5M8M8nj+9/tKUnqvhTO/DvK+/nzk4wknM2TGdXbH/h/fpKzWmvfneRxSQ7McW2DJpxN7yHpPmx+JUlaa59trX26qr63qt5TVdf2R8Eeknz96NYfVNX7+6MAj+/nP76f99H+56NnWkBVnVVVH6iqj/RH9U7u5++rqgv7+TdW1Xf181dW1bv6+X9cVbf2R3q3J3lkfxTmt/vVn1xVb+mPrL2hOicm+Zkkmyf93v/SWntTv/4vVtXL+9/9r/vf7aqq+kRV/ego/ujcZ/PZTq9O/0Gj//l7uXdYe3+/rq+fBevruL6qPpDkF/p5xyf5n0nO7dvkuf06Tp/Unp7Xz9uQ5FBr7TUTRbTWrmutva+6s3rvqao3VdXfV3fG9yeqO9t7Y1U9cvZ/XkbgfUm+M0mq6jn963Ndv486rqq2J1nRz3tDv9yf92335qraNNMN9fvAt1bVNf3tyf38l1bVJVO0r1TV/+j3g++qqp3VnXE4J8m6JG/o61rRL7758P1ukl9Nsq219rdJ0lr7amvtVf26X19Vr66qXf12n9rXsbeqXj+bPyojNxftdPI+87uT3JTkjqp6UFWdkGRNko/WvXsVrKiup8ANVfWnSVb0879h+0mOq6rX9tu/clI7fXGSn2+tfSFJWmsHWmuX9uvZV1X/q7rPFnuq6nH9e8Q/VBfqGJ9veD9Pck66g0S7qmpXMu1nw2N6bavqkVX1zr49v6/u+Vz5+qr6w/5zwSf6fWOq6n5V9aq+7V1eXY+Wc/p9673q7Zff1n8W+GBVTRxcfVGSF7TWPt3/vl9urb22X/6q6s48v7ffX/77qnpbdb26fmNUf/DBaa25HeWW5OQk1yX5+ySvSvLUJMvTfQBd2S9zbpJL+umrkry2n35Kkpv66QckWdZPPyPJW/vppyW5vJ++IMlFh23/tCTvTXJSf/+FSX69n96XLkAl3Rmx1/XTFyV5UT/9A0lav57VE/VM2vaBJA9PF9Q/kGR9ksck+ehR/iYtyQ/203+W5Mr+b3JmkuvG/Zotxds8t9OnJfmbfvp9/bb39Pdfm+S5/fRL0+1wk+SGJE/tp3970vbu1eb757w/yQl9m/3X/vd4XpLfP8Lv/rQk/5buDe2EJP+U5ML+sV9K8gfjfn2W6i3JF/ufy5L8RZKfS/dB9C+TLO8fe1WSn5y8/KTnf1P/c0W6D7Tf3N/fl+S0qZ7Tz7ssyfp+elWSvdO0r3X9/8+KdD0EPjap7V6VZN2kde/L1PvdjyQ58wh/h9cneWO6sxbPSvKFJGek2+9em+Sx436tlvJtntrpvr4t/rd0Z+Zelq7XwJOTvLdfZnXu2Tf+cu7ZXz8myVcn2uHk7ffP+epEG0rypiTP6dvx54/yO+9L8nP99O+n20efkmRlks+M+zVZyrdM8X4+RXua7rPhUV/bHPZ5cNK2353kUf309+We9/rXJ3lzv886PcnH+/nnJHlHP//BST6f5JzD6+3vtyQ/0k//VpJf66c/l+TUI/wtrkry8n76l5J8Ove819828b+22G7LwlG11r5YVd+b5D+kO3r/p0l+I12XlXdVVZIcl+T2SU/b2T/3vVX1gKp6YLp/jEur6lHpGujyGZbwhHT/CFf32zo+XYia8Lb+57VJ/lM/vT7Js/sa3llVnz/K+j/cWrstSarqunT/sDdMU9NdSd7ZT9+Y5CuttUNVdWP/fObZPLfTDyf5nqo6Kd0Hly/2R9K+M93R4d+dvHBVnZrkga219/Sz/k+So12/eEXrjhh+pao+k5l1XbymtXZ7v71/SHfAIOna54YZPJ+5saLfryRdkN+RZFOS701yTd8uVyT5zBGe/7yqenY//W1JHpUuUE3nGenOwE7cf0BVTXTLnqp9rU/yF621g0lSVX85zfqn2u9O5y9ba63fT/5La+3Gfls3p9tvXne0JzOn5qOdTpw9m+ht8LB++kD63gaHeUqSP0yS1toNVXW09+V/bK1N1H9tuvZU6fbhR/P2/ueNSU5urd2R7ozel6vqga21f5vm+cyBqd7Pq2rLYYtN99nwqK/tVNvtz7w9KcmbJ+07T5i0yJ+31u5Ocsuks17rk7y5n//Pk8+STeGuJBPjHFybrsvtTEz+XW6e9F7/iXT/bzN5T1hQhLMZaK19LV16v6p/Y/2FdA3kiUd6yhT3X5ZkV2vt2VW1ul/fTFSSd7XWzjvC41/pf34t97ye96VP+VcmTU+s4+NJVlXVKf0/9OEOtf4wRpK7J9bRWru7qrSpMZmvdtpa+1JVfTzJc9OdLUiSD6Y7CvwtSf7usKfM5EPCZFO1yZvTHaGbyXPunnT/7tjPjdPB1tpjJ8+o7l3/0tbai472xKp6WrqQ9cS+zV2V5P4z3O79+ucdPGydydTt675ehzPVfvfmdB/mr5/mOZPb58R9bXS85qOdTlx3dka6s2ufSvIr6c6iXnKE1c90v3l4m17RWvtCVd1ZVd/RWjvStY/a5EBN8X7+U4ctMtPPhvfltb1fkn87/H9hinVObH/yz5mY/Nlxqn3n30yz3SXTTl1zNo2qenR/FmHCY5PsTbKyuos2J0Y2nHxx77n9/PVJDrTWDiQ5NV13q6TryjVTH0zy5P6sRKrqxJp+hLrdSf5Lv/xZSR7Uz78jMxjUo7X2pXRHDv+wuuuCJkble859qJt5NIZ2enW6C3gnjtR9IF2Xgw9O2vkmSfqjrwfqnhEdf2LSwzNqk+l22idU1c9MzOj7nj91Bs9lWN6d5Jyq+pYkqapvqqpH9I8dqqqJs7WnpuuW9aX+uocn3IdtXJnkFyfuVNWRPmxM2J3kR6rq/v3R47MnPTbTNvrbSV48sX/ur8X45ftQM8My6nZ6dbpBHj7XWvtaa+1z6QbpemLufcZjwnvT7yurG2zmMZMem7z9o/nNJH9UVQ/o1/OAug/XbjIeR3g/vzX33hcdy2fDo2rdtYn/WFU/1q+zqurMaZ62O8l/7vd335ruMoMJM913/maS36qqB/fbPaEmXQ+8FAln0zs5XTevW/puBacn+fV0R/FfXlXXp+uO8qRJz/l8Vb0/yWuSbOzn/VaS36yqq9N1LzuSC6rqtolbulPKFyTZ2W//g0m+6yjPT5ILk5xVVR9J133s9iR3tNb+Nd0p8JvqngFBjuTXkuxPd/r6piR/3t9nmOa7nV6d5Dtyz4eKj6S7dnGq7jlJ8tPpPiR8IMnksxm70nU/mzwgyDfoA9+zkzyzuouab053/dCnj1IjA9RauyXd/uXKvq2+K901BElycZIbqhvo4J1JlvXLvCzdvm8qJ07eZ/aB6HlJ1lU3mMItmWb0vdbaNem6zlyfrsvintwzWtjrk7ym7j0gyFTruCHdAYudVbU33dmRhxxpeYZtDtrpjemuE/rgYfMOtG7Ah8O9Ot2AXTekG2zmw5Mem7z9o3l1un3sNf37+HuSfGma5zB+U72fvzTd6/7/qmpXa21/7vtnw8M9+rB954+lOyCwsf/McHO6a2SP5q3prv26KckfpxvNeWLf+fV6j7aC1to7kvxRkr/u39uvzSI9IzZTddhBbmap79LwgtbanjHWcEKSr7XWvtqfNXn1UU5TswQNoZ3CkFTVyf21HiemO2uxqbX2kemeB7CUTdp3fnO6gwhPbq3987jrWsiWdDJdxFYleVN136dyV7ph8QE4sour6vR01wtdKpgBzMjl1Q0ycnySlwlms+fMGQAAwAC45gwAAGAAhDMAAIABEM4AAAAGQDgDAAAYAOEMAABgAIQzAACAAfj/bSiO+8UJaLwAAAAASUVORK5CYII=\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris.plot.box(figsize = (15,5))" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[,\n", + " ],\n", + " [,\n", + " ],\n", + " [,\n", + " ]],\n", + " dtype=object)" + ] + }, + "execution_count": 51, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris['StemLengthCmreplacedby0']=iris['StemLengthCm'].fillna(4.8, inplace = False)\n", + "iris.hist(figsize = (15,15))" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 52, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris.plot.box(figsize = (15,5))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/module-3/Data-Cleaning-Challenge/.ipynb_checkpoints/Lab Code-checkpoint.ipynb b/module-3/Data-Cleaning-Challenge/.ipynb_checkpoints/Lab Code-checkpoint.ipynb new file mode 100644 index 00000000..00ac9b7b --- /dev/null +++ b/module-3/Data-Cleaning-Challenge/.ipynb_checkpoints/Lab Code-checkpoint.ipynb @@ -0,0 +1,624 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sepal_length_cmsepal_width_cmpetal_length_cmpetal_width_cmclass
05.13.51.40.2Iris-setosa
14.93.01.40.2Iris-setosa
24.73.21.30.2Iris-setosa
34.63.11.50.2Iris-setosa
45.03.61.40.2Iris-setosa
..................
1456.73.05.22.3Iris-virginica
1466.32.55.02.3Iris-virginica
1476.53.05.22.0Iris-virginica
1486.23.45.42.3Iris-virginica
1495.93.05.11.8Iris-virginica
\n", + "

150 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " sepal_length_cm sepal_width_cm petal_length_cm petal_width_cm \\\n", + "0 5.1 3.5 1.4 0.2 \n", + "1 4.9 3.0 1.4 0.2 \n", + "2 4.7 3.2 1.3 0.2 \n", + "3 4.6 3.1 1.5 0.2 \n", + "4 5.0 3.6 1.4 0.2 \n", + ".. ... ... ... ... \n", + "145 6.7 3.0 5.2 2.3 \n", + "146 6.3 2.5 5.0 2.3 \n", + "147 6.5 3.0 5.2 2.0 \n", + "148 6.2 3.4 5.4 2.3 \n", + "149 5.9 3.0 5.1 1.8 \n", + "\n", + " class \n", + "0 Iris-setosa \n", + "1 Iris-setosa \n", + "2 Iris-setosa \n", + "3 Iris-setosa \n", + "4 Iris-setosa \n", + ".. ... \n", + "145 Iris-virginica \n", + "146 Iris-virginica \n", + "147 Iris-virginica \n", + "148 Iris-virginica \n", + "149 Iris-virginica \n", + "\n", + "[150 rows x 5 columns]" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris = pd.read_csv('iris-data.csv')\n", + "iris" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "sepal_length_cm float64\n", + "sepal_width_cm float64\n", + "petal_length_cm float64\n", + "petal_width_cm float64\n", + "class object\n", + "dtype: object" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "##check the data is encoded/formatted properly\n", + "iris.dtypes\n", + "\n", + "#they are all float which is what we wanted - so yes" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "sepal_length_cm 0\n", + "sepal_width_cm 0\n", + "petal_length_cm 0\n", + "petal_width_cm 5\n", + "class 0\n", + "dtype: int64" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Find any null values\n", + "iris.isna().sum()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "1.2365517241379318" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#we can see that petal_width_cm has null values which I have chosen to replace with the mean\n", + "\n", + "#So finding the mean\n", + "\n", + "iris[\"petal_width_cm\"].mean()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sepal_length_cmsepal_width_cmpetal_length_cmpetal_width_cm
count150.000000150.000000150.000000145.000000
mean5.6446273.0546673.7586671.236552
std1.3127810.4331231.7644200.755058
min0.0550002.0000001.0000000.100000
25%5.1000002.8000001.6000000.400000
50%5.7000003.0000004.3500001.300000
75%6.4000003.3000005.1000001.800000
max7.9000004.4000006.9000002.500000
\n", + "
" + ], + "text/plain": [ + " sepal_length_cm sepal_width_cm petal_length_cm petal_width_cm\n", + "count 150.000000 150.000000 150.000000 145.000000\n", + "mean 5.644627 3.054667 3.758667 1.236552\n", + "std 1.312781 0.433123 1.764420 0.755058\n", + "min 0.055000 2.000000 1.000000 0.100000\n", + "25% 5.100000 2.800000 1.600000 0.400000\n", + "50% 5.700000 3.000000 4.350000 1.300000\n", + "75% 6.400000 3.300000 5.100000 1.800000\n", + "max 7.900000 4.400000 6.900000 2.500000" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris.describe()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "class\n", + "Iris-setosa 0.250000\n", + "Iris-setossa 0.300000\n", + "Iris-versicolor 1.335556\n", + "Iris-virginica 2.034000\n", + "versicolor 1.240000\n", + "Name: petal_width_cm, dtype: float64" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "\n", + "iris['petal_width_cm'].groupby(iris['class']).mean()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 0.2\n", + "1 0.2\n", + "2 0.2\n", + "3 0.2\n", + "4 0.2\n", + " ... \n", + "145 2.3\n", + "146 2.3\n", + "147 2.0\n", + "148 2.3\n", + "149 1.8\n", + "Name: petal_width_cm, Length: 150, dtype: float64" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#replacing null values with the mean of the class\n", + "iris['petal_width_cm'].fillna(iris['petal_width_cm'].groupby(iris['class']).mean())\n" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "sepal_length_cm 0\n", + "sepal_width_cm 0\n", + "petal_length_cm 0\n", + "petal_width_cm 0\n", + "class 0\n", + "dtype: int64" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "#check it's worked - null values are filled\n", + "iris.isna().sum()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "#We can see from the box plot that there are outliers/ they do not all fall within the expected mean? \n", + "#I think pls confirm if this is correct or not?\n", + "\n", + "iris.plot.box()\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[,\n", + " ],\n", + " [,\n", + " ]],\n", + " dtype=object)" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "#visualise the data \n", + "\n", + "iris.hist(bins=10)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\chris\\anaconda3\\lib\\site-packages\\seaborn\\distributions.py:283: UserWarning: Data must have variance to compute a kernel density estimate.\n", + " warnings.warn(msg, UserWarning)\n", + "C:\\Users\\chris\\anaconda3\\lib\\site-packages\\seaborn\\distributions.py:369: UserWarning: Default bandwidth for data is 0; skipping density estimation.\n", + " warnings.warn(msg, UserWarning)\n", + "C:\\Users\\chris\\anaconda3\\lib\\site-packages\\seaborn\\distributions.py:283: UserWarning: Data must have variance to compute a kernel density estimate.\n", + " warnings.warn(msg, UserWarning)\n", + "C:\\Users\\chris\\anaconda3\\lib\\site-packages\\seaborn\\distributions.py:283: UserWarning: Data must have variance to compute a kernel density estimate.\n", + " warnings.warn(msg, UserWarning)\n", + "C:\\Users\\chris\\anaconda3\\lib\\site-packages\\seaborn\\distributions.py:283: UserWarning: Data must have variance to compute a kernel density estimate.\n", + " warnings.warn(msg, UserWarning)\n" + ] + }, + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "import seaborn as sns\n", + "\n", + "sns.pairplot(iris, hue = 'class')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/module-3/Data-Cleaning-Challenge/1- Scikit-Learn Clean and transform - Lecture Live code along.ipynb b/module-3/Data-Cleaning-Challenge/1- Scikit-Learn Clean and transform - Lecture Live code along.ipynb new file mode 100644 index 00000000..a4f1a569 --- /dev/null +++ b/module-3/Data-Cleaning-Challenge/1- Scikit-Learn Clean and transform - Lecture Live code along.ipynb @@ -0,0 +1,1943 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Intro to Data Cleaning & Preprocessing with Scikit Learn Transformers" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Data splitting" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [], + "source": [ + "iris = pd.read_csv(\"iris_codealong.csv\", index_col=0)" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmColorStemLengthCmSpecies
Id
15.13.51.40.2purple3.636364Iris-setosa
24.93.01.40.2yellowNaNIris-setosa
34.73.21.30.2blue2.727273Iris-setosa
44.63.11.50.2purpleNaNIris-setosa
55.03.61.40.2blue1.919192Iris-setosa
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Color \\\n", + "Id \n", + "1 5.1 3.5 1.4 0.2 purple \n", + "2 4.9 3.0 1.4 0.2 yellow \n", + "3 4.7 3.2 1.3 0.2 blue \n", + "4 4.6 3.1 1.5 0.2 purple \n", + "5 5.0 3.6 1.4 0.2 blue \n", + "\n", + " StemLengthCm Species \n", + "Id \n", + "1 3.636364 Iris-setosa \n", + "2 NaN Iris-setosa \n", + "3 2.727273 Iris-setosa \n", + "4 NaN Iris-setosa \n", + "5 1.919192 Iris-setosa " + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "150" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(iris)" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "SepalLengthCm 0\n", + "SepalWidthCm 0\n", + "PetalLengthCm 0\n", + "PetalWidthCm 0\n", + "Color 0\n", + "StemLengthCm 50\n", + "Species 0\n", + "dtype: int64" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris.isna().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Id\n", + "1 3.636364\n", + "2 NaN\n", + "3 2.727273\n", + "4 NaN\n", + "5 1.919192\n", + " ... \n", + "146 0.101010\n", + "147 NaN\n", + "148 3.434343\n", + "149 8.181818\n", + "150 NaN\n", + "Name: StemLengthCm, Length: 150, dtype: float64" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris['StemLengthCm']" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "SepalLengthCm float64\n", + "SepalWidthCm float64\n", + "PetalLengthCm float64\n", + "PetalWidthCm float64\n", + "Color object\n", + "StemLengthCm float64\n", + "Species object\n", + "dtype: object" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris.dtypes" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAD4CAYAAAD8Zh1EAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAOqElEQVR4nO3df6zdd13H8eeLlsloYWAKN7hWWmNBmlUzuNmGS+TWzeQOTesf02wJCGTQf6ig1B9DzUjmP4hO1GWiDcwi1tU5iWuW6jBjN6hxS1eGbF1tvBbcrpsUGEw70HHD2z/uwVzubu/59u7cnt3PeT6SZvd7vp9z7vuzds977rf3nKWqkCStfi8Y9gCSpMEw6JLUCIMuSY0w6JLUCIMuSY1YO6xPvGHDhtq8efOy7vv000+zbt26wQ70POeeR4N7Hg3PZc9Hjx79SlW9YrFzQwv65s2beeCBB5Z136mpKSYmJgY70POcex4N7nk0PJc9J/n3M53zkoskNcKgS1IjDLokNcKgS1IjDLokNcKgS1Ij+gY9ya1JTiV5+Aznk+QPkkwn+XyS1w9+TElSP12eoe8HJpc4fxWwtfdrN/CR5z6WJOls9Q16VX0GeHKJJbuAP6059wEvS/KqQQ0oSeomXf4HF0k2A3dV1UWLnLsL+GBV/UPv+B7gV6vqWS8DTbKbuWfxjI2NveHgwYPLGvrUk0/xpW8u666r1tj5uOcR4J5Hw5YL1rB+/fpl3XfHjh1Hq2p8sXODeOl/Frlt0a8SVbUP2AcwPj5ey33p680H7uSmh4b2rgVDsXf7rHseAe55NOyfXLcib3cwiJ9ymQE2zTveCDw+gMeVJJ2FQQT9EPBzvZ92uQx4qqqeGMDjSpLOQt/vc5LcBkwAG5LMAB8AXghQVX8EHAbeDEwD3wDesVLDSpLOrG/Qq+raPucLePfAJpIkLYuvFJWkRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWpEp6AnmUxyIsl0kusXOf/9Se5N8mCSzyd58+BHlSQtpW/Qk6wBbgGuArYB1ybZtmDZbwC3V9XFwDXAHw56UEnS0ro8Q78EmK6qk1X1DHAQ2LVgTQEv7X18AfD44EaUJHWRqlp6QXI1MFlV7+wdvxW4tKr2zFvzKuBTwMuBdcCVVXV0kcfaDewGGBsbe8PBgweXNfSpJ5/iS99c1l1XrbHzcc8jwD2Phi0XrGH9+vXLuu+OHTuOVtX4YufWdrh/Frlt4VeBa4H9VXVTkjcCn0hyUVV9+7vuVLUP2AcwPj5eExMTHT79s9184E5ueqjL6O3Yu33WPY8A9zwa9k+uY7n9W0qXSy4zwKZ5xxt59iWV64DbAarqn4AXARsGMaAkqZsuQT8CbE2yJcl5zP2l56EFax4FrgBI8jrmgv7lQQ4qSVpa36BX1SywB7gbOM7cT7McS3Jjkp29ZXuBdyX5Z+A24O3V7+K8JGmgOl24qqrDwOEFt90w7+NHgMsHO5ok6Wz4SlFJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGdAp6kskkJ5JMJ7n+DGt+NskjSY4l+fPBjilJ6mdtvwVJ1gC3AD8BzABHkhyqqkfmrdkKvB+4vKq+luSVKzWwJGlxXZ6hXwJMV9XJqnoGOAjsWrDmXcAtVfU1gKo6NdgxJUn9dAn6hcBj845nerfN9xrgNUn+Mcl9SSYHNaAkqZu+l1yALHJbLfI4W4EJYCPw90kuqqqvf9cDJbuB3QBjY2NMTU2d7bwAjJ0Pe7fPLuu+q5V7Hg3ueTScPn162f1bSpegzwCb5h1vBB5fZM19VfUt4AtJTjAX+CPzF1XVPmAfwPj4eE1MTCxr6JsP3MlND3UZvR17t8+65xHgnkfD/sl1LLd/S+lyyeUIsDXJliTnAdcAhxas+WtgB0CSDcxdgjk5yEElSUvrG/SqmgX2AHcDx4Hbq+pYkhuT7Owtuxv4apJHgHuBX66qr67U0JKkZ+v0fU5VHQYOL7jthnkfF/C+3i9J0hD4SlFJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJaoRBl6RGGHRJakSnoCeZTHIiyXSS65dYd3WSSjI+uBElSV30DXqSNcAtwFXANuDaJNsWWfcS4D3A/YMeUpLUX5dn6JcA01V1sqqeAQ4CuxZZ95vAh4D/GeB8kqSO1nZYcyHw2LzjGeDS+QuSXAxsqqq7kvzSmR4oyW5gN8DY2BhTU1NnPTDA2Pmwd/vssu67Wrnn0eCeR8Pp06eX3b+ldAl6Frmt/v9k8gLgw8Db+z1QVe0D9gGMj4/XxMREpyEXuvnAndz0UJfR27F3+6x7HgHueTTsn1zHcvu3lC6XXGaATfOONwKPzzt+CXARMJXki8BlwCH/YlSSzq0uQT8CbE2yJcl5wDXAoe+crKqnqmpDVW2uqs3AfcDOqnpgRSaWJC2qb9CrahbYA9wNHAdur6pjSW5MsnOlB5QkddPpwlVVHQYOL7jthjOsnXjuY0mSzpavFJWkRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWpEp6AnmUxyIsl0kusXOf++JI8k+XySe5K8evCjSpKW0jfoSdYAtwBXAduAa5NsW7DsQWC8qn4YuAP40KAHlSQtrcsz9EuA6ao6WVXPAAeBXfMXVNW9VfWN3uF9wMbBjilJ6mdthzUXAo/NO54BLl1i/XXA3yx2IsluYDfA2NgYU1NT3aZcYOx82Lt9dln3Xa3c82hwz6Ph9OnTy+7fUroEPYvcVosuTN4CjANvWux8Ve0D9gGMj4/XxMREtykXuPnAndz0UJfR27F3+6x7HgHueTTsn1zHcvu3lC7/FmeATfOONwKPL1yU5Erg14E3VdX/DmY8SVJXXa6hHwG2JtmS5DzgGuDQ/AVJLgb+GNhZVacGP6YkqZ++Qa+qWWAPcDdwHLi9qo4luTHJzt6y3wbWA3+Z5HNJDp3h4SRJK6TThauqOgwcXnDbDfM+vnLAc0mSzpKvFJWkRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRhh0SWqEQZekRnQKepLJJCeSTCe5fpHz35PkL3rn70+yedCDSpKW1jfoSdYAtwBXAduAa5NsW7DsOuBrVfWDwIeB3xr0oJKkpXV5hn4JMF1VJ6vqGeAgsGvBml3Ax3sf3wFckSSDG1OS1E+qaukFydXAZFW9s3f8VuDSqtozb83DvTUzveN/6635yoLH2g3s7h2+FjixzLk3AF/pu6ot7nk0uOfR8Fz2/OqqesViJ9Z2uPNiz7QXfhXosoaq2gfs6/A5lx4oeaCqxp/r46wm7nk0uOfRsFJ77nLJZQbYNO94I/D4mdYkWQtcADw5iAElSd10CfoRYGuSLUnOA64BDi1Ycwh4W+/jq4FPV79rOZKkgep7yaWqZpPsAe4G1gC3VtWxJDcCD1TVIeBjwCeSTDP3zPyalRyaAVy2WYXc82hwz6NhRfbc9y9FJUmrg68UlaRGGHRJasSqC3q/tyFoTZJNSe5NcjzJsSTvHfZM50KSNUkeTHLXsGc5F5K8LMkdSf6l93v9xmHPtNKS/GLvz/TDSW5L8qJhzzRoSW5Ncqr3Wp3v3Pa9Sf4uyb/2/vnyQX2+VRX0jm9D0JpZYG9VvQ64DHj3COwZ4L3A8WEPcQ79PvC3VfVDwI/Q+N6TXAi8BxivqouY+4GLlf5himHYD0wuuO164J6q2grc0zseiFUVdLq9DUFTquqJqvps7+P/Zu4/9AuHO9XKSrIR+Engo8Oe5VxI8lLgx5j7aTGq6pmq+vpwpzon1gLn91678mKe/fqWVa+qPsOzX5Mz/61SPg789KA+32oL+oXAY/OOZ2g8bvP13sXyYuD+4U6y4n4P+BXg28Me5Bz5AeDLwJ/0LjN9NMm6YQ+1kqrqP4DfAR4FngCeqqpPDXeqc2asqp6AuSdswCsH9cCrLeid3mKgRUnWA38F/EJV/dew51kpSX4KOFVVR4c9yzm0Fng98JGquhh4mgF+G/581LtuvAvYAnwfsC7JW4Y71eq32oLe5W0ImpPkhczF/EBVfXLY86ywy4GdSb7I3CW1H0/yZ8MdacXNADNV9Z3vvO5gLvAtuxL4QlV9uaq+BXwS+NEhz3SufCnJqwB6/zw1qAdebUHv8jYETem9DfHHgONV9bvDnmelVdX7q2pjVW1m7vf301XV9DO3qvpP4LEkr+3ddAXwyBBHOhceBS5L8uLen/EraPwvgueZ/1YpbwPuHNQDd3m3xeeNM70NwZDHWmmXA28FHkryud5tv1ZVh4c4kwbv54EDvScqJ4F3DHmeFVVV9ye5A/gscz/J9SANvgVAktuACWBDkhngA8AHgduTXMfcF7afGdjn86X/ktSG1XbJRZJ0BgZdkhph0CWpEQZdkhph0CWpEQZdkhph0CWpEf8HF3LuSvWwLEUAAAAASUVORK5CYII=\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris['StemLengthCm'].hist(bins=100)" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris['StemLengthCm'].plot.box()" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "4.999999999999999" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris['StemLengthCm'].mean()" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmStemLengthCm
count150.000000150.000000150.000000150.000000100.000000
mean5.8433333.0540003.7586671.1986675.000000
std0.8280660.4335941.7644200.7631612.930454
min4.3000002.0000001.0000000.1000000.000000
25%5.1000002.8000001.6000000.3000002.500000
50%5.8000003.0000004.3500001.3000005.000000
75%6.4000003.3000005.1000001.8000007.500000
max7.9000004.4000006.9000002.50000010.000000
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm StemLengthCm\n", + "count 150.000000 150.000000 150.000000 150.000000 100.000000\n", + "mean 5.843333 3.054000 3.758667 1.198667 5.000000\n", + "std 0.828066 0.433594 1.764420 0.763161 2.930454\n", + "min 4.300000 2.000000 1.000000 0.100000 0.000000\n", + "25% 5.100000 2.800000 1.600000 0.300000 2.500000\n", + "50% 5.800000 3.000000 4.350000 1.300000 5.000000\n", + "75% 6.400000 3.300000 5.100000 1.800000 7.500000\n", + "max 7.900000 4.400000 6.900000 2.500000 10.000000" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.model_selection import train_test_split\n", + "train_set, test_set = train_test_split(iris, test_size=0.2, random_state=123)" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmColorStemLengthCmSpecies
Id
1317.42.86.11.9purpleNaNIris-virginica
1206.02.25.01.5purple4.141414Iris-virginica
304.73.21.60.2blue5.757576Iris-setosa
15.13.51.40.2purple3.636364Iris-setosa
636.02.24.01.0red8.989899Iris-versicolor
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Color \\\n", + "Id \n", + "131 7.4 2.8 6.1 1.9 purple \n", + "120 6.0 2.2 5.0 1.5 purple \n", + "30 4.7 3.2 1.6 0.2 blue \n", + "1 5.1 3.5 1.4 0.2 purple \n", + "63 6.0 2.2 4.0 1.0 red \n", + "\n", + " StemLengthCm Species \n", + "Id \n", + "131 NaN Iris-virginica \n", + "120 4.141414 Iris-virginica \n", + "30 5.757576 Iris-setosa \n", + "1 3.636364 Iris-setosa \n", + "63 8.989899 Iris-versicolor " + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_set.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmStemLengthCm
count120.000000120.000000120.000000120.00000080.000000
mean5.8691673.0408333.8208331.2233334.830808
std0.8129000.4404921.7288410.7425522.980444
min4.4000002.0000001.0000000.1000000.000000
25%5.1000002.8000001.6000000.4000002.297980
50%5.8000003.0000004.3500001.3000004.696970
75%6.4000003.3000005.1000001.8000007.601010
max7.9000004.4000006.9000002.50000010.000000
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm StemLengthCm\n", + "count 120.000000 120.000000 120.000000 120.000000 80.000000\n", + "mean 5.869167 3.040833 3.820833 1.223333 4.830808\n", + "std 0.812900 0.440492 1.728841 0.742552 2.980444\n", + "min 4.400000 2.000000 1.000000 0.100000 0.000000\n", + "25% 5.100000 2.800000 1.600000 0.400000 2.297980\n", + "50% 5.800000 3.000000 4.350000 1.300000 4.696970\n", + "75% 6.400000 3.300000 5.100000 1.800000 7.601010\n", + "max 7.900000 4.400000 6.900000 2.500000 10.000000" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_set.describe()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Do you see anything rare?" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "Int64Index: 120 entries, 131 to 110\n", + "Data columns (total 7 columns):\n", + "SepalLengthCm 120 non-null float64\n", + "SepalWidthCm 120 non-null float64\n", + "PetalLengthCm 120 non-null float64\n", + "PetalWidthCm 120 non-null float64\n", + "Color 120 non-null object\n", + "StemLengthCm 80 non-null float64\n", + "Species 120 non-null object\n", + "dtypes: float64(5), object(2)\n", + "memory usage: 7.5+ KB\n" + ] + } + ], + "source": [ + "train_set.info()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Now we will drop the text column so all of them are numerical." + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmColorStemLengthCm
Id
1317.42.86.11.9purpleNaN
1206.02.25.01.5purple4.141414
304.73.21.60.2blue5.757576
15.13.51.40.2purple3.636364
636.02.24.01.0red8.989899
.....................
185.13.51.40.3purple4.545455
995.12.53.01.1red9.898990
675.63.04.51.5blue4.949495
1276.22.84.81.8yellowNaN
1107.23.66.12.5purple0.606061
\n", + "

120 rows × 6 columns

\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Color \\\n", + "Id \n", + "131 7.4 2.8 6.1 1.9 purple \n", + "120 6.0 2.2 5.0 1.5 purple \n", + "30 4.7 3.2 1.6 0.2 blue \n", + "1 5.1 3.5 1.4 0.2 purple \n", + "63 6.0 2.2 4.0 1.0 red \n", + ".. ... ... ... ... ... \n", + "18 5.1 3.5 1.4 0.3 purple \n", + "99 5.1 2.5 3.0 1.1 red \n", + "67 5.6 3.0 4.5 1.5 blue \n", + "127 6.2 2.8 4.8 1.8 yellow \n", + "110 7.2 3.6 6.1 2.5 purple \n", + "\n", + " StemLengthCm \n", + "Id \n", + "131 NaN \n", + "120 4.141414 \n", + "30 5.757576 \n", + "1 3.636364 \n", + "63 8.989899 \n", + ".. ... \n", + "18 4.545455 \n", + "99 9.898990 \n", + "67 4.949495 \n", + "127 NaN \n", + "110 0.606061 \n", + "\n", + "[120 rows x 6 columns]" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_labels = iris[\"Species\"]\n", + "train_set.drop(\"Species\", axis = 1)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Fill missing values\n", + "\n", + "**Exercise**: read https://scikit-learn.org/stable/modules/generated/sklearn.impute.SimpleImputer.html and figure out how to impute the mean or the median to missing values in \"StemLengthCm\"" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "\u001b[0;31mInit signature:\u001b[0m\n", + "\u001b[0mSimpleImputer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mmissing_values\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mnan\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mstrategy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'mean'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mfill_value\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mverbose\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mcopy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0madd_indicator\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mDocstring:\u001b[0m \n", + "Imputation transformer for completing missing values.\n", + "\n", + "Read more in the :ref:`User Guide `.\n", + "\n", + "Parameters\n", + "----------\n", + "missing_values : number, string, np.nan (default) or None\n", + " The placeholder for the missing values. All occurrences of\n", + " `missing_values` will be imputed.\n", + "\n", + "strategy : string, optional (default=\"mean\")\n", + " The imputation strategy.\n", + "\n", + " - If \"mean\", then replace missing values using the mean along\n", + " each column. Can only be used with numeric data.\n", + " - If \"median\", then replace missing values using the median along\n", + " each column. Can only be used with numeric data.\n", + " - If \"most_frequent\", then replace missing using the most frequent\n", + " value along each column. Can be used with strings or numeric data.\n", + " - If \"constant\", then replace missing values with fill_value. Can be\n", + " used with strings or numeric data.\n", + "\n", + " .. versionadded:: 0.20\n", + " strategy=\"constant\" for fixed value imputation.\n", + "\n", + "fill_value : string or numerical value, optional (default=None)\n", + " When strategy == \"constant\", fill_value is used to replace all\n", + " occurrences of missing_values.\n", + " If left to the default, fill_value will be 0 when imputing numerical\n", + " data and \"missing_value\" for strings or object data types.\n", + "\n", + "verbose : integer, optional (default=0)\n", + " Controls the verbosity of the imputer.\n", + "\n", + "copy : boolean, optional (default=True)\n", + " If True, a copy of X will be created. If False, imputation will\n", + " be done in-place whenever possible. Note that, in the following cases,\n", + " a new copy will always be made, even if `copy=False`:\n", + "\n", + " - If X is not an array of floating values;\n", + " - If X is encoded as a CSR matrix;\n", + " - If add_indicator=True.\n", + "\n", + "add_indicator : boolean, optional (default=False)\n", + " If True, a `MissingIndicator` transform will stack onto output\n", + " of the imputer's transform. This allows a predictive estimator\n", + " to account for missingness despite imputation. If a feature has no\n", + " missing values at fit/train time, the feature won't appear on\n", + " the missing indicator even if there are missing values at\n", + " transform/test time.\n", + "\n", + "Attributes\n", + "----------\n", + "statistics_ : array of shape (n_features,)\n", + " The imputation fill value for each feature.\n", + "\n", + "indicator_ : :class:`sklearn.impute.MissingIndicator`\n", + " Indicator used to add binary indicators for missing values.\n", + " ``None`` if add_indicator is False.\n", + "\n", + "See also\n", + "--------\n", + "IterativeImputer : Multivariate imputation of missing values.\n", + "\n", + "Examples\n", + "--------\n", + ">>> import numpy as np\n", + ">>> from sklearn.impute import SimpleImputer\n", + ">>> imp_mean = SimpleImputer(missing_values=np.nan, strategy='mean')\n", + ">>> imp_mean.fit([[7, 2, 3], [4, np.nan, 6], [10, 5, 9]])\n", + "... # doctest: +NORMALIZE_WHITESPACE\n", + "SimpleImputer(add_indicator=False, copy=True, fill_value=None,\n", + " missing_values=nan, strategy='mean', verbose=0)\n", + ">>> X = [[np.nan, 2, 3], [4, np.nan, 6], [10, np.nan, 9]]\n", + ">>> print(imp_mean.transform(X))\n", + "... # doctest: +NORMALIZE_WHITESPACE\n", + "[[ 7. 2. 3. ]\n", + " [ 4. 3.5 6. ]\n", + " [10. 3.5 9. ]]\n", + "\n", + "Notes\n", + "-----\n", + "Columns which only contained missing values at `fit` are discarded upon\n", + "`transform` if strategy is not \"constant\".\n", + "\u001b[0;31mFile:\u001b[0m ~/opt/anaconda3/lib/python3.7/site-packages/sklearn/impute/_base.py\n", + "\u001b[0;31mType:\u001b[0m type\n", + "\u001b[0;31mSubclasses:\u001b[0m \n" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "from sklearn.impute import SimpleImputer\n", + "\n", + "# Function for the value replacements\n", + "\n", + "?SimpleImputer" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "4.830808080808081" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_num['StemLengthCm'].mean()" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "SepalLengthCm float64\n", + "SepalWidthCm float64\n", + "PetalLengthCm float64\n", + "PetalWidthCm float64\n", + "Color object\n", + "StemLengthCm float64\n", + "Species object\n", + "dtype: object" + ] + }, + "execution_count": 39, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_set.dtypes" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmStemLengthCm
Id
1317.42.86.11.94.830808
1206.02.25.01.54.141414
304.73.21.60.25.757576
15.13.51.40.23.636364
636.02.24.01.08.989899
945.02.33.31.01.717172
1327.93.86.42.04.343434
65.43.91.70.42.828283
175.43.91.30.40.505051
835.82.73.91.25.656566
615.02.03.51.00.808081
365.03.21.20.24.830808
1446.83.25.92.34.830808
1466.73.05.22.30.101010
1435.82.75.11.94.830808
1155.82.85.12.44.830808
1376.33.45.62.44.830808
545.52.34.01.30.404040
205.13.81.50.32.020202
394.43.01.30.25.858586
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm StemLengthCm\n", + "Id \n", + "131 7.4 2.8 6.1 1.9 4.830808\n", + "120 6.0 2.2 5.0 1.5 4.141414\n", + "30 4.7 3.2 1.6 0.2 5.757576\n", + "1 5.1 3.5 1.4 0.2 3.636364\n", + "63 6.0 2.2 4.0 1.0 8.989899\n", + "94 5.0 2.3 3.3 1.0 1.717172\n", + "132 7.9 3.8 6.4 2.0 4.343434\n", + "6 5.4 3.9 1.7 0.4 2.828283\n", + "17 5.4 3.9 1.3 0.4 0.505051\n", + "83 5.8 2.7 3.9 1.2 5.656566\n", + "61 5.0 2.0 3.5 1.0 0.808081\n", + "36 5.0 3.2 1.2 0.2 4.830808\n", + "144 6.8 3.2 5.9 2.3 4.830808\n", + "146 6.7 3.0 5.2 2.3 0.101010\n", + "143 5.8 2.7 5.1 1.9 4.830808\n", + "115 5.8 2.8 5.1 2.4 4.830808\n", + "137 6.3 3.4 5.6 2.4 4.830808\n", + "54 5.5 2.3 4.0 1.3 0.404040\n", + "20 5.1 3.8 1.5 0.3 2.020202\n", + "39 4.4 3.0 1.3 0.2 5.858586" + ] + }, + "execution_count": 41, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# I'll show how we'd do it for all numerical features\n", + "train_num = train_set.select_dtypes(include=[\"float64\"])\n", + "\n", + "# we 'initiate' the transformer\n", + "imputer = SimpleImputer(strategy=\"mean\")\n", + "\n", + "# we use its 'fit_transform' method on the selected features of the training set\n", + "# 'fit' in this case means looking for the mean in each selected feature\n", + "# 'transform' means actually replacing NANs with the mean\n", + "X = imputer.fit_transform(train_num)\n", + "# transform output back to dataframe \n", + "# (not needed for modelling, but it might help if you have to keep exploring)\n", + "train_num = pd.DataFrame(X,\n", + " columns=train_num.columns,\n", + " index=train_num.index)\n", + "train_num.head(20)" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "4.830808080808081" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_num['StemLengthCm'].mean()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Now we do it on the test set. Important to understand that we don't want to 'fit' the transformer again! We just want to replace the NAN's with the value we already decidid (in this case the mean). We'll make sure everyone understands why! \n", + "\n", + "Optional reading: https://medium.com/@chipk215/are-you-unknowingly-data-snooping-when-training-your-ml-models-7d6a70bdff1b\n", + "\n", + "Extra example: in a 'production' setting, it's likely you won't have to make predictions on any 'set' of observations, you'll make predictions on individual observations (you can't take the mean to fill NAN's there). We're trying to replicate the conditions we'll have in 'production' to see whether or not we can produce a model capable of making good generalizations." + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SepalLengthCmSepalWidthCmPetalLengthCmPetalWidthCmStemLengthCm
Id
736.32.54.91.58.383838
1136.83.05.52.16.868687
1336.42.85.62.27.474747
895.63.04.11.33.535354
384.93.11.50.16.969697
1396.03.04.81.87.272727
886.32.34.41.34.830808
434.43.21.30.20.303030
94.42.91.40.28.787879
915.52.64.41.20.909091
1426.93.15.12.36.060606
345.54.21.40.24.830808
605.22.73.91.44.830808
1176.53.05.51.84.444444
1367.73.06.12.34.830808
1056.53.05.82.29.696970
375.53.51.30.26.161616
144.33.01.10.14.830808
646.12.94.71.44.830808
464.83.01.40.36.767677
\n", + "
" + ], + "text/plain": [ + " SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm StemLengthCm\n", + "Id \n", + "73 6.3 2.5 4.9 1.5 8.383838\n", + "113 6.8 3.0 5.5 2.1 6.868687\n", + "133 6.4 2.8 5.6 2.2 7.474747\n", + "89 5.6 3.0 4.1 1.3 3.535354\n", + "38 4.9 3.1 1.5 0.1 6.969697\n", + "139 6.0 3.0 4.8 1.8 7.272727\n", + "88 6.3 2.3 4.4 1.3 4.830808\n", + "43 4.4 3.2 1.3 0.2 0.303030\n", + "9 4.4 2.9 1.4 0.2 8.787879\n", + "91 5.5 2.6 4.4 1.2 0.909091\n", + "142 6.9 3.1 5.1 2.3 6.060606\n", + "34 5.5 4.2 1.4 0.2 4.830808\n", + "60 5.2 2.7 3.9 1.4 4.830808\n", + "117 6.5 3.0 5.5 1.8 4.444444\n", + "136 7.7 3.0 6.1 2.3 4.830808\n", + "105 6.5 3.0 5.8 2.2 9.696970\n", + "37 5.5 3.5 1.3 0.2 6.161616\n", + "14 4.3 3.0 1.1 0.1 4.830808\n", + "64 6.1 2.9 4.7 1.4 4.830808\n", + "46 4.8 3.0 1.4 0.3 6.767677" + ] + }, + "execution_count": 44, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# select only numerical features\n", + "test_num = test_set.select_dtypes(include=[\"float64\"])\n", + "\n", + "# the imputer's already created and fitted. we just need to use the .transform() method \n", + "# to fill Nan's with the mean\n", + "test_X = imputer.transform(test_num)\n", + "# transform output back to dataframe \n", + "# (not needed for modelling, but it might help if you have to keep exploring)\n", + "test_num = pd.DataFrame(test_X,\n", + " columns=test_num.columns,\n", + " index=test_num.index)\n", + "\n", + "test_num.head(20)" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "4.830808080808081" + ] + }, + "execution_count": 45, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_num['StemLengthCm'].mean()" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "5.394781144781145" + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "test_num['StemLengthCm'].mean()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Summary\n", + "\n", + "Beware with nans. The replacement decision will impact for sure the outcome of the analysis. Most common reactions;\n", + "+ delete all rows with nans.\n", + "+ Replace by zeroes.\n", + "+ Replace by the average or median (Imputer).\n", + "\n", + "If the replacement is done based on actual data distribution, make sure not to cheat yourself. You shouldn't use test data for that. If you then need to extrapolate the replacement to the test dataset then you must use the value concluded as per the training dataset.\n", + "\n", + "## What about if we didn't want to replace by the mean?" + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "SepalLengthCm 0\n", + "SepalWidthCm 0\n", + "PetalLengthCm 0\n", + "PetalWidthCm 0\n", + "Color 0\n", + "StemLengthCm 50\n", + "Species 0\n", + "dtype: int64" + ] + }, + "execution_count": 47, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris = pd.read_csv(\"iris_codealong.csv\", index_col=0)\n", + "iris.isna().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[,\n", + " ],\n", + " [,\n", + " ],\n", + " [,\n", + " ]],\n", + " dtype=object)" + ] + }, + "execution_count": 48, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris.hist(figsize = (15,15))" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 49, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris.plot.box(figsize = (15,5))" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[,\n", + " ],\n", + " [,\n", + " ],\n", + " [,\n", + " ]],\n", + " dtype=object)" + ] + }, + "execution_count": 51, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA2wAAANeCAYAAABu3o33AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAgAElEQVR4nOzdfZyldX3f/9ebu7ABFSM4XYG4NpJU41awE2JKaiZoEiJVsDWphipU81iTX2z0kY0J2lbxJg22QdNYa7oGhUaqEtCCgiaoTJDGYEDRBddUxY0CK3jD3RBLOvj5/XGuIYed2Z0zM+ec65ozr+fjcR57zve6+1zfuc5+z+e6vtf3SlUhSZIkSeqeA9oOQJIkSZK0NBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNm04SbYkqSQHtR1LvySzSX657TgkSRqGtba3SW5OMrOPaTNJbh3VtqUuMWFTpyTZneS7SeaS3JHk3UkOX2aZs5Jcu4Ztjj1RSnJOkvescJlDmuW+lOT+pq7elWTLaKKUJE2qcbe3SV6Y5At7lV21j7KzAarqR6tqdsD1707yrBXG9MNJ/iTJt5Lck+TzSX4jyYErWY80aiZs6qLnVNXhwNOAHwP+fcvxdMUlwHOBXwIeBTwVuAF4ZptBSZLWrXG2t38OPCnJUQDNla+nAt+/V9lPANeMMA6abf0QcB3wdWBrVT0K+AVgGnjEqLcvrYQJmzqrqm4DPgI8JcmjkpyfZE+S25K8KcmBSZ4E/CHwE81ZwrsBkpya5LNJ7k3y9STnrCaGJE9P8hdJ7k7yuf6uGc2VuTcm+d9J7kvyZ0mO7Jv+4iR/k+TbSf7Dwtm/JKcArwH+VRPz5/o2+fil1tecNfwZ4LSq+quqmq+qe6rq7VV1fl88b2rinUvyoSSPSXJRUw9/5dU4SdLextHeVtXtwC3AM5qipwE300vk+ssOAK5v1v3QVbMkm5JckOSu5qrcjy2sO8kfAz8IfKiJ7bf6Nn1Gkq81V9H+XV/564G/qKrfqKo9TYx/XVW/VFV393Wp/DfNft2V5FeS/FhzJe7uJP91dTUurYwJmzorybHAs4HPAhcC88ATgROAnwV+uap2Ab8CfKqqDq+qI5rF7wdeDBwBnAr8apLTV7j9o4ErgDcBPwD8JnDpwpnAxi8B/wZ4LHBIMw9Jngz8N+AMYDO9K2JHA1TVR4H/CLy/ifmpy60PeBbw6ar6+jJhvwB4UbOtHwI+Bby7iX8X8LqV1IEkafKNsb29hr9Pzp4BfBK4dq+yv6yqv1ti2dfRa9d+CPg54MyFCVX1IuBrNFcMq+o/9S33k8CP0OuN8tom8YReu3rJ/uql8ePAccC/An4f+HfNsj8K/GKSnxpgHdKamLCpi/5Xc+buWnpn3v4I+HnglVV1f1XdCbyVXnKypKqaraqdVfW9qvo88F5gpf+p/mvgyqq6slnPVfTO+j27b553V9X/qarvAhcDxzflzwc+VFXXNg3Pa4EaYJv7Wt9jgD0DLv+VqrqH3tnSr1TVx6pqHvgTeo2vJEkw/va2/2raP6OXsH1yr7I/38eyvwj8TlV9pzl5+QcD7uPrq+q7VfU54HP0umHC4O3qG6vq/1bVn9FLTt9bVXc2VyU/ie2qxsCRc9RFp1fVxxY+JDkROBjYk2Sh+AB6/c6XlOTHgXOBp9C7UvV99BKWlXg88AtJntNXdjBwdd/nb/S9/1tg4Ybtx/XHV1V/m+TbA2xzX+v7NvDDAyx/R9/77y7xeb83lEuSNpRxt7fXAOcneTTwdOCMqppLsrkp+0l6V7GW8rB2FfibZfZtwf7a1c0DLG+7qtZ5hU3rwdeBB4Ajq+qI5vXIqvrRZvpSV67+J3A5cGxzI/EfAllivuW2+8d92zyiqg6rqnMHWHYPcMzChySb6J3NWzDI1bZ+HwNOTHLMsnNKkrQ6I21vq+oW4HZgG/C1qpprJn2qKTsc+Mt9xLYHOLbv8w/uvfr97tliHwP+5QqXkVphwqbOa24G/jPgvCSPTHJAkh/q6zd+B3BMkkP6FnsE8J2q+r/NGcNfWmYzByU5tO91MPAe4DlJfq654frQ9J77MkjSdEmz7D9t4no9D2/A7gC2JBnoO9icAb0K+GCSf5LkoCSPaG6Afskg65AkaX/G1N5+EviN5t8F1zZl1ze3BCzlYuDVSR7dtMP/dq/pdwD/cLl97PM64J8m+c9J/gFAkicmeU+SI5ZZVhorEzatFy+m19XiC8Bd9BKiha4Mn6A30tQ3knyrKfv/gDckuY/e/WMXL7P+d9Dr2rDwenfTR/40eiM6fpPemcdXMcD3pqpupteYvI/eWcH7gDvpnbmEv+8u8u0kn1lufY3nA1cC7wfuAW6iN/zwx/a3kCRJKzDq9vbP6Q2s1f88t082Zfsbzv/19LpBfpVeUvnHe03/XeDfN6M3/ubeC++tqr5C7xECW4Cbk9wDXErvXvX7llteGqdUrfQKsqSVSu9hpHcDx1XVV9uOR5IkSeuDV9ikEUnynCTfn+Qw4PeAncDudqOSJEnSemLCJo3OafRurr6d3jNcXlBe0pYkSdIK2CVSkiRJkjrKK2ySJEmS1FFjfXD2kUceWVu2bFn18vfffz+HHXbY8ALqoEnfR/dvfXP/1reV7N8NN9zwrao6asQhaYj629hJP5ZXwzpZzDpZzDp5OOtjsWHUyUrb2LEmbFu2bOH6669f9fKzs7PMzMwML6AOmvR9dP/WN/dvfVvJ/iX5m9FGo2Hrb2Mn/VheDetkMetkMevk4ayPxYZRJyttY+0SKUmSJEkdZcImSZIkSR1lwiZJkiRJHWXCJkmSJEkdZcImSZIkSR1lwiZJkiRJHWXCJkmSJEkdZcImSZIkSR1lwiZJkiRJHXVQ2wGsxM7b7uGss69oOwx2n3tq2yFIkjR0W2xjJalzvMImSZIkSR1lwiZJUsuSHJjks0k+3Hx+QpLrknwpyfuTHNJ2jJKkdpiwSZLUvlcAu/o+vxl4a1UdB9wFvLSVqCRJrTNhkySpRUmOAU4F/qj5HOBk4JJmlguB09uJTpLUtnU16IgkSRPo94HfAh7RfH4McHdVzTefbwWOXmrBJNuAbQBTU1PMzs4CMDc399D7ldi+dX75mUZsNXEPYrV1Msmsk8Wsk4ezPhZro05M2CRJakmSfw7cWVU3JJlZKF5i1lpq+araAewAmJ6erpmZ3ipmZ2dZeL8SnRiJ+YyZkax3tXUyyayTxayTh7M+FmujTkzYJElqz0nAc5M8GzgUeCS9K25HJDmoucp2DHB7izFKklrkPWySJLWkql5dVcdU1RbgBcAnquoM4Grg+c1sZwKXtRSiJKllyyZsSQ5N8ukkn0tyc5LXN+UXJPlqkhub1/GjD1eSpA3ht4HfSPJleve0nd9yPJKklgzSJfIB4OSqmktyMHBtko80015VVZfsZ1lJkjSAqpoFZpv3twAnthmPJKkblk3YqqqAuebjwc1ryZufJUmSJEnDM9CgI0kOBG4Angi8vaquS/KrwO8keS3wceDsqnpgiWWXHHJ4NaY2TfaQwzD5w6e6f+ub+7e+Tfr+SZI0iQZK2KrqQeD4JEcAH0zyFODVwDeAQ+gNKfzbwBuWWHbJIYdX420XXcZ5O9sf2HJUQw7D5A+f6v6tb+7f+jbp+ydJ0iRa0SiRVXU3vf71p1TVnup5AHg39rWXJEmSpKEaZJTIo5orayTZBDwL+GKSzU1ZgNOBm0YZqCRJkiRtNIP0L9wMXNjcx3YAcHFVfTjJJ5IcBQS4EfiVEcYpSZIkSRvOIKNEfh44YYnyk0cSkSRJkiQJWOE9bJIkSZKk8TFhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJKklSQ5N8ukkn0tyc5LXN+UXJPlqkhub1/FtxypJasdBbQcgSdIG9gBwclXNJTkYuDbJR5ppr6qqS1qMTZLUASZskiS1pKoKmGs+Hty8qr2IJEldY8ImSVKLkhwI3AA8EXh7VV2X5FeB30nyWuDjwNlV9cASy24DtgFMTU0xOzsLwNzc3EPvV2L71vlV7sXwrCbuQay2TiaZdbKYdfJw1sdibdSJCZskSS2qqgeB45McAXwwyVOAVwPfAA4BdgC/DbxhiWV3NNOZnp6umZkZoJf0LLxfibPOvmJV+zBMu8+YGcl6V1snk8w6Wcw6eTjrY7E26sRBRyRJ6oCquhuYBU6pqj3V8wDwbuDEVoOTJLXGhE2SpJYkOaq5skaSTcCzgC8m2dyUBTgduKm9KCVJbbJLpCRJ7dkMXNjcx3YAcHFVfTjJJ5IcBQS4EfiVNoOUJLXHhE2SpJZU1eeBE5YoP7mFcCRJHbRsl8j9PNTzCUmuS/KlJO9Pcsjow5UkSZKkjWOQe9gWHur5VOB44JQkTwfeDLy1qo4D7gJeOrowJUmSJGnjWTZha0apWuqhnicDlzTlF9K7KVqSJEmSNCQD3cO290M9ga8Ad1fVwhM2bwWO3seySz7UczWmNk32Qz1h8h9Q6P6tb+7f+jbp+ydJ0iQaKGHb+6GewJOWmm0fyy75UM/VeNtFl3HezvbHSRnVQz1h8h9Q6P6tb+7f+jbp+ydp8mwZ88Pct2+dX/QA+d3nnjrWGKS9reg5bH0P9Xw6cESShezpGOD24YYmSZIkSRvbIKNELvVQz13A1cDzm9nOBC4bVZCSJEmStBEN0r9wXw/1/ALwviRvAj4LnD/COCVJkiRpw1k2YdvPQz1vAU4cRVCSJEmSpAEHHZHUbeO6KXupm7EXeFO2JEnS8K1o0BFJkiRJ0viYsEmSJElSR5mwSZIkSVJHmbBJkiRJUkeZsEmSJElSR5mwSZIkSVJHmbBJkiRJUkeZsEmS1JIkhyb5dJLPJbk5yeub8ickuS7Jl5K8P8khbccqSWqHCZskSe15ADi5qp4KHA+ckuTpwJuBt1bVccBdwEtbjFGS1CITNkmSWlI9c83Hg5tXAScDlzTlFwKntxCeJKkDDmo7AEmSNrIkBwI3AE8E3g58Bbi7quabWW4Fjt7HstuAbQBTU1PMzs4CMDc399D7ldi+dX75mUZsNXEPYrV1MsnWQ52M+5ic2rR4m12vo1FaD8fIuLVRJyZskiS1qKoeBI5PcgTwQeBJS822j2V3ADsApqena2ZmBuj9wFx4vxJnnX3FipcZtt1nzIxkvautk0m2Hupk3Mfk9q3znLfz4T+PR3VMrgfr4RgZtzbqxC6RkiR1QFXdDcwCTweOSLLwq/EY4Pa24pIktcuETZKkliQ5qrmyRpJNwLOAXcDVwPOb2c4ELmsnQklS2+wSKUlSezYDFzb3sR0AXFxVH07yBeB9Sd4EfBY4v80gJUntMWGTJKklVfV54IQlym8BThx/RJKkrjFhk9ZoS98N0du3znfipn1JkiRNBu9hkyRJkqSOMmGTJEmSpI5aNmFLcmySq5PsSnJzklc05eckuS3Jjc3r2aMPV5IkSZI2jkHuYZsHtlfVZ5I8ArghyVXNtLdW1e+NLjxJkiRJ2riWTdiqag+wp3l/X5JdwNGjDkySJEmSNroVjRKZZAu94YevA04CXp7kxcD19K7C3bXEMtuAbQBTU1PMzs6uOtipTb1R+Nq2ln1Yztzc3EjX37ZJ3L/+Y7Irx+io7G//JuHvOonHZ79J3z9JkibRwAlbksOBS4FXVtW9Sd4BvBGo5t/zgJfsvVxV7QB2AExPT9fMzMyqg33bRZdx3s72n0Sw+4yZka17dnaWtdRR103i/p2117D+XThGR2V/+zfK78W4TOLx2W/S90+SpEk00CiRSQ6ml6xdVFUfAKiqO6rqwar6HvBOfMCnJEmSJA3VIKNEBjgf2FVVb+kr39w32/OAm4YfniRJkiRtXIP03ToJeBGwM8mNTdlrgBcmOZ5el8jdwMtGEqEkSZIkbVCDjBJ5LZAlJl05/HAkSZIkSQsGuodNkiRJkjR+JmySJEmS1FEmbJIkSZLUUSZskiRJktRRJmySJEmS1FEmbJIktSTJsUmuTrIryc1JXtGUn5PktiQ3Nq9ntx2rJKkdgzyHTZIkjcY8sL2qPpPkEcANSa5qpr21qn6vxdgkSR1gwiZJUkuqag+wp3l/X5JdwNHtRiVJ6hITNkmSOiDJFuAE4DrgJODlSV4MXE/vKtxdSyyzDdgGMDU1xezsLABzc3MPvV+J7VvnVxX7MK0m7kGstk4m2Xqok3Efk1ObFm+z63U0SuvhGBm3NurEhE2SpJYlORy4FHhlVd2b5B3AG4Fq/j0PeMney1XVDmAHwPT0dM3MzAC9H5gL71firLOvWN0ODNHuM2ZGst7V1skkWw91Mu5jcvvWec7b+fCfx6M6JteD9XCMjFsbdeKgI5IktSjJwfSStYuq6gMAVXVHVT1YVd8D3gmc2GaMkqT2mLBJktSSJAHOB3ZV1Vv6yjf3zfY84KZxxyZJ6ga7REqS1J6TgBcBO5Pc2JS9BnhhkuPpdYncDbysnfAkSW0zYZMkqSVVdS2QJSZdOe5YJEndZJdISZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6ihHiZQkSZI6bMvZV7Sy3e1b5zmr2fbuc09tJQYNcIUtybFJrk6yK8nNSV7RlP9AkquSfKn599GjD1eSJEmSNo5BukTOA9ur6knA04FfS/Jk4Gzg41V1HPDx5rMkSZIkaUiWTdiqak9VfaZ5fx+wCzgaOA24sJntQuD0UQUpSZIkSRvRiu5hS7IFOAG4Dpiqqj3QS+qSPHYfy2wDtgFMTU0xOzu76mCnNvX60rZtLfuwnLm5uZGuv22TuH/9x2RXjtFR2d/+TcLfdRKPz36Tvn+SJE2igRO2JIcDlwKvrKp7kwy0XFXtAHYATE9P18zMzCrC7HnbRZdx3s72x0nZfcbMyNY9OzvLWuqo6yZx/87quxF4+9b5Thyjo7K//Rvl92JcJvH47Dfp+ydJ0iQaaFj/JAfTS9YuqqoPNMV3JNncTN8M3DmaECVJkiRpYxpklMgA5wO7quotfZMuB85s3p8JXDb88CRJkiRp4xqk79ZJwIuAnUlubMpeA5wLXJzkpcDXgF8YTYiSJEmStDEtm7BV1bXAvm5Ye+Zww5EkSZIkLRjoHjZJkiRJ0viZsEmSJElSR5mwSZLUkiTHJrk6ya4kNyd5RVP+A0muSvKl5t9Htx2rJKkdJmySJLVnHtheVU8Cng78WpInA2cDH6+q44CPN58lSRuQCZskSS2pqj1V9Znm/X3ALuBo4DTgwma2C4HT24lQktQ2EzZJkjogyRbgBOA6YKqq9kAvqQMe215kkqQ2DfIcNkla1pazr2g7BHafe2rbIUirkuRw4FLglVV1b7Kvp+ksWm4bsA1gamqK2dlZAObm5h56vxLbt86veJlhW03cg1htnUyy9VAn4z4mpzYt3mYX6qit72Z/fXShHrqgje+NCZskSS1KcjC9ZO2iqvpAU3xHks1VtSfJZuDOpZatqh3ADoDp6emamZkBej+sFt6vxFldOPFyxsxI1rvaOplk66FOxn1Mbt86z3k7H/7zeFTH5Eq09d3sr48u1EMXtPG9sUukJEktSe9S2vnArqp6S9+ky4Ezm/dnApeNOzZJUjd4hU2SpPacBLwI2JnkxqbsNcC5wMVJXgp8DfiFluKTJLXMhE2SpJZU1bXAvm5Ye+Y4Y5EkdZNdIiVJkiSpo0zYJEmSJKmjTNgkSZIkqaNM2CRJkiSpo0zYJEmSJKmjTNgkSZIkqaNM2CRJkiSpo0zYJEmSJKmjTNgkSZIkqaOWTdiSvCvJnUlu6is7J8ltSW5sXs8ebZiSJEmStPEMcoXtAuCUJcrfWlXHN68rhxuWJEmSJGnZhK2qrgG+M4ZYJEmSJEl9DlrDsi9P8mLgemB7Vd211ExJtgHbAKamppidnV31Bqc2wfat86tefljWsg/LmZubG+n62zaJ+9d/THblGB2Vru/fWo+tSTw++036/kmSNIlWm7C9A3gjUM2/5wEvWWrGqtoB7ACYnp6umZmZVW4S3nbRZZy3cy055nDsPmNmZOuenZ1lLXXUdZO4f2edfcVD77dvne/EMToqXd+/tX43J/H47Dfp+ydJ0iRa1SiRVXVHVT1YVd8D3gmcONywJEmSJEmrStiSbO77+Dzgpn3NK0mSJElanWX7NiV5LzADHJnkVuB1wEyS4+l1idwNvGyEMUqSJEnShrRswlZVL1yi+PwRxCJJkiRJ6rOqLpGSJGntkrwryZ1JbuorOyfJbUlubF7PbjNGSVK7TNgkSWrPBcApS5S/taqOb15XjjkmSVKHmLBJktSSqroG+E7bcUiSuqu7D1SSJGnjenmSFwPXA9ur6q6lZkqyDdgGMDU19dCD0Vf7kPTtW+dXGe7wjOrh7j44frH1UCfjPianNi3eZhfqqK3vZn99dKEeuqCN740JmyRJ3fIO4I30RmJ+I3Ae8JKlZqyqHcAOgOnp6Vp4MPpqH5J+1tlXrCbeodp9xsxI1uuD4xdbD3Uy7mNy+9Z5ztv58J/HozomV6Kt72Z/fXShHrqgje+NXSIlSeqQqrqjqh6squ8B7wRObDsmSVJ7vMK2CltGeJZj+9b5gc6i7D731JHFIElqT5LNVbWn+fg84Kb9zS9JmmwmbJIktSTJe4EZ4MgktwKvA2aSHE+vS+Ru4GWtBShJap0JmyRJLamqFy5RfP7YA5GkdWCUvdwGdcEph419m97DJkmSJEkdZcImSZIkSR1lwiZJkiRJHWXCJkmSJEkdZcImSZIkSR1lwiZJkiRJHWXCJkmSJEkdZcImSZIkSR1lwiZJkiRJHXVQ2wFI0rBsOfuKNS2/fes8Z61xHbvPPXVNy0uSJPXzCpskSZIkddSyCVuSdyW5M8lNfWU/kOSqJF9q/n30aMOUJEmSpI1nkCtsFwCn7FV2NvDxqjoO+HjzWZIkSZI0RMsmbFV1DfCdvYpPAy5s3l8InD7kuCRJkiRpw1vtPWxTVbUHoPn3scMLSZIkSZIEYxglMsk2YBvA1NQUs7Ozq17X1KbeKG6TbNB9XEs9tmlubm7dxr4v/X+vST9G3b/ldfn4nsTvnyRJk261CdsdSTZX1Z4km4E79zVjVe0AdgBMT0/XzMzMKjcJb7voMs7bOdlPIti+dX6gfdx9xszogxmB2dlZ1nIMdFH/MPCD/v3WK/dveV3+bk7i90+SpEm32i6RlwNnNu/PBC4bTjiSJG0sjsYsSdqfQYb1fy/wKeBHktya5KXAucDPJPkS8DPNZ0mStHIX4GjMkqR9WLbvT1W9cB+TnjnkWCRJ2nCq6pokW/YqPg2Yad5fCMwCvz22oCRJnTG5N6NIkrR+PWw05iRLjsa8r4G9VjvATBcGFRrVwDgOurPYeqiTcR+TSw0+1YU6auu72V8fG7ke+rXxvTFhkyRpndrXwF6rHWCmfxCltoxq4B4H3VlsPdTJuI/JpQaf6sJgUm19N/vrYyPXQ78LTjls7N+b1Q46IkmSRueOZhRmlhuNWZI02UzYJEnqHkdjliQBJmySJLXK0ZglSfvjPWySJLXI0ZglSftjwqZ1bUsHbj6VJEmadP7mao9dIiVJkiSpo0zYJEmSJKmjTNgkSZIkqaNM2CRJkiSpoxx0RJIkdcaoBjbYvnWeswZc9+5zTx1JDOuNg0xI3eAVNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKAcdkSRJ6phxDPixkoFYJLXHK2ySJEmS1FEmbJIkSZLUUSZskiRJktRRJmySJEmS1FFrGnQkyW7gPuBBYL6qpocRlCRJktQF4xgARtqfYYwS+dNV9a0hrEeSJEmS1Mdh/SVJ6iB7sUiSYO0JWwF/lqSA/15VO/aeIck2YBvA1NQUs7Ozq97Y1KbeM0Mm2aD7uJZ6bNPc3NxQY+/a8TDpx6j7t7y3XXTZkKJZva1HP2rJ8mF//zQW9mKRpA1urQnbSVV1e5LHAlcl+WJVXdM/Q5PE7QCYnp6umZmZVW/sbRddxnk7J/ui4Pat8wPt4+4zZkYfzAjMzs6ylmNgb1174Oegf7/1yv1bH/b1/8Owv3+SJGn01jRKZFXd3vx7J/BB4MRhBCVJkh7qxXJD01tFkrQBrfpUcpLDgAOq6r7m/c8CbxhaZJIkbWzL9mLZ120Hq+3+apfnni50HR7H32LSu7mvhnXycNbHYm3cXrCWvj9TwAeTLKznf1bVR4cSlSRJG1x/L5YkC71YBrrtYLXdX7vWzXyYVtLluQu3HYzjbzEp3cCHyTp5OOtjsQtOOWzstxes+i9QVbcATx1iLJIkCXuxSJL+nimzJEndYy8WSRJgwiZJUufYi0WStGBNo0RKkiRJkkbHhE2SJEmSOsqETZIkSZI6ynvYtGpbVjHk8Pat8xM9bLQkSZI0TF5hkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjJhkyRJkqSOMmGTJEmSpI4yYZMkSZKkjjqo7QAkSZK6ZMvZV7QdgiQ9xCtskiRJktRRa0rYkpyS5K+TfDnJ2cMKSpKkjc42VpIEa0jYkhwIvB34eeDJwAuTPHlYgUmStFHZxkqSFqzlCtuJwJer6paq+jvgfcBpwwlLkqQNzTZWkgRAqmp1CybPB06pql9uPr8I+PGqevle820DtjUffwT469WHy5HAt9aw/How6fvo/q1v7t/6tpL9e3xVHTXKYLRvQ2hjJ/1YXg3rZDHrZDHr5OGsj8WGUScramPXMkpklihblP1V1Q5gxxq28/cbTK6vqulhrKurJn0f3b/1zf1b3yZ9/ybMmtpY/9aLWSeLWSeLWScPZ30s1kadrKVL5K3AsX2fjwFuX1s4kiQJ21hJUmMtCdtfAccleUKSQ4AXAJcPJyxJkjY021hJErCGLpFVNZ/k5cCfAgcC76qqm4cW2dKG0rWy4yZ9H92/9c39W98mff8mxrXn4DMAACAASURBVBDaWP/Wi1kni1kni1knD2d9LDb2Oln1oCOSJEmSpNFa04OzJUmSJEmjY8ImSZIkSR21LhK2JO9KcmeSm9qOZRSSHJvk6iS7ktyc5BVtxzRMSQ5N8ukkn2v27/VtxzQKSQ5M8tkkH247lmFLsjvJziQ3Jrm+7XiGLckRSS5J8sXme/gTbcc0TEl+pPnbLbzuTfLKtuPS2iU5JclfJ/lykrOXmP59Sd7fTL8uyZbxRzk+A9THWUm+2fdd+OU24hyn5X5DpecPmjr7fJKnjTvGcRugTmaS3NN3nLx23DGO0yC/QzfacTJgnYztOFnLc9jG6QLgvwL/o+U4RmUe2F5Vn0nyCOCGJFdV1RfaDmxIHgBOrqq5JAcD1yb5SFX9ZduBDdkrgF3AI9sOZER+uqom9eGZ/wX4aFU9vxmR7/vbDmiYquqvgeOhd2IBuA34YKtBac2av+XbgZ+h9xiAv0py+V5tx0uBu6rqiUleALwZ+Ffjj3b0BqwPgPfv/QDyCXcB+/8N9fPAcc3rx4F3NP9OsgtY/nflJ6vqn48nnNYN8jt0ox0ng/42H8txsi6usFXVNcB32o5jVKpqT1V9pnl/H70f/Ue3G9XwVM9c8/Hg5jVRo90kOQY4FfijtmPRyiR5JPAM4HyAqvq7qrq73ahG6pnAV6rqb9oORGt2IvDlqrqlqv4OeB9w2l7znAZc2Ly/BHhmkqUeyj0JBqmPDWeA31CnAf+jaav/EjgiyebxRNeOSf9duVID/g7dUMdJ136br4uEbSNpuqucAFzXbiTD1XQXvBG4E7iqqiZq/4DfB34L+F7bgYxIAX+W5IYk29oOZsj+IfBN4N1Nl9Y/SnJY20GN0AuA97YdhIbiaODrfZ9vZfEPiofmqap54B7gMWOJbvwGqQ+Af9l06bokybFLTN9oBq23jeYnmls5PpLkR9sOZlz28zt0wx4ny/w2H8txYsLWIUkOBy4FXllV97YdzzBV1YNVdTxwDHBikqe0HdOwJPnnwJ1VdUPbsYzQSVX1NHpdIn4tyTPaDmiIDgKeBryjqk4A7gcW3fsyCZruns8F/qTtWDQUS10p27v3wiDzTIpB9vVDwJaq+sfAx/j7q48b2UY6Rgb1GeDxVfVU4G3A/2o5nrFY5nfohjxOlqmTsR0nJmwd0dzbdSlwUVV9oO14RqXpajYLnNJyKMN0EvDcJLvpdcE5Ocl72g1puKrq9ubfO+nd+3RiuxEN1a3ArX1XfS+hl8BNop8HPlNVd7QdiIbiVqD/CtExwO37mifJQcCjmNyuYMvWR1V9u6oeaD6+E/gnY4qtywY5jjaUqrp34VaOqroSODjJkS2HNVID/A7dcMfJcnUyzuPEhK0DmvsJzgd2VdVb2o5n2JIcleSI5v0m4FnAF9uNaniq6tVVdUxVbaHX3ewTVfWvWw5raJIc1txwS9NV8GeBiRmxtaq+AXw9yY80Rc8EJmXAn729ELtDTpK/Ao5L8oTm6ukLgMv3mudy4Mzm/fPp/f80qWfFl62Pve65eS69+1I2usuBFzejAD4duKeq9rQdVJuS/IOFez2TnEjv9/K3241qdAb8HbqhjpNB6mScx8m6GCUyyXuBGeDIJLcCr6uq89uNaqhOAl4E7Gzu8wJ4TZOtT4LNwIXNCF4HABdX1cQNfT/BpoAPNv8nHQT8z6r6aLshDd2/BS5qfuTdAvybluMZuiTfT2/0vJe1HYuGo6rmk7wc+FPgQOBdVXVzkjcA11fV5fR+cPxxki/Tu7L2gvYiHq0B6+PXkzyX3ghw3wHOai3gMVnqNxS9wb+oqj8ErgSeDXwZ+Fsm8P+/vQ1QJ88HfjXJPPBd4AUTfKID9vE7FPhB2LDHySB1MrbjJJN9/EmSJEnS+mWXSEmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNm1oSXYneVbbcfRLck6S97QdhyRJw7KW9jbJHyb5D/uZXkmeOIptS11gwqbOSPKTSf4iyT1JvpPkfyf5sTFuf+yJUpKZJLeuYrlfSnJ9krkke5J8JMlPjiJGSdJkabO9TbK5SbCm+sr+3T7KPgpQVb9SVW8ccP0XJHnTCmN6ZJLfT/K1pl39cvP5yJWsRxoVEzZ1QpJHAh8G3gb8AHA08HrggTbj6qIkvwH8PvAfgSngB4H/BpzWZlySpO5ru72tqj3Al4Fn9BU/A/jiEmXXjDqeJIcAHwd+FDgFeCTwT4FvAyeOevvSIEzY1BU/DFBV762qB6vqu1X1Z1X1eYAkL0myK8ldSf40yeMXFmzOyv16kluSfCvJf05yQDPth5J8Ism3m2kXJTlipcEleVySS5N8M8lXk/x637Rzklyc5H8kuS/JzUmm+6Y/Lclnm2l/kuT9Sd6U5DDgI8DjmjN6c0ke1yx2yFLrS/Io4A3Ar1XVB6rq/qr6f1X1oap6VV88f5LkPc3yO5P8cJJXJ7kzydeT/OxK60CSNBG60N5eQ5OcJTkQOAH4L3uV/UQz36KrZkle1fQuuT3JS/rKtwFnAL/VtKkf6tvm8Uk+31xVfH+SQ5vyF9M78fm8qvpCVX2vqu6sqjdW1ZXNenc32/x8kvuTnJ9kqundcl+SjyV59Kr+GtIATNjUFf8HeDDJhUl+vv8/viSnA68B/gVwFPBJ4L17Lf88YBp4Gr0rTQv/gQf4XeBxwJOAY4FzVhJY0xh9CPgcvTORzwRemeTn+mZ7LvA+4AjgcuC/NsseAnwQuIDemcz3NrFSVfcDPw/cXlWHN6/b97c+eg3Yoc069+c5wB8DjwY+C/wpve/70fQSvv++kjqQJE2MLrS3DyVs9JK1L9K7ytVfdjDw6b0XTHIK8JvAzwDHAQ/dm1ZVO4CLgP/UtKnP6Vv0F+ldQXsC8I+Bs5ryZwEfraq5fcS64F822/xhem3sR+jV1ZH02tdf3/ei0tqYsKkTqupe4CeBAt4JfDPJ5U1/9pcBv1tVu6pqnl5XwOP7z/oBb66q71TV1+h1F3xhs94vV9VVVfVAVX0TeAvwUysM78eAo6rqDVX1d1V1SxPjC/rmubaqrqyqB+klSk9typ8OHAT8QXMl7AMs0QAtYV/rewzwraYe9ueTVfWnzXx/Qq/hPbeq/h+9RHDLaq40SpLWt460t38OPKVJFv8ZvTbrS8CRfWV/WVV/t8Syvwi8u6puak58njPgrv9BVd1eVd+hdxL2+Kb8McCeAZZ/W1XdUVW30Utkr6uqz1bVA/ROop4wYBzSipmwqTOaBuKsqjoGeAq9s3S/Dzwe+C9J7k5yN/Ademfyju5b/Ot97/+mWZYkj03yviS3JbkXeA+9s2Er8Xh63Rbv7ovhNfTuH1vwjb73fwscmuSgJo7bqqr2Eeu+7Gt936bXoB20zPJ39L3/Lr0k78G+zwCHDxCHJGnCtN3eVtVu4FZ6ieMz6CVAAJ/qK9vX/WuPWyKGQezdri60gd8GNg+w/N7t6t6fbVM1MiZs6qSq+iK9boRPofcf88uq6oi+16aq+ou+RY7te/+DwELXwt+ldxbxH1fVI4F/Ta/xWYmvA1/da/uPqKpnD7DsHuDoJP3b7I+1WJlPAf8XOH2Fy0mStEiL7e0n6SVmPwH8xV5lP8m+E7Y9S8TwsF3azzaX8jHg55r7yqVOMmFTJyT5R0m2Jzmm+XwsvW4Wfwn8IfDqJD/aTHtUkl/YaxWvSvLoZrlXAO9vyh8BzAF3JzkaeNUyoRyQ5NC+1/fR68J4b5LfTrIpyYFJnpLBhkD+FPAg8PIkByU5jYePOnUH8JhmMJFlVdU9wGuBtyc5Pcn3Jzm4uQ/hPw2yDknSxtWh9vYaegN+3N500wS4til7FL32cykXA2cleXKS7wdet9f0O4B/uMy2+/0xvUT10qZuDkjymCSvSTLIiVlp5EzY1BX3AT8OXJfkfnoNx03A9qr6IPBm4H1NN4ub6A3W0e8y4AbgRuAK4Pym/PX0boy+pyn/wDJxvJBe14aF11earoTPodff/avAt4A/oteg7FfT//5fAC8F7qZ3xvHDNMMnN2c23wvc0nRBedy+1tW3zrcAvwH8e+Cb9BqalwP/a7llJUkbXlfa2z8HHksvSVtwI7AJuKGq/napharqI/S6b36C3uMBPrHXLOcDT27a1GXbxeYetGfRG/jkKuBeeidqjwSuW255aRzy8FtrpPUnSQHHVdWX245lEEmuA/6wqt7ddiySJA1qvbW30qTwCps0Ykl+Ksk/aLpEnklvOOGPth2XJEmSum+5keYkrd2P0OtzfzjwFeD5VTXIEMKSJEna4OwSKUmSJEkdZZdISZIkSeqosXaJPPLII2vLli3j3OQ+3X///Rx22Pp75IZxj5dxj5dxj9f+4r7hhhu+VVVHjTkkrcEw2tj1eiyPknXycNbHYtbJYtbJYv11stI2dqwJ25YtW7j++uvHucl9mp2dZWZmpu0wVsy4x8u4x8u4x2t/cSf5m/FGo7UaRhu7Xo/lUbJOHs76WMw6Wcw6Way/TlbaxtolUpIkSZI6yoRNkiRJkjrKhE2SJEmSOsqETZIkSZI6yoRNkiRJkjrKhE2SJEmSOsqETZIkSZI6yoRNkiRJkjrKhE2SJEmSOuqgtgPQ+rXl7CsGnnf71nnOWsH8g9p97qlDX6ckSVq6nR9Ve74vtvOSV9gkSZIkqbNM2CRJkiSpo0zYJEmSJKmjTNgkSZIkqaNM2CRJkiSpo0zYJEmSJKmjTNgkSZIkqaN8Dpu0Rit5Ht2o+JwaSZKkyeQVNkmSJEnqKBM2SZIkSeooEzZJkiRJ6qhlE7Ykxya5OsmuJDcneUVTfk6S25Lc2LyePfpwJUmSJGnjGGTQkXlge1V9JskjgBuSXNVMe2tV/d7owpMkaXIlORS4Bvg+em3yJVX1uiQXAD8F3NPMelZV3dhOlJKkNi2bsFXVHmBP8/6+JLuAo0cdmCRJG8ADwMlVNZfkYODaJB9ppr2qqi5pMTZJUges6B62JFuAE4DrmqKXJ/l8knclefSQY5MkaaJVz1zz8eDmVS2GJEnqmIGfw5bkcOBS4JVVdW+SdwBvpNewvBE4D3jJEsttA7YBTE1NMTs7O4Sw125ubq4zsaxEl+LevnV+4HmnNq1s/kGNui4Gqe9R7NdK7R1jl46TlTDu8VqvcU+aJAcCNwBPBN5eVdcl+VXgd5K8Fvg4cHZVPdBmnJKkdqRq+RN5TTeNDwN/WlVvWWL6FuDDVfWU/a1nenq6rr/++tVFOmSzs7PMzMy0HcaKdSnulTwwevvWec7bOfzntI/6gdGD1HcXH5zdpeNkJYx7vPYXd5Ibqmp6vBFtbEmOAD4I/Fvg28A3gEOAHcBXquoNSyzTf1L0n7zvfe9bUwxzc3Mcfvjha1rHpNnIdbLztnsWlU1tgju+O74Yth79qPFtbJU28jGyL9bJYv118tM//dMramOX/QWdJMD5wK7+ZC3J5ub+NoDnATetKGpJkvSQqro7ySxwSt+AXg8keTfwm/tYZge9hI7p6ela64mD9XryYZQ2cp2ctcQJyVGdgN2X3WfMjG1bq7WRj5F9sU4WW0udDPKNOwl4EbAzycIIVa8BXpjkeHpdIncDL1tVBJIkbVBJjgL+X5OsbQKeBbx54aRoc9L0dDwpKkkb1iCjRF4LZIlJVw4/HEmSNpTNwIXNfWwHABdX1YeTfKJJ5gLcCPxKm0FKktozvmvakiTpYarq8/RGX967/OQWwpEkddCKhvWXJEmSJI2PCZskSZIkdZQJmyRJkiR1lAmbJEmSJHWUCZskSZIkdZQJmyRJkiR1lAmbJEmSJHWUCZskSZIkdZQJmyRJkiR1lAmbJEmSJHXUQW0HsB5tOfuK1ra9fes8Z519BbvPPbW1GCRJkiSNh1fYJEmSJKmjTNgkSZIkqaNM2CRJkiSpo0zYJEmSJKmjTNgkSZIkqaNM2CRJkiSpoxzWX5IkSZ3U5qOUFvgoJbXNK2ySJEmS1FEmbJIkSZLUUSZskiS1JMmhST6d5HNJbk7y+qb8CUmuS/KlJO9PckjbsUqS2mHCJklSex4ATq6qpwLHA6ckeTrwZuCtVXUccBfw0hZjlCS1yIRNkqSWVM9c8/Hg5lXAycAlTfmFwOkthCdJ6gBHiZQkqUVJDgRuAJ4IvB34CnB3Vc03s9wKHL2PZbcB2wCmpqaYnZ1dUyxzc3NrXsek2ch1sn3r/KKyqU1Ll0+y5f7+G/kY2RfrZLG11IkJmyRJLaqqB4HjkxwBfBB40lKz7WPZHcAOgOnp6ZqZmVlTLLOzs6x1HZNmI9fJWUsMqb996zzn7dxYPx93nzGz3+kb+RjZF+tksbXUiV0iJUnqgKq6G5gFng4ckWThV/ExwO1txSVJapcJmyRJLUlyVHNljSSbgGcBu4Crgec3s50JXNZOhJKktm2sa9qSJHXLZuDC5j62A4CLq+rDSb4AvC/Jm4DPAue3GaQkqT0mbJIktaSqPg+csET5LcCJ449IktQ1domUJEmSpI5aNmFLcmySq5PsSnJzklc05T+Q5KokX2r+ffTow5UkSZKkjWOQK2zzwPaqehK9kat+LcmTgbOBj1fVccDHm8+SJEmSpCFZNmGrqj1V9Znm/X30Rq86GjgNuLCZ7ULg9FEFKUmSJEkb0YruYUuyhd7N0dcBU1W1B3pJHfDYYQcnSZIkSRvZwKNEJjkcuBR4ZVXdm2TQ5bYB2wCmpqaYnZ1dRZjDNzc3t+pYtm+dH24wKzC1qbf9LtTjSuphIe5hG3U9DHKctHk8LNg7xrUc320y7vFar3FLkrSRDJSwJTmYXrJ2UVV9oCm+I8nmqtqTZDNw51LLVtUOYAfA9PR0zczMrD3qIZidnWW1sZx19hXDDWYFtm+d57ydB7H7jJnWYliwknpYiHvYRl0PgxwnbR4PC/auh7Uc320y7vFar3FLkrSRDDJKZOg9sHNXVb2lb9LlwJnN+zOBy4YfniRJkiRtXINc8jgJeBGwM8mNTdlrgHOBi5O8FPga8AujCVGSJEmSNqZlE7aquhbY1w1rzxxuOJIkSZKkBSsaJVKSJEmSND4mbJIkSZLUUSZskiRJktRRJmySJEmS1FEmbJIkSZLUUSZskiRJktRRJmySJEmS1FEmbJIkSZLUUSZskiRJktRRJmySJLUkybFJrk6yK8nNSV7RlJ+T5LYkNzavZ7cdqySpHQe1HYAkSRvYPLC9qj6T5BHADUmuaqa9tap+r8XYJEkdYMImTYAtZ1/xsM/bt85z1l5lo7b73FPHuj1pElTVHmBP8/6+JLuAo9uNSpLUJSZskiR1QJItwAnAdcBJwMuTvBi4nt5VuLuWWGYbsA1gamqK2dnZNcUwNze35nVMmo1cJ9u3zi8qm9q0dPkkW+7vv5GPkX2xThZbS52YsEmS1LIkhwOXAq+sqnuTvAN4I1DNv+cBL9l7uaraAewAmJ6erpmZmTXFMTs7y1rXMWk2cp0s1VNj+9Z5ztu5sX4+7j5jZr/TN/Ixsi/WyWJrqRMHHZEkqUVJDqaXrF1UVR8AqKo7qurBqvoe8E7gxDZjlCS1x4RNkqSWJAlwPrCrqt7SV765b7bnATeNOzZJUjdsrGvakiR1y0nAi4CdSW5syl4DvDDJ8fS6RO4GXtZOeJKktpmwSZLUkqq6FsgSk64cdyySpG4yYZMkSeqYvR/XImnj8h42SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igTNkmSJEnqKBM2SZIkSeooEzZJkiRJ6igfnK11bdQPFt2+dZ6zfHipJEmSWuIVNkmSJEnqKK+wSZIk9envvWFPC0lt8wqbJEmSJHXUsglbkncluTPJTX1l5yS5LcmNzevZow1TkvT/t3f3UZbddZ3v3x/SIE1CCBgoQxJpvGaiSJuAZQTj1YIINzwMiXPBgQFMMNxmZsmT9lIDa66oM45xluHBjFdtCaaVGIghMREQyARqIQ5GSUCT0DDE0ECTJg2EhBQi0PC9f+xdcFJd3V2pc6r2r6rer7Vq1XnY5+xvfeuc8zufs397H0mStPEsZQvbJcCZi1z+uqo6tf9552TLkiRJkiQdNrBV1fuBO1ehFkmSJEnSiHH2YXtpkn/qp0w+dGIVSZIkSZKA5R8l8g+A/wJU//tC4OcXWzDJNmAbwNTUFLOzs8tc5WTNzc0tu5btW/dPtpj7YGpzt/4W+nhf+jBf91pj3Us3icfkOM/LIVm3JElaKcsKbFV1x/zpJH8MvP0Qy+4AdgBMT0/XzMzMclY5cbOzsyy3liEP77t9634uvGkTu58/M1gN8+5LH+brXmuse+km8Zgc53k5JOuWJEkrZVlTIpMcN3L2Z4CbD7asJEmSJGl5DvsRfJLLgBng2CR7gNcAM0lOpZsSuRt4yQrWKEnSupTkROBPge8BvgXsqKo3JHkY8FZgC904+7NV9aWh6pQkDeewga2qnrfIxRevQC2SJG00+4HtVXVjkgcDNyS5FjgXuK6qLkhyPnA+8KsD1ilJGsg4R4mUJEljqKq9VXVjf/oeYBdwPHAWsLNfbCdw9jAVSpKGtvaOpiBJ0jqUZAvwOOB6YKqq9kIX6pI84iC3meiRmD1yaGf0KLtr9WjBK2Uj9uNwzwmfNweyJwcapycGtjVqy4BHqpQkTVaSo4C3Aa+sqi8nWdLtJn0kZo8c2hk9CvJaPVrwStmI/TjcUZB93hzInhxonJ44JVKSpAEluT9dWLu0qq7sL75j/ojM/e99Q9UnSRqWgU2SpIGk25R2MbCrql47ctU1wDn96XOAq1e7NklSGzbWNm1JktpyOvBC4KYkH+kvezVwAXB5kvOATwPPGag+SdLADGySJA2kqj4AHGyHtTNWsxZJUpucEilJkiRJjTKwSZIkSVKjDGySJEmS1CgDmyRJkiQ1ysAmSZIkSY0ysEmSJElSowxskiRJktQoA5skSZIkNcrAJkmSJEmNMrBJkiRJUqMMbJIkSZLUKAObJEmSJDXKwCZJkiRJjTKwSZIkSVKjDGySJEmS1CgDmyRJkiQ1ysAmSZIkSY0ysEmSJElSowxskiRJktQoA5skSQNJ8qYk+5LcPHLZryf5bJKP9D9PH7JGSdKwDGySJA3nEuDMRS5/XVWd2v+8c5VrkiQ1xMAmSdJAqur9wJ1D1yFJatemoQuQJEkHeGmSnwM+BGyvqi8ttlCSbcA2gKmpKWZnZ8da6dzc3Nj3sR5s37r/26enNt/7/Ea3EftxuOeEz5sD2ZMDjdMTA5skSW35A+C/ANX/vhD4+cUWrKodwA6A6enpmpmZGWvFs7OzjHsf68G557/j26e3b93PhTf5dmneRuzH7ufPHPJ6nzcHsicHGqcnh50SeZAdoh+W5Nokn+h/P3RZa5ckSfdSVXdU1Ter6lvAHwOnDV2TJGk4S9mH7RIO3CH6fOC6qjoJuK4/L0mSxpTkuJGzPwPcfLBlJUnr32G3aVfV+5NsWXDxWcBMf3onMAv86gTrkiRp3UtyGd14emySPcBrgJkkp9JNidwNvGSwAiVJg1vuJOSpqtoLUFV7kzziYAtOeofoSRlnx78hd7Zdqzv7WvfqGqLuSTy31+pOytat5aqq5y1y8cWrXogkqVkrvtfopHeInpRxdvwb3Rl5ta3VnX2te3UNUffhdspeirW6k7J1S5KklbLc72G7Y36Off973+RKkiRJkiTB8gPbNcA5/elzgKsnU44kSZIkad5SDut/GfBB4OQke5KcB1wAPCXJJ4Cn9OclSZIkSRO0lKNELrZDNMAZE65FkiRJkjRiuVMiJUmSJEkrzMAmSZIkSY1aU8cr3zLBw+lv37p/0MPzS5IkSdLhuIVNkiRJkhplYJMkSZKkRhnYJEmSJKlRBjZJkiRJapSBTZIkSZIaZWCTJEmSpEYZ2CRJkiSpUQY2SZIkSWqUgU2SJEmSGrVp6AIkSZIkHdyW898xdAnsvuAZQ5ewYbmFTZIkSZIaZWCTJGlASd6UZF+Sm0cue1iSa5N8ov/90CFrlCQNx8AmSdKwLgHOXHDZ+cB1VXUScF1/XpK0ARnYJEkaUFW9H7hzwcVnATv70zuBs1e1KElSMwxskiS1Z6qq9gL0vx8xcD2SpIF4lEhJktaoJNuAbQBTU1PMzs6OdX9zc3Nj38d6sH3r/m+fntp87/Mb3Ubsx+GeE6vxvGmh5/flb/S15EDj9MTAJklSe+5IclxV7U1yHLBvsYWqagewA2B6erpmZmbGWuns7Czj3sd6cO7IIdS3b93PhTf5dmneRuzH7ufPHPL61XjenNvCYf0P04dRvpYcaJyeOCVSkqT2XAOc058+B7h6wFokSQMysEmSNKAklwEfBE5OsifJecAFwFOSfAJ4Sn9ekrQBbaxt2pIkNaaqnneQq85Y1UIkSU0ysEmSJEkHseUw+49t37q/iX3MtH45JVKSJEmSGmVgkyRJkqRGOSVS0kQcbsrIUow7rWT3Bc8Yu4ZxTaIP42qhD5IkaTLcwiZJkiRJjTKwSZIkSVKjDGySJEmS1CgDmyRJkiQ1aqyDjiTZDdwDfBPYX1XTkyhKkiRJkjSZo0Q+qaq+MIH7kSRJkiSNcEqkJEmSJDVq3C1sokXyfAAAIABJREFUBbwnSQF/VFU7Fi6QZBuwDWBqaorZ2dllr2z71v3Lvu1CU5sne3+rxbpXl3WvrnHrvujSqydYzdJNbf7OurdvHaSEe1nq6+zc3NxYr8mSJGnljRvYTq+q25M8Arg2yceq6v2jC/QhbgfA9PR0zczMLHtl43yh7kLbt+7nwpvW3veGW/fqsu7VZd2Tsfv5M0tabnZ2lnFek6WV0MKXz0tSS8aaEllVt/e/9wFXAadNoihJkiRJ0hiBLcmRSR48fxp4KnDzpAqTJEmSpI1unDk8U8BVSebv58+r6l0TqUqSJEmStPzAVlW3AadMsBZJkiRJ0ggP6y9JkiRJjTKwSZIkSVKjDGySJEmS1Kh2vjhIkiR9W5LdwD3AN4H9VTU9bEWSpCEY2CRJateTquoLQxchSRqOUyIlSZIkqVFuYZMkqU0FvCdJAX9UVTsWLpBkG7ANYGpqitnZ2bFWODc3N/Z9jGv71v2Drn+hqc3t1TQk+3GgjdKT+/La0MJrSWvG6YmBTZKkNp1eVbcneQRwbZKPVdX7RxfoQ9wOgOnp6ZqZmRlrhbOzs4x7H+M69/x3DLr+hbZv3c+FN/l2aZ79ONBG6cnu588sedkWXktaM05PnBIpSVKDqur2/vc+4CrgtGErkiQNwcAmSVJjkhyZ5MHzp4GnAjcPW5UkaQjrf/utJElrzxRwVRLoxuo/r6p3DVuSJGkIBjZJkhpTVbcBpwxdhyRpeAY2SZIEwE2fvbu5g35I0kbnPmySJEmS1CgDmyRJkiQ1ysAmSZIkSY0ysEmSJElSowxskiRJktQoA5skSZIkNcrAJkmSJEmNMrBJkiRJUqMMbJIkSZLUKAObJEmSJDVq09AFSJIkSWrblvPfseRlt2/dz7n3Yfm1ZPcFz1j1dbqFTZIkSZIaZWCTJEmSpEYZ2CRJkiSpUQY2SZIkSWqUgU2SJEmSGmVgkyRJkqRGGdgkSZIkqVFjBbYkZyb5eJJbk5w/qaIkSdroHGMlSTBGYEtyBPD7wNOAxwDPS/KYSRUmSdJG5RgrSZo3zha204Bbq+q2qvo68BbgrMmUJUnShuYYK0kCIFW1vBsmzwbOrKoX9+dfCPxYVb10wXLbgG392ZOBjy+/3Ik6FvjC0EUsg3WvLuteXda9ug5V96Oq6uGrWYy+Y8Axdq0+lleSPbk3+3Ege3Ige3Kg0Z7cpzF20xgrzSKXHZD+qmoHsGOM9ayIJB+qqumh67ivrHt1Wffqsu7VtVbr3iAGGWN9TBzIntyb/TiQPTmQPTnQOD0ZZ0rkHuDEkfMnALePcX+SJKnjGCtJAsYLbP8AnJTk0UkeADwXuGYyZUmStKE5xkqSgDGmRFbV/iQvBd4NHAG8qapumVhlK6+5aZpLZN2ry7pXl3WvrrVa97o34BjrY+JA9uTe7MeB7MmB7MmBlt2TZR90RJIkSZK0ssb64mxJkiRJ0soxsEmSJElSo9Z9YEtyRJIPJ3n7Itedm+TzST7S/7x4iBoXk2R3kpv6uj60yPVJ8ntJbk3yT0keP0SdCy2h7pkkd4/0/NeGqHOhJMckuSLJx5LsSvLEBdc31+8l1Nxcr5OcPFLPR5J8OckrFyzTYq+XUndz/QZI8otJbklyc5LLkjxwwfXfleStfb+vT7JlmEq1GpKcmOR9/WvGLUlescgyzT0HV9ISe9Lk83ulJHlgkr9P8o99T35jkWU21GvHEnvS7PvKlZRDv9feUI+TeYfpyX1+nIzzPWxrxSuAXcDRB7n+rQu/iLQhT6qqg33p4NOAk/qfHwP+oP/dgkPVDfA3VfXMVatmad4AvKuqnp3uiGwPWnB9i/0+XM3QWK+r6uPAqdC9mAGfBa5asFhzvV5i3dBYv5McD7wceExVfTXJ5XRHG7xkZLHzgC9V1fcneS7wO8C/X/VitVr2A9ur6sYkDwZuSHJtVX10ZJnmnoMrbCk9gcae3yvsa8CTq2ouyf2BDyT566r6u5FlNtprx1J6Am2/r1wph3qvvdEeJ/Mmmj/W9Ra2JCcAzwDeOHQtK+As4E+r83fAMUmOG7qotSjJ0cBPAhcDVNXXq+quBYs11e8l1ty6M4B/rqpPLbi8qV4v4mB1t2oTsDnJJrpQv/C7vM4CdvanrwDOSLLYlzZrHaiqvVV1Y3/6Hro3FMcvWKz15+BELbEnG0r/v5/rz96//1l4lLoN9dqxxJ5sOEt4r72hHiewMvljXQc24PXArwDfOsQy/3c/5eOKJCceYrnVVsB7ktyQZNsi1x8PfGbk/B7aGGAOVzfAE/spBX+d5IdWs7iD+D7g88Cf9Juv35jkyAXLtNbvpdQM7fV61HOByxa5vLVeL3SwuqGxflfVZ4HfBT4N7AXurqr3LFjs2/2uqv3A3cB3r2adGkY/NelxwPULrmr9ObhiDtETaOz5vdL6KV0fAfYB11bVQR8nG+W1Ywk9gXbfV66Uw73X3nCPE1Ygf6zbwJbkmcC+qrrhEIv9FbClqn4Y+J985xOAFpxeVY+nm5ryC0l+csH1i3060cInPYer+0bgUVV1CnAR8JerXeAiNgGPB/6gqh4HfAU4f8EyrfV7KTW32GsA+imczwL+YrGrF7mshcf24epurt9JHkr36eajgUcCRyZ5wcLFFrlpE/3WyklyFPA24JVV9eWFVy9yk3X/mDhMT5p7fq+0qvpmVZ0KnACcluSxCxbZcI+TJfSk5feVE7fE99ob6nGyUvlj3QY24HTgWUl2A28BnpzkzaMLVNUXq+pr/dk/Bn5kdUs8uKq6vf+9j25fmdMWLLIHGE3kJ3DgVKdVd7i6q+rL81MKquqdwP2THLvqhd7bHmDPyCdlV9CFoYXLtNTvw9bcaK/nPQ24saruWOS61no96qB1N9rvnwY+WVWfr6pvAFcCP75gmW/3u582+RDgzlWtUquq3//mbcClVXXlIou0/BxcEYfrSaPP71XRT7efBc5ccNWGfe04WE9afl+5Qg77XpuN9zhZkfyxbgNbVb2qqk6oqi10U5jeW1X3+mR5wZz8Z9HNWx9ckiP7HZ/pp7k9Fbh5wWLXAD+XzhPopjrtXeVS72UpdSf5nvm5y0lOo3sMfnG1ax1VVZ8DPpPk5P6iM4CFO5s31e+l1Nxir0c8j4NPK2yq1wsctO5G+/1p4AlJHtTXdgYHvs5dA5zTn3423Wvluv30c6PrHwcXA7uq6rUHWazl5+DELaUnjT6/V0yShyc5pj+9me7Dn48tWGxDvXYspSetvq9cKUt5r80Ge5ysVP7YCEeJvJckvwl8qKquAV6e5Fl0R4i6Ezh3yNpGTAFX9WPDJuDPq+pdSf4jQFX9IfBO4OnArcC/AC8aqNZRS6n72cB/SrIf+Crw3EaeuC8DLu2nvN0GvGgN9PtwNTfZ6yQPAp4CvGTkstZ7vZS6m+t3VV2f5Aq66Vz7gQ8DOxa8Dl4M/FmSW+leB587WMFaDacDLwRu6vfFAXg18L3Q9nNwBS2lJ809v1fYccDOdEfFvR9weVW9fYO/diylJ62+r1xVG/xxsqhxHydZ3683kiRJkrR2rdspkZIkSZK01hnYJEmSJKlRBjZJkiRJapSBTZIkSZIaZWCTJEmSpEYZ2CRJkiSpUQY2SZIkSWqUgU2SJEmSGmVgkyRJkqRGGdgkSZIkqVEGNkmSJElqlIFNkiRJkhplYJMkSZKkRhnYJEmSJKlRBjZJkiRJapSBTZIkSZIaZWCTJEmSpEYZ2CRJkiSpUQY2SZIkSWqUgU2SJEmSGmVgkyRJkqRGGdgkSZIkqVEGNkmSJElqlIFNkiRJkhplYJMkSZKkRhnYJEmSJKlRBjZJkiRJapSBTZIkSZIaZWCTJEmSpEYZ2CRJkiSpUQY2SZIkSWqUgU2SJEmSGmVgkyRJkqRGGdgkSZIkqVEGNkmSJElqlIFNkiRJkhplYJMakuTXk7x56DokSRrHWh/PkswmefFQ60xybpIPrOb61S4Dm5qS5CeS/K8kdye5M8nfJvnRlX7hGmJgSTKTZM8ybvcfknwoyVySvUn+OslPrESNkqTlcTxb0u0cz1ZAOr+T5Iv9z39PkqHr0vIZ2NSMJEcDbwcuAh4GHA/8BvC1IetqSZJfAl4P/DdgCvhe4P8DzhqyLknSdzieHd5Kjmd9YNnI73G3AWcDpwA/DDwTeMmgFWksG/nBrPb8G4CquqyqvllVX62q9wDfAP4QeGL/KdxdAEm+K8nvJvl0kjuS/GGSzf11M0n2JPmVJPv6T+7OTvL0JP+7/7Tz1UspKskjk7wtyeeTfDLJy0eu+/Uklyf50yT3JLklyfTI9Y9P8uH+ur9I8tYk/zXJkcBfA4/s/6a5JI/sb/aAxe4vyUOA3wR+oaqurKqvVNU3quqvquqXR+r5iyRv7m9/U5J/k+RVfR8+k+Sp4/2bJEmH4XjWWbXxLN10wt9K8rfAvwDfl+QhSS7ue/bZvt4j+uXPTbfV86J0W0E/luSMg/Tt/0jy3nRbq76Q5NIkx4xcf2KSK/u+fjHJ/xi57ueT7ErypSTvTvKokeue0q/37v42C7eCZbH6kjwnyQ0LFtye5C/7s+cAF1bVnqr6LHAhcO7BHhdqn4FNLfnfwDeT7EzytCQPBaiqXcB/BD5YVUdV1fyL5O/QDYqnAt9P9wnmr43c3/cADxy5/I+BFwA/AvyfwK8l+b5DFZTuE7q/Av6xv58zgFcm+b9GFnsW8BbgGOAa4H/0t30AcBVwCd0nrJcBP9P/TV8Bngbc3v9NR1XV7Ye6P+CJ/d9z1aFqBv4t8GfAQ4EPA++me64fTzdA/tFhbi9JGo/j2SHuj5Ubz15It3XpwcCngJ3AfrqePg54KjC6X9qPAbcBxwKvAa5M8rBF6gjw28AjgR8ETgR+ve/NEXRbUz8FbOlre0t/3dnAq4F/Bzwc+Bu63pHkWOBtwH/u1//PwOkL1nuw+q4BHp3kB0eWfUHfK4Afovs/z/vH/jKtUQY2NaOqvgz8BFB0g9Hnk1yTZGrhskkC/D/AL1bVnVV1D920iueOLPYN4Leq6ht0L57HAm+oqnuq6hbgFrqpAofyo8DDq+o3q+rrVXVbX9voej5QVe+sqm/SvVie0l/+BGAT8Hv9J4dXAn+/hFYc7P6+G/hCVe0/zO3/pqre3S/3F3SDxAUjfdgy+smgJGmyHM8Oe38rNZ5dUlW39Ms/jC5IvrLfgrcPeN2Cv3cf8Pr+b3or8HHgGQuLqKpbq+raqvpaVX0eeC3wU/3Vp9EFuV/u1/OvVTW/j+JLgN+uql19Tf8NOLXfyvZ04KNVdUX/97we+NyCVS9aX1V9DXgrXUgjyQ/RhcW397c7Crh75H7uBo7qH2tagzYNXYA0qv/08VyAJD8AvJnuRezdCxZ9OPAg4IaR158AR4ws88V+kAD4av/7jpHrv0r3onYoj6Kb5nHXyGVH0H1KNm/0BfZfgAcm2UT3Av7ZqqqR6z9zmPUd6v6+CBybZNNhBrmFf+MXFunDUcBdSJJWhOPZIe9vpcaz0ZoeBdwf2DvS1/stWGbh3/Qpur/1XpI8Avg9uq2ZD+7v50v91ScCnzrI3/Eo4A1JLhy9O7qtcI8craWqKsnCnh6qvp3AZUn+M92Wxcv7IAcwBxw9crujgbkF96U1xC1salZVfYxu+sVj6T6lHPUFuhfrH6qqY/qfh1TV4Qas++ozwCdH1nFMVT24qp6+hNvuBY5f8InWiSOn7+sL5weBf6XbkViStEY4nh1gpcazhYHya8CxI3/v0VU1OjVw4d/0vcDtHOi3+/v+4ao6mm7L1vztPgN8bx9EF/oM8JIFPd9cVf+Lrqff7mFfx4kLbn/Q+qrq74Cv04XI/8B3pkNCt8X1lJHzp/SXaY0ysKkZSX6g32n2hP78icDzgL+j+5TthH4ePVX1LbqpHK/rP/kiyfEL5uLfV/dL8sCRn++im/Lx5SS/mmRzkiOSPDbJjy7h/j4IfBN4aZJNSc6imzox7w7gu9PtfH1YVXU33b4Lv59uh/MHJbl/v3/Ef79vf6okaaU4nh3aaoxnVbUXeA9wYZKjk9wv3cFDfmpksUcAL+/X/Ry6/dPeucjdPZhuq9VdSY4Hfnnkur+nC18XJDmy7/f8vmh/CLyqn7JIuoOgPKe/7h3ADyX5d33YezndvoqjDlffn9LtF7h/ZBrm/OW/1D+OHglsp/vAQGuUgU0tuYduB9vrk3yFbmC7me6F5r10nw59LskX+uV/FbgV+LskXwb+J3DyGOt/Ht2nnPM//9xPvfi3dDuCf5Luk9A3AocdlKrq63Q7Gp9HN13jBXTzy7/WX/8xup2Pb0tyV75zVK1D3edrgV+i20n583Sf3r0U+MtD3U6StKoczw5/n6sxnv0c8ADgo3RTGK8Ajhu5/nrgJLpe/Bbw7Kr64iL38xvA4+n2BXsHcOXI3zHf1+8HPg3sAf59f91VdAeUeUv/f72Zbr86quoLwHOAC+imiJ4E/O2C9R6uvj+j22r7Zwtu90d0B5i5qV/nO/CAY2tanM4qrZ4k1wN/WFV/MnQtkiQt11ofz5KcC7y4qtbsF3Wn++qHfcDjq+oTQ9ejleMWNmkFJfmpJN/TTyE5h+4oXu8aui5Jku4Lx7Mm/SfgHwxr659HiZRW1snA5XRHsfpnuukMe4ctSZKk+8zxrCFJdtMd+MQDkW0ATomUJEmSpEY5JVKSJEmSGrWqUyKPPfbY2rJly7Jv/5WvfIUjjzxycgWtYfaiYx869qFjHzqT6MMNN9zwhap6+IRK0ioYd4wFn0Pz7EPHPnTsQ8c+dIYYY1c1sG3ZsoUPfehDy7797OwsMzMzkytoDbMXHfvQsQ8d+9CZRB+SfGoy1Wi1jDvGgs+hefahYx869qFjHzpDjLFOiZQkSZKkRhnYJEmSJKlRBjZJkiRJapSBTZIkSZIaZWCTJEmSpEYZ2CRJkiSpUYcNbEnelGRfkptHLntYkmuTfKL//dCVLVOSpPUpyTFJrkjysSS7kjzRcVaSNG8pW9guAc5ccNn5wHVVdRJwXX9ekiTdd28A3lVVPwCcAuzCcVaS1DtsYKuq9wN3Lrj4LGBnf3oncPaE65Ikad1LcjTwk8DFAFX19aq6C8dZSVIvVXX4hZItwNur6rH9+buq6piR679UVYtO10iyDdgGMDU19SNvectbll3svjvv5o6vLvvm68rUZuwF9mGefejYh86jH3IERx111Fj38aQnPemGqpqeUEk6iCSnAjuAj9JtXbsBeAXw2aWMs5McYwHm5ubGfuysB/ah08L7rq3HP2TYAvDxMM8+dCbRh/s6xm4aa21LUFU76AYjpqena2ZmZtn3ddGlV3PhTSte8pqwfet+e4F9mGcfOvahc8mZRzLOa61W1Sbg8cDLqur6JG/gPkx/nOQYCzA7O+tjB/swr4X3XbufPzPo+sHHwzz70BmiD8s9SuQdSY4D6H/vm1xJkiRtGHuAPVV1fX/+CroA5zgrSQKWH9iuAc7pT58DXD2ZciRJ2jiq6nPAZ5Kc3F90Bt30SMdZSRKwhCmRSS4DZoBjk+wBXgNcAFye5Dzg08BzVrJISZLWsZcBlyZ5AHAb8CK6D1QdZyVJhw9sVfW8g1x1xoRrkSRpw6mqjwCL7XzuOCtJWvaUSEmSJEnSCjOwSZIkSVKjDGySJEmS1CgDmyRJkiQ1ysAmSZIkSY0ysEmSJElSowxskiRJktQoA5skSZIkNcrAJkmSJEmNMrBJkiRJUqMMbJIkSZLUKAObJEmSJDXKwCZJkiRJjTKwSZIkSVKjDGySJEmS1CgDmyRJkiQ1ysAmSZIkSY0ysEmSJElSowxskiRJktQoA5skSZIkNcrAJkmSJEmNMrBJkiRJUqMMbJIkSZLUKAObJEmSJDXKwCZJkiRJjTKwSZIkSVKjDGySJEmS1KhNQxcgSdJGlmQ3cA/wTWB/VU0neRjwVmALsBv42ar60lA1SpKG4xY2SZKG96SqOrWqpvvz5wPXVdVJwHX9eUnSBmRgkySpPWcBO/vTO4GzB6xFkjQgp0RKkjSsAt6TpIA/qqodwFRV7QWoqr1JHrHYDZNsA7YBTE1NMTs7O1Yhc3NzY9/HemAfOlObYfvW/YPW0ML/wcdDxz50huiDgU2SpGGdXlW396Hs2iQfW+oN+3C3A2B6erpmZmbGKmR2dpZx72M9sA+diy69mgtvGvat4u7nzwy6fvDxMM8+dIbog1MiJUkaUFXd3v/eB1wFnAbckeQ4gP73vuEqlCQNycAmSdJAkhyZ5MHzp4GnAjcD1wDn9IudA1w9TIWSpKGNtZ07yS8CL6abf38T8KKq+tdJFCZJ0gYwBVyVBLox+c+r6l1J/gG4PMl5wKeB5wxYoyRpQMsObEmOB14OPKaqvprkcuC5wCUTqk2SpHWtqm4DTlnk8i8CZ6x+RZKk1ow7JXITsDnJJuBBwO3jlyRJkiRJgjG2sFXVZ5P8Lt1Uja8C76mq9yxcbpKHHG7h8LKtsBcd+9CxDx370PHQy5IkrR/jTIl8KN0Xez4auAv4iyQvqKo3jy43yUMOt3B42VZs37rfXmAf5tmHjn3oXHLmkR56WZKkdWKcKZE/DXyyqj5fVd8ArgR+fDJlSZIkSZLGCWyfBp6Q5EHpDm91BrBrMmVJkiRJkpYd2KrqeuAK4Ea6Q/rfj37qoyRJkiRpfGPt7FFVrwFeM6FaJEmSJEkjxj2svyRJkiRphRjYJEmSJKlRBjZJkiRJapSBTZIkSZIaZWCTJEmSpEYZ2CRJkiSpUQY2SZIkSWqUgU2SJEmSGmVgkyRJkqRGGdgkSZIkqVEGNkmSJElqlIFNkiRJkhplYJMkSZKkRhnYJEmSJKlRBjZJkiRJapSBTZIkSZIaZWCTJEmSpEYZ2CRJkiSpUQY2SZIkSWqUgU2SJEmSGmVgkyRpYEmOSPLhJG/vzz86yfVJPpHkrUkeMHSNkqRhGNgkSRreK4BdI+d/B3hdVZ0EfAk4b5CqJEmDM7BJkjSgJCcAzwDe2J8P8GTgin6RncDZw1QnSRrapqELkCRpg3s98CvAg/vz3w3cVVX7+/N7gOMXu2GSbcA2gKmpKWZnZ8cqZG5ubuz7WA/sQ2dqM2zfuv/wC66gFv4PPh469qEzRB8MbJIkDSTJM4F9VXVDkpn5ixdZtBa7fVXtAHYATE9P18zMzGKLLdns7Czj3sd6YB86F116NRfeNOxbxd3Pnxl0/eDjYZ596AzRBwObJEnDOR14VpKnAw8Ejqbb4nZMkk39VrYTgNsHrFGSNCD3YZMkaSBV9aqqOqGqtgDPBd5bVc8H3gc8u1/sHODqgUqUJA3MwCZJUnt+FfilJLfS7dN28cD1SJIG4pRISZIaUFWzwGx/+jbgtCHrkSS1wS1skiRJktQoA5skSZIkNcrAJkmSJEmNMrBJkiRJUqMMbJIkSZLUqLECW5JjklyR5GNJdiV54qQKkyRJkqSNbtzD+r8BeFdVPTvJA4AHTaAmSZIkSRJjBLYkRwM/CZwLUFVfB74+mbIkSZIkSeNsYfs+4PPAnyQ5BbgBeEVVfWV0oSTbgG0AU1NTzM7OLnuFU5th+9b9y779emIvOvahYx869qEzNzc31mutJElqxziBbRPweOBlVXV9kjcA5wP/7+hCVbUD2AEwPT1dMzMzy17hRZdezYU3jTuLc33YvnW/vcA+zLMPHfvQueTMIxnntVaSJLVjnIOO7AH2VNX1/fkr6AKcJEmSJGkClh3YqupzwGeSnNxfdAbw0YlUJUmSJEka+yiRLwMu7Y8QeRvwovFLkiRJkiTBmIGtqj4CTE+oFkmSJEnSiLG+OFuSJEmStHIMbJIkSZLUKAObJEmSJDXKwCZJkiRJjTKwSZIkSVKjDGySJEmS1CgDmyRJkiQ1ysAmSZIkSY0ysEmSJElSowxskiRJktQoA5skSZIkNcrAJkmSJEmNMrBJkiRJUqMMbJIkDSTJA5P8fZJ/THJLkt/oL390kuuTfCLJW5M8YOhaJUnDMLBJkjScrwFPrqpTgFOBM5M8Afgd4HVVdRLwJeC8AWuUJA3IwCZJ0kCqM9efvX//U8CTgSv6y3cCZw9QniSpAZuGLkCSpI0syRHADcD3A78P/DNwV1Xt7xfZAxx/kNtuA7YBTE1NMTs7O1Ytc3NzY9/HemAfOlObYfvW/YdfcAW18H/w8dCxD50h+mBgkyRpQFX1TeDUJMcAVwE/uNhiB7ntDmAHwPT0dM3MzIxVy+zsLOPex3pgHzoXXXo1F9407FvF3c+fGXT94ONhnn3oDNEHp0RKktSAqroLmAWeAByTZP6d8gnA7UPVJUkaloFNkqSBJHl4v2WNJJuBnwZ2Ae8Dnt0vdg5w9TAVSpKG5pRISZKGcxyws9+P7X7A5VX19iQfBd6S5L8CHwYuHrJISdJwDGySJA2kqv4JeNwil98GnLb6FUmSWuOUSEmSJElqlIFNkiRJkhplYJMkSZKkRhnYJEmSJKlRBjZJkiRJapSBTZIkSZIaZWCTJEmSpEYZ2CRJkiSpUQY2SZIkSWqUgU2SJEmSGmVgkyRJkqRGGdgkSZIkqVFjB7YkRyT5cJK3T6IgSZIkSVJnElvYXgHsmsD9SJIkSZJGjBXYkpwAPAN442TKkSRJkiTNG3cL2+uBXwG+NYFaJEmSJEkjNi33hkmeCeyrqhuSzBxiuW3ANoCpqSlmZ2eXu0qmNsP2rfuXffv1xF507EPHPnTsQ2dubm6s11pJktSOZQc24HTgWUmeDjwQODrJm6vqBaMLVdUOYAfA9PR0zczMLHuFF116NRfeNE7J68f2rfvtBfZhnn3o2IfOJWceyTivtZIkqR3LnhJZVa+qqhOqagvwXOC9C8OaJEmSJGn5/B42SZIkSWrUROYOVdUsMDuJ+5IkSZIkddzCJkmSJEmNMrBJkiRJUqMMbJIkSZLUKAObJEmSJDXKwCZJkiQN5D1/AAAJ70lEQVRJjTKwSZIkSVKjDGySJA0kyYlJ3pdkV5Jbkryiv/xhSa5N8on+90OHrlWSNAwDmyRJw9kPbK+qHwSeAPxCkscA5wPXVdVJwHX9eUnSBmRgkyRpIFW1t6pu7E/fA+wCjgfOAnb2i+0Ezh6mQknS0DYNXYAkSYIkW4DHAdcDU1W1F7pQl+QRB7nNNmAbwNTUFLOzs2PVMDc3N/Z9rAf2oTO1GbZv3T9oDS38H3w8dOxDZ4g+GNgkSRpYkqOAtwGvrKovJ1nS7apqB7ADYHp6umZmZsaqY3Z2lnHvYz2wD52LLr2aC28a9q3i7ufPDLp+8PEwzz50huiDUyIlSRpQkvvThbVLq+rK/uI7khzXX38csG+o+iRJwzKwSZI0kHSb0i4GdlXVa0euugY4pz99DnD1atcmSWqDUyIlSRrO6cALgZuSfKS/7NXABcDlSc4DPg08Z6D6JEkDM7BJkjSQqvoAcLAd1s5YzVokSW1ySqQkSZIkNcrAJkmSJEmNMrBJkiRJUqMMbJIkSZLUKAObJEmSJDXKwCZJkiRJjTKwSZIkSVKjDGySJEmS1CgDmyRJkiQ1ysAmSZIkSY0ysEmSJElSowxskiRJktQoA5skSZIkNcrAJkmSJEmNMrBJkiRJUqMMbJIkSZLUKAObJEmSJDXKwCZJkiRJjTKwSZIkSVKjlh3YkpyY5H1JdiW5JckrJlmYJEmSJG10m8a47X5ge1XdmOTBwA1Jrq2qj06oNkmSJEna0Ja9ha2q9lbVjf3pe4BdwPGTKkySJEmSNrqJ7MOWZAvwOOD6SdyfJEmSJGm8KZEAJDkKeBvwyqr68iLXbwO2AUxNTTE7O7vsdU1thu1b9y/79uuJvejYh4596NiHztzc3FivtZIkqR1jBbYk96cLa5dW1ZWLLVNVO4AdANPT0zUzM7Ps9V106dVceNPYGXNd2L51v73APsyzDx370LnkzCMZ57VWkiS1Y5yjRAa4GNhVVa+dXEmSJEmSJBhvH7bTgRcCT07ykf7n6ROqS5IkSZI2vGXPHaqqDwCZYC2SJG04Sd4EPBPYV1WP7S97GPBWYAuwG/jZqvrSUDVKkoYzkaNESpKkZbsEOHPBZecD11XVScB1/XlJ0gZkYJMkaUBV9X7gzgUXnwXs7E/vBM5e1aIkSc3wcGqSJLVnqqr2AlTV3iSPWGyhSX51DsC+O+/mokuvHus+1oOpzdgH2viqlBb+Dz4eOvah8+iHHLHqX51jYJMkaY2a5FfngF+fM8+vCOnYh4596NiHzhBfneOUSEmS2nNHkuMA+t/7Bq5HkjQQA5skSe25BjinP30O4DwkSdqgDGySJA0oyWXAB4GTk+xJch5wAfCUJJ8AntKflyRtQE5ElSRpQFX1vINcdcaqFiJJapJb2CRJkiSpUQY2SZIkSWqUgU2SJEmSGmVgkyRJkqRGGdgkSZIkqVEGNkmSJElqlIFNkiRJkhplYJMkSZKkRhnYJEmSJKlRBjZJkiRJapSBTZIkSZIaZWCTJEmSpEYZ2CRJkiSpUQY2SZIkSWqUgU2SJEmSGmVgkyRJkqRGGdgkSZIkqVEGNkmSJElqlIFNkiRJkhplYJMkSZKkRhnYJEmSJKlRBjZJkiRJapSBTZIkSZIaZWCTJEmSpEYZ2CRJkiSpUQY2SZIkSWqUgU2SJEmSGjVWYEtyZpKPJ7k1yfmTKkqSpI3OMVaSBGMEtiRHAL8PPA14DPC8JI+ZVGGSJG1UjrGSpHnjbGE7Dbi1qm6rqq8DbwHOmkxZkiRtaI6xkiQAUlXLu2HybODMqnpxf/6FwI9V1UsXLLcN2NafPRn4+PLL5VjgC2Pcfj2xFx370LEPHfvQmUQfHlVVD59EMbrvBhpjwefQPPvQsQ8d+9CxD51VH2M3jbGiLHLZAemvqnYAO8ZYz3dWmHyoqqYncV9rnb3o2IeOfejYh459WBdWfYwFHzvz7EPHPnTsQ8c+dIbowzhTIvcAJ46cPwG4fbxyJEkSjrGSpN44ge0fgJOSPDrJA4DnAtdMpixJkjY0x1hJEjDGlMiq2p/kpcC7gSOAN1XVLROrbHETm/axDtiLjn3o2IeOfejYhzVuoDEWfOzMsw8d+9CxDx370Fn1Piz7oCOSJEmSpJU11hdnS5IkSZJWjoFNkiRJkhq1ZgJbkjOTfDzJrUnOH7qeISQ5Mcn7kuxKckuSVwxd05CSHJHkw0nePnQtQ0pyTJIrknysf2w8ceiahpDkF/vnxc1JLkvywKFrWg1J3pRkX5KbRy57WJJrk3yi//3QIWtU+xxjHWMXcoztOMZ2HGOHHWPXRGBLcgTw+8DTgMcAz0vymGGrGsR+YHtV/SDwBOAXNmgf5r0C2DV0EQ14A/CuqvoB4BQ2YE+SHA+8HJiuqsfSHaThucNWtWouAc5ccNn5wHVVdRJwXX9eWpRj7Lc5xt6bY2zHMdYxdvAxdk0ENuA04Naquq2qvg68BThr4JpWXVXtraob+9P30L1oHD9sVcNIcgLwDOCNQ9cypCRHAz8JXAxQVV+vqruGrWowm4DNSTYBD2KDfGdVVb0fuHPBxWcBO/vTO4GzV7UorTWOsTjGjnKM7TjG3otj7Hes+hi7VgLb8cBnRs7vYYO+iM5LsgV4HHD9sJUM5vXArwDfGrqQgX0f8HngT/qpK29McuTQRa22qvos8LvAp4G9wN1V9Z5hqxrUVFXthe5NKPCIgetR2xxjF3CMdYztOcbiGLuIVR9j10pgyyKXbdjvI0hyFPA24JVV9eWh61ltSZ4J7KuqG4aupQGbgMcDf1BVjwO+wgac/tbPHz8LeDTwSODIJC8YtippzXCMHeEY6xg7wjEWx9gWrJXAtgc4ceT8CWyQTbELJbk/3UByaVVdOXQ9AzkdeFaS3XRTd56c5M3DljSYPcCeqpr/FPgKusFlo/lp4JNV9fmq+gZwJfDjA9c0pDuSHAfQ/943cD1qm2NszzEWcIwd5RjbcYy9t1UfY9dKYPsH4KQkj07yALodHa8ZuKZVlyR086h3VdVrh65nKFX1qqo6oaq20D0W3ltVG/KTnqr6HPCZJCf3F50BfHTAkobyaeAJSR7UP0/OYAPuGD7iGuCc/vQ5wNUD1qL2OcbiGDvPMfY7HGO/zTH23lZ9jN200iuYhKran+SlwLvpjkzzpqq6ZeCyhnA68ELgpiQf6S97dVW9c8CaNLyXAZf2b7RuA140cD2rrqquT3IFcCPdkd4+DOwYtqrVkeQyYAY4Nske4DXABcDlSc6jG2ifM1yFap1j7Lc5xmoxjrGOsTMMPMamasNOU5ckSZKkpq2VKZGSJEmStOEY2CRJkiSpUQY2SZIkSWqUgU2SJEmSGmVgkyRJkqRGGdgkSZIkqVEGNkmSJElq1P8PUZ37OImG9coAAAAASUVORK5CYII=\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris['StemLengthCmreplacedby0']=iris['StemLengthCm'].fillna(4.8, inplace = False)\n", + "iris.hist(figsize = (15,15))" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 52, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "iris.plot.box(figsize = (15,5))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/module-3/Data-Cleaning-Challenge/Lab Code.ipynb b/module-3/Data-Cleaning-Challenge/Lab Code.ipynb new file mode 100644 index 00000000..00ac9b7b --- /dev/null +++ b/module-3/Data-Cleaning-Challenge/Lab Code.ipynb @@ -0,0 +1,624 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sepal_length_cmsepal_width_cmpetal_length_cmpetal_width_cmclass
05.13.51.40.2Iris-setosa
14.93.01.40.2Iris-setosa
24.73.21.30.2Iris-setosa
34.63.11.50.2Iris-setosa
45.03.61.40.2Iris-setosa
..................
1456.73.05.22.3Iris-virginica
1466.32.55.02.3Iris-virginica
1476.53.05.22.0Iris-virginica
1486.23.45.42.3Iris-virginica
1495.93.05.11.8Iris-virginica
\n", + "

150 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " sepal_length_cm sepal_width_cm petal_length_cm petal_width_cm \\\n", + "0 5.1 3.5 1.4 0.2 \n", + "1 4.9 3.0 1.4 0.2 \n", + "2 4.7 3.2 1.3 0.2 \n", + "3 4.6 3.1 1.5 0.2 \n", + "4 5.0 3.6 1.4 0.2 \n", + ".. ... ... ... ... \n", + "145 6.7 3.0 5.2 2.3 \n", + "146 6.3 2.5 5.0 2.3 \n", + "147 6.5 3.0 5.2 2.0 \n", + "148 6.2 3.4 5.4 2.3 \n", + "149 5.9 3.0 5.1 1.8 \n", + "\n", + " class \n", + "0 Iris-setosa \n", + "1 Iris-setosa \n", + "2 Iris-setosa \n", + "3 Iris-setosa \n", + "4 Iris-setosa \n", + ".. ... \n", + "145 Iris-virginica \n", + "146 Iris-virginica \n", + "147 Iris-virginica \n", + "148 Iris-virginica \n", + "149 Iris-virginica \n", + "\n", + "[150 rows x 5 columns]" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris = pd.read_csv('iris-data.csv')\n", + "iris" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "sepal_length_cm float64\n", + "sepal_width_cm float64\n", + "petal_length_cm float64\n", + "petal_width_cm float64\n", + "class object\n", + "dtype: object" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "##check the data is encoded/formatted properly\n", + "iris.dtypes\n", + "\n", + "#they are all float which is what we wanted - so yes" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "sepal_length_cm 0\n", + "sepal_width_cm 0\n", + "petal_length_cm 0\n", + "petal_width_cm 5\n", + "class 0\n", + "dtype: int64" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Find any null values\n", + "iris.isna().sum()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "1.2365517241379318" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#we can see that petal_width_cm has null values which I have chosen to replace with the mean\n", + "\n", + "#So finding the mean\n", + "\n", + "iris[\"petal_width_cm\"].mean()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sepal_length_cmsepal_width_cmpetal_length_cmpetal_width_cm
count150.000000150.000000150.000000145.000000
mean5.6446273.0546673.7586671.236552
std1.3127810.4331231.7644200.755058
min0.0550002.0000001.0000000.100000
25%5.1000002.8000001.6000000.400000
50%5.7000003.0000004.3500001.300000
75%6.4000003.3000005.1000001.800000
max7.9000004.4000006.9000002.500000
\n", + "
" + ], + "text/plain": [ + " sepal_length_cm sepal_width_cm petal_length_cm petal_width_cm\n", + "count 150.000000 150.000000 150.000000 145.000000\n", + "mean 5.644627 3.054667 3.758667 1.236552\n", + "std 1.312781 0.433123 1.764420 0.755058\n", + "min 0.055000 2.000000 1.000000 0.100000\n", + "25% 5.100000 2.800000 1.600000 0.400000\n", + "50% 5.700000 3.000000 4.350000 1.300000\n", + "75% 6.400000 3.300000 5.100000 1.800000\n", + "max 7.900000 4.400000 6.900000 2.500000" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "iris.describe()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "class\n", + "Iris-setosa 0.250000\n", + "Iris-setossa 0.300000\n", + "Iris-versicolor 1.335556\n", + "Iris-virginica 2.034000\n", + "versicolor 1.240000\n", + "Name: petal_width_cm, dtype: float64" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "\n", + "iris['petal_width_cm'].groupby(iris['class']).mean()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 0.2\n", + "1 0.2\n", + "2 0.2\n", + "3 0.2\n", + "4 0.2\n", + " ... \n", + "145 2.3\n", + "146 2.3\n", + "147 2.0\n", + "148 2.3\n", + "149 1.8\n", + "Name: petal_width_cm, Length: 150, dtype: float64" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#replacing null values with the mean of the class\n", + "iris['petal_width_cm'].fillna(iris['petal_width_cm'].groupby(iris['class']).mean())\n" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "sepal_length_cm 0\n", + "sepal_width_cm 0\n", + "petal_length_cm 0\n", + "petal_width_cm 0\n", + "class 0\n", + "dtype: int64" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "#check it's worked - null values are filled\n", + "iris.isna().sum()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "#We can see from the box plot that there are outliers/ they do not all fall within the expected mean? \n", + "#I think pls confirm if this is correct or not?\n", + "\n", + "iris.plot.box()\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[,\n", + " ],\n", + " [,\n", + " ]],\n", + " dtype=object)" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "#visualise the data \n", + "\n", + "iris.hist(bins=10)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\chris\\anaconda3\\lib\\site-packages\\seaborn\\distributions.py:283: UserWarning: Data must have variance to compute a kernel density estimate.\n", + " warnings.warn(msg, UserWarning)\n", + "C:\\Users\\chris\\anaconda3\\lib\\site-packages\\seaborn\\distributions.py:369: UserWarning: Default bandwidth for data is 0; skipping density estimation.\n", + " warnings.warn(msg, UserWarning)\n", + "C:\\Users\\chris\\anaconda3\\lib\\site-packages\\seaborn\\distributions.py:283: UserWarning: Data must have variance to compute a kernel density estimate.\n", + " warnings.warn(msg, UserWarning)\n", + "C:\\Users\\chris\\anaconda3\\lib\\site-packages\\seaborn\\distributions.py:283: UserWarning: Data must have variance to compute a kernel density estimate.\n", + " warnings.warn(msg, UserWarning)\n", + "C:\\Users\\chris\\anaconda3\\lib\\site-packages\\seaborn\\distributions.py:283: UserWarning: Data must have variance to compute a kernel density estimate.\n", + " warnings.warn(msg, UserWarning)\n" + ] + }, + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "import seaborn as sns\n", + "\n", + "sns.pairplot(iris, hue = 'class')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/module-3/Data-Cleaning-Challenge/iris_codealong.csv b/module-3/Data-Cleaning-Challenge/iris_codealong.csv new file mode 100644 index 00000000..b80603ee --- /dev/null +++ b/module-3/Data-Cleaning-Challenge/iris_codealong.csv @@ -0,0 +1,151 @@ +Id,SepalLengthCm,SepalWidthCm,PetalLengthCm,PetalWidthCm,Color,StemLengthCm,Species +1,5.1,3.5,1.4,0.2,purple,3.636363636,Iris-setosa +2,4.9,3,1.4,0.2,yellow,,Iris-setosa +3,4.7,3.2,1.3,0.2,blue,2.727272727,Iris-setosa +4,4.6,3.1,1.5,0.2,purple,,Iris-setosa +5,5,3.6,1.4,0.2,blue,1.919191919,Iris-setosa +6,5.4,3.9,1.7,0.4,blue,2.828282828,Iris-setosa +7,4.6,3.4,1.4,0.3,blue,6.262626263,Iris-setosa +8,5,3.4,1.5,0.2,blue,,Iris-setosa +9,4.4,2.9,1.4,0.2,blue,8.787878788,Iris-setosa +10,4.9,3.1,1.5,0.1,blue,7.575757576,Iris-setosa +11,5.4,3.7,1.5,0.2,red,,Iris-setosa +12,4.8,3.4,1.6,0.2,blue,,Iris-setosa +13,4.8,3,1.4,0.1,red,5.252525253,Iris-setosa +14,4.3,3,1.1,0.1,red,,Iris-setosa +15,5.8,4,1.2,0.2,blue,6.464646465,Iris-setosa +16,5.7,4.4,1.5,0.4,red,1.313131313,Iris-setosa +17,5.4,3.9,1.3,0.4,blue,0.505050505,Iris-setosa +18,5.1,3.5,1.4,0.3,purple,4.545454545,Iris-setosa +19,5.7,3.8,1.7,0.3,blue,,Iris-setosa +20,5.1,3.8,1.5,0.3,blue,2.02020202,Iris-setosa +21,5.4,3.4,1.7,0.2,purple,2.525252525,Iris-setosa +22,5.1,3.7,1.5,0.4,purple,,Iris-setosa +23,4.6,3.6,1,0.2,purple,5.95959596,Iris-setosa +24,5.1,3.3,1.7,0.5,blue,4.848484848,Iris-setosa +25,4.8,3.4,1.9,0.2,blue,6.363636364,Iris-setosa +26,5,3,1.6,0.2,blue,2.323232323,Iris-setosa +27,5,3.4,1.6,0.4,blue,4.747474747,Iris-setosa +28,5.2,3.5,1.5,0.2,red,,Iris-setosa +29,5.2,3.4,1.4,0.2,blue,,Iris-setosa +30,4.7,3.2,1.6,0.2,blue,5.757575758,Iris-setosa +31,4.8,3.1,1.6,0.2,blue,8.080808081,Iris-setosa +32,5.4,3.4,1.5,0.4,blue,,Iris-setosa +33,5.2,4.1,1.5,0.1,purple,3.03030303,Iris-setosa +34,5.5,4.2,1.4,0.2,red,,Iris-setosa +35,4.9,3.1,1.5,0.1,purple,,Iris-setosa +36,5,3.2,1.2,0.2,blue,,Iris-setosa +37,5.5,3.5,1.3,0.2,blue,6.161616162,Iris-setosa +38,4.9,3.1,1.5,0.1,purple,6.96969697,Iris-setosa +39,4.4,3,1.3,0.2,blue,5.858585859,Iris-setosa +40,5.1,3.4,1.5,0.2,blue,7.070707071,Iris-setosa +41,5,3.5,1.3,0.3,blue,5.555555556,Iris-setosa +42,4.5,2.3,1.3,0.3,blue,5.151515152,Iris-setosa +43,4.4,3.2,1.3,0.2,blue,0.303030303,Iris-setosa +44,5,3.5,1.6,0.6,blue,6.565656566,Iris-setosa +45,5.1,3.8,1.9,0.4,red,1.414141414,Iris-setosa +46,4.8,3,1.4,0.3,purple,6.767676768,Iris-setosa +47,5.1,3.8,1.6,0.2,blue,,Iris-setosa +48,4.6,3.2,1.4,0.2,yellow,9.797979798,Iris-setosa +49,5.3,3.7,1.5,0.2,blue,,Iris-setosa +50,5,3.3,1.4,0.2,blue,9.393939394,Iris-setosa +51,7,3.2,4.7,1.4,red,,Iris-versicolor +52,6.4,3.2,4.5,1.5,red,,Iris-versicolor +53,6.9,3.1,4.9,1.5,red,0.202020202,Iris-versicolor +54,5.5,2.3,4,1.3,blue,0.404040404,Iris-versicolor +55,6.5,2.8,4.6,1.5,red,8.282828283,Iris-versicolor +56,5.7,2.8,4.5,1.3,red,9.595959596,Iris-versicolor +57,6.3,3.3,4.7,1.6,red,,Iris-versicolor +58,4.9,2.4,3.3,1,red,1.01010101,Iris-versicolor +59,6.6,2.9,4.6,1.3,blue,,Iris-versicolor +60,5.2,2.7,3.9,1.4,blue,,Iris-versicolor +61,5,2,3.5,1,blue,0.808080808,Iris-versicolor +62,5.9,3,4.2,1.5,red,8.888888889,Iris-versicolor +63,6,2.2,4,1,red,8.98989899,Iris-versicolor +64,6.1,2.9,4.7,1.4,red,,Iris-versicolor +65,5.6,2.9,3.6,1.3,red,,Iris-versicolor +66,6.7,3.1,4.4,1.4,blue,4.242424242,Iris-versicolor +67,5.6,3,4.5,1.5,blue,4.949494949,Iris-versicolor +68,5.8,2.7,4.1,1,red,4.646464646,Iris-versicolor +69,6.2,2.2,4.5,1.5,red,3.333333333,Iris-versicolor +70,5.6,2.5,3.9,1.1,red,,Iris-versicolor +71,5.9,3.2,4.8,1.8,red,,Iris-versicolor +72,6.1,2.8,4,1.3,blue,,Iris-versicolor +73,6.3,2.5,4.9,1.5,blue,8.383838384,Iris-versicolor +74,6.1,2.8,4.7,1.2,red,,Iris-versicolor +75,6.4,2.9,4.3,1.3,red,6.666666667,Iris-versicolor +76,6.6,3,4.4,1.4,blue,3.131313131,Iris-versicolor +77,6.8,2.8,4.8,1.4,red,2.222222222,Iris-versicolor +78,6.7,3,5,1.7,blue,1.212121212,Iris-versicolor +79,6,2.9,4.5,1.5,red,,Iris-versicolor +80,5.7,2.6,3.5,1,blue,,Iris-versicolor +81,5.5,2.4,3.8,1.1,red,,Iris-versicolor +82,5.5,2.4,3.7,1,red,3.737373737,Iris-versicolor +83,5.8,2.7,3.9,1.2,red,5.656565657,Iris-versicolor +84,6,2.7,5.1,1.6,red,1.818181818,Iris-versicolor +85,5.4,3,4.5,1.5,purple,7.676767677,Iris-versicolor +86,6,3.4,4.5,1.6,red,,Iris-versicolor +87,6.7,3.1,4.7,1.5,red,7.171717172,Iris-versicolor +88,6.3,2.3,4.4,1.3,red,,Iris-versicolor +89,5.6,3,4.1,1.3,red,3.535353535,Iris-versicolor +90,5.5,2.5,4,1.3,purple,,Iris-versicolor +91,5.5,2.6,4.4,1.2,red,0.909090909,Iris-versicolor +92,6.1,3,4.6,1.4,red,9.494949495,Iris-versicolor +93,5.8,2.6,4,1.2,red,5.454545455,Iris-versicolor +94,5,2.3,3.3,1,red,1.717171717,Iris-versicolor +95,5.6,2.7,4.2,1.3,blue,1.616161616,Iris-versicolor +96,5.7,3,4.2,1.2,red,,Iris-versicolor +97,5.7,2.9,4.2,1.3,blue,8.484848485,Iris-versicolor +98,6.2,2.9,4.3,1.3,purple,3.232323232,Iris-versicolor +99,5.1,2.5,3,1.1,red,9.898989899,Iris-versicolor +100,5.7,2.8,4.1,1.3,red,,Iris-versicolor +101,6.3,3.3,6,2.5,purple,9.191919192,Iris-virginica +102,5.8,2.7,5.1,1.9,blue,1.515151515,Iris-virginica +103,7.1,3,5.9,2.1,purple,8.585858586,Iris-virginica +104,6.3,2.9,5.6,1.8,purple,,Iris-virginica +105,6.5,3,5.8,2.2,red,9.696969697,Iris-virginica +106,7.6,3,6.6,2.1,purple,2.121212121,Iris-virginica +107,4.9,2.5,4.5,1.7,purple,,Iris-virginica +108,7.3,2.9,6.3,1.8,purple,,Iris-virginica +109,6.7,2.5,5.8,1.8,yellow,5.353535354,Iris-virginica +110,7.2,3.6,6.1,2.5,purple,0.606060606,Iris-virginica +111,6.5,3.2,5.1,2,purple,1.111111111,Iris-virginica +112,6.4,2.7,5.3,1.9,purple,8.686868687,Iris-virginica +113,6.8,3,5.5,2.1,yellow,6.868686869,Iris-virginica +114,5.7,2.5,5,2,purple,5.050505051,Iris-virginica +115,5.8,2.8,5.1,2.4,purple,,Iris-virginica +116,6.4,3.2,5.3,2.3,purple,7.777777778,Iris-virginica +117,6.5,3,5.5,1.8,purple,4.444444444,Iris-virginica +118,7.7,3.8,6.7,2.2,purple,,Iris-virginica +119,7.7,2.6,6.9,2.3,purple,7.97979798,Iris-virginica +120,6,2.2,5,1.5,purple,4.141414141,Iris-virginica +121,6.9,3.2,5.7,2.3,purple,,Iris-virginica +122,5.6,2.8,4.9,2,purple,7.373737374,Iris-virginica +123,7.7,2.8,6.7,2,red,3.939393939,Iris-virginica +124,6.3,2.7,4.9,1.8,purple,0,Iris-virginica +125,6.7,3.3,5.7,2.1,purple,2.424242424,Iris-virginica +126,7.2,3.2,6,1.8,purple,,Iris-virginica +127,6.2,2.8,4.8,1.8,yellow,,Iris-virginica +128,6.1,3,4.9,1.8,yellow,7.878787879,Iris-virginica +129,6.4,2.8,5.6,2.1,purple,9.292929293,Iris-virginica +130,7.2,3,5.8,1.6,purple,2.626262626,Iris-virginica +131,7.4,2.8,6.1,1.9,purple,,Iris-virginica +132,7.9,3.8,6.4,2,yellow,4.343434343,Iris-virginica +133,6.4,2.8,5.6,2.2,purple,7.474747475,Iris-virginica +134,6.3,2.8,5.1,1.5,purple,3.838383838,Iris-virginica +135,6.1,2.6,5.6,1.4,purple,0.707070707,Iris-virginica +136,7.7,3,6.1,2.3,purple,,Iris-virginica +137,6.3,3.4,5.6,2.4,purple,,Iris-virginica +138,6.4,3.1,5.5,1.8,purple,2.929292929,Iris-virginica +139,6,3,4.8,1.8,purple,7.272727273,Iris-virginica +140,6.9,3.1,5.4,2.1,yellow,4.04040404,Iris-virginica +141,6.7,3.1,5.6,2.4,red,9.090909091,Iris-virginica +142,6.9,3.1,5.1,2.3,purple,6.060606061,Iris-virginica +143,5.8,2.7,5.1,1.9,purple,,Iris-virginica +144,6.8,3.2,5.9,2.3,purple,,Iris-virginica +145,6.7,3.3,5.7,2.5,purple,10,Iris-virginica +146,6.7,3,5.2,2.3,purple,0.101010101,Iris-virginica +147,6.3,2.5,5,1.9,blue,,Iris-virginica +148,6.5,3,5.2,2,purple,3.434343434,Iris-virginica +149,6.2,3.4,5.4,2.3,purple,8.181818182,Iris-virginica +150,5.9,3,5.1,1.8,yellow,,Iris-virginica