From 4cddcce120280c8b52e816550c425bff9871325c Mon Sep 17 00:00:00 2001 From: Guillermo Fiallo Montero Date: Tue, 18 Feb 2025 18:42:45 +0100 Subject: [PATCH] e2 lab-advanced-topics-with-pandas commit --- your-code/main.ipynb | 3430 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 3377 insertions(+), 53 deletions(-) diff --git a/your-code/main.ipynb b/your-code/main.ipynb index 7687137..6236bac 100644 --- a/your-code/main.ipynb +++ b/your-code/main.ipynb @@ -12,11 +12,13 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 25, "metadata": {}, "outputs": [], "source": [ - "# import numpy and pandas" + "# import numpy and pandas\n", + "import numpy as np\n", + "import pandas as pd" ] }, { @@ -34,11 +36,224 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 26, "metadata": {}, "outputs": [], "source": [ - "admissions = pd.read_csv('data/Admission_Predict.csv')" + "admissions = pd.read_csv('../data/Admission_Predict.csv') # Add the two .. to access a file that is not in the same directory as the Notebook!!" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "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", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
0133711844.54.59.6510.92
1231610433.03.58.0010.72
2332211033.52.58.6710.80
3431410322.03.08.2100.65
4533011554.53.09.3410.90
..............................
38038132411033.53.59.0410.82
38138232510733.03.59.1110.84
38238333011645.04.59.4510.91
38338431210333.54.08.7800.67
38438533311745.04.09.6610.95
\n", + "

385 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "0 1 337 118 4 4.5 4.5 9.65 \n", + "1 2 316 104 3 3.0 3.5 8.00 \n", + "2 3 322 110 3 3.5 2.5 8.67 \n", + "3 4 314 103 2 2.0 3.0 8.21 \n", + "4 5 330 115 5 4.5 3.0 9.34 \n", + ".. ... ... ... ... ... ... ... \n", + "380 381 324 110 3 3.5 3.5 9.04 \n", + "381 382 325 107 3 3.0 3.5 9.11 \n", + "382 383 330 116 4 5.0 4.5 9.45 \n", + "383 384 312 103 3 3.5 4.0 8.78 \n", + "384 385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit \n", + "0 1 0.92 \n", + "1 1 0.72 \n", + "2 1 0.80 \n", + "3 0 0.65 \n", + "4 1 0.90 \n", + ".. ... ... \n", + "380 1 0.82 \n", + "381 1 0.84 \n", + "382 1 0.91 \n", + "383 0 0.67 \n", + "384 1 0.95 \n", + "\n", + "[385 rows x 9 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display(admissions)" ] }, { @@ -50,9 +265,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 28, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['Serial No.', 'GRE Score', 'TOEFL Score', 'University Rating', 'SOP',\n", + " 'LOR', 'CGPA', 'Research', 'Chance of Admit'],\n", + " dtype='object')" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "admissions.columns = [col.strip() for col in admissions.columns]\n", "admissions.columns\n", @@ -70,11 +298,130 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 29, "metadata": {}, - "outputs": [], + "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", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
0133711844.54.59.6510.92
1231610433.03.58.0010.72
2332211033.52.58.6710.80
3431410322.03.08.2100.65
4533011554.53.09.3410.90
\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "0 1 337 118 4 4.5 4.5 9.65 \n", + "1 2 316 104 3 3.0 3.5 8.00 \n", + "2 3 322 110 3 3.5 2.5 8.67 \n", + "3 4 314 103 2 2.0 3.0 8.21 \n", + "4 5 330 115 5 4.5 3.0 9.34 \n", + "\n", + " Research Chance of Admit \n", + "0 1 0.92 \n", + "1 1 0.72 \n", + "2 1 0.80 \n", + "3 0 0.65 \n", + "4 1 0.90 " + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "admissions.head()" ] }, { @@ -86,11 +433,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "False" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "admissions.isnull().values.any() # isnull alone will give you the whole list as a boolean for True if there \n" ] }, { @@ -102,11 +461,233 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 31, "metadata": {}, - "outputs": [], + "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", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
Serial No.
1133711844.54.59.6510.92
2231610433.03.58.0010.72
3332211033.52.58.6710.80
4431410322.03.08.2100.65
5533011554.53.09.3410.90
..............................
38138132411033.53.59.0410.82
38238232510733.03.59.1110.84
38338333011645.04.59.4510.91
38438431210333.54.08.7800.67
38538533311745.04.09.6610.95
\n", + "

385 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR \\\n", + "Serial No. \n", + "1 1 337 118 4 4.5 4.5 \n", + "2 2 316 104 3 3.0 3.5 \n", + "3 3 322 110 3 3.5 2.5 \n", + "4 4 314 103 2 2.0 3.0 \n", + "5 5 330 115 5 4.5 3.0 \n", + "... ... ... ... ... ... ... \n", + "381 381 324 110 3 3.5 3.5 \n", + "382 382 325 107 3 3.0 3.5 \n", + "383 383 330 116 4 5.0 4.5 \n", + "384 384 312 103 3 3.5 4.0 \n", + "385 385 333 117 4 5.0 4.0 \n", + "\n", + " CGPA Research Chance of Admit \n", + "Serial No. \n", + "1 9.65 1 0.92 \n", + "2 8.00 1 0.72 \n", + "3 8.67 1 0.80 \n", + "4 8.21 0 0.65 \n", + "5 9.34 1 0.90 \n", + "... ... ... ... \n", + "381 9.04 1 0.82 \n", + "382 9.11 1 0.84 \n", + "383 9.45 1 0.91 \n", + "384 8.78 0 0.67 \n", + "385 9.66 1 0.95 \n", + "\n", + "[385 rows x 9 columns]" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "# Keep the \"Serial No.\" column and also make it the index\n", + "admissions = admissions.set_index('Serial No.', drop=False)\n", + "admissions" ] }, { @@ -118,13 +699,34 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": { "scrolled": true }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Do GRE Score and CGPA uniquely identify the data? True\n" + ] + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "# I do not understand the task but an LLM wrote:\n", + "\n", + "# Create a temporary DataFrame by combining 'GRE Score' and 'CGPA'\n", + "temp = admissions[['GRE Score', 'CGPA']]\n", + "\n", + "# Check for duplicated rows in this new temporary DataFrame\n", + "duplicates = temp.duplicated()\n", + "\n", + "# If there are no duplicates, the sum of this will be 0\n", + "are_unique = not duplicates.any()\n", + "\n", + "# Output the result\n", + "print(f\"Do GRE Score and CGPA uniquely identify the data? {are_unique}\")" ] }, { @@ -136,11 +738,141 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 33, "metadata": {}, - "outputs": [], + "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", + "
Serial No.TOEFL ScoreUniversity RatingSOPLORResearchChance of Admit
GRE ScoreCGPA
3379.65111844.54.510.92
3168.00210433.03.510.72
3228.67311033.52.510.80
3148.21410322.03.000.65
3309.34511554.53.010.90
\n", + "
" + ], + "text/plain": [ + " Serial No. TOEFL Score University Rating SOP LOR \\\n", + "GRE Score CGPA \n", + "337 9.65 1 118 4 4.5 4.5 \n", + "316 8.00 2 104 3 3.0 3.5 \n", + "322 8.67 3 110 3 3.5 2.5 \n", + "314 8.21 4 103 2 2.0 3.0 \n", + "330 9.34 5 115 5 4.5 3.0 \n", + "\n", + " Research Chance of Admit \n", + "GRE Score CGPA \n", + "337 9.65 1 0.92 \n", + "316 8.00 1 0.72 \n", + "322 8.67 1 0.80 \n", + "314 8.21 0 0.65 \n", + "330 9.34 1 0.90 " + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "# Set 'GRE Score' and 'CGPA' as a multi-index and remove them from the DataFrame\n", + "admissions.set_index(['GRE Score', 'CGPA'], inplace=True)\n", + "\n", + "# Display the modified DataFrame\n", + "admissions.head()" ] }, { @@ -152,11 +884,135 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "metadata": {}, - "outputs": [], + "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", + "
GRE ScoreCGPASerial No.TOEFL ScoreUniversity RatingSOPLORResearchChance of Admit
03379.65111844.54.510.92
13168.00210433.03.510.72
23228.67311033.52.510.80
33148.21410322.03.000.65
43309.34511554.53.010.90
\n", + "
" + ], + "text/plain": [ + " GRE Score CGPA Serial No. TOEFL Score University Rating SOP LOR \\\n", + "0 337 9.65 1 118 4 4.5 4.5 \n", + "1 316 8.00 2 104 3 3.0 3.5 \n", + "2 322 8.67 3 110 3 3.5 2.5 \n", + "3 314 8.21 4 103 2 2.0 3.0 \n", + "4 330 9.34 5 115 5 4.5 3.0 \n", + "\n", + " Research Chance of Admit \n", + "0 1 0.92 \n", + "1 1 0.72 \n", + "2 1 0.80 \n", + "3 0 0.65 \n", + "4 1 0.90 " + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "# Did not know how to do this\n", + "# Reset the index of the DataFrame\n", + "admissions.reset_index(inplace=True)\n", + "\n", + "# Optionally, display the modified DataFrame to verify the change\n", + "admissions.head()\n" ] }, { @@ -170,11 +1026,248 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 35, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The number of rows where CGPA is higher than 9 and the student has conducted research is 101.\n" + ] + }, + { + "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", + "
GRE ScoreCGPASerial No.TOEFL ScoreUniversity RatingSOPLORResearchChance of Admit
03379.65111844.54.510.92
43309.34511554.53.010.90
103289.101111244.04.510.78
193289.502011655.05.010.94
203349.702111955.04.510.95
..............................
3793299.2338011144.54.010.89
3803249.0438111033.53.510.82
3813259.1138210733.03.510.84
3823309.4538311645.04.510.91
3843339.6638511745.04.010.95
\n", + "

101 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " GRE Score CGPA Serial No. TOEFL Score University Rating SOP LOR \\\n", + "0 337 9.65 1 118 4 4.5 4.5 \n", + "4 330 9.34 5 115 5 4.5 3.0 \n", + "10 328 9.10 11 112 4 4.0 4.5 \n", + "19 328 9.50 20 116 5 5.0 5.0 \n", + "20 334 9.70 21 119 5 5.0 4.5 \n", + ".. ... ... ... ... ... ... ... \n", + "379 329 9.23 380 111 4 4.5 4.0 \n", + "380 324 9.04 381 110 3 3.5 3.5 \n", + "381 325 9.11 382 107 3 3.0 3.5 \n", + "382 330 9.45 383 116 4 5.0 4.5 \n", + "384 333 9.66 385 117 4 5.0 4.0 \n", + "\n", + " Research Chance of Admit \n", + "0 1 0.92 \n", + "4 1 0.90 \n", + "10 1 0.78 \n", + "19 1 0.94 \n", + "20 1 0.95 \n", + ".. ... ... \n", + "379 1 0.89 \n", + "380 1 0.82 \n", + "381 1 0.84 \n", + "382 1 0.91 \n", + "384 1 0.95 \n", + "\n", + "[101 rows x 9 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "\"Explanation:\\nadmissions[(condition1) & (condition2)]: The conditions are enclosed in parentheses and combined using & to create a composite criterion that both have to be met.\\nlen(filtered_df): Counts the number of rows in the filtered DataFrame, which gives you the result you seek.\\nBy using logical filtering, you're able to slice the DataFrame to focus only on entries that meet both specified criteria.\\nThis is a powerful feature of Pandas, allowing you to perform complex data queries efficiently.\"" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "# Do not know well how:\n", + "# Filter the DataFrame for rows where CGPA > 9 and Research = 1\n", + "filtered_df = admissions[(admissions['CGPA'] > 9) & (admissions['Research'] == 1)]\n", + "\n", + "# Get the number of rows in this filtered DataFrame\n", + "number_of_rows = len(filtered_df)\n", + "\n", + "# Output the result\n", + "print(f\"The number of rows where CGPA is higher than 9 and the student has conducted research is {number_of_rows}.\")\n", + "display(filtered_df)\n", + "\n", + "\"\"\"Explanation:\n", + "admissions[(condition1) & (condition2)]: The conditions are enclosed in parentheses and combined using & to create a composite criterion that both have to be met.\n", + "len(filtered_df): Counts the number of rows in the filtered DataFrame, which gives you the result you seek.\n", + "By using logical filtering, you're able to slice the DataFrame to focus only on entries that meet both specified criteria.\n", + "This is a powerful feature of Pandas, allowing you to perform complex data queries efficiently.\"\"\"\n" ] }, { @@ -186,11 +1279,220 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 36, "metadata": {}, - "outputs": [], + "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", + "
GRE ScoreCGPASerial No.TOEFL ScoreUniversity RatingSOPLORResearchChance of Admit
03379.65111844.54.510.92
43309.34511554.53.010.90
103289.101111244.04.510.78
193289.502011655.05.010.94
203349.702111955.04.510.95
..............................
3793299.2338011144.54.010.89
3803249.0438111033.53.510.82
3813259.1138210733.03.510.84
3823309.4538311645.04.510.91
3843339.6638511745.04.010.95
\n", + "

101 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " GRE Score CGPA Serial No. TOEFL Score University Rating SOP LOR \\\n", + "0 337 9.65 1 118 4 4.5 4.5 \n", + "4 330 9.34 5 115 5 4.5 3.0 \n", + "10 328 9.10 11 112 4 4.0 4.5 \n", + "19 328 9.50 20 116 5 5.0 5.0 \n", + "20 334 9.70 21 119 5 5.0 4.5 \n", + ".. ... ... ... ... ... ... ... \n", + "379 329 9.23 380 111 4 4.5 4.0 \n", + "380 324 9.04 381 110 3 3.5 3.5 \n", + "381 325 9.11 382 107 3 3.0 3.5 \n", + "382 330 9.45 383 116 4 5.0 4.5 \n", + "384 333 9.66 385 117 4 5.0 4.0 \n", + "\n", + " Research Chance of Admit \n", + "0 1 0.92 \n", + "4 1 0.90 \n", + "10 1 0.78 \n", + "19 1 0.94 \n", + "20 1 0.95 \n", + ".. ... ... \n", + "379 1 0.89 \n", + "380 1 0.82 \n", + "381 1 0.84 \n", + "382 1 0.91 \n", + "384 1 0.95 \n", + "\n", + "[101 rows x 9 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "# Filter the DataFrame for rows where CGPA > 9 and SOP<3.5\n", + "filtered_df2 = admissions[(admissions['CGPA'] > 9) & (admissions['SOP'] < 3.5)]\n", + "# Get the number of rows in this filtered DataFrame\n", + "number_of_rows = len(filtered_df)\n", + "display(filtered_df)" ] }, { @@ -208,7 +1510,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 37, "metadata": {}, "outputs": [], "source": [ @@ -219,7 +1521,14 @@ " and dividing by the column's standard deviation.\n", " \"\"\"\n", " \n", - " # Your code here:" + " # Your code here:\n", + " mean = np.mean(col)\n", + " std_dev = np.std(col)\n", + " standardized_column = (col - mean) / std_dev\n", + "\n", + " return standardized_column\n", + "\n", + "\n" ] }, { @@ -231,11 +1540,264 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 38, "metadata": {}, "outputs": [], "source": [ - "# Your code here:" + "# Your code here:\n", + "\n", + "admissions['CGPA_std'] = standardize(admissions['CGPA'])\n", + "admissions['GRE_std'] = standardize(admissions['GRE Score'])\n", + "admissions['LOR_std'] = standardize(admissions['LOR'])" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "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", + " \n", + " \n", + " \n", + " \n", + "
GRE ScoreCGPASerial No.TOEFL ScoreUniversity RatingSOPLORResearchChance of AdmitCGPA_stdGRE_stdLOR_std
03379.65111844.54.510.921.7501741.7556631.193197
13168.00210433.03.510.72-0.992501-0.0634500.076840
23228.67311033.52.510.800.1211910.456297-1.039517
33148.21410322.03.000.65-0.643433-0.236698-0.481338
43309.34511554.53.010.901.2348841.149292-0.481338
.......................................
3803249.0438111033.53.510.820.7362160.6295460.076840
3813259.1138210733.03.510.840.8525710.7161700.076840
3823309.4538311645.04.510.911.4177291.1492921.193197
3833128.7838410333.54.000.670.304036-0.4099470.635019
3843339.6638511745.04.010.951.7667961.4091650.635019
\n", + "

385 rows × 12 columns

\n", + "
" + ], + "text/plain": [ + " GRE Score CGPA Serial No. TOEFL Score University Rating SOP LOR \\\n", + "0 337 9.65 1 118 4 4.5 4.5 \n", + "1 316 8.00 2 104 3 3.0 3.5 \n", + "2 322 8.67 3 110 3 3.5 2.5 \n", + "3 314 8.21 4 103 2 2.0 3.0 \n", + "4 330 9.34 5 115 5 4.5 3.0 \n", + ".. ... ... ... ... ... ... ... \n", + "380 324 9.04 381 110 3 3.5 3.5 \n", + "381 325 9.11 382 107 3 3.0 3.5 \n", + "382 330 9.45 383 116 4 5.0 4.5 \n", + "383 312 8.78 384 103 3 3.5 4.0 \n", + "384 333 9.66 385 117 4 5.0 4.0 \n", + "\n", + " Research Chance of Admit CGPA_std GRE_std LOR_std \n", + "0 1 0.92 1.750174 1.755663 1.193197 \n", + "1 1 0.72 -0.992501 -0.063450 0.076840 \n", + "2 1 0.80 0.121191 0.456297 -1.039517 \n", + "3 0 0.65 -0.643433 -0.236698 -0.481338 \n", + "4 1 0.90 1.234884 1.149292 -0.481338 \n", + ".. ... ... ... ... ... \n", + "380 1 0.82 0.736216 0.629546 0.076840 \n", + "381 1 0.84 0.852571 0.716170 0.076840 \n", + "382 1 0.91 1.417729 1.149292 1.193197 \n", + "383 0 0.67 0.304036 -0.409947 0.635019 \n", + "384 1 0.95 1.766796 1.409165 0.635019 \n", + "\n", + "[385 rows x 12 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display(admissions)" ] }, { @@ -247,7 +1809,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 40, "metadata": {}, "outputs": [], "source": [ @@ -257,9 +1819,404 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 41, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "['CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std']" + ] + }, + "execution_count": 41, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# Run this code:\n", "\n", @@ -269,6 +2226,277 @@ "decision_choice" ] }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": {}, + "outputs": [], + "source": [ + "# Add the 'decision_choice' as a new column to the DataFrame for lookup purposes\n", + "admissions['decision_choice'] = decision_choice" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GRE ScoreCGPASerial No.TOEFL ScoreUniversity RatingSOPLORResearchChance of AdmitCGPA_stdGRE_stdLOR_stddecision_choice
03379.65111844.54.510.921.7501741.7556631.193197CGPA_std
13168.00210433.03.510.72-0.992501-0.0634500.076840CGPA_std
23228.67311033.52.510.800.1211910.456297-1.039517CGPA_std
33148.21410322.03.000.65-0.643433-0.236698-0.481338CGPA_std
43309.34511554.53.010.901.2348841.149292-0.481338LOR_std
..........................................
3803249.0438111033.53.510.820.7362160.6295460.076840GRE_std
3813259.1138210733.03.510.840.8525710.7161700.076840CGPA_std
3823309.4538311645.04.510.911.4177291.1492921.193197GRE_std
3833128.7838410333.54.000.670.304036-0.4099470.635019GRE_std
3843339.6638511745.04.010.951.7667961.4091650.635019GRE_std
\n", + "

385 rows × 13 columns

\n", + "
" + ], + "text/plain": [ + " GRE Score CGPA Serial No. TOEFL Score University Rating SOP LOR \\\n", + "0 337 9.65 1 118 4 4.5 4.5 \n", + "1 316 8.00 2 104 3 3.0 3.5 \n", + "2 322 8.67 3 110 3 3.5 2.5 \n", + "3 314 8.21 4 103 2 2.0 3.0 \n", + "4 330 9.34 5 115 5 4.5 3.0 \n", + ".. ... ... ... ... ... ... ... \n", + "380 324 9.04 381 110 3 3.5 3.5 \n", + "381 325 9.11 382 107 3 3.0 3.5 \n", + "382 330 9.45 383 116 4 5.0 4.5 \n", + "383 312 8.78 384 103 3 3.5 4.0 \n", + "384 333 9.66 385 117 4 5.0 4.0 \n", + "\n", + " Research Chance of Admit CGPA_std GRE_std LOR_std decision_choice \n", + "0 1 0.92 1.750174 1.755663 1.193197 CGPA_std \n", + "1 1 0.72 -0.992501 -0.063450 0.076840 CGPA_std \n", + "2 1 0.80 0.121191 0.456297 -1.039517 CGPA_std \n", + "3 0 0.65 -0.643433 -0.236698 -0.481338 CGPA_std \n", + "4 1 0.90 1.234884 1.149292 -0.481338 LOR_std \n", + ".. ... ... ... ... ... ... \n", + "380 1 0.82 0.736216 0.629546 0.076840 GRE_std \n", + "381 1 0.84 0.852571 0.716170 0.076840 CGPA_std \n", + "382 1 0.91 1.417729 1.149292 1.193197 GRE_std \n", + "383 0 0.67 0.304036 -0.409947 0.635019 GRE_std \n", + "384 1 0.95 1.766796 1.409165 0.635019 GRE_std \n", + "\n", + "[385 rows x 13 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display(admissions)\n" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -276,13 +2504,323 @@ "Now create the deciding column using the `lookup` function. The lookup column is `decision_choice` found above. Call the column resulting from the lookup function `deciding_column` and add it to the `admissions` dataframe." ] }, + { + "cell_type": "code", + "execution_count": 50, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GRE ScoreCGPASerial No.TOEFL ScoreUniversity RatingSOPLORResearchChance of AdmitCGPA_stdGRE_stdLOR_stddecision_choicedeciding_column
03379.65111844.54.510.921.7501741.7556631.193197CGPA_std1.750174
13168.00210433.03.510.72-0.992501-0.0634500.076840CGPA_std-0.992501
23228.67311033.52.510.800.1211910.456297-1.039517CGPA_std0.121191
33148.21410322.03.000.65-0.643433-0.236698-0.481338CGPA_std-0.643433
43309.34511554.53.010.901.2348841.149292-0.481338LOR_std-0.481338
.............................................
3803249.0438111033.53.510.820.7362160.6295460.076840GRE_std0.629546
3813259.1138210733.03.510.840.8525710.7161700.076840CGPA_std0.852571
3823309.4538311645.04.510.911.4177291.1492921.193197GRE_std1.149292
3833128.7838410333.54.000.670.304036-0.4099470.635019GRE_std-0.409947
3843339.6638511745.04.010.951.7667961.4091650.635019GRE_std1.409165
\n", + "

385 rows × 14 columns

\n", + "
" + ], + "text/plain": [ + " GRE Score CGPA Serial No. TOEFL Score University Rating SOP LOR \\\n", + "0 337 9.65 1 118 4 4.5 4.5 \n", + "1 316 8.00 2 104 3 3.0 3.5 \n", + "2 322 8.67 3 110 3 3.5 2.5 \n", + "3 314 8.21 4 103 2 2.0 3.0 \n", + "4 330 9.34 5 115 5 4.5 3.0 \n", + ".. ... ... ... ... ... ... ... \n", + "380 324 9.04 381 110 3 3.5 3.5 \n", + "381 325 9.11 382 107 3 3.0 3.5 \n", + "382 330 9.45 383 116 4 5.0 4.5 \n", + "383 312 8.78 384 103 3 3.5 4.0 \n", + "384 333 9.66 385 117 4 5.0 4.0 \n", + "\n", + " Research Chance of Admit CGPA_std GRE_std LOR_std decision_choice \\\n", + "0 1 0.92 1.750174 1.755663 1.193197 CGPA_std \n", + "1 1 0.72 -0.992501 -0.063450 0.076840 CGPA_std \n", + "2 1 0.80 0.121191 0.456297 -1.039517 CGPA_std \n", + "3 0 0.65 -0.643433 -0.236698 -0.481338 CGPA_std \n", + "4 1 0.90 1.234884 1.149292 -0.481338 LOR_std \n", + ".. ... ... ... ... ... ... \n", + "380 1 0.82 0.736216 0.629546 0.076840 GRE_std \n", + "381 1 0.84 0.852571 0.716170 0.076840 CGPA_std \n", + "382 1 0.91 1.417729 1.149292 1.193197 GRE_std \n", + "383 0 0.67 0.304036 -0.409947 0.635019 GRE_std \n", + "384 1 0.95 1.766796 1.409165 0.635019 GRE_std \n", + "\n", + " deciding_column \n", + "0 1.750174 \n", + "1 -0.992501 \n", + "2 0.121191 \n", + "3 -0.643433 \n", + "4 -0.481338 \n", + ".. ... \n", + "380 0.629546 \n", + "381 0.852571 \n", + "382 1.149292 \n", + "383 -0.409947 \n", + "384 1.409165 \n", + "\n", + "[385 rows x 14 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "admissions['deciding_column'] = admissions.apply(lambda row: row[row['decision_choice']], axis= 1)\n", + "display(admissions)" + ] + }, { "cell_type": "code", "execution_count": null, "metadata": {}, - "outputs": [], + "outputs": [ + { + "ename": "AttributeError", + "evalue": "'DataFrame' object has no attribute 'lookup'", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/var/folders/tx/45hhw1yn48jfdqn2hmnhbhvw0000gn/T/ipykernel_5452/2944434794.py\u001b[0m in \u001b[0;36m?\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# Use the 'lookup' function to create the 'deciding_column'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mdeciding_column\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0madmissions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlookup\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0madmissions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0madmissions\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'decision_choice'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;31m# Add the 'deciding_column' to the DataFrame\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0madmissions\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'deciding_column'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdeciding_column\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/opt/anaconda3/lib/python3.12/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36m?\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m 6295\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_accessors\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6296\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6297\u001b[0m \u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6298\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 6299\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[0;31mAttributeError\u001b[0m: 'DataFrame' object has no attribute 'lookup'" + ] + } + ], "source": [ - "# Your code here:" + "'''\n", + "Apparently lookup is deprecated!!\n", + "# Use the 'lookup' function to create the 'deciding_column' \n", + "deciding_column = admissions.lookup(admissions.index, admissions['decision_choice'])\n", + "\n", + "# Add the 'deciding_column' to the DataFrame\n", + "admissions['deciding_column'] = deciding_column\n", + "\n", + "# Output the first few rows to verify\n", + "admissions.head()\n", + "'''" ] }, { @@ -294,11 +2832,303 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 51, "metadata": {}, - "outputs": [], + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GRE ScoreCGPASerial No.TOEFL ScoreUniversity RatingSOPLORResearchChance of AdmitCGPA_stdGRE_stdLOR_stddecision_choicedeciding_columndecision
03379.65111844.54.510.921.7501741.7556631.193197CGPA_std1.7501741
13168.00210433.03.510.72-0.992501-0.0634500.076840CGPA_std-0.9925010
23228.67311033.52.510.800.1211910.456297-1.039517CGPA_std0.1211910
33148.21410322.03.000.65-0.643433-0.236698-0.481338CGPA_std-0.6434330
43309.34511554.53.010.901.2348841.149292-0.481338LOR_std-0.4813380
................................................
3803249.0438111033.53.510.820.7362160.6295460.076840GRE_std0.6295460
3813259.1138210733.03.510.840.8525710.7161700.076840CGPA_std0.8525711
3823309.4538311645.04.510.911.4177291.1492921.193197GRE_std1.1492921
3833128.7838410333.54.000.670.304036-0.4099470.635019GRE_std-0.4099470
3843339.6638511745.04.010.951.7667961.4091650.635019GRE_std1.4091651
\n", + "

385 rows × 15 columns

\n", + "
" + ], + "text/plain": [ + " GRE Score CGPA Serial No. TOEFL Score University Rating SOP LOR \\\n", + "0 337 9.65 1 118 4 4.5 4.5 \n", + "1 316 8.00 2 104 3 3.0 3.5 \n", + "2 322 8.67 3 110 3 3.5 2.5 \n", + "3 314 8.21 4 103 2 2.0 3.0 \n", + "4 330 9.34 5 115 5 4.5 3.0 \n", + ".. ... ... ... ... ... ... ... \n", + "380 324 9.04 381 110 3 3.5 3.5 \n", + "381 325 9.11 382 107 3 3.0 3.5 \n", + "382 330 9.45 383 116 4 5.0 4.5 \n", + "383 312 8.78 384 103 3 3.5 4.0 \n", + "384 333 9.66 385 117 4 5.0 4.0 \n", + "\n", + " Research Chance of Admit CGPA_std GRE_std LOR_std decision_choice \\\n", + "0 1 0.92 1.750174 1.755663 1.193197 CGPA_std \n", + "1 1 0.72 -0.992501 -0.063450 0.076840 CGPA_std \n", + "2 1 0.80 0.121191 0.456297 -1.039517 CGPA_std \n", + "3 0 0.65 -0.643433 -0.236698 -0.481338 CGPA_std \n", + "4 1 0.90 1.234884 1.149292 -0.481338 LOR_std \n", + ".. ... ... ... ... ... ... \n", + "380 1 0.82 0.736216 0.629546 0.076840 GRE_std \n", + "381 1 0.84 0.852571 0.716170 0.076840 CGPA_std \n", + "382 1 0.91 1.417729 1.149292 1.193197 GRE_std \n", + "383 0 0.67 0.304036 -0.409947 0.635019 GRE_std \n", + "384 1 0.95 1.766796 1.409165 0.635019 GRE_std \n", + "\n", + " deciding_column decision \n", + "0 1.750174 1 \n", + "1 -0.992501 0 \n", + "2 0.121191 0 \n", + "3 -0.643433 0 \n", + "4 -0.481338 0 \n", + ".. ... ... \n", + "380 0.629546 0 \n", + "381 0.852571 1 \n", + "382 1.149292 1 \n", + "383 -0.409947 0 \n", + "384 1.409165 1 \n", + "\n", + "[385 rows x 15 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "\n", + "admissions['decision'] = np.where(admissions['deciding_column'] > 0.8, 1, 0)\n", + "display(admissions)" ] }, { @@ -310,11 +3140,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 52, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Total number of students accepted: 86\n" + ] + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "\n", + "# Sum the total number of 1s in the 'decision' column\n", + "total_accepted = admissions['decision'].sum()\n", + "\n", + "# Print the result\n", + "print(f\"Total number of students accepted: {total_accepted}\")\n" ] }, { @@ -330,11 +3174,305 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 56, "metadata": {}, - "outputs": [], + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
gre_scorecgpaserial_no.toefl_scoreuniversity_ratingsoplorresearchchance_of_admitcgpa_stdgre_stdlor_stddecision_choicedeciding_columndecision
03379.65111844.54.510.921.7501741.7556631.193197CGPA_std1.7501741
13168.00210433.03.510.72-0.992501-0.0634500.076840CGPA_std-0.9925010
23228.67311033.52.510.800.1211910.456297-1.039517CGPA_std0.1211910
33148.21410322.03.000.65-0.643433-0.236698-0.481338CGPA_std-0.6434330
43309.34511554.53.010.901.2348841.149292-0.481338LOR_std-0.4813380
................................................
3803249.0438111033.53.510.820.7362160.6295460.076840GRE_std0.6295460
3813259.1138210733.03.510.840.8525710.7161700.076840CGPA_std0.8525711
3823309.4538311645.04.510.911.4177291.1492921.193197GRE_std1.1492921
3833128.7838410333.54.000.670.304036-0.4099470.635019GRE_std-0.4099470
3843339.6638511745.04.010.951.7667961.4091650.635019GRE_std1.4091651
\n", + "

385 rows × 15 columns

\n", + "
" + ], + "text/plain": [ + " gre_score cgpa serial_no. toefl_score university_rating sop lor \\\n", + "0 337 9.65 1 118 4 4.5 4.5 \n", + "1 316 8.00 2 104 3 3.0 3.5 \n", + "2 322 8.67 3 110 3 3.5 2.5 \n", + "3 314 8.21 4 103 2 2.0 3.0 \n", + "4 330 9.34 5 115 5 4.5 3.0 \n", + ".. ... ... ... ... ... ... ... \n", + "380 324 9.04 381 110 3 3.5 3.5 \n", + "381 325 9.11 382 107 3 3.0 3.5 \n", + "382 330 9.45 383 116 4 5.0 4.5 \n", + "383 312 8.78 384 103 3 3.5 4.0 \n", + "384 333 9.66 385 117 4 5.0 4.0 \n", + "\n", + " research chance_of_admit cgpa_std gre_std lor_std decision_choice \\\n", + "0 1 0.92 1.750174 1.755663 1.193197 CGPA_std \n", + "1 1 0.72 -0.992501 -0.063450 0.076840 CGPA_std \n", + "2 1 0.80 0.121191 0.456297 -1.039517 CGPA_std \n", + "3 0 0.65 -0.643433 -0.236698 -0.481338 CGPA_std \n", + "4 1 0.90 1.234884 1.149292 -0.481338 LOR_std \n", + ".. ... ... ... ... ... ... \n", + "380 1 0.82 0.736216 0.629546 0.076840 GRE_std \n", + "381 1 0.84 0.852571 0.716170 0.076840 CGPA_std \n", + "382 1 0.91 1.417729 1.149292 1.193197 GRE_std \n", + "383 0 0.67 0.304036 -0.409947 0.635019 GRE_std \n", + "384 1 0.95 1.766796 1.409165 0.635019 GRE_std \n", + "\n", + " deciding_column decision \n", + "0 1.750174 1 \n", + "1 -0.992501 0 \n", + "2 0.121191 0 \n", + "3 -0.643433 0 \n", + "4 -0.481338 0 \n", + ".. ... ... \n", + "380 0.629546 0 \n", + "381 0.852571 1 \n", + "382 1.149292 1 \n", + "383 -0.409947 0 \n", + "384 1.409165 1 \n", + "\n", + "[385 rows x 15 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "\n", + "admissions.columns = admissions.columns.str.strip().str.lower().str.replace(' ', '_')\n", + "admissions.columns\n", + "\n", + "display(admissions)\n" ] }, { @@ -346,17 +3484,203 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 57, "metadata": {}, - "outputs": [], + "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", + "
gre_scorecgpaserial_no.toefl_scoreuniversity_ratingsoplorresearchchance_of_admitcgpa_stdgre_stdlor_stddecision_choicedeciding_columndecisionadjusted_greadjusted_gre_bins
03379.65111844.54.510.921.7501741.7556631.193197CGPA_std1.7501741347Very High
13168.00210433.03.510.72-0.992501-0.0634500.076840CGPA_std-0.9925010316Average
23228.67311033.52.510.800.1211910.456297-1.039517CGPA_std0.1211910322High
33148.21410322.03.000.65-0.643433-0.236698-0.481338CGPA_std-0.6434330314Average
43309.34511554.53.010.901.2348841.149292-0.481338LOR_std-0.4813380340Very High
\n", + "
" + ], + "text/plain": [ + " gre_score cgpa serial_no. toefl_score university_rating sop lor \\\n", + "0 337 9.65 1 118 4 4.5 4.5 \n", + "1 316 8.00 2 104 3 3.0 3.5 \n", + "2 322 8.67 3 110 3 3.5 2.5 \n", + "3 314 8.21 4 103 2 2.0 3.0 \n", + "4 330 9.34 5 115 5 4.5 3.0 \n", + "\n", + " research chance_of_admit cgpa_std gre_std lor_std decision_choice \\\n", + "0 1 0.92 1.750174 1.755663 1.193197 CGPA_std \n", + "1 1 0.72 -0.992501 -0.063450 0.076840 CGPA_std \n", + "2 1 0.80 0.121191 0.456297 -1.039517 CGPA_std \n", + "3 0 0.65 -0.643433 -0.236698 -0.481338 CGPA_std \n", + "4 1 0.90 1.234884 1.149292 -0.481338 LOR_std \n", + "\n", + " deciding_column decision adjusted_gre adjusted_gre_bins \n", + "0 1.750174 1 347 Very High \n", + "1 -0.992501 0 316 Average \n", + "2 0.121191 0 322 High \n", + "3 -0.643433 0 314 Average \n", + "4 -0.481338 0 340 Very High " + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "# Step 1: Boost GRE scores for students with university rating of 4 or higher\n", + "admissions['adjusted_gre'] = admissions['gre_score']\n", + "\n", + "# Apply the 10-point boos\n", + "admissions.loc[admissions['university_rating'] >=4, 'adjusted_gre' ] += 10\n", + "\n", + "# Step 2: Create bins for the adjusted GRE scores\n", + "# Define the number of bins and labels. This creates four ranges of GRE scores.\n", + "bin_labels = ['Low', 'Average', 'High', 'Very High']\n", + "\n", + "# Use cut to create the bins. Change the bin edges as required for your data range.\n", + "admissions['adjusted_gre_bins'] = pd.cut(admissions['adjusted_gre'], bins=4, labels=bin_labels)\n", + "\n", + "display(admissions.head())" ] } ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "base", "language": "python", "name": "python3" }, @@ -370,7 +3694,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.4" + "version": "3.12.7" } }, "nbformat": 4,