From 81d4bcbddf442d1d3669d301ed783a4f123451c2 Mon Sep 17 00:00:00 2001 From: martijnooo Date: Thu, 13 Feb 2025 15:51:08 +0100 Subject: [PATCH] Exercises solved --- your-code/main.ipynb | 3134 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 3080 insertions(+), 54 deletions(-) diff --git a/your-code/main.ipynb b/your-code/main.ipynb index 7687137..653ceea 100644 --- a/your-code/main.ipynb +++ b/your-code/main.ipynb @@ -16,7 +16,9 @@ "metadata": {}, "outputs": [], "source": [ - "# import numpy and pandas" + "# import numpy and pandas\n", + "import numpy as np\n", + "import pandas as pd" ] }, { @@ -38,7 +40,134 @@ "metadata": {}, "outputs": [], "source": [ - "admissions = pd.read_csv('data/Admission_Predict.csv')" + "admissions = pd.read_csv(r'G:\\My Drive\\Ironhack\\lab-advanced-topics-with-pandas\\data\\Admission_Predict.csv')" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "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", + "
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": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.head()" ] }, { @@ -50,9 +179,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "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": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "admissions.columns = [col.strip() for col in admissions.columns]\n", "admissions.columns\n", @@ -70,11 +212,130 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "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": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "admissions.head()" ] }, { @@ -86,11 +347,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "Serial No. 0\n", + "GRE Score 0\n", + "TOEFL Score 0\n", + "University Rating 0\n", + "SOP 0\n", + "LOR 0\n", + "CGPA 0\n", + "Research 0\n", + "Chance of Admit 0\n", + "dtype: int64" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "admissions.isnull().sum()" ] }, { @@ -102,11 +384,218 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 7, "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", + "
GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
Serial No.
133711844.54.59.6510.92
231610433.03.58.0010.72
332211033.52.58.6710.80
431410322.03.08.2100.65
533011554.53.09.3410.90
...........................
38132411033.53.59.0410.82
38232510733.03.59.1110.84
38333011645.04.59.4510.91
38431210333.54.08.7800.67
38533311745.04.09.6610.95
\n", + "

385 rows × 8 columns

\n", + "
" + ], + "text/plain": [ + " GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "Serial No. \n", + "1 337 118 4 4.5 4.5 9.65 \n", + "2 316 104 3 3.0 3.5 8.00 \n", + "3 322 110 3 3.5 2.5 8.67 \n", + "4 314 103 2 2.0 3.0 8.21 \n", + "5 330 115 5 4.5 3.0 9.34 \n", + "... ... ... ... ... ... ... \n", + "381 324 110 3 3.5 3.5 9.04 \n", + "382 325 107 3 3.0 3.5 9.11 \n", + "383 330 116 4 5.0 4.5 9.45 \n", + "384 312 103 3 3.5 4.0 8.78 \n", + "385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit \n", + "Serial No. \n", + "1 1 0.92 \n", + "2 1 0.72 \n", + "3 1 0.80 \n", + "4 0 0.65 \n", + "5 1 0.90 \n", + "... ... ... \n", + "381 1 0.82 \n", + "382 1 0.84 \n", + "383 1 0.91 \n", + "384 0 0.67 \n", + "385 1 0.95 \n", + "\n", + "[385 rows x 8 columns]" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "admissions.set_index(\"Serial No.\")" ] }, { @@ -118,13 +607,22 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": { - "scrolled": true - }, - "outputs": [], + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "admissions.duplicated(subset=[\"GRE Score\", \"CGPA\"]).sum()" ] }, { @@ -136,11 +634,227 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ - "# Your code here:" + "# Your code here:\n", + "admissions.set_index([\"GRE Score\", \"CGPA\"], inplace=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "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", + "
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
...........................
3249.0438111033.53.510.82
3259.1138210733.03.510.84
3309.4538311645.04.510.91
3128.7838410333.54.000.67
3339.6638511745.04.010.95
\n", + "

385 rows × 7 columns

\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", + "324 9.04 381 110 3 3.5 3.5 \n", + "325 9.11 382 107 3 3.0 3.5 \n", + "330 9.45 383 116 4 5.0 4.5 \n", + "312 8.78 384 103 3 3.5 4.0 \n", + "333 9.66 385 117 4 5.0 4.0 \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 \n", + "... ... ... \n", + "324 9.04 1 0.82 \n", + "325 9.11 1 0.84 \n", + "330 9.45 1 0.91 \n", + "312 8.78 0 0.67 \n", + "333 9.66 1 0.95 \n", + "\n", + "[385 rows x 7 columns]" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions" ] }, { @@ -152,11 +866,218 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "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
13168.00210433.03.510.72
23228.67311033.52.510.80
33148.21410322.03.000.65
43309.34511554.53.010.90
..............................
3803249.0438111033.53.510.82
3813259.1138210733.03.510.84
3823309.4538311645.04.510.91
3833128.7838410333.54.000.67
3843339.6638511745.04.010.95
\n", + "

385 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", + "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 \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]" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "admissions.reset_index(inplace=True)\n", + "admissions" ] }, { @@ -170,11 +1091,217 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "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]" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "admissions[(admissions[\"CGPA\"] > 9) & (admissions[\"Research\"] == 1)]" ] }, { @@ -186,11 +1313,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "0.8" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "admissions[(admissions[\"CGPA\"] > 9) & (admissions[\"SOP\"] < 3.5)][\"Chance of Admit\"].mean().round(2)" ] }, { @@ -208,7 +1347,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 14, "metadata": {}, "outputs": [], "source": [ @@ -218,8 +1357,10 @@ " and returns a standardized column by subtracting the column's mean\n", " and dividing by the column's standard deviation.\n", " \"\"\"\n", - " \n", - " # Your code here:" + " mean = col.mean()\n", + " stdev = col.std()\n", + " return (col - mean) / stdev\n", + "\n" ] }, { @@ -231,11 +1372,259 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "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", + "
GRE ScoreCGPASerial No.TOEFL ScoreUniversity RatingSOPLORResearchChance of AdmitCGPA_stdGRE_stdLOR_std
03379.65111844.54.510.921.7479001.7533811.191647
13168.00210433.03.510.72-0.991211-0.0633670.076740
23228.67311033.52.510.800.1210340.455704-1.038166
33148.21410322.03.000.65-0.642597-0.236391-0.480713
43309.34511554.53.010.901.2332791.147798-0.480713
.......................................
3803249.0438111033.53.510.820.7352590.6287270.076740
3813259.1138210733.03.510.840.8514630.7152390.076740
3823309.4538311645.04.510.911.4158861.1477981.191647
3833128.7838410333.54.000.670.303641-0.4094140.634193
3843339.6638511745.04.010.951.7645001.4073340.634193
\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 1.747900 1.753381 1.191647 \n", + "1 1 0.72 -0.991211 -0.063367 0.076740 \n", + "2 1 0.80 0.121034 0.455704 -1.038166 \n", + "3 0 0.65 -0.642597 -0.236391 -0.480713 \n", + "4 1 0.90 1.233279 1.147798 -0.480713 \n", + ".. ... ... ... ... ... \n", + "380 1 0.82 0.735259 0.628727 0.076740 \n", + "381 1 0.84 0.851463 0.715239 0.076740 \n", + "382 1 0.91 1.415886 1.147798 1.191647 \n", + "383 0 0.67 0.303641 -0.409414 0.634193 \n", + "384 1 0.95 1.764500 1.407334 0.634193 \n", + "\n", + "[385 rows x 12 columns]" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "tests = [\"CGPA\", \"GRE Score\", \"LOR\"]\n", + "\n", + "for test in tests:\n", + " admissions[f\"{test}_std\"] = standardize(admissions[test])\n", + "\n", + "admissions.rename(columns={\"GRE Score_std\": \"GRE_std\"}, inplace=True)\n", + "\n", + "admissions" ] }, { @@ -247,7 +1636,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 16, "metadata": {}, "outputs": [], "source": [ @@ -257,9 +1646,404 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "['LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_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", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_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", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_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", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_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", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_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", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_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", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_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", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_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", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_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", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_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", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'GRE_std',\n", + " 'LOR_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", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'LOR_std',\n", + " 'GRE_std',\n", + " 'CGPA_std',\n", + " 'GRE_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'LOR_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std',\n", + " 'CGPA_std']" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# Run this code:\n", "\n", @@ -278,11 +2062,291 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 18, "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", + "
GRE ScoreCGPASerial No.TOEFL ScoreUniversity RatingSOPLORResearchChance of AdmitCGPA_stdGRE_stdLOR_stddecision_choicedeciding_column
03379.65111844.54.510.921.7479001.7533811.191647LOR_std1.191647
13168.00210433.03.510.72-0.991211-0.0633670.076740LOR_std0.076740
23228.67311033.52.510.800.1210340.455704-1.038166GRE_std0.455704
33148.21410322.03.000.65-0.642597-0.236391-0.480713LOR_std-0.480713
43309.34511554.53.010.901.2332791.147798-0.480713LOR_std-0.480713
.............................................
3803249.0438111033.53.510.820.7352590.6287270.076740CGPA_std0.735259
3813259.1138210733.03.510.840.8514630.7152390.076740LOR_std0.076740
3823309.4538311645.04.510.911.4158861.1477981.191647CGPA_std1.415886
3833128.7838410333.54.000.670.303641-0.4094140.634193CGPA_std0.303641
3843339.6638511745.04.010.951.7645001.4073340.634193CGPA_std1.764500
\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 1.747900 1.753381 1.191647 LOR_std \n", + "1 1 0.72 -0.991211 -0.063367 0.076740 LOR_std \n", + "2 1 0.80 0.121034 0.455704 -1.038166 GRE_std \n", + "3 0 0.65 -0.642597 -0.236391 -0.480713 LOR_std \n", + "4 1 0.90 1.233279 1.147798 -0.480713 LOR_std \n", + ".. ... ... ... ... ... ... \n", + "380 1 0.82 0.735259 0.628727 0.076740 CGPA_std \n", + "381 1 0.84 0.851463 0.715239 0.076740 LOR_std \n", + "382 1 0.91 1.415886 1.147798 1.191647 CGPA_std \n", + "383 0 0.67 0.303641 -0.409414 0.634193 CGPA_std \n", + "384 1 0.95 1.764500 1.407334 0.634193 CGPA_std \n", + "\n", + " deciding_column \n", + "0 1.191647 \n", + "1 0.076740 \n", + "2 0.455704 \n", + "3 -0.480713 \n", + "4 -0.480713 \n", + ".. ... \n", + "380 0.735259 \n", + "381 0.076740 \n", + "382 1.415886 \n", + "383 0.303641 \n", + "384 1.764500 \n", + "\n", + "[385 rows x 14 columns]" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "admissions[\"decision_choice\"] = decision_choice\n", + "admissions[\"deciding_column\"] = admissions.apply(lambda row: row[row[\"decision_choice\"]], axis=1)\n", + "admissions" ] }, { @@ -294,11 +2358,303 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 19, "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
03379.65111844.54.510.921.7479001.7533811.191647LOR_std1.1916471
13168.00210433.03.510.72-0.991211-0.0633670.076740LOR_std0.0767400
23228.67311033.52.510.800.1210340.455704-1.038166GRE_std0.4557040
33148.21410322.03.000.65-0.642597-0.236391-0.480713LOR_std-0.4807130
43309.34511554.53.010.901.2332791.147798-0.480713LOR_std-0.4807130
................................................
3803249.0438111033.53.510.820.7352590.6287270.076740CGPA_std0.7352590
3813259.1138210733.03.510.840.8514630.7152390.076740LOR_std0.0767400
3823309.4538311645.04.510.911.4158861.1477981.191647CGPA_std1.4158861
3833128.7838410333.54.000.670.303641-0.4094140.634193CGPA_std0.3036410
3843339.6638511745.04.010.951.7645001.4073340.634193CGPA_std1.7645001
\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 1.747900 1.753381 1.191647 LOR_std \n", + "1 1 0.72 -0.991211 -0.063367 0.076740 LOR_std \n", + "2 1 0.80 0.121034 0.455704 -1.038166 GRE_std \n", + "3 0 0.65 -0.642597 -0.236391 -0.480713 LOR_std \n", + "4 1 0.90 1.233279 1.147798 -0.480713 LOR_std \n", + ".. ... ... ... ... ... ... \n", + "380 1 0.82 0.735259 0.628727 0.076740 CGPA_std \n", + "381 1 0.84 0.851463 0.715239 0.076740 LOR_std \n", + "382 1 0.91 1.415886 1.147798 1.191647 CGPA_std \n", + "383 0 0.67 0.303641 -0.409414 0.634193 CGPA_std \n", + "384 1 0.95 1.764500 1.407334 0.634193 CGPA_std \n", + "\n", + " deciding_column decision \n", + "0 1.191647 1 \n", + "1 0.076740 0 \n", + "2 0.455704 0 \n", + "3 -0.480713 0 \n", + "4 -0.480713 0 \n", + ".. ... ... \n", + "380 0.735259 0 \n", + "381 0.076740 0 \n", + "382 1.415886 1 \n", + "383 0.303641 0 \n", + "384 1.764500 1 \n", + "\n", + "[385 rows x 15 columns]" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "admissions[\"decision\"] = np.where(admissions[\"deciding_column\"]>0.8,1,0)\n", + "admissions" ] }, { @@ -310,11 +2666,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "85" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "admissions[\"decision\"].sum()" ] }, { @@ -330,11 +2698,315 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "metadata": {}, "outputs": [], "source": [ - "# Your code here:" + "# Your code here:\n", + "\n", + "# remove everything that is not a letter or number\n", + "# replace space with underscores\n", + "# change upper case to lower case\n", + "admissions.columns = admissions.columns.str.lower().str.replace(r'[^A-Za-z0-9 _ ]', '', regex=True).str.replace(\" \", \"_\")" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
gre_scorecgpaserial_notoefl_scoreuniversity_ratingsoplorresearchchance_of_admitcgpa_stdgre_stdlor_stddecision_choicedeciding_columndecision
03379.65111844.54.510.921.7479001.7533811.191647LOR_std1.1916471
13168.00210433.03.510.72-0.991211-0.0633670.076740LOR_std0.0767400
23228.67311033.52.510.800.1210340.455704-1.038166GRE_std0.4557040
33148.21410322.03.000.65-0.642597-0.236391-0.480713LOR_std-0.4807130
43309.34511554.53.010.901.2332791.147798-0.480713LOR_std-0.4807130
................................................
3803249.0438111033.53.510.820.7352590.6287270.076740CGPA_std0.7352590
3813259.1138210733.03.510.840.8514630.7152390.076740LOR_std0.0767400
3823309.4538311645.04.510.911.4158861.1477981.191647CGPA_std1.4158861
3833128.7838410333.54.000.670.303641-0.4094140.634193CGPA_std0.3036410
3843339.6638511745.04.010.951.7645001.4073340.634193CGPA_std1.7645001
\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 1.747900 1.753381 1.191647 LOR_std \n", + "1 1 0.72 -0.991211 -0.063367 0.076740 LOR_std \n", + "2 1 0.80 0.121034 0.455704 -1.038166 GRE_std \n", + "3 0 0.65 -0.642597 -0.236391 -0.480713 LOR_std \n", + "4 1 0.90 1.233279 1.147798 -0.480713 LOR_std \n", + ".. ... ... ... ... ... ... \n", + "380 1 0.82 0.735259 0.628727 0.076740 CGPA_std \n", + "381 1 0.84 0.851463 0.715239 0.076740 LOR_std \n", + "382 1 0.91 1.415886 1.147798 1.191647 CGPA_std \n", + "383 0 0.67 0.303641 -0.409414 0.634193 CGPA_std \n", + "384 1 0.95 1.764500 1.407334 0.634193 CGPA_std \n", + "\n", + " deciding_column decision \n", + "0 1.191647 1 \n", + "1 0.076740 0 \n", + "2 0.455704 0 \n", + "3 -0.480713 0 \n", + "4 -0.480713 0 \n", + ".. ... ... \n", + "380 0.735259 0 \n", + "381 0.076740 0 \n", + "382 1.415886 1 \n", + "383 0.303641 0 \n", + "384 1.764500 1 \n", + "\n", + "[385 rows x 15 columns]" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions" ] }, { @@ -346,17 +3018,371 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 23, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here:\n", + "admissions[\"gre_score\"] = np.where(admissions[\"gre_score\"]>4,admissions[\"gre_score\"]+10, admissions[\"gre_score\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 24, "metadata": {}, "outputs": [], "source": [ - "# Your code here:" + "adjusted_gre = pd.cut(admissions[\"gre_score\"], bins=4)" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 (337.5, 350.0]\n", + "1 (325.0, 337.5]\n", + "2 (325.0, 337.5]\n", + "3 (312.5, 325.0]\n", + "4 (337.5, 350.0]\n", + " ... \n", + "380 (325.0, 337.5]\n", + "381 (325.0, 337.5]\n", + "382 (337.5, 350.0]\n", + "383 (312.5, 325.0]\n", + "384 (337.5, 350.0]\n", + "Name: gre_score, Length: 385, dtype: category\n", + "Categories (4, interval[float64, right]): [(299.95, 312.5] < (312.5, 325.0] < (325.0, 337.5] < (337.5, 350.0]]" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "adjusted_gre" + ] + }, + { + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \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_notoefl_scoreuniversity_ratingsoplorresearchchance_of_admitcgpa_stdgre_stdlor_stddecision_choicedeciding_columndecisiongre_bins
03479.65111844.54.510.921.7479001.7533811.191647LOR_std1.1916471(337.5, 350.0]
13268.00210433.03.510.72-0.991211-0.0633670.076740LOR_std0.0767400(325.0, 337.5]
23328.67311033.52.510.800.1210340.455704-1.038166GRE_std0.4557040(325.0, 337.5]
33248.21410322.03.000.65-0.642597-0.236391-0.480713LOR_std-0.4807130(312.5, 325.0]
43409.34511554.53.010.901.2332791.147798-0.480713LOR_std-0.4807130(337.5, 350.0]
...................................................
3803349.0438111033.53.510.820.7352590.6287270.076740CGPA_std0.7352590(325.0, 337.5]
3813359.1138210733.03.510.840.8514630.7152390.076740LOR_std0.0767400(325.0, 337.5]
3823409.4538311645.04.510.911.4158861.1477981.191647CGPA_std1.4158861(337.5, 350.0]
3833228.7838410333.54.000.670.303641-0.4094140.634193CGPA_std0.3036410(312.5, 325.0]
3843439.6638511745.04.010.951.7645001.4073340.634193CGPA_std1.7645001(337.5, 350.0]
\n", + "

385 rows × 16 columns

\n", + "
" + ], + "text/plain": [ + " gre_score cgpa serial_no toefl_score university_rating sop lor \\\n", + "0 347 9.65 1 118 4 4.5 4.5 \n", + "1 326 8.00 2 104 3 3.0 3.5 \n", + "2 332 8.67 3 110 3 3.5 2.5 \n", + "3 324 8.21 4 103 2 2.0 3.0 \n", + "4 340 9.34 5 115 5 4.5 3.0 \n", + ".. ... ... ... ... ... ... ... \n", + "380 334 9.04 381 110 3 3.5 3.5 \n", + "381 335 9.11 382 107 3 3.0 3.5 \n", + "382 340 9.45 383 116 4 5.0 4.5 \n", + "383 322 8.78 384 103 3 3.5 4.0 \n", + "384 343 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 1.747900 1.753381 1.191647 LOR_std \n", + "1 1 0.72 -0.991211 -0.063367 0.076740 LOR_std \n", + "2 1 0.80 0.121034 0.455704 -1.038166 GRE_std \n", + "3 0 0.65 -0.642597 -0.236391 -0.480713 LOR_std \n", + "4 1 0.90 1.233279 1.147798 -0.480713 LOR_std \n", + ".. ... ... ... ... ... ... \n", + "380 1 0.82 0.735259 0.628727 0.076740 CGPA_std \n", + "381 1 0.84 0.851463 0.715239 0.076740 LOR_std \n", + "382 1 0.91 1.415886 1.147798 1.191647 CGPA_std \n", + "383 0 0.67 0.303641 -0.409414 0.634193 CGPA_std \n", + "384 1 0.95 1.764500 1.407334 0.634193 CGPA_std \n", + "\n", + " deciding_column decision gre_bins \n", + "0 1.191647 1 (337.5, 350.0] \n", + "1 0.076740 0 (325.0, 337.5] \n", + "2 0.455704 0 (325.0, 337.5] \n", + "3 -0.480713 0 (312.5, 325.0] \n", + "4 -0.480713 0 (337.5, 350.0] \n", + ".. ... ... ... \n", + "380 0.735259 0 (325.0, 337.5] \n", + "381 0.076740 0 (325.0, 337.5] \n", + "382 1.415886 1 (337.5, 350.0] \n", + "383 0.303641 0 (312.5, 325.0] \n", + "384 1.764500 1 (337.5, 350.0] \n", + "\n", + "[385 rows x 16 columns]" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions[\"gre_bins\"] = adjusted_gre\n", + "admissions" ] } ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "datasci_env", "language": "python", "name": "python3" }, @@ -370,7 +3396,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.4" + "version": "3.8.20" } }, "nbformat": 4,