{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "ffd6067e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[33mWARNING: You are using pip version 21.1.2; however, version 21.1.3 is available.\n", "You should consider upgrading via the '/home/ec2-user/anaconda3/envs/python3/bin/python -m pip install --upgrade pip' command.\u001b[0m\n" ] } ], "source": [ "!pip install varname --quiet" ] }, { "cell_type": "code", "execution_count": 2, "id": "7ee1750d", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "from varname import nameof" ] }, { "cell_type": "markdown", "id": "5fe951a6", "metadata": {}, "source": [ "## Download the original sample dataset" ] }, { "cell_type": "code", "execution_count": 3, "id": "7606296b", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "download: s3://sagemaker-sample-files/datasets/tabular/synthetic/churn.txt to ./churn.txt\n" ] } ], "source": [ "!aws s3 cp s3://sagemaker-sample-files/datasets/tabular/synthetic/churn.txt ./" ] }, { "cell_type": "code", "execution_count": 4, "id": "fa03f4fc", "metadata": {}, "outputs": [], "source": [ "churn = pd.read_csv(\"./churn.txt\")" ] }, { "cell_type": "code", "execution_count": 5, "id": "49fc099a", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | State | \n", "Account Length | \n", "Area Code | \n", "Phone | \n", "Int'l Plan | \n", "VMail Plan | \n", "VMail Message | \n", "Day Mins | \n", "Day Calls | \n", "Day Charge | \n", "... | \n", "Eve Calls | \n", "Eve Charge | \n", "Night Mins | \n", "Night Calls | \n", "Night Charge | \n", "Intl Mins | \n", "Intl Calls | \n", "Intl Charge | \n", "CustServ Calls | \n", "Churn? | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "PA | \n", "163 | \n", "806 | \n", "403-2562 | \n", "no | \n", "yes | \n", "300 | \n", "8.162204 | \n", "3 | \n", "7.579174 | \n", "... | \n", "4 | \n", "6.508639 | \n", "4.065759 | \n", "100 | \n", "5.111624 | \n", "4.928160 | \n", "6 | \n", "5.673203 | \n", "3 | \n", "True. | \n", "
1 | \n", "SC | \n", "15 | \n", "836 | \n", "158-8416 | \n", "yes | \n", "no | \n", "0 | \n", "10.018993 | \n", "4 | \n", "4.226289 | \n", "... | \n", "0 | \n", "9.972592 | \n", "7.141040 | \n", "200 | \n", "6.436188 | \n", "3.221748 | \n", "6 | \n", "2.559749 | \n", "8 | \n", "False. | \n", "
2 | \n", "MO | \n", "131 | \n", "777 | \n", "896-6253 | \n", "no | \n", "yes | \n", "300 | \n", "4.708490 | \n", "3 | \n", "4.768160 | \n", "... | \n", "3 | \n", "4.566715 | \n", "5.363235 | \n", "100 | \n", "5.142451 | \n", "7.139023 | \n", "2 | \n", "6.254157 | \n", "4 | \n", "False. | \n", "
3 | \n", "WY | \n", "75 | \n", "878 | \n", "817-5729 | \n", "yes | \n", "yes | \n", "700 | \n", "1.268734 | \n", "3 | \n", "2.567642 | \n", "... | \n", "5 | \n", "2.333624 | \n", "3.773586 | \n", "450 | \n", "3.814413 | \n", "2.245779 | \n", "6 | \n", "1.080692 | \n", "6 | \n", "False. | \n", "
4 | \n", "WY | \n", "146 | \n", "878 | \n", "450-4942 | \n", "yes | \n", "no | \n", "0 | \n", "2.696177 | \n", "3 | \n", "5.908916 | \n", "... | \n", "3 | \n", "3.670408 | \n", "3.751673 | \n", "250 | \n", "2.796812 | \n", "6.905545 | \n", "4 | \n", "7.134343 | \n", "6 | \n", "True. | \n", "
5 rows × 21 columns
\n", "