{ "cells": [ { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "from datascience import *\n", "import numpy as np\n", "import pandas as pd\n", "import seaborn as sns\n", "sns.set_palette('husl')\n", "import matplotlib.pyplot as plt\n", "%matplotlib inline\n", "\n", "from sklearn import metrics\n", "from sklearn.neighbors import KNeighborsClassifier\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.model_selection import train_test_split\n", "path_data = 'http://www.millerjw.com/dom/mgmt462/pfiles/'\n", "crime = Table.read_table(path_data + 'crime.csv')\n", "# Make a copy of the usda data in pandas dataframe format \n", "crimep = crime.to_df()\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "You can get infromation from a Python dataframe using\n", "df.head(), df.describe(), and dr.info(). The crime data is in the data frame named crimep. (Use creimep instead of df).\n", "Code three statements in the boxes below to get infromation from the crimep dataframe" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 5, "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", "
IDBeatYearLatitudeLongitude
count1.916410e+05191641.000000191641.000000189365.000000189365.000000
mean4.968629e+061258.8107712006.13494041.844555-87.677782
std2.342997e+06702.5304653.5202850.0855830.057333
min1.310022e+06111.0000002001.00000041.644710-87.925510
25%2.832144e+06722.0000002003.00000041.771618-87.718474
50%4.762956e+061121.0000002006.00000041.850029-87.677597
75%7.201878e+061733.0000002009.00000041.917116-87.635513
max9.181151e+062535.0000002012.00000042.022878-87.524676
\n", "
" ], "text/plain": [ " ID Beat Year Latitude \\\n", "count 1.916410e+05 191641.000000 191641.000000 189365.000000 \n", "mean 4.968629e+06 1258.810771 2006.134940 41.844555 \n", "std 2.342997e+06 702.530465 3.520285 0.085583 \n", "min 1.310022e+06 111.000000 2001.000000 41.644710 \n", "25% 2.832144e+06 722.000000 2003.000000 41.771618 \n", "50% 4.762956e+06 1121.000000 2006.000000 41.850029 \n", "75% 7.201878e+06 1733.000000 2009.000000 41.917116 \n", "max 9.181151e+06 2535.000000 2012.000000 42.022878 \n", "\n", " Longitude \n", "count 189365.000000 \n", "mean -87.677782 \n", "std 0.057333 \n", "min -87.925510 \n", "25% -87.718474 \n", "50% -87.677597 \n", "75% -87.635513 \n", "max -87.524676 " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "crimep.describe()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Run the code below to see how many crimes had an arrest" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "15536\n", "176105\n", "191641\n" ] } ], "source": [ "x = crimep['Arrest'].value_counts()\n", "arrested = x[1]\n", "notarrested = x[0]\n", "totalrows = x[1] + x[0]\n", "print(arrested)\n", "print(notarrested)\n", "print(totalrows)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In the cell below, use the variables arrested and total rows to calculate the percentage of arrests. Remember to multiply by 100 to get a percentage." ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "8.106824740008662" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\n", "arrested/totalrows*100\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Run the cell below to create dataframe y that will contain crime counts by year." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "2001 20669\n", "2002 18753\n", "2004 16862\n", "2003 16657\n", "2005 16484\n", "2006 16098\n", "2011 15637\n", "2010 15497\n", "2008 14445\n", "2007 14280\n", "2012 14092\n", "2009 12167\n", "Name: Year, dtype: int64" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "y = (crimep['Year'].value_counts())\n", "display(y)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Use the cell below to run describe on dataframe y. Just like you ran describe on dataframe crimep earlier." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Run the cell below and look at the output. The statement that you will run does the same thing as an Excel Pivot Table using LocationDescription and Arrest in Rows and the count of any column in the values box." ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "LocationDescription Arrest\n", "ABANDONED BUILDING False 4\n", "AIRPORT BUILDING NON-TERMINAL - NON-SECURE AREA False 4\n", "AIRPORT BUILDING NON-TERMINAL - SECURE AREA False 1\n", "AIRPORT EXTERIOR - NON-SECURE AREA False 18\n", " True 6\n", "AIRPORT EXTERIOR - SECURE AREA False 1\n", "AIRPORT PARKING LOT False 8\n", " True 3\n", "AIRPORT TERMINAL UPPER LEVEL - NON-SECURE AREA False 5\n", "AIRPORT VENDING ESTABLISHMENT False 4\n", " True 6\n", "AIRPORT/AIRCRAFT False 267\n", " True 96\n", "ALLEY False 2059\n", " True 249\n", "ANIMAL HOSPITAL False 1\n", "APARTMENT False 157\n", " True 27\n", "APPLIANCE STORE False 1\n", "ATHLETIC CLUB False 6\n", " True 3\n", "BANK False 6\n", " True 1\n", "BAR OR TAVERN False 15\n", " True 2\n", "BARBERSHOP False 4\n", "BOWLING ALLEY False 2\n", " True 1\n", "BRIDGE False 2\n", "CAR WASH False 37\n", " ... \n", "RESTAURANT True 5\n", "SAVINGS AND LOAN False 4\n", "SCHOOL, PRIVATE, BUILDING False 12\n", " True 2\n", "SCHOOL, PRIVATE, GROUNDS False 20\n", " True 3\n", "SCHOOL, PUBLIC, BUILDING False 92\n", " True 22\n", "SCHOOL, PUBLIC, GROUNDS False 168\n", " True 38\n", "SIDEWALK False 419\n", " True 43\n", "SMALL RETAIL STORE False 26\n", " True 7\n", "SPORTS ARENA/STADIUM False 161\n", " True 5\n", "STREET False 144969\n", " True 11595\n", "TAVERN/LIQUOR STORE False 12\n", " True 2\n", "TAXICAB False 18\n", " True 3\n", "VACANT LOT/LAND False 918\n", " True 67\n", "VEHICLE NON-COMMERCIAL False 758\n", " True 59\n", "VEHICLE-COMMERCIAL False 22\n", " True 1\n", "WAREHOUSE False 16\n", " True 1\n", "Name: Arrest, Length: 134, dtype: int64" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "crimep.groupby(['LocationDescription','Arrest'])['Arrest'].count()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }