From 93b7ec60d2dfbf3755131af7801c26c8e9940670 Mon Sep 17 00:00:00 2001 From: shraddha-19 <70126672+shraddha-19@users.noreply.github.com> Date: Sun, 6 Sep 2020 12:44:55 +0530 Subject: [PATCH] Add files via upload Assignment 2 By Shraddha --- Assignment2DS.ipynb | 1150 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1150 insertions(+) create mode 100644 Assignment2DS.ipynb diff --git a/Assignment2DS.ipynb b/Assignment2DS.ipynb new file mode 100644 index 0000000..2d252bb --- /dev/null +++ b/Assignment2DS.ipynb @@ -0,0 +1,1150 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Assignment 2" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 1.import the dataset into a dataframe" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "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", + "
EmployeeNameJobTitleBasePayOvertimePayOtherPayBenefitsTotalPayTotalPayBenefitsYearNotesAgencyStatus
Id
1NATHANIEL FORDGENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY167411.180.00400184.25NaN567595.43567595.432011NaNSan FranciscoNaN
2GARY JIMENEZCAPTAIN III (POLICE DEPARTMENT)155966.02245131.88137811.38NaN538909.28538909.282011NaNSan FranciscoNaN
3ALBERT PARDINICAPTAIN III (POLICE DEPARTMENT)212739.13106088.1816452.60NaN335279.91335279.912011NaNSan FranciscoNaN
4CHRISTOPHER CHONGWIRE ROPE CABLE MAINTENANCE MECHANIC77916.0056120.71198306.90NaN332343.61332343.612011NaNSan FranciscoNaN
5PATRICK GARDNERDEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)134401.609737.00182234.59NaN326373.19326373.192011NaNSan FranciscoNaN
\n", + "
" + ], + "text/plain": [ + " EmployeeName JobTitle \\\n", + "Id \n", + "1 NATHANIEL FORD GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY \n", + "2 GARY JIMENEZ CAPTAIN III (POLICE DEPARTMENT) \n", + "3 ALBERT PARDINI CAPTAIN III (POLICE DEPARTMENT) \n", + "4 CHRISTOPHER CHONG WIRE ROPE CABLE MAINTENANCE MECHANIC \n", + "5 PATRICK GARDNER DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT) \n", + "\n", + " BasePay OvertimePay OtherPay Benefits TotalPay TotalPayBenefits \\\n", + "Id \n", + "1 167411.18 0.00 400184.25 NaN 567595.43 567595.43 \n", + "2 155966.02 245131.88 137811.38 NaN 538909.28 538909.28 \n", + "3 212739.13 106088.18 16452.60 NaN 335279.91 335279.91 \n", + "4 77916.00 56120.71 198306.90 NaN 332343.61 332343.61 \n", + "5 134401.60 9737.00 182234.59 NaN 326373.19 326373.19 \n", + "\n", + " Year Notes Agency Status \n", + "Id \n", + "1 2011 NaN San Francisco NaN \n", + "2 2011 NaN San Francisco NaN \n", + "3 2011 NaN San Francisco NaN \n", + "4 2011 NaN San Francisco NaN \n", + "5 2011 NaN San Francisco NaN " + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = pd.read_csv('Salaries.csv',index_col = 'Id')\n", + "df.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 2.display the column names" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['EmployeeName', 'JobTitle', 'BasePay', 'OvertimePay', 'OtherPay',\n", + " 'Benefits', 'TotalPay', 'TotalPayBenefits', 'Year', 'Notes', 'Agency',\n", + " 'Status'],\n", + " dtype='object')" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.columns" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 3.display the number of rows and cols" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(148654, 12)" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.shape" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 4.display the dataframe info (types of data in columns and not null values etc.)" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "Int64Index: 148654 entries, 1 to 148654\n", + "Data columns (total 12 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 EmployeeName 148654 non-null object \n", + " 1 JobTitle 148654 non-null object \n", + " 2 BasePay 148045 non-null float64\n", + " 3 OvertimePay 148650 non-null float64\n", + " 4 OtherPay 148650 non-null float64\n", + " 5 Benefits 112491 non-null float64\n", + " 6 TotalPay 148654 non-null float64\n", + " 7 TotalPayBenefits 148654 non-null float64\n", + " 8 Year 148654 non-null int64 \n", + " 9 Notes 0 non-null float64\n", + " 10 Agency 148654 non-null object \n", + " 11 Status 0 non-null float64\n", + "dtypes: float64(8), int64(1), object(3)\n", + "memory usage: 14.7+ MB\n" + ] + } + ], + "source": [ + "df.info()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 5.display stats of the dataframe like count, mean, std, max, 25% etc.." + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "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", + "
BasePayOvertimePayOtherPayBenefitsTotalPayTotalPayBenefitsYearNotesStatus
count148045.000000148650.000000148650.000000112491.000000148654.000000148654.000000148654.0000000.00.0
mean66325.4488415066.0598863648.76729725007.89315174768.32197293692.5548112012.522643NaNNaN
std42764.63549511454.3805598056.60186615402.21585850517.00527462793.5334831.117538NaNNaN
min-166.010000-0.010000-7058.590000-33.890000-618.130000-618.1300002011.000000NaNNaN
25%33588.2000000.0000000.00000011535.39500036168.99500044065.6500002012.000000NaNNaN
50%65007.4500000.000000811.27000028628.62000071426.61000092404.0900002013.000000NaNNaN
75%94691.0500004658.1750004236.06500035566.855000105839.135000132876.4500002014.000000NaNNaN
max319275.010000245131.880000400184.25000096570.660000567595.430000567595.4300002014.000000NaNNaN
\n", + "
" + ], + "text/plain": [ + " BasePay OvertimePay OtherPay Benefits \\\n", + "count 148045.000000 148650.000000 148650.000000 112491.000000 \n", + "mean 66325.448841 5066.059886 3648.767297 25007.893151 \n", + "std 42764.635495 11454.380559 8056.601866 15402.215858 \n", + "min -166.010000 -0.010000 -7058.590000 -33.890000 \n", + "25% 33588.200000 0.000000 0.000000 11535.395000 \n", + "50% 65007.450000 0.000000 811.270000 28628.620000 \n", + "75% 94691.050000 4658.175000 4236.065000 35566.855000 \n", + "max 319275.010000 245131.880000 400184.250000 96570.660000 \n", + "\n", + " TotalPay TotalPayBenefits Year Notes Status \n", + "count 148654.000000 148654.000000 148654.000000 0.0 0.0 \n", + "mean 74768.321972 93692.554811 2012.522643 NaN NaN \n", + "std 50517.005274 62793.533483 1.117538 NaN NaN \n", + "min -618.130000 -618.130000 2011.000000 NaN NaN \n", + "25% 36168.995000 44065.650000 2012.000000 NaN NaN \n", + "50% 71426.610000 92404.090000 2013.000000 NaN NaN \n", + "75% 105839.135000 132876.450000 2014.000000 NaN NaN \n", + "max 567595.430000 567595.430000 2014.000000 NaN NaN " + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.describe()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 6. display null values per column" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "EmployeeName 0\n", + "JobTitle 0\n", + "BasePay 609\n", + "OvertimePay 4\n", + "OtherPay 4\n", + "Benefits 36163\n", + "TotalPay 0\n", + "TotalPayBenefits 0\n", + "Year 0\n", + "Notes 148654\n", + "Agency 0\n", + "Status 148654\n", + "dtype: int64" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df1 = df.isnull().sum()\n", + "df1" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 7. remove columns will all values as NaN" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "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", + "
EmployeeNameJobTitleBasePayOvertimePayOtherPayBenefitsTotalPayTotalPayBenefitsYearAgency
Id
1NATHANIEL FORDGENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY167411.180.00400184.25NaN567595.43567595.432011San Francisco
2GARY JIMENEZCAPTAIN III (POLICE DEPARTMENT)155966.02245131.88137811.38NaN538909.28538909.282011San Francisco
3ALBERT PARDINICAPTAIN III (POLICE DEPARTMENT)212739.13106088.1816452.60NaN335279.91335279.912011San Francisco
4CHRISTOPHER CHONGWIRE ROPE CABLE MAINTENANCE MECHANIC77916.0056120.71198306.90NaN332343.61332343.612011San Francisco
5PATRICK GARDNERDEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)134401.609737.00182234.59NaN326373.19326373.192011San Francisco
.................................
148650Roy I TilleryCustodian0.000.000.000.00.000.002014San Francisco
148651Not providedNot providedNaNNaNNaNNaN0.000.002014San Francisco
148652Not providedNot providedNaNNaNNaNNaN0.000.002014San Francisco
148653Not providedNot providedNaNNaNNaNNaN0.000.002014San Francisco
148654Joe LopezCounselor, Log Cabin Ranch0.000.00-618.130.0-618.13-618.132014San Francisco
\n", + "

148654 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " EmployeeName JobTitle \\\n", + "Id \n", + "1 NATHANIEL FORD GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY \n", + "2 GARY JIMENEZ CAPTAIN III (POLICE DEPARTMENT) \n", + "3 ALBERT PARDINI CAPTAIN III (POLICE DEPARTMENT) \n", + "4 CHRISTOPHER CHONG WIRE ROPE CABLE MAINTENANCE MECHANIC \n", + "5 PATRICK GARDNER DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT) \n", + "... ... ... \n", + "148650 Roy I Tillery Custodian \n", + "148651 Not provided Not provided \n", + "148652 Not provided Not provided \n", + "148653 Not provided Not provided \n", + "148654 Joe Lopez Counselor, Log Cabin Ranch \n", + "\n", + " BasePay OvertimePay OtherPay Benefits TotalPay \\\n", + "Id \n", + "1 167411.18 0.00 400184.25 NaN 567595.43 \n", + "2 155966.02 245131.88 137811.38 NaN 538909.28 \n", + "3 212739.13 106088.18 16452.60 NaN 335279.91 \n", + "4 77916.00 56120.71 198306.90 NaN 332343.61 \n", + "5 134401.60 9737.00 182234.59 NaN 326373.19 \n", + "... ... ... ... ... ... \n", + "148650 0.00 0.00 0.00 0.0 0.00 \n", + "148651 NaN NaN NaN NaN 0.00 \n", + "148652 NaN NaN NaN NaN 0.00 \n", + "148653 NaN NaN NaN NaN 0.00 \n", + "148654 0.00 0.00 -618.13 0.0 -618.13 \n", + "\n", + " TotalPayBenefits Year Agency \n", + "Id \n", + "1 567595.43 2011 San Francisco \n", + "2 538909.28 2011 San Francisco \n", + "3 335279.91 2011 San Francisco \n", + "4 332343.61 2011 San Francisco \n", + "5 326373.19 2011 San Francisco \n", + "... ... ... ... \n", + "148650 0.00 2014 San Francisco \n", + "148651 0.00 2014 San Francisco \n", + "148652 0.00 2014 San Francisco \n", + "148653 0.00 2014 San Francisco \n", + "148654 -618.13 2014 San Francisco \n", + "\n", + "[148654 rows x 10 columns]" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df=df.dropna(axis=1,how='all')\n", + "df" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 8.display number of unique values in each column " + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "EmployeeName 110811\n", + "JobTitle 2159\n", + "BasePay 109489\n", + "OvertimePay 65998\n", + "OtherPay 83225\n", + "Benefits 98465\n", + "TotalPay 138486\n", + "TotalPayBenefits 142098\n", + "Year 4\n", + "Agency 1\n" + ] + } + ], + "source": [ + "for col in df.columns:\n", + " print(col,df[col].nunique())" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 9.mean of total pay of all people based on year" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Year\n", + "2011 71744.103871\n", + "2012 74113.262265\n", + "2013 77611.443142\n", + "2014 75463.918140\n", + "Name: TotalPay, dtype: float64" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.groupby('Year')['TotalPay'].mean()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 10. how many people have 0 overtime pay" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "77321" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(df[df['OvertimePay']==0]['OvertimePay'])" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 11. max, min, mean, median and other stats of TotalPay of people having 0 OvertimePay\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "count 77321.000000\n", + "mean 60229.348901\n", + "std 49307.912350\n", + "min -618.130000\n", + "25% 13290.450000\n", + "50% 58158.590000\n", + "75% 91115.090000\n", + "max 567595.430000\n", + "Name: TotalPay, dtype: float64" + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[df['OvertimePay']==0]['TotalPay'].describe()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 12.find Id of that person with max TotalPay you got in previous question" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Int64Index([1], dtype='int64', name='Id')" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[df['TotalPay']==567595.430000].index" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 13.name of employee with total pay benefits = 87619.78" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "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", + "
EmployeeNameJobTitleBasePayOvertimePayOtherPayBenefitsTotalPayTotalPayBenefitsYearNotesAgencyStatus
Id
12346REBECCA CHIUPRINCIPAL ACCOUNTANT87619.780.00.0NaN87619.7887619.782011NaNSan FranciscoNaN
\n", + "
" + ], + "text/plain": [ + " EmployeeName JobTitle BasePay OvertimePay OtherPay \\\n", + "Id \n", + "12346 REBECCA CHIU PRINCIPAL ACCOUNTANT 87619.78 0.0 0.0 \n", + "\n", + " Benefits TotalPay TotalPayBenefits Year Notes Agency \\\n", + "Id \n", + "12346 NaN 87619.78 87619.78 2011 NaN San Francisco \n", + "\n", + " Status \n", + "Id \n", + "12346 NaN " + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.loc[df['TotalPayBenefits']==87619.78]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 14.how many people have BasePay > 150000 and OvertimePay > 100000" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "12" + ] + }, + "execution_count": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(df[(df['BasePay']>150000) & (df['OvertimePay']>100000)])" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 14.which job title generally has highest average TotalPayBenefits\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Id\n", + "1 GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY\n", + "Name: JobTitle, dtype: object" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[df['TotalPay']==max(df['TotalPay'])]['JobTitle']" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 15.How many employees are POLICE" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "2512" + ] + }, + "execution_count": 43, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(df[df['JobTitle'].str.contains('POLICE')])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +}