SF Salaries Exercise

We will be using the SF Salaries Dataset from Kaggle!

Import pandas as pd.

In [2]:
import pandas as pd

Read Salaries.csv as a dataframe called sal.

In [3]:
sal = pd.read_csv('Salaries.csv')

Check the head of the DataFrame.

In [4]:
sal.head()
Out[4]:
Id EmployeeName JobTitle BasePay OvertimePay OtherPay Benefits TotalPay TotalPayBenefits Year Notes Agency Status
0 1 NATHANIEL FORD GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY 167411.18 0.00 400184.25 NaN 567595.43 567595.43 2011 NaN San Francisco NaN
1 2 GARY JIMENEZ CAPTAIN III (POLICE DEPARTMENT) 155966.02 245131.88 137811.38 NaN 538909.28 538909.28 2011 NaN San Francisco NaN
2 3 ALBERT PARDINI CAPTAIN III (POLICE DEPARTMENT) 212739.13 106088.18 16452.60 NaN 335279.91 335279.91 2011 NaN San Francisco NaN
3 4 CHRISTOPHER CHONG WIRE ROPE CABLE MAINTENANCE MECHANIC 77916.00 56120.71 198306.90 NaN 332343.61 332343.61 2011 NaN San Francisco NaN
4 5 PATRICK GARDNER DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT) 134401.60 9737.00 182234.59 NaN 326373.19 326373.19 2011 NaN San Francisco NaN

Use the .info() method to find out how many entries there are.

In [5]:
sal.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 148654 entries, 0 to 148653
Data columns (total 13 columns):
Id                  148654 non-null int64
EmployeeName        148654 non-null object
JobTitle            148654 non-null object
BasePay             148045 non-null float64
OvertimePay         148650 non-null float64
OtherPay            148650 non-null float64
Benefits            112491 non-null float64
TotalPay            148654 non-null float64
TotalPayBenefits    148654 non-null float64
Year                148654 non-null int64
Notes               0 non-null float64
Agency              148654 non-null object
Status              0 non-null float64
dtypes: float64(8), int64(2), object(3)
memory usage: 14.7+ MB

What is the average BasePay ?

In [6]:
sal['BasePay'].mean()
Out[6]:
66325.44884050643

What is the highest amount of OvertimePay in the dataset ?

In [7]:
sal['OvertimePay'].max()
Out[7]:
245131.88

What is the job title of JOSEPH DRISCOLL ? Note: Use all caps, (there is also a lowercase Joseph Driscoll).

In [8]:
joseph_driscoll = sal[sal['EmployeeName'] == 'JOSEPH DRISCOLL']
joseph_driscoll['JobTitle']
Out[8]:
24    CAPTAIN, FIRE SUPPRESSION
Name: JobTitle, dtype: object

How much does JOSEPH DRISCOLL make (including benefits)?

In [9]:
joseph_driscoll['TotalPayBenefits']
Out[9]:
24    270324.91
Name: TotalPayBenefits, dtype: float64

What is the name of highest paid person (including benefits)?

In [10]:
# highest_paid = sal[sal['EmployeeName'] & sal['TotalPayBenefits'].max()]
highest_paid = sal.loc[sal['TotalPayBenefits'].idxmax()]
highest_paid['EmployeeName']
Out[10]:
'NATHANIEL FORD'

What is the name of lowest paid person (including benefits)? Do you notice something strange about how much he or she is paid?

In [11]:
lowest_paid = sal.loc[sal['TotalPayBenefits'].idxmin()]

lowest_paid
Out[11]:
Id                                      148654
EmployeeName                         Joe Lopez
JobTitle            Counselor, Log Cabin Ranch
BasePay                                      0
OvertimePay                                  0
OtherPay                               -618.13
Benefits                                     0
TotalPay                               -618.13
TotalPayBenefits                       -618.13
Year                                      2014
Notes                                      NaN
Agency                           San Francisco
Status                                     NaN
Name: 148653, dtype: object

What was the average (mean) BasePay of all employees per year? (2011-2014) ?

In [12]:
sal.groupby('Year').mean()['BasePay']
Out[12]:
Year
2011    63595.956517
2012    65436.406857
2013    69630.030216
2014    66564.421924
Name: BasePay, dtype: float64

How many unique job titles are there?

In [13]:
sal['JobTitle'].nunique()
Out[13]:
2159

What are the top 5 most common jobs?

In [14]:
sal['JobTitle'].value_counts().head(5)
Out[14]:
Transit Operator                7036
Special Nurse                   4389
Registered Nurse                3736
Public Svc Aide-Public Works    2518
Police Officer 3                2421
Name: JobTitle, dtype: int64

How many Job Titles were represented by only one person in 2013? (e.g. Job Titles with only one occurence in 2013?)

In [21]:
sum(sal[sal['Year']==2013]['JobTitle'].value_counts()==1)
Out[21]:
202

How many people have the word Chief in their job title? (This is pretty tricky)

In [22]:
def chief_string(title):
    if 'chief' in title.lower().split():
        return True
    else:
        return False
In [25]:
sum(sal['JobTitle'].apply(lambda x:chief_string(x)))
Out[25]:
477

Bonus: Is there a correlation between length of the Job Title string and Salary?

In [32]:
# create new title
sal['title_len'] = sal['JobTitle'].apply(len)
In [34]:
sal[['TotalPayBenefits', 'title_len']].corr()
Out[34]:
TotalPayBenefits title_len
TotalPayBenefits 1.000000 -0.036878
title_len -0.036878 1.000000

Great Job!