import pandas as pd

# Read 'police.csv' into a DataFrame named ri
ri = pd.read_csv('./dataset/police.csv')

Do the genders commit different violations?

Examining traffic violations 

print(ri['violation'].value_counts())

# Express the counts as proportions
print(ri['violation'].value_counts(normalize=True))

Speeding               48424
Moving violation       16224
Equipment              10922
Other                   4410
Registration/plates     3703
Seat belt               2856
Name: violation, dtype: int64
Speeding               0.559563
Moving violation       0.187476
Equipment              0.126209
Other                  0.050960
Registration/plates    0.042790
Seat belt              0.033002
Name: violation, dtype: float64

Comparing violations by gender 

female = ri[ri['driver_gender'] == 'F']

# Create a DataFrame of male drivers
male = ri[ri['driver_gender'] == 'M']

# Compute the violations by female drivers (as proportions)
print(female['violation'].value_counts(normalize=True))

# Compute the violations by male drivers (as proportions)
print(male['violation'].value_counts(normalize=True))

Speeding               0.658114
Moving violation       0.138218
Equipment              0.105199
Registration/plates    0.044418
Other                  0.029738
Seat belt              0.024312
Name: violation, dtype: float64
Speeding               0.522243
Moving violation       0.206144
Equipment              0.134158
Other                  0.058985
Registration/plates    0.042175
Seat belt              0.036296
Name: violation, dtype: float64

Does gender affect who gets a ticket for speeding?

Comparing speeding outcomes by gender 

female_and_speeding = ri[(ri['driver_gender'] == 'F') & (ri['violation'] == 'Speeding')]

# Create a DataFrame of male drivers stopped for speeding
male_and_speeding = ri[(ri['driver_gender'] == 'M') & (ri['violation'] == 'Speeding')]

# Compute the stop outcomes for female drivers (as proportions)
print(female_and_speeding.stop_outcome.value_counts(normalize=True))

# Compute the stop outcomes for male drivers (as proportions)
print(male_and_speeding.stop_outcome.value_counts(normalize=True))

Citation            0.952192
Warning             0.040074
Arrest Driver       0.005752
N/D                 0.000959
Arrest Passenger    0.000639
No Action           0.000383
Name: stop_outcome, dtype: float64
Citation            0.944595
Warning             0.036184
Arrest Driver       0.015895
Arrest Passenger    0.001281
No Action           0.001068
N/D                 0.000976
Name: stop_outcome, dtype: float64

Does gender affect whose vehicle is searched?

Calculating the search rate 

print(ri['search_conducted'].dtypes)

# Calculate the search rate by counting the values
print(ri['search_conducted'].value_counts(normalize=True))

# Calculate the search rate by taking the mean
print(ri['search_conducted'].mean())

bool
False    0.963953
True     0.036047
Name: search_conducted, dtype: float64
0.03604713268876511

Comparing search rates by gender 

print(ri[ri['driver_gender'] == 'F'].search_conducted.mean())

# Calculating the search rate for male drivers
print(ri[ri['driver_gender'] == 'M'].search_conducted.mean())

# Calculate the search rate for both groups simultaneously
print(ri.groupby('driver_gender').search_conducted.mean())

0.019180617481282074
0.04542557598546892
driver_gender
F    0.019181
M    0.045426
Name: search_conducted, dtype: float64

Adding a second factor to the analysis 

print(ri.groupby(['driver_gender', 'violation']).search_conducted.mean())

# Reverse the ordering to group by violation before gender
print(ri.groupby(['violation', 'driver_gender']).search_conducted.mean())

driver_gender  violation          
F              Equipment              0.039984
               Moving violation       0.039257
               Other                  0.041018
               Registration/plates    0.054924
               Seat belt              0.017301
               Speeding               0.008309
M              Equipment              0.071496
               Moving violation       0.061524
               Other                  0.046191
               Registration/plates    0.108802
               Seat belt              0.035119
               Speeding               0.027885
Name: search_conducted, dtype: float64
violation            driver_gender
Equipment            F                0.039984
                     M                0.071496
Moving violation     F                0.039257
                     M                0.061524
Other                F                0.041018
                     M                0.046191
Registration/plates  F                0.054924
                     M                0.108802
Seat belt            F                0.017301
                     M                0.035119
Speeding             F                0.008309
                     M                0.027885
Name: search_conducted, dtype: float64

Does gender affect who is frisked during a search?

Counting protective frisks

During a vehicle search, the police officer may pat down the driver to check if they have a weapon. This is known as a "protective frisk."

In this exercise, you'll first check to see how many times "Protective Frisk" was the only search type. Then, you'll use a string method to locate all instances in which the driver was frisked.

print(ri['search_type'].value_counts())

# Check if 'search_type' contains the string 'Protective Frisk'
ri['frisk'] = ri.search_type.str.contains('Protective Frisk', na=False)

# Check the data type of 'frisk'
print(ri['frisk'].dtypes)

# Take the sum of frisk
print(ri['frisk'].sum())

Incident to Arrest                                          1290
Probable Cause                                               924
Inventory                                                    219
Reasonable Suspicion                                         214
Protective Frisk                                             164
Incident to Arrest,Inventory                                 123
Incident to Arrest,Probable Cause                            100
Probable Cause,Reasonable Suspicion                           54
Probable Cause,Protective Frisk                               35
Incident to Arrest,Inventory,Probable Cause                   35
Incident to Arrest,Protective Frisk                           33
Inventory,Probable Cause                                      25
Protective Frisk,Reasonable Suspicion                         19
Incident to Arrest,Inventory,Protective Frisk                 18
Incident to Arrest,Probable Cause,Protective Frisk            13
Inventory,Protective Frisk                                    12
Incident to Arrest,Reasonable Suspicion                        8
Incident to Arrest,Probable Cause,Reasonable Suspicion         5
Probable Cause,Protective Frisk,Reasonable Suspicion           5
Incident to Arrest,Inventory,Reasonable Suspicion              4
Inventory,Reasonable Suspicion                                 2
Incident to Arrest,Protective Frisk,Reasonable Suspicion       2
Inventory,Probable Cause,Protective Frisk                      1
Inventory,Protective Frisk,Reasonable Suspicion                1
Inventory,Probable Cause,Reasonable Suspicion                  1
Name: search_type, dtype: int64
bool
303

Comparing frisk rates by gender

In this exercise, you'll compare the rates at which female and male drivers are frisked during a search. Are males frisked more often than females, perhaps because police officers consider them to be higher risk?

Before doing any calculations, it's important to filter the DataFrame to only include the relevant subset of data, namely stops in which a search was conducted.

searched = ri[ri.search_conducted == True]

# Calculate the overall frisk rate by taking the mean of 'frisk'
print(searched.frisk.mean())

# Calculate the frisk rate for each gender
print(searched.groupby('driver_gender').frisk.mean())

0.09162382824312065
driver_gender
F    0.074561
M    0.094353
Name: frisk, dtype: float64