cfa_ex1_violations.py

#!/usr/env/python

from __future__ import print_function
import pandas as pd


# Read the csv
violations_df = pd.read_csv('violations-2012.csv')

# Covert Violations to datetime object
violations_df['violation_date'] = pd.to_datetime(violations_df['violation_date'])
violations_df['violation_date_closed'] = pd.to_datetime(violations_df['violation_date_closed'])

# Group by Category
category_group = violations_df.groupby('violation_category')

# Calcuate Min, Max and Value Counts
violation_min_date = category_group['violation_date'].min()
violation_max_date = category_group['violation_date'].max()
violation_count = category_group.size()

violations_result = pd.DataFrame({'violation_count': violation_count,
                                  'violation_min_date': violation_min_date,
                                  'violation_max_date': violation_max_date})


print(violations_result)