>>> import pandas
>>> # Read a CSV file, skipping last line
>>> rats = pandas.read_csv('rats.csv', skip_footer=1)
>>> # Investigate range of values for a certain field
>>> rats['Current Activity'].unique()
array([nan, Dispatch Crew, Request Sanitation Inspector], dtype=object)
>>> # Filter the data
>>> crew_dispatched = rats[rats['Current Activity'] == 'Dispatch Crew']
>>> len(crew_dispatched)
65676
>>> # Find 10 most rat-infested ZIP codes in Chicago
>>> crew_dispatched['ZIP Code'].value_counts()[:10]
60647 3837
60618 3530
60614 3284
60629 3251
60636 2801
60657 2465
60641 2238
60609 2206
60651 2152
60632 2071
>>> # Group by completion date
>>> dates = crew_dispatched.groupby('Completion Date')
<pandas.core.groupby.DataFrameGroupBy object at 0x10d0a2a10>
>>> len(dates)
472
>>> # Determine counts on each day
>>> date_counts = dates.size()
>>> date_counts[0:10]
Completion Date
01/03/2011 4
01/03/2012 125
01/04/2011 54
01/04/2012 38
01/05/2011 78
01/05/2012 100
01/06/2011 100
01/06/2012 58
01/07/2011 1
01/09/2012 12
>>> # Sort the counts
>>> date_counts.sort()
>>> date_counts[-10:]
Completion Date
10/12/2012 313
10/21/2011 314
09/20/2011 316
10/26/2011 319
02/22/2011 325
10/26/2012 333
03/17/2011 336
10/13/2011 378
10/14/2011 391
10/07/2011 457