import pandas as pd

pj = '/Users/danielmsheehan/Desktop/data/'
pj = '/Users/danielmsheehan/Dropbox/data/'

df = pd.read_csv(pj+'output/all/taxi_2013.csv', dtype={'tuid':object,'geoid':object})

print df.dtypes

df = df[(df.tuid.str[4:6] == '07')]
                 
df.to_csv(pj+'output/all/taxi_2013_m07.csv', index=False)

df

%reset

import pandas as pd

pd.options.display.max_columns = 5200
pd.options.display.max_rows    = 5200

pj = '/Users/danielmsheehan/Desktop/data/'
pj = '/Users/danielmsheehan/Dropbox/data/'
pj = '/Volumes/Hotel/Dropbox/data/'

df = pd.read_csv(pj+'output/all/taxi_2013_m07.csv', dtype={'tuid':object,'geoid':object})

df['count'] = 1

dfg = df.groupby(['tuid','type']).sum()

dfg.to_csv(pj+'output/all/taxi_2013_m07_groupby.csv', index=True)

df = pd.read_csv(pj+'output/all/taxi_2013_m07_groupby.csv')

df.dtypes

df1 = df[(df['count'] < 1)]

df1

df2 = pd.read_csv(pj+'output/all/taxi_2013_m07.csv', dtype={'tuid':object,'geoid':object})

df3 = df2[(df2.tuid == '20130723462939')]

df3