In [1]:

    

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from datetime import datetime
%matplotlib inline


dtypes = {'Timestamp': datetime,
          'Station ID': str,
          'Lane 1 Flow': np.float,
          'Lane 1 Occupancy': np.float,
          'Lane 2 Flow': np.float,
          'Lane 2 Occupancy': np.float,
          'Lane 3 Flow': np.float,
          'Lane 3 Occupancy': np.float,
          'Lane 4 Flow': np.float,
          'Lane 4 Occupancy': np.float,
          'Lane 5 Flow': np.float,
          'Lane 5 Occupancy': np.float,
          'Lane 6 Flow': np.float,
          'Lane 6 Occupancy': np.float,
          'Lane 7 Flow': np.float,
          'Lane 7 Occupancy': np.float,
          'Lane 8 Flow': np.float,
          'Lane 8 Occupancy': np.float}


    

In [2]:

    

raw_data = pd.read_csv("../resources/Freeways-Rawaa.csv", header =1, dtype = dtypes, names = dtypes.keys())


    

    




/usr/local/lib/python2.7/site-packages/pandas-0.16.2-py2.7-macosx-10.10-x86_64.egg/pandas/io/parsers.py:1170: DtypeWarning: Columns (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17) have mixed types. Specify dtype option on import or set low_memory=False.
  data = self._reader.read(nrows)

In [4]:

    

print raw_data.describe()


    

    




        01/01/2010 00:00:00   1118695  Unnamed: 2  Unnamed: 3  Unnamed: 4  \
count              39969484  39969484    39129123    22296330    34459569   
unique                87663      2323         113        1193         124   
top     01/12/2010 06:40:30   1118663           0           0           0   
freq                   1155     34651    14505021     5367933     9770172   

        Unnamed: 5  Unnamed: 6  Unnamed: 7  Unnamed: 8  Unnamed: 9  \
count     21783593    20488307    18748159    15729494    15659545   
unique        1174         104        1192         123        1211   
top              0           0           0           0           0   
freq       2576236     2823021     1820240     2006419     1736427   

        Unnamed: 10  Unnamed: 11  Unnamed: 12  Unnamed: 13  Unnamed: 14  \
count       5377065      5377065      1107236      1107236           12   
unique           78         1122           51          851            1   
top               0            0            0            0  Lane 7 Flow   
freq        1075714       992234       223743       194044           12   

             Unnamed: 15  Unnamed: 16       Unnamed: 17  
count                 12           12                12  
unique                 1            1                 1  
top     Lane 7 Occupancy  Lane 8 Flow  Lane 8 Occupancy  
freq                  12           12                12  

In [ ]: