In [1]:
import modelBuilding

ingest data


In [2]:
dataFrame = modelBuilding.loadData('~/Downloads/train.csv.zip')


---------------------------------------------------------------------------
IOError                                   Traceback (most recent call last)
<ipython-input-2-c5b8544a8cd4> in <module>()
----> 1 dataFrame = modelBuilding.loadData('~/Downloads/train.csv.zip')

/Users/aqo793/src/training/regressions/modelBuilding/loadingData.py in loadData(dataZipFileLocation)
      3 
      4 def loadData(dataZipFileLocation):
----> 5     z = zipfile.ZipFile(dataZipFileLocation)

/Users/aqo793/anaconda/lib/python2.7/zipfile.pyc in __init__(self, file, mode, compression, allowZip64)
    754             modeDict = {'r' : 'rb', 'w': 'wb', 'a' : 'r+b'}
    755             try:
--> 756                 self.fp = open(file, modeDict[mode])
    757             except IOError:
    758                 if mode == 'a':

IOError: [Errno 2] No such file or directory: '~/Downloads/train.csv.zip'

exploratory stuff...

basic descriptive statistics


In [4]:
for columnName in dataFrame.columns:
    dataFrame[columnName].value_counts()


---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-4-f874ca4be75c> in <module>()
----> 1 for columnName in dataFrame.columns:
      2     dataFrame[columnName].value_counts()

NameError: name 'dataFrame' is not defined

In [ ]: