DataIO.py 文件源码

def LoadFromTextFile(InputDir):

        ## raw data
        TrainData = pd.read_csv('%s/train_2016_v2.csv' % InputDir, parse_dates=['transactiondate'], header=0)
        TestData = pd.read_csv('%s/sample_submission.csv' % InputDir, header=0)
        TestData['parcelid'] = TestData['ParcelId']
        TestData.drop('ParcelId', axis=1, inplace=True)
        PropertyData = pd.read_csv('%s/properties_2016.csv' % InputDir,header=0)
        for c, dtype in zip(PropertyData.columns, PropertyData.dtypes):
            if dtype == np.float64:
                PropertyData[c] = PropertyData[c].astype(np.float32)

        ## join dynamic data with static data
        TrainData = pd.merge(TrainData, PropertyData, how='left', on='parcelid')
        TestData = pd.merge(TestData, PropertyData, how='left', on='parcelid')

        return TrainData,TestData

    ## class method, save data with pkl format