train_df = pandas.read_csv(train_fullpath,
sep=',',
na_values='NA',
low_memory=False)
#for item in train_df.columns.values:
# pandas.to_numeric(train_df[item])
X_train = train_df[attributes]
y_train = train_df[target_key]
train_datapreprocessing = DataPreprocessing(
pandas.concat([X_train, y_train], axis=1), attributes, target_key)
#train_datapreprocessing.data_summary()
binary_transform_attrs = [
'user_live_address', 'user_rela_name', 'user_relation',
'user_rela_phone', 'user_high_edu', 'user_company_name'
]
X_train = train_datapreprocessing.transform_x_to_binary(
binary_transform_attrs)
X_train = train_datapreprocessing.transform_x_dtype(binary_transform_attrs,
d_type=[int],
uniform_type=True)
area_attrs = ['user_live_province', 'user_live_city']
resource_dir = '../resources'
X_train = train_datapreprocessing.china_area_number_mapping(
area_attrs, resource_dir)
X_train = train_datapreprocessing.transform_x_dtype(area_attrs,
d_type=[int],
uniform_type=True)
X_train = train_datapreprocessing.x_dummies_and_fillna()
#train_datapreprocessing.data_summary()
Gini_DF = pandas.concat([X_train, y_train], axis=1)
#gini_attrs = Gini_DF.axes[1]
train_df = pandas.read_csv(train_fullpath,
sep=',',
na_values='NA',
low_memory=False)
#for item in train_df.columns.values:
# pandas.to_numeric(train_df[item])
X_train = train_df[attributes]
y_train = train_df[target_key]
train_datapreprocessing = DataPreprocessing(
pandas.concat([X_train, y_train], axis=1), attributes, target_key)
#train_datapreprocessing.data_summary()
binary_transform_attrs = [
'user_live_address', 'user_rela_name', 'user_relation',
'user_rela_phone', 'user_high_edu', 'user_company_name'
]
X_train = train_datapreprocessing.transform_x_to_binary(
binary_transform_attrs)
X_train = train_datapreprocessing.transform_x_dtype(binary_transform_attrs,
d_type=[int],
uniform_type=True)
area_attrs = ['user_live_province', 'user_live_city']
resource_dir = '../resources'
X_train = train_datapreprocessing.china_area_number_mapping(
area_attrs, resource_dir)
X_train = train_datapreprocessing.transform_x_dtype(area_attrs,
d_type=[int],
uniform_type=True)
X_train = train_datapreprocessing.x_dummies_and_fillna()
#train_datapreprocessing.data_summary()
#Gini_DF = pandas.concat([X_train,y_train],axis=1)
##gini_attrs = Gini_DF.axes[1]