def Run(self, data_container, store_folder='', store_key=''):
temp_frame = data_container.GetFrame().select_dtypes(include=None, exclude=['object'])
new_data_container = DataContainer()
new_data_container.SetFrame(temp_frame)
if store_folder and os.path.isdir(store_folder):
feature_store_path = os.path.join(store_folder, 'numeric_feature.csv')
featureinfo_store_path = os.path.join(store_folder, 'feature_select_info.csv')
new_data_container.Save(feature_store_path)
SaveSelectInfo(new_data_container.GetFeatureName(), featureinfo_store_path, is_merge=False)
return new_data_container
vif_dict[exog] = vif
# calculate tolerance
tolerance = 1 - r_squared
tolerance_dict[exog] = tolerance
# return VIF DataFrame
df_vif = pd.DataFrame({'VIF': vif_dict, 'Tolerance': tolerance_dict})
return df_vif
if __name__ == '__main__':
data_path = r'..\..\Demo\train_numeric_feature.csv'
from BC.DataContainer.DataContainer import DataContainer
from BC.FeatureAnalysis.Normalizer import NormalizerZeroCenter
pca = DimensionReductionByPCA()
dc = DataContainer()
dc.Load(data_path)
dc = NormalizerZeroCenter.Run(dc)
# dc = pca.Run(dc)
df = pd.DataFrame(dc.GetArray(),
index=dc.GetCaseName(),
columns=dc.GetFeatureName())
dr = DimensionReductionByVIF()
new_df = dr.CalculateVIF(df)
print(dc.GetArray().shape, new_df.shape)
