def data_process(self, dataframe):
"""
Apply data process to features
:param dataframe: extracted feature in data frame
:param label_name: name of label column in data frame
:return processed_dataframe: extracted feature in pandas data frame
"""
# Make a copy of dataframe
processed_dataframe = dataframe.copy()
# Apply normalization to data frame
processed_dataframe = DataProcess.normalize_dataframe(
processed_dataframe, self.cfg.label_name)
# Factorize label
processed_dataframe = DataProcess.factorize_label(
processed_dataframe, self.cfg.label_name)
return processed_dataframe
def data_process(self, dataframe):
"""
Apply data process to features
:param dataframe: extracted feature in data frame
:param label_name: name of label column in data frame
:return processed_dataframe: extracted feature in pandas data frame
"""
# Make a copy of dataframe
processed_dataframe = dataframe.copy()
# Centerize data and apply standardization to data frame
#processed_dataframe = DataProcess.normalize_dataframe(processed_dataframe, self.cfg.label_name)
centerized_dataframe, mean_list = DataProcess.centerize_dataframe(processed_dataframe, self.cfg.label_name)
cleaned_dataframe, std_list = DataProcess.standardize_dataframe(centerized_dataframe, self.cfg.label_name)
# Factorize label
cleaned_dataframe = DataProcess.factorize_label(cleaned_dataframe, self.cfg.label_name)
# Write out mean values
FileUtil.list2csv(mean_list, "../mean_list.csv")
FileUtil.list2csv(std_list, "../std_list.csv")
return cleaned_dataframe
