data_node_frame.py 文件源码

def make_preprocessing_pandas(self, _df_csv_read_ori, _preprocessing_type , _label):
        """ SKLearn? ???? Pandas? Proprocessing
            label? Preprocessing ?? ??
        Args:
          params:
            * _preprocessing_type: ['scale', 'minmax_scale', 'robust_scale', 'normalize', 'maxabs_scale']
            * _df_csv_read_ori : pandas dataframe
            * _label
        Returns:
          Preprocessing DataFrame
        """
        if _preprocessing_type == None or _preprocessing_type == 'null':
            logging.info("No Preprocessing")
            result_df =  _df_csv_read_ori
        else :
            logging.info("Preprocessing type : {0}".format(_preprocessing_type))
            numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']
            for i, v in _df_csv_read_ori.dtypes.iteritems():
                if v in numerics:
                    if i not in _label:
                        #preprocessing_types = ['scale', 'minmax_scale', 'robust_scale', 'normalize', 'maxabs_scale']
                        #_preprocessing_type = ['maxabs_scale']
                        if 'scale' in _preprocessing_type:
                            _df_csv_read_ori[i] = preprocessing.scale(_df_csv_read_ori[i].fillna(0.0))
                        if 'minmax_scale' in _preprocessing_type:
                            _df_csv_read_ori[i] = preprocessing.minmax_scale(_df_csv_read_ori[i].fillna(0.0))
                        if 'robust_scale' in _preprocessing_type:
                            _df_csv_read_ori[i] = preprocessing.robust_scale(_df_csv_read_ori[i].fillna(0.0))
                        if 'normalize' in _preprocessing_type:
                            _df_csv_read_ori[i] = preprocessing.normalize(_df_csv_read_ori[i].fillna(0.0))
                        if 'maxabs_scale' in _preprocessing_type:
                            _df_csv_read_ori[i] = preprocessing.maxabs_scale(_df_csv_read_ori[i].fillna(0.0))
            result_df = _df_csv_read_ori
        return result_df