代码之家 › 专栏 › 技术社区 › KubiK888

在Python中尝试将ColumnTransformer适配到测试功能数据子集时发生属性错误

one-hot-encoding scikit-learn machine-learning python-3.x

0

KubiK888 · 技术社区 · 6 年前

我从这个应用类似的编码路径 tutorial 对于我自己的项目,使用ColumnTransformer一步传递分类变量和数值变量的值。但我被它困住了 X_test = colT.fit(X_test) 我不知道预期的输出应该是什么。

这是我的代码,我在 def standardize_values 功能

import pandas as pd
import numpy as np
import ctypes
import re
import pickle
from scipy import stats
from sklearn.model_selection import train_test_split
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import Normalizer, OneHotEncoder
from sklearn.tree import DecisionTreeRegressor
from sklearn.linear_model import LinearRegression
from sklearn import metrics
import helper_functions.helper_functions as hf
import data_preparation as data_prep

# Main class
######################################################################
class Machine_Learning_ProjectX(data_prep.DataPreparation_ProjectX):
    def __init__(self):
        self.pickle_descriptive_stats_demographic = None
        self.pickle_descriptive_stats_clinical = None
        self.pickle_descriptive_stats_rx = None
        self.pickle_descriptive_stats_csu = None    
        self.df_demographic = None
        self.df_clinical = None
        self.df_rx = None
        self.df_csu = None  
        self.df_master = None
        self.varname_cat_all = ['INDEX_RURAL_CAT', 'INDEX_SEX', 'AIDS_TAG', 'CHF_TAG', 'CKD_TAG', 'CLD_MILD_TAG', 'CLD_SEVERE_TAG',
                            'COPD_TAG', 'CTD_TAG', 'CVA_TAG', 'DM_MILD_TAG', 'DM_SEVERE_TAG', 'METS_TAG', 'MI_TAG', 'PUD_TAG',
                            'PVD_TAG', 'DEMENTIA_TAG', 'HEMIPLEGIA_TAG', 'TUMOR_TAG', 'INDEX_DIN_CAT']
        self.varname_num_all = ['INDEX_AGE', 'CCI_SCORE', 'PREINDEX1YR_N_DRUGX_FG_MPR', 'PREINDEX1YR_N_DRUGX_SG_MPR', 'PREINDEX1YR_N_DRUGY_TYPICAL_MPR',
                            'PREINDEX1YR_N_DRUGY_ATYPICAL_MPR', 'POSTINDEX1YR_N_DRUGX_FG_MPR', 'POSTINDEX1YR_N_DRUGX_SG_MPR',
                            'POSTINDEX1YR_N_DRUGY_TYPICAL_MPR', 'POSTINDEX1YR_N_DRUGY_ATYPICAL_MPR',
                            'SUMMED_ALLCAUSE_NUM_PRE2YR', 'SUMMED_ALLCAUSE_NUM_POST2YR', 'SUMMED_ALLCAUSE_COST_PRE2YR',
                            'SUMMED_ALLCAUSE_COST_POST2YR', 'SUMMED_DXTARGET_NUM_PRE2YR', 'SUMMED_DXTARGET_NUM_POST2YR',
                            'SUMMED_DXTARGET_COST_PRE2YR', 'SUMMED_DXTARGET_COST_POST2YR', 'DAD_ALLCAUSE_NUM_PRE2YR',
                            'DAD_ALLCAUSE_NUM_POST2YR', 'DAD_ALLCAUSE_COST_PRE2YR', 'DAD_ALLCAUSE_COST_POST2YR',
                            'DAD_DXTARGET_NUM_PRE2YR', 'DAD_DXTARGET_NUM_POST2YR', 'DAD_DXTARGET_COST_PRE2YR',
                            'DAD_DXTARGET_COST_POST2YR', 'PC_ALLCAUSE_NUM_PRE2YR', 'PC_ALLCAUSE_NUM_POST2YR', 
                            'PC_ALLCAUSE_COST_PRE2YR', 'PC_ALLCAUSE_COST_POST2YR', 'PC_DXTARGET_NUM_PRE2YR',
                            'PC_DXTARGET_NUM_POST2YR', 'PC_DXTARGET_COST_PRE2YR', 'PC_DXTARGET_COST_POST2YR',
                            'NACRS_ALLCAUSE_NUM_PRE2YR', 'NACRS_ALLCAUSE_NUM_POST2YR', 'NACRS_ALLCAUSE_COST_PRE2YR',
                            'NACRS_ALLCAUSE_COST_POST2YR', 'NACRS_DXTARGET_NUM_PRE2YR', 'NACRS_DXTARGET_NUM_POST2YR',
                            'NACRS_DXTARGET_COST_PRE2YR', 'NACRS_DXTARGET_COST_POST2YR']
        self.varname_num_unused = ['POSTINDEX1YR_N_DRUGX_FG_MPR', 'POSTINDEX1YR_N_DRUGX_SG_MPR', 'POSTINDEX1YR_N_DRUGY_TYPICAL_MPR', 
                            'POSTINDEX1YR_N_DRUGY_ATYPICAL_MPR', 'SUMMED_ALLCAUSE_NUM_POST2YR', 'SUMMED_ALLCAUSE_COST_POST2YR', 
                            'SUMMED_DXTARGET_NUM_POST2YR', 'SUMMED_DXTARGET_COST_POST2YR', 'DAD_ALLCAUSE_NUM_POST2YR', 
                            'DAD_ALLCAUSE_COST_POST2YR', 'DAD_DXTARGET_NUM_POST2YR', 'DAD_DXTARGET_COST_POST2YR', 'PC_ALLCAUSE_NUM_POST2YR', 
                            'PC_ALLCAUSE_COST_POST2YR', 'PC_DXTARGET_NUM_POST2YR',  'PC_DXTARGET_COST_POST2YR', 'NACRS_ALLCAUSE_NUM_POST2YR', 
                            'NACRS_ALLCAUSE_COST_POST2YR', 'NACRS_DXTARGET_NUM_POST2YR', 'NACRS_DXTARGET_COST_POST2YR']
        self.varname_id = ['PHN_ENC', 'INDEX_DATE']
        varname_label = ['SUMMED_ALLCAUSE_NUM_POST2YR', 'SUMMED_DXTARGET_NUM_POST2YR', 'SUMMED_ALLCAUSE_COST_POST2YR', 
                            'SUMMED_DXTARGET_COST_POST2YR', ]
        self.y_label = varname_label[0]
        self.varname_import = list(set(self.varname_id+self.varname_cat_all+self.varname_num_all)-set(self.varname_num_unused))+[self.y_label]
        self.result_dict_ml = {}

    def ml_steps(self):
        self.import_references()
        self.import_pickle_descriptive_stats_demographic(on_switch=True,
                                import_dir=self.result_dir,
                                import_filename='JAHIP_V2_SubjectGroup_DescriptiveStats_Demographic.pickle')
        self.import_pickle_descriptive_stats_clinical(on_switch=True,
                                import_dir=self.result_dir,
                                import_filename='JAHIP_V2_SubjectGroup_DescriptiveStats_Clinical.pickle')
        self.import_pickle_descriptive_stats_rx(on_switch=True,
                                import_dir=self.result_dir,
                                import_filename='JAHIP_V2_SubjectGroup_DescriptiveStats_Rx.pickle')
        self.import_pickle_descriptive_stats_csu(on_switch=True,
                                import_dir=self.result_dir,
                                import_filename='JAHIP_V2_SubjectGroup_DescriptiveStats_CSU.pickle')
        self.import_df_demographic(on_switch=True,
                                import_dir=self.result_dir,
                                import_filename='JAHIP_V2_SubjectGroup_DF_Demographic_SubjectLevel.csv')
        self.import_df_clinical(on_switch=True,
                                import_dir=self.result_dir,
                                import_filename='JAHIP_V2_SubjectGroup_DF_Clinical_SubjectLevel.csv')
        self.import_df_rx(on_switch=True,
                                import_dir=self.result_dir,
                                import_filename='JAHIP_V2_SubjectGroup_DF_Rx_SubjectLevel.csv')
        self.import_df_csu(on_switch=True,
                                import_dir=self.result_dir,
                                import_filename='JAHIP_V2_SubjectGroup_DF_CSU_SubjectLevel.csv')
        self.merge_dfs(on_switch=True)
        self.split_into_training_and_test_sets(on_switch=True)
        self.generate_new_features(on_switch=False)
        self.handle_missing_values(on_switch=True)
        self.standardize_values(on_switch=True)
        self.ml_pipeline(on_switch=True)

    def import_references(self):
        super().__init__()
        super()._pandas_output_setting()
        super().dir_name()
        super().file_name()
        super().constant_var()
        super().import_ref_data()

    # Decorators
    def on_or_off(func):
        def wrapper(self, *args, on_switch=False, **kwargs):
            if on_switch:
                func(self, *args, on_switch=on_switch, **kwargs)
        return wrapper

    # Core class functions
    @on_or_off
    def import_pickle_descriptive_stats_demographic(self, on_switch, import_dir=None, import_filename=None):
        with open(import_dir+import_filename, 'rb') as handle:
            self.pickle_descriptive_stats_demographic = pickle.load(handle)
    @on_or_off
    def import_pickle_descriptive_stats_clinical(self, on_switch, import_dir=None, import_filename=None):
        with open(import_dir+import_filename, 'rb') as handle:
            self.pickle_descriptive_stats_clinical = pickle.load(handle)
    @on_or_off
    def import_pickle_descriptive_stats_rx(self, on_switch, import_dir=None, import_filename=None):
        with open(import_dir+import_filename, 'rb') as handle:
            self.pickle_descriptive_stats_rx = pickle.load(handle)
    @on_or_off
    def import_pickle_descriptive_stats_csu(self, on_switch, import_dir=None, import_filename=None):
        with open(import_dir+import_filename, 'rb') as handle:
            self.pickle_descriptive_stats_csu = pickle.load(handle)

    @on_or_off
    def import_df_demographic(self, on_switch, import_dir=None, import_filename=None):
        self.df_demographic = pd.read_csv(import_dir+import_filename, dtype={'PHN_ENC':'str'})
    @on_or_off
    def import_df_clinical(self, on_switch, import_dir=None, import_filename=None):
        self.df_clinical = pd.read_csv(import_dir+import_filename, dtype={'PHN_ENC':'str'})
    @on_or_off
    def import_df_rx(self, on_switch, import_dir=None, import_filename=None):
        self.df_rx = pd.read_csv(import_dir+import_filename, dtype={'PHN_ENC':'str'})
    @on_or_off
    def import_df_csu(self, on_switch, import_dir=None, import_filename=None):
        self.df_csu = pd.read_csv(import_dir+import_filename, dtype={'PHN_ENC':'str'})

    @on_or_off
    def merge_dfs(self, on_switch):
        self.df_master = self.df_demographic.copy()
        self.df_master = self.df_master.merge(self.df_clinical, on='PHN_ENC', how='outer')
        self.df_master = self.df_master.merge(self.df_rx, on='PHN_ENC', how='outer')
        self.df_master = self.df_master.merge(self.df_csu, on='PHN_ENC', how='outer')
        assert (len(self.df_master)==self.df_master['PHN_ENC'].nunique()), 'Error: Same subject appears on multiple rows.'
        # Remove duplicated columns
        self.df_master = self.df_master.loc[:,~self.df_master.columns.str.contains('_y', case=True)]
        self.df_master.columns = self.df_master.columns.str.replace('_x', '')
        self.df_master = self.df_master.loc[:,~self.df_master.columns.duplicated()]
        # Remove unused columns
        self.df_master = self.df_master.loc[:, ~self.df_master.columns.str.contains('^Unnamed')]
        self.df_master = self.df_master.drop(['temp'], axis=1)
        # Retain only needed columns
        self.df_master = self.df_master[self.varname_import]

    @on_or_off
    def split_into_training_and_test_sets(self, on_switch):
        self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(self.df_master, self.df_master[self.y_label], 
            test_size=0.3, random_state=888)
        self.X_train = self.X_train.drop(['PHN_ENC', 'INDEX_DATE'], axis=1)
        self.X_test = self.X_test.drop(['PHN_ENC', 'INDEX_DATE'], axis=1)

    @on_or_off
    def generate_new_features(self, on_switch):
        pass

    @on_or_off
    def handle_missing_values(self, on_switch):
        self.X_train = self.X_train.apply(lambda x:x.fillna(x.value_counts().index[0]))
        self.X_test = self.X_test.apply(lambda x:x.fillna(x.value_counts().index[0]))
        self.y_train = self.y_train.fillna(0)
        self.y_test = self.y_test.fillna(0)

    @on_or_off
    def standardize_values(self, on_switch):
        colT = ColumnTransformer(
            [   ('DUMMY_COL', OneHotEncoder(categories=[['URBAN', 'RURAL'],
                                                        ['M', 'F'],
                                                        ['AIDS', 'NON-AIDS'],
                                                        ['CHF', 'NON-CHF'],
                                                        ['CKD', 'NON-CKD'],
                                                        ['CLD_MILD', 'NON-CLD_MILD'],
                                                        ['CLD_SEVERE', 'NON-CLD_SEVERE'],
                                                        ['COPD', 'NON-COPD'],
                                                        ['CTD', 'NON-CTD'],
                                                        ['CVA', 'NON-CVA'],
                                                        ['DM_MILD', 'NON-DM_MILD'],
                                                        ['DM_SEVERE', 'NON-DM_SEVERE'],
                                                        ['METS', "NON-METS"],
                                                        ['MI', 'NON-MI'],
                                                        ['PUD', 'NON-PUD'],
                                                        ['PVD', 'NON-PVD'],
                                                        ['DEMENTIA', 'NON-DEMENTIA'],
                                                        ['HEMIPLEGIA', 'NON-HEMIPLEGIA'],
                                                        ['TUMOR', 'NON-TUMOR'],
                                                        ['XX', 'YY', 'ZZ'],
                                                        ]),
                    self.varname_cat_all),
                ('NORM_COL', Normalizer(norm='l1'),
                    list(set(self.varname_num_all)-set(self.varname_num_unused)))
            ])

        print(self.X_train.shape) # (920, 43)
        print(self.X_test.shape) # (395, 43)

        self.X_train = colT.fit_transform(self.X_train)
        self.X_test = colT.fit(self.X_test)

        print(self.X_train.shape) # (920, 63)

        print(self.X_test) # Printing some weird output "ColumnTransformer..."
        print(self.X_test.shape) # AttributeError: 'ColumnTransformer' object has no attribute 'shape'

    @on_or_off
    def ml_pipeline(self, on_switch):
        regressor = LinearRegression()
        regressor.fit(self.X_train, self.y_train) # training the algorithm
        #y_pred = regressor.predict(self.X_test) # doesn't work

# Main function
######################################################################
def main():
    x = Machine_Learning_ProjectX()
    x.ml_steps()

if __name__ == '__main__':
    main()

# Output below
(920, 43)
(395, 43)
(920, 63)
ColumnTransformer(n_jobs=None, remainder='drop', sparse_threshold=0.3,
         transformer_weights=None,
         transformers=[('DUMMY_COL', OneHotEncoder(categorical_features=None,
       categories=[['URBAN', 'RURAL'], ['M', 'F'], ['AIDS', 'NON-AIDS'], ['CHF', 'NON-CHF'], ['CKD', 'NON-CKD'], ['CLD_MILD', 'NON-CLD_MILD'], ['CLD_SEVERE', 'NON-CLD_SEVERE'], ['COPD', 'NON-COPD'], ['CTD', 'NON-CTD'], ['CVA', 'NON..._DXTARGET_NUM_PRE2YR', 'PREINDEX1YR_N_DRUGY_TYPICAL_MPR', 'INDEX_AGE', 'NACRS_ALLCAUSE_NUM_PRE2YR'])])Traceback (most recent call last):
... line 212, in standardize_values
    print(self.X_test.shape)
AttributeError: 'ColumnTransformer' object has no attribute 'shape'

0 回复 | 直到 6 年前

1

seralouk 6 年前

教程的作者犯了一个错误。

self.X_train = colT.fit_transform(self.X_train)
self.X_test = colT.fit(self.X_test)

在这里 self.X_train 是 .fit_transform 所以这是一个 numpy 对象。另一方面, self.X_test 是的输出 .fit 方法,它是一个没有 .shape 属性!

您需要:

self.X_train = colT.fit_transform(self.X_train)
self.X_test = colT.transform(self.X_test)

P、 S:在文章的最后,检查其他人在本教程的评论中说了什么。