python - 我如何使用列转换器获取_feature_names

Question

import numpy as np
import pandas as pd
from sklearn.preprocessing import OneHotEncoder,StandardScaler
from sklearn.compose import ColumnTransformer, make_column_transformer
from sklearn.linear_model import LinearRegression

df = pd.DataFrame({'brand'      : ['aaaa', 'asdfasdf', 'sadfds', 'NaN'],
                   'category'   : ['asdf','asfa','asdfas','as'], 
                   'num1'       : [1, 1, 0, 0] ,
                   'target'     : [0.2,0.11,1.34,1.123]})



train_continuous_cols = df.select_dtypes(include=["int64","float64"]).columns.tolist()
train_categorical_cols = df.select_dtypes(include=["object"]).columns.tolist()


preprocess = make_column_transformer( 
    (StandardScaler(),train_continuous_cols),
    (OneHotEncoder(), train_categorical_cols)
)
df= preprocess.fit_transform(df)

只是想获取所有功能名称:

preprocess.get_feature_names()

收到此错误:

Transformer standardscaler (type StandardScaler) does not provide get_feature_names

我该如何解决？在线示例使用管道，我试图避免这种情况。

Answer 1

以下对 ColumnTransformer 的重新实现返回一个 Pandas DataFrame。请注意，仅当您将 Pandas DataFrame 输入管道时才应使用它。
所有荣誉都归于提供 get_feature_names() 的 Johannes Haupt对没有此功能的转换器具有弹性的功能(请参阅博客文章 Extracting Column Names from the ColumnTransformer)。我对警告进行了评论，因为我不想要它们，并且还预先将转换步骤添加到列名中；但是可以很容易地根据需要取消评论。

#import warnings
import sklearn
import pandas as pd

class ColumnTransformerWithNames(ColumnTransformer):
        
        
    def get_feature_names(column_transformer):
        """Get feature names from all transformers.
        Returns
        -------
        feature_names : list of strings
            Names of the features produced by transform.
        """
        # Remove the internal helper function
        #check_is_fitted(column_transformer)

        # Turn loopkup into function for better handling with pipeline later
        def get_names(trans):
            # >> Original get_feature_names() method
            if trans == 'drop' or (
                    hasattr(column, '__len__') and not len(column)):
                return []
            if trans == 'passthrough':
                if hasattr(column_transformer, '_df_columns'):
                    if ((not isinstance(column, slice))
                            and all(isinstance(col, str) for col in column)):
                        return column
                    else:
                        return column_transformer._df_columns[column]
                else:
                    indices = np.arange(column_transformer._n_features)
                    return ['x%d' % i for i in indices[column]]
            if not hasattr(trans, 'get_feature_names'):
            # >>> Change: Return input column names if no method avaiable
                # Turn error into a warning
    #             warnings.warn("Transformer %s (type %s) does not "
    #                                  "provide get_feature_names. "
    #                                  "Will return input column names if available"
    #                                  % (str(name), type(trans).__name__))
                # For transformers without a get_features_names method, use the input
                # names to the column transformer
                if column is None:
                    return []
                else:
                    return [#name + "__" + 
                            f for f in column]

            return [#name + "__" + 
                    f for f in trans.get_feature_names()]

        ### Start of processing
        feature_names = []

        # Allow transformers to be pipelines. Pipeline steps are named differently, so preprocessing is needed
        if type(column_transformer) == sklearn.pipeline.Pipeline:
            l_transformers = [(name, trans, None, None) for step, name, trans in column_transformer._iter()]
        else:
            # For column transformers, follow the original method
            l_transformers = list(column_transformer._iter(fitted=True))


        for name, trans, column, _ in l_transformers: 
            if type(trans) == sklearn.pipeline.Pipeline:
                # Recursive call on pipeline
                _names = column_transformer.get_feature_names(trans)
                # if pipeline has no transformer that returns names
                if len(_names)==0:
                    _names = [#name + "__" + 
                              f for f in column]
                feature_names.extend(_names)
            else:
                feature_names.extend(get_names(trans))

        return feature_names
        
    def transform(self, X):
        indices = X.index.values.tolist()
        original_columns = X.columns.values.tolist()
        X_mat = super().transform(X)
        new_cols = self.get_feature_names()
        new_X = pd.DataFrame(X_mat.toarray(), index=indices, columns=new_cols)
        return new_X

    def fit_transform(self, X, y=None):
        super().fit_transform(X, y)
        return self.transform(X)

然后你可以替换对 ColumnTransformer 的调用至 ColumnTransformerWithNames .输出是一个数据帧，这一步现在有一个工作 get_feature_names() .