在scikit-learn中估算分类缺失值

要将平均值用于数字列，将最频繁的值用于非数字列，您可以执行以下 *** 作。您可以进一步区分整数和浮点数。我想用中位数代替整数列可能有意义。

import pandas as pdimport numpy as npfrom sklearn.base import TransformerMixinclass DataframeImputer(TransformerMixin):    def __init__(self):        """Impute missing values.        Columns of dtype object are imputed with the most frequent value         in column.        Columns of other types are imputed with mean of column.        """    def fit(self, X, y=None):        self.fill = pd.Series([X[c].value_counts().index[0] if X[c].dtype == np.dtype('O') else X[c].mean() for c in X], index=X.columns)        return self    def transform(self, X, y=None):        return X.fillna(self.fill)data = [    ['a', 1, 2],    ['b', 1, 1],    ['b', 2, 2],    [np.nan, np.nan, np.nan]]X = pd.Dataframe(data)xt = DataframeImputer().fit_transform(X)print('before...')print(X)print('after...')print(xt)

哪个打印，

before...     0   1   20    a   1   21    b   1   12    b   2   23  NaN NaN NaNafter...   0         1         20  a  1.000000  2.0000001  b  1.000000  1.0000002  b  2.000000  2.0000003  b  1.333333  1.666667