Scikit-learn的Iterative Imputer可以以轮循的方式填补缺失值。为了评估其与其他传统回归器的性能，可以构建一个简单的管道并从cross_val_score中获取评分指标。问题在于Iterative Imputer没有’predict’方法，错误信息如下：

AttributeError: 'IterativeImputer' object has no attribute 'predict'

请看一个尝试实现的简单示例：

# import librariesimport pandas as pdfrom sklearn.experimental import enable_iterative_imputerfrom sklearn.impute import IterativeImputerfrom sklearn.preprocessing import StandardScalerfrom sklearn.model_selection import cross_val_scorefrom sklearn.pipeline import Pipeline# define scaler, model and pipelinescaler = StandardScaler() # use any scalerimputer = IterativeImputer() # with any estimator, default = BayesianRidge()pipeline = Pipeline(steps=[('s', scaler), ('i', imputer)])train, test = df.values, df['A'].values scores = cross_val_score(pipeline, train, test, cv=10, scoring='r2')print(scores)

有什么可能的解决方案？如果需要自定义包装类，应该如何编写以包含’predict’方法？

回答：

cross_val_score 需要 pipeline 以 model 结束（该模型具有 predict 方法）

scaler  = StandardScaler()imputer = IterativeImputer()model   = BayesianRidge()  # any modelpipeline = Pipeline(steps=[('s', scaler), ('i', imputer), ('m', model)])

没有 model 的 cross_val_score 是没有意义的。

我还看到了另一个问题 – 关于你在 cross_val_score 中使用的 train, test 值。

应该使用 X, y 而不是 train, test，但这只是名称问题，所以不是那么重要，重要的是你分配给变量的值。

问题在于 X 不应该包含 y，但你使用了 train = df.values，所以你创建的 X 包含了 y

df_train = pd.DataFrame({                'X': range(20),                 'y': range(20),           })X_train = df_train[ ['X'] ]  # it needs inner `[]` to create DataFrame, not Seriesy_train = df_train[  'y'  ]  # it has to be single column (Series)scores = cross_val_score(pipeline, X_train, y_train, cv=10, scoring='r2')

（顺便说一下：你不需要使用 .values）

对于更多列也是如此

df_train = pd.DataFrame({                'A': range(20),                 'B': range(20),                 'y': range(20),           })X_train = df_train[ ['A', 'B'] ]y_train = df_train[ 'y' ]

最小工作代码，但使用的是无用的假数据

# import librariesimport pandas as pdfrom sklearn.experimental import enable_iterative_imputerfrom sklearn.impute import IterativeImputerfrom sklearn.preprocessing import StandardScalerfrom sklearn.model_selection import cross_val_scorefrom sklearn.pipeline import Pipelinefrom sklearn.linear_model import BayesianRidgedf_train = pd.DataFrame({                'A': range(100),  # fake data                'B': range(100),  # fake data                'y': range(100),  # fake data           })df_test = pd.DataFrame({                'A': range(20),  # fake data                'B': range(20),  # fake data                'y': range(20),  # fake data           })# define scaler, model and pipelinescaler  = StandardScaler()imputer = IterativeImputer()model   = BayesianRidge()pipeline = Pipeline(steps=[('s', scaler), ('i', imputer), ('m', model)])X_train = df_train[ ['A', 'B'] ]  # it needs inner `[]` to create DataFrame, not Seriesy_train = df_train[ 'y' ]         # it has to be single column (Series)scores = cross_val_score(pipeline, X_train, y_train, cv=10, scoring='r2')print(scores)X_test = df_test[['A', 'B']]y_test = df_test['y']scores = cross_val_score(pipeline, X_test, y_test, cv=10, scoring='r2')print(scores)