Scikit管道中的链接转换

你必须申请 FunctionTransformer 顺序地。试试这个!

def create_pipeline(df):
    all_but_recency = ['monetary', 'frequency1','frequency2']

    # Preprocess
    # Preprocess
    preprocessor1 = ColumnTransformer([('log', FunctionTransformer(np.log), all_but_recency)],'passthrough')
    preprocessor2 = ColumnTransformer([('standardize', preprocessing.StandardScaler(), all_but_recency)],'passthrough' )


    # Pipeline
    estimators = [('preprocess1', preprocessor1),('standardize', preprocessor2)]
    pipe = Pipeline(steps=estimators)

    print(pipe.set_params().fit_transform(df).shape)

工作实例

from sklearn.datasets import load_iris
import pandas as pd
import numpy as np
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import Normalizer
from sklearn.preprocessing import FunctionTransformer
from sklearn.pipeline import Pipeline
from sklearn import preprocessing

iris = load_iris()
X, y = iris.data, iris.target
df= pd.DataFrame(X,columns = iris.feature_names)

all_but_one = [0,1,2]

# Preprocess
preprocessor1 = ColumnTransformer([('log', FunctionTransformer(np.log), all_but_one)],'passthrough')
preprocessor2 = ColumnTransformer([('standardize', preprocessing.StandardScaler(), all_but_one)],'passthrough' )

# Pipeline
estimators = [('preprocess1', preprocessor1),('scalling', preprocessor2)]
pipe = Pipeline(steps=estimators,)

pipe.fit_transform(df)