VotingClassifier: Different Feature Sets

Question

I have two different feature sets (so, with same number of rows and the labels are the same), in my case DataFrames:

df1:

| A          


        

Answer 1

To use as much as sklearn tools as possible, I find following way more appealing.

from sklearn.base import TransformerMixin, BaseEstimator
import numpy as np
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import VotingClassifier

######################
# custom transformer for sklearn pipeline
class ColumnExtractor(TransformerMixin, BaseEstimator):
    def __init__(self, cols):
        self.cols = cols

    def transform(self, X):
        col_list = []
        for c in self.cols:
            col_list.append(X[:, c:c+1])
        return np.concatenate(col_list, axis=1)

    def fit(self, X, y=None):
        return self

######################
# processing data
data = load_iris()
X = data.data
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X, y)

######################
# fit clf1 with df1
pipe1 = Pipeline([
    ('col_extract', ColumnExtractor( cols=range(0,2) )), # selecting features 0 and 1 (df1) to be used with LR (clf1)
    ('clf', LogisticRegression())
    ])

pipe1.fit(X_train, y_train) # sanity check
pipe1.score(X_test,y_test) # sanity check
# output: 0.6842105263157895

######################
# fit clf2 with df2
pipe2 = Pipeline([
    ('col_extract', ColumnExtractor( cols=range(2,4) )), # selecting features 2 and 3 (df2) to be used with SVC (clf2)
    ('clf', SVC(probability=True))
    ])

pipe2.fit(X_train, y_train) # sanity check
pipe2.score(X_test,y_test) # sanity check
# output: 0.9736842105263158

######################
# ensemble/voting classifier where clf1 fitted with df1 and clf2 fitted with df2
eclf = VotingClassifier(estimators=[('df1-clf1', pipe1), ('df2-clf2', pipe2)], voting='soft', weights= [1, 0.5])
eclf.fit(X_train, y_train)
eclf.score(X_test,y_test)
# output: 0.9473684210526315