Using Pipelines

Using Pipelines.py

import pandas as pd
import numpy as np

from sklearn.impute import SimpleImputer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline

train = pd.DataFrame({'feature1' : [10, 20, np.nan, 2], 'feature2':  [25., 20, 5, 3], 'label':['A', 'A', 'B', 'B']})
test = pd.DataFrame({'feature1' : [30., 5, 15], 'feature2' :[ 12, 10, np.nan]})

train[:1] # One Row of the Training Set
test[:1] # One Row of the Test Set, we have to predict the label

imputer = SimpleImputer() # Initate the Imputer Class
clf = LogisticRegression() # Initiate the ML Model

# Pipeline: Impute missing values, then pass the results to the classifier
pipe = make_pipeline(imputer, clf)
features = ['feature1', 'feature2']

X, y = train[features], train['label']
X_new = test[features]

# Pipeline applies the imputer to X before fitting the classifier
pipe.fit(X, y)

# Pipeline applies the imputer to X_new before making predictions
pipe.predict(X_new)