tpot_automated_pipeline.py

import numpy as np
import pandas as pd
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import BernoulliNB
from sklearn.pipeline import make_pipeline, make_union
from sklearn.preprocessing import RobustScaler
from tpot.builtins import StackingEstimator

# NOTE: Make sure that the class is labeled 'target' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE', sep='COLUMN_SEPARATOR', dtype=np.float64)
features = tpot_data.drop('target', axis=1).values
training_features, testing_features, training_target, testing_target = \
            train_test_split(features, tpot_data['target'].values, random_state=None)

# Average CV score on the training set was:0.7615725359911407
exported_pipeline = make_pipeline(
    StackingEstimator(estimator=BernoulliNB(alpha=0.001, fit_prior=False)),
    RobustScaler(),
    RobustScaler(),
    StackingEstimator(estimator=ExtraTreesClassifier(bootstrap=False, criterion="gini", max_features=0.35000000000000003, min_samples_leaf=17, min_samples_split=6, n_estimators=100)),
    StackingEstimator(estimator=BernoulliNB(alpha=1.0, fit_prior=False)),
    RobustScaler(),
    ExtraTreesClassifier(bootstrap=False, criterion="entropy", max_features=0.55, min_samples_leaf=6, min_samples_split=19, n_estimators=100))

exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)