optimal_pipeline.py

import numpy as np
import pandas as pd
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.feature_selection import VarianceThreshold
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import PolynomialFeatures
from tpot.builtins import ZeroCount
from tpot.export_utils import set_param_recursive

# NOTE: Make sure that the outcome column 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)
training_features, testing_features, training_target, testing_target = \
            train_test_split(features, tpot_data['target'], random_state=1)

# Average CV score on the training set was: 0.9347254053136407
exported_pipeline = make_pipeline(
    PolynomialFeatures(degree=2, include_bias=False, interaction_only=False),
    VarianceThreshold(threshold=0.2),
    ZeroCount(),
    GradientBoostingClassifier(learning_rate=1.0, max_depth=10, max_features=0.9000000000000001, min_samples_leaf=16, min_samples_split=3, n_estimators=100, subsample=0.7000000000000001)
)
# Fix random state for all the steps in exported pipeline
set_param_recursive(exported_pipeline.steps, 'random_state', 1)

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