import numpy as np
import pandas as pd
from sklearn.decomposition import PCA
from sklearn.ensemble import ExtraTreesRegressor, GradientBoostingRegressor
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline, make_union
from sklearn.preprocessing import Imputer
from tpot.builtins import OneHotEncoder, 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)

imputer = Imputer(strategy="median")
imputer.fit(training_features)
training_features = imputer.transform(training_features)
testing_features = imputer.transform(testing_features)

# Average CV score on the training set was:-3.08563298707127
exported_pipeline = make_pipeline(
    StackingEstimator(estimator=GradientBoostingRegressor(alpha=0.75, learning_rate=0.01, loss="quantile", max_depth=3, max_features=0.2, min_samples_leaf=16, min_samples_split=10, n_estimators=100, subsample=0.45)),
    OneHotEncoder(minimum_fraction=0.25, sparse=False, threshold=10),
    PCA(iterated_power=9, svd_solver="randomized"),
    ExtraTreesRegressor(bootstrap=False, max_features=0.9500000000000001, min_samples_leaf=5, min_samples_split=19, n_estimators=100)
)

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