chess_tpotgbm_pipeline.py

import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline, make_union
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=42)

# Score on the training set was:0.9825643176733779
exported_pipeline = make_pipeline(
    StackingEstimator(estimator=RandomForestClassifier(bootstrap=True, criterion="entropy", max_depth=40, max_features="auto", min_samples_leaf=2, min_samples_split=18, n_estimators=800)),
    StackingEstimator(estimator=RandomForestClassifier(bootstrap=False, criterion="entropy", max_depth=10, max_features="sqrt", min_samples_leaf=12, min_samples_split=6, n_estimators=200)),
    RandomForestClassifier(bootstrap=False, criterion="gini", max_depth=None, max_features="auto", min_samples_leaf=18, min_samples_split=6, n_estimators=1000)
)

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