tpot_breast_cancer_pipepline.py

import numpy as np
import pandas as pd
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
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=None)

# Average CV score on the training set was:0.9889616180920529
exported_pipeline = make_pipeline(
    StackingEstimator(estimator=LogisticRegression(C=0.5, dual=False, penalty="l2")),
    StackingEstimator(estimator=GradientBoostingClassifier(learning_rate=0.1, max_depth=8, max_features=0.2, min_samples_leaf=10, min_samples_split=5, n_estimators=100, subsample=0.6000000000000001)),
    LogisticRegression(C=0.5, dual=True, penalty="l2")
)

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