tpot_pipeline.py

import numpy as np
import pandas as pd
from sklearn.decomposition import FastICA
from sklearn.kernel_approximation import Nystroem
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.pipeline import make_pipeline
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=1337)

# Average CV score on the training set was: 0.599539016730704
exported_pipeline = make_pipeline(
    Nystroem(gamma=0.15000000000000002, kernel="rbf", n_components=5),
    FastICA(tol=0.0),
    GaussianNB()
)
# Fix random state for all the steps in exported pipeline
set_param_recursive(exported_pipeline.steps, 'random_state', 1337)

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