How to use the tpot.export_utils.generate_pipeline_code function in TPOT

18,
        'uniform',
        2
    ]

    expected_code = """make_pipeline(
    make_union(
        StackingEstimator(estimator=GradientBoostingClassifier(learning_rate=38.0, max_depth=5, max_features=5, min_samples_leaf=5, min_samples_split=0.05, n_estimators=0.5)),
        StackingEstimator(estimator=make_pipeline(
            ZeroCount(),
            GaussianNB()
        ))
    ),
    KNeighborsClassifier(n_neighbors=18, p="uniform", weights=2)
)"""
    assert expected_code == generate_pipeline_code(pipeline, tpot_obj.operators)

expected_code = """make_pipeline(
    make_union(
        StackingEstimator(estimator=GradientBoostingClassifier(learning_rate=38.0, max_depth=5, max_features=5, min_samples_leaf=5, min_samples_split=0.05, n_estimators=0.5)),
        make_union(
            MinMaxScaler(),
            make_pipeline(
                MaxAbsScaler(),
                ZeroCount()
            )
        )
    ),
    KNeighborsClassifier(n_neighbors=18, p="uniform", weights=2)
)"""

    assert expected_code == generate_pipeline_code(pipeline, tpot_obj.operators)

while bad_pipeline and num_test < NUM_TESTS:
            # clone individual before each func call so it is not altered for
            # the possible next cycle loop
            args = [self._toolbox.clone(arg) if isinstance(arg, creator.Individual) else arg for arg in args]

            try:
                with warnings.catch_warnings():
                    warnings.simplefilter('ignore')

                    expr = func(self, *args, **kwargs)
                    # mutation operator returns tuple (ind,); crossover operator
                    # returns tuple of (ind1, ind2)
                    expr_tuple = expr if isinstance(expr, tuple) else (expr,)

                    for expr_test in expr_tuple:
                        pipeline_code = generate_pipeline_code(
                            expr_to_tree(expr_test, self._pset),
                            self.operators
                        )
                        sklearn_pipeline = eval(pipeline_code, self.operators_context)

                        if self.classification:
                            sklearn_pipeline.fit(pretest_X, pretest_y)
                        else:
                            sklearn_pipeline.fit(pretest_X_reg, pretest_y_reg)
                        bad_pipeline = False
            except BaseException as e:
                message = '_pre_test decorator: {fname}: num_test={n} {e}'.format(
                    n=num_test,
                    fname=func.__name__,
                    e=e
                )