test_automl.py

FAILED            [100%]Recreating table test_cls with data from file
Done
Task: cls
|   iter    |  target   | algo_i... | prepro... |
-------------------------------------------------
Child Iteration accuracy: 0.884955
Child Iteration accuracy: 0.862831
|  1        |  0.885    |  2.063    |  1.061    |
Child Iteration accuracy: 0.871681
Child Iteration accuracy: 0.865044
|  2        |  0.8717   |  6.983    |  0.008468 |
Child Iteration accuracy: 0.873893
Child Iteration accuracy: 0.871681
|  3        |  0.8739   |  0.02296  |  0.001014 |
Child Iteration accuracy: 0.873893
Child Iteration accuracy: 0.871681
|  4        |  0.8739   |  6.053e-0 |  2.0      |
Child Iteration accuracy: 0.871681
Child Iteration accuracy: 0.865044
|  5        |  0.8717   |  6.996    |  1.989    |
100%|██████████| 1/1 [00:00<00:00,  2.44it/s]

test_automl.py:21 (test_classification[BayesianOptimizer])
self = <bayes_opt.target_space.TargetSpace object at 0x127f140d0>
params = {'algo_index_tuned': 3.6414726857916424, 'preprocess_method': 1.9853704004756136}

    def probe(self, params):
        """
        Evaulates a single point x, to obtain the value y and then records them
        as observations.
    
        Notes
        -----
        If x has been previously seen returns a cached value of y.
    
        Parameters
        ----------
        x : ndarray
            a single point, with len(x) == self.dim
    
        Returns
        -------
        y : float
            target function value.
        """
        x = self._as_array(params)
    
        try:
>           target = self._cache[_hashable(x)]
E           KeyError: (3.6414726857916424, 1.9853704004756136)

../../venv/lib/python3.9/site-packages/bayes_opt/target_space.py:191: KeyError

During handling of the above exception, another exception occurred:

self = <bayes_opt.target_space.TargetSpace object at 0x127f86820>
params = {'c': 51.25310037619536, 'kernel': 1.5917602668158823, 'scale_info': 0.19152078694749486, 'shrink': 0.06790035819129137, ...}

    def probe(self, params):
        """
        Evaulates a single point x, to obtain the value y and then records them
        as observations.
    
        Notes
        -----
        If x has been previously seen returns a cached value of y.
    
        Parameters
        ----------
        x : ndarray
            a single point, with len(x) == self.dim
    
        Returns
        -------
        y : float
            target function value.
        """
        x = self._as_array(params)
    
        try:
>           target = self._cache[_hashable(x)]
E           KeyError: (51.25310037619536, 1.5917602668158823, 0.19152078694749486, 0.06790035819129137, 0.7871984745399134)

../../venv/lib/python3.9/site-packages/bayes_opt/target_space.py:191: KeyError

During handling of the above exception, another exception occurred:

optimizer = 'BayesianOptimizer'

    @pytest.mark.parametrize("optimizer", ["OptunaSearch", "BayesianOptimizer"])
    def test_classification(optimizer):
>       m.fit(
            table_name="test_cls",
            file_path="../../data/bank.csv",
            target="y",
            id_column="ID",
            categorical_features=["job", "marital", 'education', 'default', 'housing', 'loan', 'contact', 'month', 'y'],
            columns_to_remove=["poutcome"],
            steps=5,
            output_leaderboard=True,
            optimizer=optimizer,
        )

test_automl.py:24: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
../../automl.py:96: in fit
    self.opt = pipe.train(
../../pipeline/pipeline.py:70: in train
    self.opt.tune()
../../optimizers/bayes.py:149: in tune
    opt.maximize(n_iter=self.iter, init_points=1)
../../venv/lib/python3.9/site-packages/bayes_opt/bayesian_optimization.py:185: in maximize
    self.probe(x_probe, lazy=False)
../../venv/lib/python3.9/site-packages/bayes_opt/bayesian_optimization.py:116: in probe
    self._space.probe(params)
../../venv/lib/python3.9/site-packages/bayes_opt/target_space.py:194: in probe
    target = self.target_func(**params)
../../optimizers/bayes.py:88: in objective
    opt.maximize(n_iter=1, init_points=1)
../../venv/lib/python3.9/site-packages/bayes_opt/bayesian_optimization.py:185: in maximize
    self.probe(x_probe, lazy=False)
../../venv/lib/python3.9/site-packages/bayes_opt/bayesian_optimization.py:116: in probe
    self._space.probe(params)
../../venv/lib/python3.9/site-packages/bayes_opt/target_space.py:194: in probe
    target = self.target_func(**params)
../../optimizers/bayes.py:113: in child_objective
    algorithm.set_params(**hyperparameters)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = SupportVectorClassifier
params = {'c': 51.25310037619536, 'kernel': 1.5917602668158823, 'scale_info': 0.19152078694749486, 'shrink': 0.06790035819129137, ...}

    def set_params(self, **params):
>       params["c"] = params["с"]
E       KeyError: 'с'

../../algorithms/classification/svc.py:19: KeyError