Skip to content

hypersklearn

HyperSklearn

Hyperparameter Tuning for Sklearn.

Parameters:

Name Type Description Default
seed int

seed. See Numpy Random Sampling

126
log_level int

log level for logger. Default is 50.

50

Attributes:

Name Type Description
seed int

seed for random number generator.

rng Generator

random number generator.

fun_control dict

dictionary containing control parameters for the function.

log_level int

log level for logger.

Examples:

>>> from spotpython.fun.hypersklearn import HyperSklearn
>>> hyper_sklearn = HyperSklearn(seed=126, log_level=50)
>>> print(hyper_sklearn.seed)
126
Source code in spotpython/fun/hypersklearn.py
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
class HyperSklearn:
    """
    Hyperparameter Tuning for Sklearn.

    Args:
        seed (int): seed.
            See Numpy Random Sampling
        log_level (int): log level for logger. Default is 50.

    Attributes:
        seed (int): seed for random number generator.
        rng (Generator): random number generator.
        fun_control (dict): dictionary containing control parameters for the function.
        log_level (int): log level for logger.

    Examples:
        >>> from spotpython.fun.hypersklearn import HyperSklearn
        >>> hyper_sklearn = HyperSklearn(seed=126, log_level=50)
        >>> print(hyper_sklearn.seed)
        126
    """

    def __init__(self, seed: int = 126, log_level: int = 50):
        self.seed = seed
        self.rng = default_rng(seed=self.seed)
        self.fun_control = {
            "seed": None,
            "data": None,
            "step": 10_000,
            "horizon": None,
            "grace_period": None,
            "metric_river": None,
            "metric_sklearn": mean_absolute_error,
            "weights": array([1, 0, 0]),
            "weight_coeff": 0.0,
            "log_level": log_level,
            "var_name": [],
            "var_type": [],
            "prep_model": None,
            "predict_proba": False,
        }
        self.log_level = self.fun_control["log_level"]
        logger.setLevel(self.log_level)
        logger.info(f"Starting the logger at level {self.log_level} for module {__name__}:")

    def check_X_shape(self, X: np.ndarray) -> None:
        """
        Check the shape of the input array X.

        Args:
            X (np.ndarray): input array.

        Raises:
            Exception: if the second dimension of X does not match the length of var_name in fun_control.

        Examples:
            >>> from spotpython.fun.hypersklearn import HyperSklearn
            >>> hyper_sklearn = HyperSklearn(seed=126, log_level=50)
            >>> hyper_sklearn.fun_control["var_name"] = ["a", "b", "c"]
            >>> hyper_sklearn.check_X_shape(X=np.array([[1, 2, 3]]))
            >>> hyper_sklearn.check_X_shape(X=np.array([[1, 2]]))
            Traceback (most recent call last):
            ...
            Exception

        """
        try:
            X.shape[1]
        except ValueError:
            X = np.array([X])
        if X.shape[1] != len(self.fun_control["var_name"]):
            raise Exception

    def get_sklearn_df_eval_preds(self, model) -> tuple:
        """
        Get evaluation and prediction dataframes for a given model.
        Args:
            model (sklearn model): sklearn model.

        Returns:
            (tuple): tuple containing evaluation and prediction dataframes.

        Raises:
            Exception: if call to evaluate_model fails.

        """
        try:
            df_eval, df_preds = self.evaluate_model(model, self.fun_control)
        except Exception as err:
            print(f"Error in get_sklearn_df_eval_preds(). Call to evaluate_model failed. {err=}, {type(err)=}")
            print("Setting df_eval and df.preds to np.nan")
            df_eval = np.nan
            df_preds = np.nan
        return df_eval, df_preds

    def fun_sklearn(self, X: np.ndarray, fun_control: dict = None) -> np.ndarray:
        """
        Evaluate a sklearn model using hyperparameters specified in X.

        Args:
            X (np.ndarray): input array containing hyperparameters.
            fun_control (dict): dictionary containing control parameters for the function. Default is None.

        Returns:
            (np.ndarray): array containing evaluation results.

        Raises:
            Exception: if call to evaluate_model fails.

        """
        z_res = np.array([], dtype=float)
        self.fun_control.update(fun_control)
        self.check_X_shape(X)
        var_dict = assign_values(X, self.fun_control["var_name"])
        for config in generate_one_config_from_var_dict(var_dict, self.fun_control):
            if self.fun_control["prep_model"] is not None:
                model = make_pipeline(self.fun_control["prep_model"](), self.fun_control["core_model"](**config))
            else:
                model = self.fun_control["core_model"](**config)
            try:
                eval_type = fun_control["eval"]
                if eval_type == "eval_test":
                    df_eval, _ = evaluate_model(model, self.fun_control)
                elif eval_type == "eval_oob_score":
                    df_eval, _ = evaluate_model_oob(model, self.fun_control)
                elif eval_type == "train_cv":
                    df_eval, _ = evaluate_cv(model, self.fun_control)
                else:  # None or "evaluate_hold_out":
                    df_eval, _ = evaluate_hold_out(model, self.fun_control)
            except Exception as err:
                print(f"Error in fun_sklearn(). Call to evaluate_model failed. {err=}, {type(err)=}")
                print("Setting df_eval to np.nan")
                df_eval = np.nan
            z_res = np.append(z_res, fun_control["weights"] * df_eval)
        return z_res

check_X_shape(X)

Check the shape of the input array X.

Parameters:

Name Type Description Default
X ndarray

input array.

required

Raises:

Type Description
Exception

if the second dimension of X does not match the length of var_name in fun_control.

Examples:

>>> from spotpython.fun.hypersklearn import HyperSklearn
>>> hyper_sklearn = HyperSklearn(seed=126, log_level=50)
>>> hyper_sklearn.fun_control["var_name"] = ["a", "b", "c"]
>>> hyper_sklearn.check_X_shape(X=np.array([[1, 2, 3]]))
>>> hyper_sklearn.check_X_shape(X=np.array([[1, 2]]))
Traceback (most recent call last):
...
Exception
Source code in spotpython/fun/hypersklearn.py
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
def check_X_shape(self, X: np.ndarray) -> None:
    """
    Check the shape of the input array X.

    Args:
        X (np.ndarray): input array.

    Raises:
        Exception: if the second dimension of X does not match the length of var_name in fun_control.

    Examples:
        >>> from spotpython.fun.hypersklearn import HyperSklearn
        >>> hyper_sklearn = HyperSklearn(seed=126, log_level=50)
        >>> hyper_sklearn.fun_control["var_name"] = ["a", "b", "c"]
        >>> hyper_sklearn.check_X_shape(X=np.array([[1, 2, 3]]))
        >>> hyper_sklearn.check_X_shape(X=np.array([[1, 2]]))
        Traceback (most recent call last):
        ...
        Exception

    """
    try:
        X.shape[1]
    except ValueError:
        X = np.array([X])
    if X.shape[1] != len(self.fun_control["var_name"]):
        raise Exception

fun_sklearn(X, fun_control=None)

Evaluate a sklearn model using hyperparameters specified in X.

Parameters:

Name Type Description Default
X ndarray

input array containing hyperparameters.

required
fun_control dict

dictionary containing control parameters for the function. Default is None.

None

Returns:

Type Description
ndarray

array containing evaluation results.

Raises:

Type Description
Exception

if call to evaluate_model fails.

Source code in spotpython/fun/hypersklearn.py
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
def fun_sklearn(self, X: np.ndarray, fun_control: dict = None) -> np.ndarray:
    """
    Evaluate a sklearn model using hyperparameters specified in X.

    Args:
        X (np.ndarray): input array containing hyperparameters.
        fun_control (dict): dictionary containing control parameters for the function. Default is None.

    Returns:
        (np.ndarray): array containing evaluation results.

    Raises:
        Exception: if call to evaluate_model fails.

    """
    z_res = np.array([], dtype=float)
    self.fun_control.update(fun_control)
    self.check_X_shape(X)
    var_dict = assign_values(X, self.fun_control["var_name"])
    for config in generate_one_config_from_var_dict(var_dict, self.fun_control):
        if self.fun_control["prep_model"] is not None:
            model = make_pipeline(self.fun_control["prep_model"](), self.fun_control["core_model"](**config))
        else:
            model = self.fun_control["core_model"](**config)
        try:
            eval_type = fun_control["eval"]
            if eval_type == "eval_test":
                df_eval, _ = evaluate_model(model, self.fun_control)
            elif eval_type == "eval_oob_score":
                df_eval, _ = evaluate_model_oob(model, self.fun_control)
            elif eval_type == "train_cv":
                df_eval, _ = evaluate_cv(model, self.fun_control)
            else:  # None or "evaluate_hold_out":
                df_eval, _ = evaluate_hold_out(model, self.fun_control)
        except Exception as err:
            print(f"Error in fun_sklearn(). Call to evaluate_model failed. {err=}, {type(err)=}")
            print("Setting df_eval to np.nan")
            df_eval = np.nan
        z_res = np.append(z_res, fun_control["weights"] * df_eval)
    return z_res

get_sklearn_df_eval_preds(model)

Get evaluation and prediction dataframes for a given model. Args: model (sklearn model): sklearn model.

Returns:

Type Description
tuple

tuple containing evaluation and prediction dataframes.

Raises:

Type Description
Exception

if call to evaluate_model fails.

Source code in spotpython/fun/hypersklearn.py
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
def get_sklearn_df_eval_preds(self, model) -> tuple:
    """
    Get evaluation and prediction dataframes for a given model.
    Args:
        model (sklearn model): sklearn model.

    Returns:
        (tuple): tuple containing evaluation and prediction dataframes.

    Raises:
        Exception: if call to evaluate_model fails.

    """
    try:
        df_eval, df_preds = self.evaluate_model(model, self.fun_control)
    except Exception as err:
        print(f"Error in get_sklearn_df_eval_preds(). Call to evaluate_model failed. {err=}, {type(err)=}")
        print("Setting df_eval and df.preds to np.nan")
        df_eval = np.nan
        df_preds = np.nan
    return df_eval, df_preds