hyperactive.optimizers._optimizer_api.BaseOptimizer.add_search() - Code Metrics - Inspection of "V5 api design" - SimonBlanke/Hyperactive - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — master (#101)

by Simon

created 2025-03-04 09:50 UTC

BaseOptimizer.add_search() B

↳ Parent: hyperactive.optimizers._optimizer_api

Complexity

Conditions

Size

Total Lines	71
Code Lines	42

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	3
eloc	42
nop	15
dl	0
loc	71
rs	8.872
c	0
b	0
f	0

How to fix Long Method Many Parameters

"""Base class for optimizer."""

from typing import Union, List, Dict
import multiprocessing as mp
import pandas as pd

from .backend_stuff.search_space import SearchSpace
from .search import Search


from ..composite_optimizer import CompositeOptimizer

from skbase.base import BaseObject


class BaseOptimizer(BaseObject):
    """Base class for optimizer."""

    n_search: int
    searches: list
    opt_pros: dict

    def __init__(self, optimizer_class, opt_params):
        super().__init__()

        self.optimizer_class = optimizer_class
        self.opt_params = opt_params

        self.n_search = 0
        self.searches = []

    @staticmethod
    def _default_search_id(search_id, objective_function):
        if not search_id:
            search_id = objective_function.__name__
        return search_id

    @staticmethod
    def check_list(search_space):
        for key in search_space.keys():
            search_dim = search_space[key]

            error_msg = "Value in '{}' of search space dictionary must be of type list".format(
                key
            )
            if not isinstance(search_dim, list):
                print("Warning", error_msg)
                # raise ValueError(error_msg)

    def add_search(
        self,
        experiment: callable,
        search_space: Dict[str, list],
        n_iter: int,
        search_id=None,
        n_jobs: int = 1,
        verbosity: list = ["progress_bar", "print_results", "print_times"],
        initialize: Dict[str, int] = {"grid": 4, "random": 2, "vertices": 4},
        constraints: List[callable] = None,
        pass_through: Dict = None,
        max_score: float = None,
        early_stopping: Dict = None,
        random_state: int = None,
        memory: Union[str, bool] = "share",
        memory_warm_start: pd.DataFrame = None,
    ):
        """
        Add a new optimization search process with specified parameters.

        Parameters:
        - experiment: Experiment class containing the objective-function to optimize.
        - search_space: Dictionary defining the search space for optimization.
        - n_iter: Number of iterations for the optimization process.
        - search_id: Identifier for the search process (default: None).
        - n_jobs: Number of parallel jobs to run (default: 1).
        - initialize: Dictionary specifying initialization parameters (default: {"grid": 4, "random": 2, "vertices": 4}).
        - constraints: List of constraint functions (default: None).
        - pass_through: Dictionary of additional parameters to pass through (default: None).
        - callbacks: Dictionary of callback functions (default: None).
        - catch: Dictionary of exceptions to catch during optimization (default: None).
        - max_score: Maximum score to achieve (default: None).
        - early_stopping: Dictionary specifying early stopping criteria (default: None).
        - random_state: Seed for random number generation (default: None).
        - memory: Option to share memory between processes (default: "share").
        - memory_warm_start: DataFrame containing warm start memory (default: None).
        """

        self.n_search += 1

        self.check_list(search_space)

        constraints = constraints or []
        pass_through = pass_through or {}
        early_stopping = early_stopping or {}

        search_id = self._default_search_id(
            search_id, experiment.objective_function
        )
        s_space = SearchSpace(search_space)
        self.verbosity = verbosity

        n_jobs = mp.cpu_count() if n_jobs == -1 else n_jobs

        for _ in range(n_jobs):
            search = Search(self.optimizer_class, self.opt_params)
            search.setup(
                experiment=experiment,
                s_space=s_space,
                n_iter=n_iter,
                initialize=initialize,
                constraints=constraints,
                pass_through=pass_through,
                max_score=max_score,
                early_stopping=early_stopping,
                random_state=random_state,
                memory=memory,
                memory_warm_start=memory_warm_start,
                verbosity=verbosity,
            )
            self.searches.append(search)

    @property
    def nth_search(self):
        return len(self.composite_opt.optimizers)

    def __add__(self, optimizer_instance):
        return CompositeOptimizer(self, optimizer_instance)

    def run(
        self,
        max_time=None,
        distribution: str = "multiprocessing",
        n_processes: Union[str, int] = "auto",
    ):
        self.comp_opt = CompositeOptimizer(self)
        self.comp_opt.run(max_time, distribution, n_processes, self.verbosity)

    def best_para(self, id_):
        """
        Retrieve the best parameters for a specific ID from the results.

        Parameters:
        - id_ (int): The ID of the parameters to retrieve.

        Returns:
        - Union[Dict[str, Union[int, float]], None]: The best parameters for the specified ID if found, otherwise None.

        Raises:
        - ValueError: If the objective function name is not recognized.
        """

        return self.comp_opt.results_.best_para(id_)

    def best_score(self, id_):
        """
        Return the best score for a specific ID from the results.

        Parameters:
        - id_ (int): The ID for which the best score is requested.
        """

        return self.comp_opt.results_.best_score(id_)

    def search_data(self, id_, times=False):
        """
        Retrieve search data for a specific ID from the results. Optionally exclude evaluation and iteration times if 'times' is set to False.

        Parameters:
        - id_ (int): The ID of the search data to retrieve.
        - times (bool, optional): Whether to exclude evaluation and iteration times. Defaults to False.

        Returns:
        - pd.DataFrame: The search data for the specified ID.
        """

        search_data_ = self.comp_opt.results_.search_data(
            id_.objective_function
        )

        if times == False:
            search_data_.drop(
                labels=["eval_times", "iter_times"],
                axis=1,
                inplace=True,
                errors="ignore",
            )
        return search_data_


1			"""Base class for optimizer."""
2
3			from typing import Union, List, Dict
4			import multiprocessing as mp
5			import pandas as pd
6
7			from .backend_stuff.search_space import SearchSpace
8			from .search import Search
9
10
11			from ..composite_optimizer import CompositeOptimizer
12
13			from skbase.base import BaseObject
14
15
16			class BaseOptimizer(BaseObject):
17			"""Base class for optimizer."""
18
19			n_search: int
20			searches: list
21			opt_pros: dict
22
23			def __init__(self, optimizer_class, opt_params):
24			super().__init__()
25
26			self.optimizer_class = optimizer_class
27			self.opt_params = opt_params
28
29			self.n_search = 0
30			self.searches = []
31
32			@staticmethod
33			def _default_search_id(search_id, objective_function):
34			if not search_id:
35			search_id = objective_function.__name__
36			return search_id
37
38			@staticmethod
39			def check_list(search_space):
40			for key in search_space.keys():
41			search_dim = search_space[key]
42
43			error_msg = "Value in '{}' of search space dictionary must be of type list".format(
44			key
45			)
46			if not isinstance(search_dim, list):
47			print("Warning", error_msg)
48			# raise ValueError(error_msg)
49
50			def add_search(
51			self,
52			experiment: callable,
53			search_space: Dict[str, list],
54			n_iter: int,
55			search_id=None,
56			n_jobs: int = 1,
57			verbosity: list = ["progress_bar", "print_results", "print_times"],
58			initialize: Dict[str, int] = {"grid": 4, "random": 2, "vertices": 4},
59			constraints: List[callable] = None,
60			pass_through: Dict = None,
61			max_score: float = None,
62			early_stopping: Dict = None,
63			random_state: int = None,
64			memory: Union[str, bool] = "share",
65			memory_warm_start: pd.DataFrame = None,
66			):
67			"""
68			Add a new optimization search process with specified parameters.
69
70			Parameters:
71			- experiment: Experiment class containing the objective-function to optimize.
72			- search_space: Dictionary defining the search space for optimization.
73			- n_iter: Number of iterations for the optimization process.
74			- search_id: Identifier for the search process (default: None).
75			- n_jobs: Number of parallel jobs to run (default: 1).
76			- initialize: Dictionary specifying initialization parameters (default: {"grid": 4, "random": 2, "vertices": 4}).
77			- constraints: List of constraint functions (default: None).
78			- pass_through: Dictionary of additional parameters to pass through (default: None).
79			- callbacks: Dictionary of callback functions (default: None).
80			- catch: Dictionary of exceptions to catch during optimization (default: None).
81			- max_score: Maximum score to achieve (default: None).
82			- early_stopping: Dictionary specifying early stopping criteria (default: None).
83			- random_state: Seed for random number generation (default: None).
84			- memory: Option to share memory between processes (default: "share").
85			- memory_warm_start: DataFrame containing warm start memory (default: None).
86			"""
87
88			self.n_search += 1
89
90			self.check_list(search_space)
91
92			constraints = constraints or []
93			pass_through = pass_through or {}
94			early_stopping = early_stopping or {}
95
96			search_id = self._default_search_id(
97			search_id, experiment.objective_function
98			)
99			s_space = SearchSpace(search_space)
100			self.verbosity = verbosity
101
102			n_jobs = mp.cpu_count() if n_jobs == -1 else n_jobs
103
104			for _ in range(n_jobs):
105			search = Search(self.optimizer_class, self.opt_params)
106			search.setup(
107			experiment=experiment,
108			s_space=s_space,
109			n_iter=n_iter,
110			initialize=initialize,
111			constraints=constraints,
112			pass_through=pass_through,
113			max_score=max_score,
114			early_stopping=early_stopping,
115			random_state=random_state,
116			memory=memory,
117			memory_warm_start=memory_warm_start,
118			verbosity=verbosity,
119			)
120			self.searches.append(search)
121
122			@property
123			def nth_search(self):
124			return len(self.composite_opt.optimizers)
125
126			def __add__(self, optimizer_instance):
127			return CompositeOptimizer(self, optimizer_instance)
128
129			def run(
130			self,
131			max_time=None,
132			distribution: str = "multiprocessing",
133			n_processes: Union[str, int] = "auto",
134			):
135			self.comp_opt = CompositeOptimizer(self)
136			self.comp_opt.run(max_time, distribution, n_processes, self.verbosity)
137
138			def best_para(self, id_):
139			"""
140			Retrieve the best parameters for a specific ID from the results.
141
142			Parameters:
143			- id_ (int): The ID of the parameters to retrieve.
144
145			Returns:
146			- Union[Dict[str, Union[int, float]], None]: The best parameters for the specified ID if found, otherwise None.
147
148			Raises:
149			- ValueError: If the objective function name is not recognized.
150			"""
151
152			return self.comp_opt.results_.best_para(id_)
153
154			def best_score(self, id_):
155			"""
156			Return the best score for a specific ID from the results.
157
158			Parameters:
159			- id_ (int): The ID for which the best score is requested.
160			"""
161
162			return self.comp_opt.results_.best_score(id_)
163
164			def search_data(self, id_, times=False):
165			"""
166			Retrieve search data for a specific ID from the results. Optionally exclude evaluation and iteration times if 'times' is set to False.
167
168			Parameters:
169			- id_ (int): The ID of the search data to retrieve.
170			- times (bool, optional): Whether to exclude evaluation and iteration times. Defaults to False.
171
172			Returns:
173			- pd.DataFrame: The search data for the specified ID.
174			"""
175
176			search_data_ = self.comp_opt.results_.search_data(
177			id_.objective_function
178			)
179
180			if times == False:
181			search_data_.drop(
182			labels=["eval_times", "iter_times"],
183			axis=1,
184			inplace=True,
185			errors="ignore",
186			)
187			return search_data_
188

SimonBlanke / Hyperactive

Pull Request — master (#101)

BaseOptimizer.add_search() B

Complexity

Size

Duplication

Importance

How to fix Long Method Many Parameters

Long Method

Many Parameters

Duplication Side-by-Side

Filter issues like