module import edit

.gitignore

@@ -1,6 +1,6 @@
 **/__pycache__/
-**/data/
-nb_test.ipynb
+tests/data/
+tests/nb_test.ipynb
 temp.py
 .gitignore
 .pytest_cache

_metatune.py

@@ -1,9 +1,9 @@
 import inspect, copy
-from baseline import BaseTuner, TrialCheckMixin
+from .baseline import BaseTuner, TrialCheckMixin
 from optuna.trial import Trial, FrozenTrial
-from tune_regressor import regressor_tuning_entities, regressor_tuner_model_class_dict
-from tune_classifier import classifier_tuning_entities, classifier_tuner_model_class_dict
-from utils import make_default_tuner_type_mutable
+from .tune_regressor import regressor_search_space, regressor_tuner_model_class_map
+from .tune_classifier import classifier_search_space, classifier_tuner_model_class_map
+from .utils import make_default_tuner_type_mutable
 from typing import Iterable, Tuple, Dict, Union, Optional, Any, Callable
 
 
@@ -143,12 +143,12 @@ def __init__(
         self.single_tuner = single_tuner
 
         if self.task == "regression":
-            self.search_space: Dict[str, BaseTuner] = copy.deepcopy(regressor_tuning_entities)
-            self.tuner_model_class_map: Dict[str, Callable] = copy.deepcopy(regressor_tuner_model_class_dict)
+            self.search_space: Dict[str, BaseTuner] = copy.deepcopy(regressor_search_space)
+            self.tuner_model_class_map: Dict[str, Callable] = copy.deepcopy(regressor_tuner_model_class_map)
 
         else:
-            self.search_space:  Dict[str, BaseTuner] = copy.deepcopy(classifier_tuning_entities)
-            self.tuner_model_class_map: Dict[str, Callable] = copy.deepcopy(classifier_tuner_model_class_dict)
+            self.search_space:  Dict[str, BaseTuner] = copy.deepcopy(classifier_search_space)
+            self.tuner_model_class_map: Dict[str, Callable] = copy.deepcopy(classifier_tuner_model_class_map)
 
         self._exclude_tuners()
         self._prepare_custom_tuners()

readme.md

@@ -114,3 +114,12 @@ except Exception as e:
 ```
 
 This way, instead of terminating the metaheuristic search program, optuna simply skips to the next trial and gives you a log relating to why the trial was pruned. Similarly, if you happen to want to optimize an objective the relies on predicted probability scores for each class, rather than the class label, you can call the `predict_proba(...)` method on `X_train`  in the `try` block, just after called the `fit(...)` method.
+
+<br>
+<br>
+<hr>
+
+## Advanced Configurations
+
+
+<hr>

tests/test_tuners.py

@@ -1,7 +1,7 @@
-from baseline.base import BaseTuner
-import tune_classifier
-import tune_regressor
-from tests.utils import BaseTest
+from ..baseline.base import BaseTuner
+from .. import tune_classifier
+from .. import tune_regressor
+from .utils import BaseTest
 
 
 # run python -m pytest -v

tests/utils.py

@@ -3,9 +3,9 @@
 from sklearn import datasets
 from sklearn.preprocessing import MinMaxScaler
 from optuna.trial import Trial
-from baseline.base import BaseTuner
-from tune_classifier import classifier_tuner_model_class_dict
-from tune_regressor import regressor_tuner_model_class_dict
+from ..baseline.base import BaseTuner
+from ..tune_classifier import classifier_tuner_model_class_map
+from ..tune_regressor import regressor_tuner_model_class_map
 
 
 # load sample datasets
@@ -59,10 +59,10 @@ class BaseTest:
 
     def test_dict_mapping(self):
         if self.task == "classification":
-            assert self.model.__class__.__name__ in classifier_tuner_model_class_dict.keys()
+            assert self.model.__class__.__name__ in classifier_tuner_model_class_map.keys()
 
         elif self.task == "regression":
-            assert self.model.__class__.__name__ in regressor_tuner_model_class_dict.keys()
+            assert self.model.__class__.__name__ in regressor_tuner_model_class_map.keys()
 
         else: assert False
 

tune_classifier/__init__.py

@@ -1,4 +1,4 @@
-from utils.module_utils import get_tuner_entities, get_tuner_model_dict
+from ..utils import make_default_tuner_type_mutable
 from .svc import *
 from .tree_classifier import *
 from .linear_model_classifier import *
@@ -7,32 +7,74 @@
 from .neighbor_classifier import *
 from .mlp_classifier import *
 from .discriminant_analysis_classifier import *
-from utils import make_default_tuner_type_mutable
 from typing import Iterable, Dict, Callable
 
 
-__modules__: Iterable[str] = [
-    "tune_classifier.svc",
-    "tune_classifier.tree_classifier",
-    "tune_classifier.linear_model_classifier",
-    "tune_classifier.ensemble_classifier",
-    "tune_classifier.naive_bayes_classifier",
-    "tune_classifier.neighbor_classifier",
-    "tune_classifier.mlp_classifier",
-    "tune_classifier.discriminant_analysis_classifier"
-]
-
-classifier_tuning_entities: Dict[str, object] = {k:v for k, v in sum(list(map(get_tuner_entities, __modules__)), [])}
-classifier_tuning_entities: Dict[str, object] = dict(
-    map(lambda pair : (pair[0], make_default_tuner_type_mutable(pair[1])), classifier_tuning_entities.items()))
+classifier_tuner_model_class_map: Dict[str, Callable] = {
+    SVCTuner.__name__: SVC,
+    LinearSVCTuner.__name__: LinearSVC,
+    NuSVCTuner.__name__: NuSVC,
+    DecisionTreeClassifierTuner.__name__: DecisionTreeClassifier,
+    ExtraTreeClassifierTuner.__name__: ExtraTreeClassifier,
+    LogisticRegressionTuner.__name__: LogisticRegression,
+    PerceptronTuner.__name__: Perceptron,
+    PassiveAggressiveClassifierTuner.__name__: PassiveAggressiveClassifier,
+    SGDClassifierTuner.__name__: SGDClassifier,
+    RandomForestClassifierTuner.__name__: RandomForestClassifier,
+    ExtraTreesClassifierTuner.__name__: ExtraTreesClassifier,
+    AdaBoostClassifierTuner.__name__: AdaBoostClassifier,
+    GradientBoostingClassifierTuner.__name__: GradientBoostingClassifier,
+    BaggingClassifierTuner.__name__: BaggingClassifier,
+    HistGradientBoostingClassifierTuner.__name__: HistGradientBoostingClassifier,
+    GaussianNBTuner.__name__: GaussianNB,
+    BernoulliNBTuner.__name__: BernoulliNB,
+    MultinomialNBTuner.__name__: MultinomialNB,
+    ComplementNBTuner.__name__: ComplementNB,
+    CategoricalNBTuner.__name__: CategoricalNB,
+    KNeighborsClassifierTuner.__name__: KNeighborsClassifier,
+    RadiusNeighborsClassifierTuner.__name__: RadiusNeighborsClassifier,
+    NearestCentroidClassifierTuner.__name__: NearestCentroid,
+    MLPClassifierTuner.__name__: MLPClassifier,
+    LDAClassifierTuner.__name__: LinearDiscriminantAnalysis,
+    QDAClassifierTuner.__name__: QuadraticDiscriminantAnalysis,
+}
 
-classifier_tuner_model_class_dict: Dict[str, Callable] = {
-    k:v for _dict in map(get_tuner_model_dict, __modules__) for k, v in _dict.items()
+classifier_search_space: Dict[str, BaseTuner] = {
+    SVCTuner.__name__: SVCTuner(),
+    LinearSVCTuner.__name__: LinearSVCTuner(),
+    NuSVCTuner.__name__: NuSVCTuner(),
+    DecisionTreeClassifierTuner.__name__: DecisionTreeClassifierTuner(),
+    ExtraTreeClassifierTuner.__name__: ExtraTreeClassifierTuner(),
+    LogisticRegressionTuner.__name__: LogisticRegressionTuner(),
+    PerceptronTuner.__name__: PerceptronTuner(),
+    PassiveAggressiveClassifierTuner.__name__: PassiveAggressiveClassifierTuner(),
+    SGDClassifierTuner.__name__: SGDClassifierTuner(),
+    RandomForestClassifierTuner.__name__: RandomForestClassifierTuner(),
+    ExtraTreesClassifierTuner.__name__: ExtraTreesClassifierTuner(),
+    AdaBoostClassifierTuner.__name__: AdaBoostClassifierTuner(),
+    GradientBoostingClassifierTuner.__name__: GradientBoostingClassifierTuner(),
+    BaggingClassifierTuner.__name__: BaggingClassifierTuner(),
+    HistGradientBoostingClassifierTuner.__name__: HistGradientBoostingClassifierTuner(),
+    GaussianNBTuner.__name__: GaussianNBTuner(),
+    BernoulliNBTuner.__name__: BernoulliNBTuner(),
+    MultinomialNBTuner.__name__: MultinomialNBTuner(),
+    ComplementNBTuner.__name__: ComplementNBTuner(),
+    CategoricalNBTuner.__name__: CategoricalNBTuner(),
+    KNeighborsClassifierTuner.__name__: KNeighborsClassifierTuner(),
+    RadiusNeighborsClassifierTuner.__name__: RadiusNeighborsClassifierTuner(),
+    NearestCentroidClassifierTuner.__name__: NearestCentroidClassifierTuner(),
+    MLPClassifierTuner.__name__: MLPClassifierTuner(),
+    LDAClassifierTuner.__name__: LDAClassifierTuner(),
+    QDAClassifierTuner.__name__: QDAClassifierTuner(),
 }
 
+classifier_search_space: Dict[str, BaseTuner] = dict(
+    map(lambda pair : (pair[0], make_default_tuner_type_mutable(pair[1])), classifier_search_space.items())
+)
+
 __all__: Iterable[str] = [
-    "classifier_tuning_entities",
-    "classifier_tuner_model_class_dict",
+    "classifier_tuner_model_class_map",
+    "classifier_search_space",
     "SVCTuner", 
     "LinearSVCTuner", 
     "NuSVCTuner", 

tune_classifier/discriminant_analysis_classifier.py

@@ -1,4 +1,4 @@
-from baseline import BaseTuner
+from ..baseline import BaseTuner
 from optuna.trial import Trial
 from dataclasses import dataclass
 from types import MappingProxyType
@@ -58,10 +58,4 @@ def sample_model(self, trial: Optional[Trial] = None) -> Any:
         model = self.evaluate_sampled_model("classification", QuadraticDiscriminantAnalysis, params)
 
         self.model = model
-        return model
-
-
-tuner_model_class_dict: Dict[str, Callable] = {
-    LDAClassifierTuner.__name__: LinearDiscriminantAnalysis,
-    QDAClassifierTuner.__name__: QuadraticDiscriminantAnalysis
-}
+        return model

tune_classifier/ensemble_classifier.py

@@ -1,4 +1,4 @@
-from baseline import BaseTuner
+from ..baseline import BaseTuner
 from optuna.trial import Trial
 from dataclasses import dataclass
 from typing import Iterable, Optional, Dict, Any, Union, Callable
@@ -333,14 +333,4 @@ def sample_model(self, trial: Optional[Trial]=None) -> Any:
         model = super().evaluate_sampled_model("classification", HistGradientBoostingClassifier, params)
         self.model = model
 
-        return model
-
-
-tuner_model_class_dict: Dict[str, Callable] = {
-    RandomForestClassifierTuner.__name__: RandomForestClassifier,
-    ExtraTreesClassifierTuner.__name__: ExtraTreesClassifier,
-    AdaBoostClassifierTuner.__name__: AdaBoostClassifier,
-    GradientBoostingClassifierTuner.__name__: GradientBoostingClassifier,
-    BaggingClassifierTuner.__name__: BaggingClassifier,
-    HistGradientBoostingClassifierTuner.__name__: HistGradientBoostingClassifier,
-}
+        return model

tune_classifier/linear_model_classifier.py

@@ -1,4 +1,4 @@
-from baseline import BaseTuner
+from ..baseline import BaseTuner
 from optuna.trial import Trial
 from dataclasses import dataclass
 from typing import Iterable, Optional, Dict, Any, Callable
@@ -211,12 +211,4 @@ def sample_model(self, trial: Optional[Trial]=None) -> Any:
         model = super().evaluate_sampled_model("classification", SGDClassifier, params)
         self.model = model
 
-        return model
-
-
-tuner_model_class_dict: Dict[str, Callable] = {
-    LogisticRegressionTuner.__name__: LogisticRegression,
-    PerceptronTuner.__name__: Perceptron,
-    PassiveAggressiveClassifierTuner.__name__: PassiveAggressiveClassifier,
-    SGDClassifierTuner.__name__: SGDClassifier,
-}
+        return model

tune_classifier/mlp_classifier.py

@@ -1,4 +1,4 @@
-from baseline import BaseTuner
+from ..baseline import BaseTuner
 from optuna.trial import Trial
 from dataclasses import dataclass
 from typing import Iterable, Optional, Dict, Any, Callable
@@ -73,9 +73,4 @@ def sample_model(self, trial: Optional[Trial] = None) -> Any:
         params = self.sample_params(trial)
         model = super().evaluate_sampled_model("classification", MLPClassifier, params)
         self.model = model
-        return model
-
-
-tuner_model_class_dict: Dict[str, Callable] = {
-    MLPClassifierTuner.__name__: MLPClassifier
-}
+        return model

tune_classifier/naive_bayes_classifier.py

@@ -1,4 +1,4 @@
-from baseline import BaseTuner
+from ..baseline import BaseTuner
 from optuna.trial import Trial
 from dataclasses import dataclass
 from typing import Callable,Iterable, Optional, Dict, Any, Union
@@ -154,12 +154,4 @@ def sample_model(self, trial: Optional[Trial] = None) -> Any:
         model = super().evaluate_sampled_model("classification", CategoricalNB, params)
 
         self.model = model
-        return model
-
-tuner_model_class_dict: Dict[str, Callable] = {
-    GaussianNBTuner.__name__: GaussianNB,
-    BernoulliNBTuner.__name__: BernoulliNB,
-    MultinomialNBTuner.__name__: MultinomialNB,
-    ComplementNBTuner.__name__: ComplementNB,
-    CategoricalNBTuner.__name__: CategoricalNB,
-}
+        return model

tune_classifier/neighbor_classifier.py

@@ -1,4 +1,4 @@
-from baseline import BaseTuner
+from ..baseline import BaseTuner
 from optuna.trial import Trial
 from dataclasses import dataclass
 from typing import Iterable, Optional, Dict, Any, Callable
@@ -99,11 +99,4 @@ def sample_model(self, trial: Optional[Trial] = None) -> Any:
 
         self.model = model
 
-        return model
-
-
-tuner_model_class_dict: Dict[str, Callable] = {
-    KNeighborsClassifierTuner.__name__: KNeighborsClassifier,
-    RadiusNeighborsClassifierTuner.__name__: RadiusNeighborsClassifier,
-    NearestCentroidClassifierTuner.__name__: NearestCentroid
-}
+        return model

tune_classifier/svc.py

@@ -1,4 +1,4 @@
-from baseline import BaseTuner
+from ..baseline import BaseTuner
 from optuna.trial import Trial
 from dataclasses import dataclass
 from typing import Iterable, Optional, Dict, Any, Callable
@@ -129,10 +129,3 @@ def sample_model(self, trial: Optional[Trial]=None) -> Any:
         params = self.sample_params(trial)
         model = super().evaluate_sampled_model("classification", NuSVC, params)
         return model
-
-
-tuner_model_class_dict: Dict[str, Callable] = {
-    SVCTuner.__name__: SVC,
-    LinearSVCTuner.__name__: LinearSVC,
-    NuSVCTuner.__name__: NuSVC,
-}

tune_classifier/tree_classifier.py

@@ -1,4 +1,4 @@
-from baseline import BaseTuner
+from ..baseline import BaseTuner
 from optuna.trial import Trial
 from dataclasses import dataclass
 from typing import Iterable, Optional, Dict, Any, Union, Callable
@@ -73,10 +73,4 @@ def sample_model(self, trial: Optional[Trial]=None) -> Any:
         params = self.sample_params(trial)
         model = super(DecisionTreeClassifierTuner, self).evaluate_sampled_model("classification", ExtraTreeClassifier, params)
         self.model = model
-        return model
-
-
-tuner_model_class_dict: Dict[str, Callable] = {
-    DecisionTreeClassifierTuner.__name__: DecisionTreeClassifier,
-    ExtraTreeClassifierTuner.__name__: ExtraTreeClassifier,
-}
+        return model