def test_cv_score_is_more_than_zero_with_LSVC_SVC_KNN_GNB_accuracy_5(self):
# path to diabetes.csv file in project
path = ".\\..\\datasets\\diabetes.csv"
# get df with loader creator
csv_type = self._loader_creator.create_loader(path, "CSV")
df = csv_type.get_file_transformed()
# split df into x and y
splitter = SplitterReturner()
x, y = splitter.split_x_y_from_df(df)
# create a CVScore object with its path and data type
cv_score = CVScore()
# create a simple a svc, knn and gnb estimator
model_1 = self._estimator_creator.create_estimator("SVC")
model_2 = self._estimator_creator.create_estimator(
"KNeighborsClassifier")
model_3 = self._estimator_creator.create_estimator("GaussianNB")
model_4 = self._estimator_creator.create_estimator("LinearSVC")
estimators = [
model_1, model_2, model_3,
model_4.set_params(dual=False)
]
# get score from a linearSVC estimator with accuracy score and 5folds
bol_results = []
for clf in estimators:
score = cv_score.get_score(x, y, clf, "accuracy", 5)
print(clf.__class__.__name__, "score is:", score)
is_greater_than_zero: bool = True if score > 0 else False
bol_results.append(is_greater_than_zero)
# any will return True if there's any truth value in the iterable.
print(bol_results)
answer = all(bol_results)
# all of this should be true
self.assertTrue(answer)
def test_cv_score_is_more_than_zero_with_APROPAGATION_KMEANS_MINIKMEANS_MEANSHIFT_mutual_info_score_5(
self):
# path to diabetes.csv file in project
path = ".\\..\\datasets\\iris.csv"
# get df with loader creator
csv_type = self._loader_creator.create_loader(path, "CSV")
df = csv_type.get_file_transformed()
# split df into x and y
splitter = SplitterReturner()
x, y = splitter.split_x_y_from_df(df)
# create a CVScore object with its path and data type
cv_score = CVScore()
# create a simple a svc, knn and gnb estimator
model_1 = self._estimator_creator.create_estimator(
"AffinityPropagation")
model_2 = self._estimator_creator.create_estimator("KMeans")
model_3 = self._estimator_creator.create_estimator("MiniBatchKMeans")
model_4 = self._estimator_creator.create_estimator("MeanShift")
estimators = [
model_1.set_params(random_state=0), model_2, model_3, model_4
]
# get score from a linearSVC estimator with accuracy score and 5folds
bol_results = []
for clf in estimators:
score = cv_score.get_score(x, y, clf, "mutual_info_score", 5)
print(clf.__class__.__name__, "score is:", score)
is_greater_than_zero: bool = True if score > 0 else False
bol_results.append(is_greater_than_zero)
print(bol_results)
def test_cv_score_is_more_than_zero_with_LSVR_SVR_LASSO_SGD_explained_variance_5(
self):
# path to diabetes.csv file in project
path = ".\\..\\datasets\\winequality-white.csv"
# get df with loader creator
scsv_type = self._loader_creator.create_loader(path, "SCSV")
df = scsv_type.get_file_transformed()
# split df into x and y
splitter = SplitterReturner()
x, y = splitter.split_x_y_from_df(df)
# create a CVScore object with its path and data type
cv_score = CVScore()
# create a simple a svc, knn and gnb estimator
model_1 = self._estimator_creator.create_estimator("LinearSVR")
model_2 = self._estimator_creator.create_estimator("SVR")
model_3 = self._estimator_creator.create_estimator("Lasso")
model_4 = self._estimator_creator.create_estimator("SGDClassifier")
estimators = [model_1, model_2, model_3, model_4]
# get score from a linearSVC estimator with accuracy score and 5folds
bol_results = []
for clf in estimators:
score = cv_score.get_score(x, y, clf, "explained_variance", 5)
print(clf.__class__.__name__, "score is:", score)
is_greater_than_zero: bool = True if score > 0 else False
bol_results.append(is_greater_than_zero)
print(bol_results)
# there is at least one true element, which means on of the scores is greater than 0
self.assertTrue(any(bol_results))
def test_n_folds_validation_and_score_type_raises_ValueError(self):
# path to diabetes.csv file in project
path = ".\\..\\datasets\\diabetes.csv"
# get df with loader creator
csv_type = self._loader_creator.create_loader(path, "CSV")
df = csv_type.get_file_transformed()
# split df into x and y
splitter = SplitterReturner()
x, y = splitter.split_x_y_from_df(df)
# create a CVScore object with its path and data type
cv_score = CVScore()
# create a simple linearSVC estimator
model = self._estimator_creator.create_estimator("LinearSVC")
model.set_params(dual=False, random_state=0)
with self.assertRaises(ValueError):
# get score from a linearSVC estimator with roc_auc score and 10 folds
_ = cv_score.get_score(x, y, model, "roc", 2)
class SBSMachineLearning(ABC):
_data_frame = pd.DataFrame()
_feature_selector: FeatureSelection = None
_parameter_selector: ParameterSearch = None
_best_features: NpArray = None
_best_params: dict = None
_initial_params: dict = None
_clf: Any = None
_cv_score: CVModelScore = CVScore()
@property
def data_frame(self) -> DataFrame:
return self._data_frame
@data_frame.setter
def data_frame(self, value: DataFrame) -> None:
self._data_frame = value
@property
def feature_selector(self) -> FeatureSelection:
return self._feature_selector
@feature_selector.setter
def feature_selector(self, value: FeatureSelection) -> None:
self._feature_selector = value
@property
def parameter_selector(self) -> ParameterSearch:
return self._parameter_selector
@parameter_selector.setter
def parameter_selector(self, value: ParameterSearch) -> None:
self._parameter_selector = value
@property
def best_features(self) -> NpArray:
return self._best_features
@best_features.setter
def best_features(self, value: NpArray) -> None:
self._best_features = value
@property
def best_parameters(self) -> dict:
return self._best_params
@best_parameters.setter
def best_parameters(self, value: dict) -> None:
self._best_params = value
@property
def initial_parameters(self) -> dict:
return self._initial_params
@initial_parameters.setter
def initial_parameters(self, value: dict) -> None:
self._initial_params = value
@property
def estimator(self) -> Any:
return self._clf
@estimator.setter
def estimator(self, value: Any) -> None:
self._clf = value
@abstractmethod
def score_model(self, score_type: str, n_folds_validation: int) -> float:
pass
class FeatureSelection(ABC):
_cv_score: CVModelScore = CVScore()
@abstractmethod
def select_features(self, x: DataFrame, y: NpArray, model: Any, score_type: str, n_folds_validation: int) -> tuple:
pass