def fit(self, train_x, train_y, folds=3):
estimators = all_estimators(type_filter="classifier")
for name, ClassifierClass in estimators:
if name in model_param_map:
param_grid = model_param_map[name]
grid_clf = GridSearchCV(
ClassifierClass(),
param_grid,
cv=folds,
scoring="accuracy",
verbose=0,
n_jobs=-1,
)
start = time.time()
grid_clf.fit(train_x, train_y)
end = time.time()
clf = SimpleClassifier()
clf.metrics["Training Accuracy"] = grid_clf.best_score_
pred_y = grid_clf.predict(train_x)
clf.metrics["Jaccard Score"] = jaccard_score(train_y,
pred_y,
average="macro")
clf.metrics["F1 Score"] = f1_score(train_y,
pred_y,
average="macro")
clf.sk_model = grid_clf.best_estimator_
clf.name = name
clf.attributes = grid_clf.best_params_
clf.train_duration = grid_clf.refit_time_
clf.gridsearch_duration = end - start
self.ranked_list.append(clf)
metrik = lambda clf: clf.metrics[self.metric]
self.ranked_list.sort(reverse=True, key=metrik)
def simple_classifier(self):
clf = SimpleClassifier()
clf.fit(self.x, self.y)
clf.save()
clf2 = SimpleClassifier()
clf2.load("simple_classifier.zip")
print("\nSuccessfully saved/loaded SimpleClassifier:\n", clf2)
print(clf2)
os.remove("simple_classifier.zip")
def fit(self, train_x, train_y, folds=3):
"""Trains all classification models from
parameter grid by running model algorithm search.
Creates a ranked list of models based on selected
scoring metric.
Parameters
----------
train_x : numpy.ndarray
The features for training classification model
train_y : numpy.ndarray
The corresponding label for feature array
folds : int, optional
The number of folds for cross validation
"""
estimators = all_estimators(type_filter="classifier")
for name, ClassifierClass in estimators:
if name in model_param_map:
param_grid = model_param_map[name]
grid_clf = GridSearchCV(
ClassifierClass(),
param_grid,
cv=folds,
scoring="accuracy",
verbose=0,
n_jobs=-1,
)
start = time.time()
try:
grid_clf.fit(train_x, train_y)
except BaseException as error:
self.logger.warning(
f"{name} failed due to, Error : {error}.")
continue
end = time.time()
clf = SimpleClassifier()
clf.metrics["Training Accuracy"] = grid_clf.best_score_
pred_y = grid_clf.predict(train_x)
clf.metrics["Jaccard Score"] = jaccard_score(train_y,
pred_y,
average="macro")
clf.metrics["F1 Score"] = f1_score(train_y,
pred_y,
average="macro")
clf.sk_model = grid_clf.best_estimator_
clf.name = name
clf.attributes = grid_clf.best_params_
clf.train_duration = grid_clf.refit_time_
clf.gridsearch_duration = end - start
self.ranked_list.append(clf)
metrik = lambda clf: clf.metrics[self.metric]
self.ranked_list.sort(reverse=True, key=metrik)
def test_iris(self):
iris = datasets.load_iris()
true_x = iris.data
true_y = iris.target
clf = SimpleClassifier()
clf.fit(true_x, true_y)
self.assertIsNotNone(clf.sk_model)
self.assertTrue(clf.metrics["Training Accuracy"] > 0.0)
pred_y = clf.predict(true_x)
self.assertTrue(accuracy_score(true_y, pred_y) > 0.95)
def test_init(self):
"""
Test initialization of SimpleClassifier
Expected
-----------------
name : "Empty Model"
"""
clf = SimpleClassifier()
self.assertEqual(clf.name, "Empty Model")
def test_digits(self):
"""
Test SimpleClassifier against sklearn digits dataset
Expected
-----------------
model : Not None
training accuracy : > 0.95
accuracy score : > 0.95
"""
digits = datasets.load_digits()
true_x = digits.data
true_y = digits.target
clf = SimpleClassifier()
clf.fit(true_x, true_y)
self.assertIsNotNone(clf.sk_model)
self.assertTrue(clf.metrics["Training Accuracy"] > 0.95)
pred_y = clf.predict(true_x)
self.assertTrue(accuracy_score(true_y, pred_y) > 0.95)
def test_init(self):
clf = SimpleClassifier()
self.assertEqual(clf.name, "Empty Model")
def simple_classifier(self):
clf = SimpleClassifier()
clf.fit(self.x, self.y)
print(clf)
def fit(self, train_x, train_y, folds=3):
"""Trains all classification models from
parameter grid by running model algorithm search.
Creates a ranked list of models based on selected
scoring metric.
Parameters
----------
train_x : numpy.ndarray
The features for training classification model
train_y : numpy.ndarray
The corresponding label for feature array
folds : int, optional
The number of folds for cross validation
"""
log = logging.getLogger(__name__)
log.setLevel(logging.INFO)
log.addHandler(custom_logging.TqdmLoggingHandler())
with tqdm(
total=(len(model_param_map)),
desc="Fitting Models",
unit=" Algorithm",
ncols=100,
) as progressbar:
estimators = all_estimators(type_filter="classifier")
for name, ClassifierClass in estimators:
if name in model_param_map:
param_grid = model_param_map[name]
grid_clf = GridSearchCV(
ClassifierClass(),
param_grid,
cv=folds,
scoring="accuracy",
verbose=0,
n_jobs=-1,
)
progressbar.update(1)
start = time.time()
try:
grid_clf.fit(train_x, train_y)
except BaseException as error:
log.info(f"{name} failed due to, Error : {error}.")
continue
end = time.time()
clf = SimpleClassifier()
clf.metrics["Training Accuracy"] = grid_clf.best_score_
pred_y = grid_clf.predict(train_x)
clf.metrics["Jaccard Score"] = jaccard_score(
train_y, pred_y, average="macro")
clf.metrics["F1 Score"] = f1_score(train_y,
pred_y,
average="macro")
clf.sk_model = grid_clf.best_estimator_
clf.name = name
clf.attributes = grid_clf.best_params_
clf.train_duration = grid_clf.refit_time_
clf.gridsearch_duration = end - start
self.ranked_list.append(clf)
metrik = lambda clf: clf.metrics[self.metric]
self.ranked_list.sort(reverse=True, key=metrik)