def test_logistic_cv_mock_scorer():
class MockScorer(object):
def __init__(self):
self.calls = 0
self.scores = [0.1, 0.4, 0.8, 0.5]
def __call__(self, model, X, y, sample_weight=None):
score = self.scores[self.calls % len(self.scores)]
self.calls += 1
return score
mock_scorer = MockScorer()
Cs = [1, 2, 3, 4]
cv = 2
lr = LogisticRegressionCV(Cs=Cs, scoring=mock_scorer, cv=cv)
lr.fit(X, Y1)
# Cs[2] has the highest score (0.8) from MockScorer
assert lr.C_[0] == Cs[2]
# scorer called 8 times (cv*len(Cs))
assert mock_scorer.calls == cv * len(Cs)
# reset mock_scorer
mock_scorer.calls = 0
with pytest.warns(ChangedBehaviorWarning):
custom_score = lr.score(X, lr.predict(X))
assert custom_score == mock_scorer.scores[0]
assert mock_scorer.calls == 1
def test_logistic_cv_score_does_not_warn_by_default():
lr = LogisticRegressionCV(cv=2)
lr.fit(X, Y1)
with pytest.warns(None) as record:
lr.score(X, lr.predict(X))
assert len(record) == 0
def test_multinomial_logistic_regression_string_inputs():
# Test with string labels for LogisticRegression(CV)
n_samples, n_features, n_classes = 50, 5, 3
X_ref, y = make_classification(n_samples=n_samples,
n_features=n_features,
n_classes=n_classes,
n_informative=3,
random_state=0)
y_str = LabelEncoder().fit(['bar', 'baz', 'foo']).inverse_transform(y)
# For numerical labels, let y values be taken from set (-1, 0, 1)
y = np.array(y) - 1
# Test for string labels
lr = LogisticRegression(solver='lbfgs', multi_class='multinomial')
lr_cv = LogisticRegressionCV(solver='lbfgs', multi_class='multinomial')
lr_str = LogisticRegression(solver='lbfgs', multi_class='multinomial')
lr_cv_str = LogisticRegressionCV(solver='lbfgs', multi_class='multinomial')
lr.fit(X_ref, y)
lr_cv.fit(X_ref, y)
lr_str.fit(X_ref, y_str)
lr_cv_str.fit(X_ref, y_str)
assert_array_almost_equal(lr.coef_, lr_str.coef_)
assert_equal(sorted(lr_str.classes_), ['bar', 'baz', 'foo'])
assert_array_almost_equal(lr_cv.coef_, lr_cv_str.coef_)
assert_equal(sorted(lr_str.classes_), ['bar', 'baz', 'foo'])
assert_equal(sorted(lr_cv_str.classes_), ['bar', 'baz', 'foo'])
# The predictions should be in original labels
assert_equal(sorted(np.unique(lr_str.predict(X_ref))),
['bar', 'baz', 'foo'])
assert_equal(sorted(np.unique(lr_cv_str.predict(X_ref))),
['bar', 'baz', 'foo'])
# Make sure class weights can be given with string labels
lr_cv_str = LogisticRegression(solver='lbfgs',
class_weight={
'bar': 1,
'baz': 2,
'foo': 0
},
multi_class='multinomial').fit(
X_ref, y_str)
assert_equal(sorted(np.unique(lr_cv_str.predict(X_ref))), ['bar', 'baz'])
class LogisticRegressionCVImpl():
def __init__(self,
Cs=10,
fit_intercept=True,
cv=3,
dual=False,
penalty='l2',
scoring=None,
solver='lbfgs',
tol=0.0001,
max_iter=100,
class_weight='balanced',
n_jobs=None,
verbose=0,
refit=True,
intercept_scaling=1.0,
multi_class='ovr',
random_state=None):
self._hyperparams = {
'Cs': Cs,
'fit_intercept': fit_intercept,
'cv': cv,
'dual': dual,
'penalty': penalty,
'scoring': scoring,
'solver': solver,
'tol': tol,
'max_iter': max_iter,
'class_weight': class_weight,
'n_jobs': n_jobs,
'verbose': verbose,
'refit': refit,
'intercept_scaling': intercept_scaling,
'multi_class': multi_class,
'random_state': random_state
}
self._wrapped_model = SKLModel(**self._hyperparams)
def fit(self, X, y=None):
if (y is not None):
self._wrapped_model.fit(X, y)
else:
self._wrapped_model.fit(X)
return self
def predict(self, X):
return self._wrapped_model.predict(X)
def predict_proba(self, X):
return self._wrapped_model.predict_proba(X)
def decision_function(self, X):
return self._wrapped_model.decision_function(X)
def test_multinomial_logistic_regression_string_inputs():
# Test with string labels for LogisticRegression(CV)
n_samples, n_features, n_classes = 50, 5, 3
X_ref, y = make_classification(n_samples=n_samples, n_features=n_features,
n_classes=n_classes, n_informative=3,
random_state=0)
y_str = LabelEncoder().fit(['bar', 'baz', 'foo']).inverse_transform(y)
# For numerical labels, let y values be taken from set (-1, 0, 1)
y = np.array(y) - 1
# Test for string labels
lr = LogisticRegression(solver='lbfgs', multi_class='multinomial')
lr_cv = LogisticRegressionCV(solver='lbfgs', multi_class='multinomial')
lr_str = LogisticRegression(solver='lbfgs', multi_class='multinomial')
lr_cv_str = LogisticRegressionCV(solver='lbfgs', multi_class='multinomial')
lr.fit(X_ref, y)
lr_cv.fit(X_ref, y)
lr_str.fit(X_ref, y_str)
lr_cv_str.fit(X_ref, y_str)
assert_array_almost_equal(lr.coef_, lr_str.coef_)
assert_equal(sorted(lr_str.classes_), ['bar', 'baz', 'foo'])
assert_array_almost_equal(lr_cv.coef_, lr_cv_str.coef_)
assert_equal(sorted(lr_str.classes_), ['bar', 'baz', 'foo'])
assert_equal(sorted(lr_cv_str.classes_), ['bar', 'baz', 'foo'])
# The predictions should be in original labels
assert_equal(sorted(np.unique(lr_str.predict(X_ref))),
['bar', 'baz', 'foo'])
assert_equal(sorted(np.unique(lr_cv_str.predict(X_ref))),
['bar', 'baz', 'foo'])
# Make sure class weights can be given with string labels
lr_cv_str = LogisticRegression(
solver='lbfgs', class_weight={'bar': 1, 'baz': 2, 'foo': 0},
multi_class='multinomial').fit(X_ref, y_str)
assert_equal(sorted(np.unique(lr_cv_str.predict(X_ref))), ['bar', 'baz'])
# Random Forest
rf_clf = RandomForestClassifier(n_estimators=100, max_depth=2, random_state=0)
rf_clf.fit(X_train, y_train)
rf_predictions = rf_clf.predict(X_test)
score = accuracy_score(y_test, rf_predictions)
f_score = f1_score(y_test, rf_predictions, average='micro')
print("The accuracy score (Random Forest) is:", score)
print("The F score-Micro (Random Forest) is:", f_score)
from sklearn import metrics
# Logistic Regression
lr_classifier = LogisticRegressionCV()
lr_classifier.fit(X_train, y_train)
lt_predictions = lr_classifier.predict(X_test)
score = accuracy_score(y_test, lt_predictions)
f_score = f1_score(y_test, lt_predictions, average='micro')
print("The accuracy score (Logistic Regression) is:", score)
print("The F score-Micro (Logistic Regression) is:", f_score)
cnf_matrix = metrics.confusion_matrix(y_test, rf_predictions)
# import required modules
import seaborn as sns
class_names = [0, 1] # name of classes
fig, ax = plt.subplots()
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
