Python sklearn.linear_model.PassiveAggressiveClassifier() Examples

def passive_aggressive_train(self):
		'''Trains passive aggressive classifier

		'''
		self._clf = PassiveAggressiveClassifier(n_iter=50, C=0.2, n_jobs=-1, random_state=0)
		self._clf.fit(self._term_doc_matrix._X, self._term_doc_matrix._y)
		y_dist = self._clf.decision_function(self._term_doc_matrix._X)
		pos_ecdf = ECDF(y_dist[y_dist >= 0])
		neg_ecdf = ECDF(y_dist[y_dist <= 0])

		def proba_function(distance_from_hyperplane):
			if distance_from_hyperplane > 0:
				return pos_ecdf(distance_from_hyperplane) / 2. + 0.5
			elif distance_from_hyperplane < 0:
				return pos_ecdf(distance_from_hyperplane) / 2.
			return 0.5

		self._proba = proba_function
		return self 

def test_class_weights():
    # Test class weights.
    X2 = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0],
                   [1.0, 1.0], [1.0, 0.0]])
    y2 = [1, 1, 1, -1, -1]

    clf = PassiveAggressiveClassifier(C=0.1, max_iter=100, class_weight=None,
                                      random_state=100)
    clf.fit(X2, y2)
    assert_array_equal(clf.predict([[0.2, -1.0]]), np.array([1]))

    # we give a small weights to class 1
    clf = PassiveAggressiveClassifier(C=0.1, max_iter=100,
                                      class_weight={1: 0.001},
                                      random_state=100)
    clf.fit(X2, y2)

    # now the hyperplane should rotate clock-wise and
    # the prediction on this point should shift
    assert_array_equal(clf.predict([[0.2, -1.0]]), np.array([-1])) 

def test_classifier_correctness():
    y_bin = y.copy()
    y_bin[y != 1] = -1

    for loss in ("hinge", "squared_hinge"):

        clf1 = MyPassiveAggressive(
            C=1.0, loss=loss, fit_intercept=True, n_iter=2)
        clf1.fit(X, y_bin)

        for data in (X, X_csr):
            clf2 = PassiveAggressiveClassifier(
                C=1.0, loss=loss, fit_intercept=True, max_iter=2,
                shuffle=False, tol=None)
            clf2.fit(data, y_bin)

            assert_array_almost_equal(clf1.w, clf2.coef_.ravel(), decimal=2) 

def test_learning_curve_batch_and_incremental_learning_are_equal():
    X, y = make_classification(n_samples=30, n_features=1, n_informative=1,
                               n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    train_sizes = np.linspace(0.2, 1.0, 5)
    estimator = PassiveAggressiveClassifier(max_iter=1, tol=None,
                                            shuffle=False)

    train_sizes_inc, train_scores_inc, test_scores_inc = \
        learning_curve(
            estimator, X, y, train_sizes=train_sizes,
            cv=3, exploit_incremental_learning=True)
    train_sizes_batch, train_scores_batch, test_scores_batch = \
        learning_curve(
            estimator, X, y, cv=3, train_sizes=train_sizes,
            exploit_incremental_learning=False)

    assert_array_equal(train_sizes_inc, train_sizes_batch)
    assert_array_almost_equal(train_scores_inc.mean(axis=1),
                              train_scores_batch.mean(axis=1))
    assert_array_almost_equal(test_scores_inc.mean(axis=1),
                              test_scores_batch.mean(axis=1)) 

def test_learning_curve_batch_and_incremental_learning_are_equal():
    X, y = make_classification(n_samples=30, n_features=1, n_informative=1,
                               n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    train_sizes = np.linspace(0.2, 1.0, 5)
    estimator = PassiveAggressiveClassifier(max_iter=1, tol=None,
                                            shuffle=False)

    train_sizes_inc, train_scores_inc, test_scores_inc = \
        learning_curve(
            estimator, X, y, train_sizes=train_sizes,
            cv=3, exploit_incremental_learning=True)
    train_sizes_batch, train_scores_batch, test_scores_batch = \
        learning_curve(
            estimator, X, y, cv=3, train_sizes=train_sizes,
            exploit_incremental_learning=False)

    assert_array_equal(train_sizes_inc, train_sizes_batch)
    assert_array_almost_equal(train_scores_inc.mean(axis=1),
                              train_scores_batch.mean(axis=1))
    assert_array_almost_equal(test_scores_inc.mean(axis=1),
                              test_scores_batch.mean(axis=1)) 

def test_partial_fit():
    est = PassiveAggressiveClassifier(random_state=0, shuffle=False,
                                      max_iter=5, tol=None)
    transformer = SelectFromModel(estimator=est)
    transformer.partial_fit(data, y,
                            classes=np.unique(y))
    old_model = transformer.estimator_
    transformer.partial_fit(data, y,
                            classes=np.unique(y))
    new_model = transformer.estimator_
    assert_true(old_model is new_model)

    X_transform = transformer.transform(data)
    transformer.fit(np.vstack((data, data)), np.concatenate((y, y)))
    assert_array_equal(X_transform, transformer.transform(data))

    # check that if est doesn't have partial_fit, neither does SelectFromModel
    transformer = SelectFromModel(estimator=RandomForestClassifier())
    assert_false(hasattr(transformer, "partial_fit")) 

def test_model_passive_aggressive_classifier_multi_class_int(self):
        model, X = fit_classification_model(
            PassiveAggressiveClassifier(random_state=42), 5, is_int=True)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn PassiveAggressiveClassifier multi-class",
            [("input", Int64TensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnPassiveAggressiveClassifierMultiInt-Out0",
            allow_failure="StrictVersion(onnx.__version__)"
                          " < StrictVersion('1.2') or "
                          "StrictVersion(onnxruntime.__version__)"
                          " <= StrictVersion('0.2.1')",
        ) 

def test_model_passive_aggressive_classifier_binary_class_int(self):
        model, X = fit_classification_model(
            PassiveAggressiveClassifier(random_state=42), 2, is_int=True)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn PassiveAggressiveClassifier binary",
            [("input", Int64TensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnPassiveAggressiveClassifierBinaryInt-Out0",
            allow_failure="StrictVersion(onnx.__version__)"
                          " < StrictVersion('1.2') or "
                          "StrictVersion(onnxruntime.__version__)"
                          " <= StrictVersion('0.2.1')",
        ) 

def test_model_passive_aggressive_classifier_multi_class(self):
        model, X = fit_classification_model(
            PassiveAggressiveClassifier(random_state=42), 5)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn PassiveAggressiveClassifier multi-class",
            [("input", FloatTensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnPassiveAggressiveClassifierMulti-Out0",
            allow_failure="StrictVersion(onnx.__version__)"
                          " < StrictVersion('1.2') or "
                          "StrictVersion(onnxruntime.__version__)"
                          " <= StrictVersion('0.2.1')",
        ) 

def test_model_passive_aggressive_classifier_binary_class(self):
        model, X = fit_classification_model(
            PassiveAggressiveClassifier(random_state=42), 2)
        model_onnx = convert_sklearn(
            model,
            "scikit-learn PassiveAggressiveClassifier binary",
            [("input", FloatTensorType([None, X.shape[1]]))],
            target_opset=TARGET_OPSET
        )
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnPassiveAggressiveClassifierBinary-Out0",
            allow_failure="StrictVersion(onnx.__version__)"
                          " < StrictVersion('1.2') or "
                          "StrictVersion(onnxruntime.__version__)"
                          " <= StrictVersion('0.2.1')",
        ) 

def test_equal_class_weight():
    X2 = [[1, 0], [1, 0], [0, 1], [0, 1]]
    y2 = [0, 0, 1, 1]
    clf = PassiveAggressiveClassifier(
        C=0.1, max_iter=1000, tol=None, class_weight=None)
    clf.fit(X2, y2)

    # Already balanced, so "balanced" weights should have no effect
    clf_balanced = PassiveAggressiveClassifier(
        C=0.1, max_iter=1000, tol=None, class_weight="balanced")
    clf_balanced.fit(X2, y2)

    clf_weighted = PassiveAggressiveClassifier(
        C=0.1, max_iter=1000, tol=None, class_weight={0: 0.5, 1: 0.5})
    clf_weighted.fit(X2, y2)

    # should be similar up to some epsilon due to learning rate schedule
    assert_almost_equal(clf.coef_, clf_weighted.coef_, decimal=2)
    assert_almost_equal(clf.coef_, clf_balanced.coef_, decimal=2)


# 0.23. warning about tol not having its correct default value. 

def test_class_weights():
    # Test class weights.
    X2 = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0],
                   [1.0, 1.0], [1.0, 0.0]])
    y2 = [1, 1, 1, -1, -1]

    clf = PassiveAggressiveClassifier(C=0.1, max_iter=100, class_weight=None,
                                      random_state=100)
    clf.fit(X2, y2)
    assert_array_equal(clf.predict([[0.2, -1.0]]), np.array([1]))

    # we give a small weights to class 1
    clf = PassiveAggressiveClassifier(C=0.1, max_iter=100,
                                      class_weight={1: 0.001},
                                      random_state=100)
    clf.fit(X2, y2)

    # now the hyperplane should rotate clock-wise and
    # the prediction on this point should shift
    assert_array_equal(clf.predict([[0.2, -1.0]]), np.array([-1]))


# 0.23. warning about tol not having its correct default value. 

def test_main(self):
		categories, documents = get_docs_categories()
		clean_function = lambda text: '' if text.startswith('[') else text
		entity_types = set(['GPE'])
		term_doc_mat = (
			TermDocMatrixFactory(
				category_text_iter=zip(categories, documents),
				clean_function=clean_function,
				nlp=_testing_nlp,
				feats_from_spacy_doc=FeatsFromSpacyDoc(entity_types_to_censor=entity_types)
			).build()
		)
		clf = PassiveAggressiveClassifier()
		fdc = FeatsFromDoc(term_doc_mat._term_idx_store,
		                   clean_function=clean_function,
		                   feats_from_spacy_doc=FeatsFromSpacyDoc(
			                   entity_types_to_censor=entity_types)).set_nlp(_testing_nlp)
		tfidf = TfidfTransformer(norm='l1')
		X = tfidf.fit_transform(term_doc_mat._X)
		clf.fit(X, term_doc_mat._y)
		X_to_predict = fdc.feats_from_doc('Did sometimes march UNKNOWNWORD')
		pred = clf.predict(tfidf.transform(X_to_predict))
		dec = clf.decision_function(X_to_predict) 

def test_classifier_partial_fit():
    classes = np.unique(y)
    for data in (X, X_csr):
        for average in (False, True):
            clf = PassiveAggressiveClassifier(
                C=1.0, fit_intercept=True, random_state=0,
                average=average, max_iter=5)
            for t in range(30):
                clf.partial_fit(data, y, classes)
            score = clf.score(data, y)
            assert_greater(score, 0.79)
            if average:
                assert hasattr(clf, 'average_coef_')
                assert hasattr(clf, 'average_intercept_')
                assert hasattr(clf, 'standard_intercept_')
                assert hasattr(clf, 'standard_coef_')


# 0.23. warning about tol not having its correct default value. 

def test_classifier_accuracy():
    for data in (X, X_csr):
        for fit_intercept in (True, False):
            for average in (False, True):
                clf = PassiveAggressiveClassifier(
                    C=1.0, max_iter=30, fit_intercept=fit_intercept,
                    random_state=1, average=average, tol=None)
                clf.fit(data, y)
                score = clf.score(data, y)
                assert_greater(score, 0.79)
                if average:
                    assert hasattr(clf, 'average_coef_')
                    assert hasattr(clf, 'average_intercept_')
                    assert hasattr(clf, 'standard_intercept_')
                    assert hasattr(clf, 'standard_coef_')


# 0.23. warning about tol not having its correct default value. 

def test_partial_fit():
    est = PassiveAggressiveClassifier(random_state=0, shuffle=False,
                                      max_iter=5, tol=None)
    transformer = SelectFromModel(estimator=est)
    transformer.partial_fit(data, y,
                            classes=np.unique(y))
    old_model = transformer.estimator_
    transformer.partial_fit(data, y,
                            classes=np.unique(y))
    new_model = transformer.estimator_
    assert old_model is new_model

    X_transform = transformer.transform(data)
    transformer.fit(np.vstack((data, data)), np.concatenate((y, y)))
    assert_array_almost_equal(X_transform, transformer.transform(data))

    # check that if est doesn't have partial_fit, neither does SelectFromModel
    transformer = SelectFromModel(estimator=RandomForestClassifier())
    assert not hasattr(transformer, "partial_fit") 

def test_learning_curve_batch_and_incremental_learning_are_equal():
    X, y = make_classification(n_samples=30, n_features=1, n_informative=1,
                               n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    train_sizes = np.linspace(0.2, 1.0, 5)
    estimator = PassiveAggressiveClassifier(max_iter=1, tol=None,
                                            shuffle=False)

    train_sizes_inc, train_scores_inc, test_scores_inc = \
        learning_curve(
            estimator, X, y, train_sizes=train_sizes,
            cv=3, exploit_incremental_learning=True)
    train_sizes_batch, train_scores_batch, test_scores_batch = \
        learning_curve(
            estimator, X, y, cv=3, train_sizes=train_sizes,
            exploit_incremental_learning=False)

    assert_array_equal(train_sizes_inc, train_sizes_batch)
    assert_array_almost_equal(train_scores_inc.mean(axis=1),
                              train_scores_batch.mean(axis=1))
    assert_array_almost_equal(test_scores_inc.mean(axis=1),
                              test_scores_batch.mean(axis=1)) 

def test_learning_curve_with_shuffle():
    # Following test case was designed this way to verify the code
    # changes made in pull request: #7506.
    X = np.array([[1, 2], [3, 4], [5, 6], [7, 8], [11, 12], [13, 14], [15, 16],
                 [17, 18], [19, 20], [7, 8], [9, 10], [11, 12], [13, 14],
                 [15, 16], [17, 18]])
    y = np.array([1, 1, 1, 2, 3, 4, 1, 1, 2, 3, 4, 1, 2, 3, 4])
    groups = np.array([1, 1, 1, 1, 1, 1, 3, 3, 3, 3, 3, 4, 4, 4, 4])
    # Splits on these groups fail without shuffle as the first iteration
    # of the learning curve doesn't contain label 4 in the training set.
    estimator = PassiveAggressiveClassifier(max_iter=5, tol=None,
                                            shuffle=False)

    cv = GroupKFold(n_splits=2)
    train_sizes_batch, train_scores_batch, test_scores_batch = learning_curve(
        estimator, X, y, cv=cv, n_jobs=1, train_sizes=np.linspace(0.3, 1.0, 3),
        groups=groups, shuffle=True, random_state=2)
    assert_array_almost_equal(train_scores_batch.mean(axis=1),
                              np.array([0.75, 0.3, 0.36111111]))
    assert_array_almost_equal(test_scores_batch.mean(axis=1),
                              np.array([0.36111111, 0.25, 0.25]))
    assert_raises(ValueError, learning_curve, estimator, X, y, cv=cv, n_jobs=1,
                  train_sizes=np.linspace(0.3, 1.0, 3), groups=groups)

    train_sizes_inc, train_scores_inc, test_scores_inc = learning_curve(
        estimator, X, y, cv=cv, n_jobs=1, train_sizes=np.linspace(0.3, 1.0, 3),
        groups=groups, shuffle=True, random_state=2,
        exploit_incremental_learning=True)
    assert_array_almost_equal(train_scores_inc.mean(axis=1),
                              train_scores_batch.mean(axis=1))
    assert_array_almost_equal(test_scores_inc.mean(axis=1),
                              test_scores_batch.mean(axis=1)) 

def test_wrong_class_weight_format():
    # ValueError due to wrong class_weight argument type.
    X2 = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0],
                   [1.0, 1.0], [1.0, 0.0]])
    y2 = [1, 1, 1, -1, -1]

    clf = PassiveAggressiveClassifier(class_weight=[0.5], max_iter=100)
    assert_raises(ValueError, clf.fit, X2, y2)

    clf = PassiveAggressiveClassifier(class_weight="the larch", max_iter=100)
    assert_raises(ValueError, clf.fit, X2, y2) 

def test_wrong_class_weight_label():
    # ValueError due to wrong class_weight label.
    X2 = np.array([[-1.0, -1.0], [-1.0, 0], [-.8, -1.0],
                   [1.0, 1.0], [1.0, 0.0]])
    y2 = [1, 1, 1, -1, -1]

    clf = PassiveAggressiveClassifier(class_weight={0: 0.5}, max_iter=100)
    assert_raises(ValueError, clf.fit, X2, y2) 

def test_partial_fit_weight_class_balanced():
    # partial_fit with class_weight='balanced' not supported
    clf = PassiveAggressiveClassifier(class_weight="balanced", max_iter=100)
    assert_raises(ValueError, clf.partial_fit, X, y, classes=np.unique(y)) 

def test_classifier_undefined_methods():
    clf = PassiveAggressiveClassifier(max_iter=100)
    for meth in ("predict_proba", "predict_log_proba", "transform"):
        assert_raises(AttributeError, lambda x: getattr(clf, x), meth) 

def test_classifier_refit():
    # Classifier can be retrained on different labels and features.
    clf = PassiveAggressiveClassifier(max_iter=5).fit(X, y)
    assert_array_equal(clf.classes_, np.unique(y))

    clf.fit(X[:, :-1], iris.target_names[y])
    assert_array_equal(clf.classes_, iris.target_names) 

def test_classifier_accuracy():
    for data in (X, X_csr):
        for fit_intercept in (True, False):
            for average in (False, True):
                clf = PassiveAggressiveClassifier(
                    C=1.0, max_iter=30, fit_intercept=fit_intercept,
                    random_state=0, average=average, tol=None)
                clf.fit(data, y)
                score = clf.score(data, y)
                assert_greater(score, 0.79)
                if average:
                    assert_true(hasattr(clf, 'average_coef_'))
                    assert_true(hasattr(clf, 'average_intercept_'))
                    assert_true(hasattr(clf, 'standard_intercept_'))
                    assert_true(hasattr(clf, 'standard_coef_')) 

def test_partial_fit_weight_class_balanced():
    # partial_fit with class_weight='balanced' not supported
    clf = PassiveAggressiveClassifier(class_weight="balanced", max_iter=100)
    assert_raises(ValueError, clf.partial_fit, X, y, classes=np.unique(y))


# 0.23. warning about tol not having its correct default value. 

def test_learning_curve_with_shuffle():
    # Following test case was designed this way to verify the code
    # changes made in pull request: #7506.
    X = np.array([[1, 2], [3, 4], [5, 6], [7, 8], [11, 12], [13, 14], [15, 16],
                 [17, 18], [19, 20], [7, 8], [9, 10], [11, 12], [13, 14],
                 [15, 16], [17, 18]])
    y = np.array([1, 1, 1, 2, 3, 4, 1, 1, 2, 3, 4, 1, 2, 3, 4])
    groups = np.array([1, 1, 1, 1, 1, 1, 3, 3, 3, 3, 3, 4, 4, 4, 4])
    # Splits on these groups fail without shuffle as the first iteration
    # of the learning curve doesn't contain label 4 in the training set.
    estimator = PassiveAggressiveClassifier(max_iter=5, tol=None,
                                            shuffle=False)

    cv = GroupKFold(n_splits=2)
    train_sizes_batch, train_scores_batch, test_scores_batch = learning_curve(
        estimator, X, y, cv=cv, n_jobs=1, train_sizes=np.linspace(0.3, 1.0, 3),
        groups=groups, shuffle=True, random_state=2)
    assert_array_almost_equal(train_scores_batch.mean(axis=1),
                              np.array([0.75, 0.3, 0.36111111]))
    assert_array_almost_equal(test_scores_batch.mean(axis=1),
                              np.array([0.36111111, 0.25, 0.25]))
    assert_raises(ValueError, learning_curve, estimator, X, y, cv=cv, n_jobs=1,
                  train_sizes=np.linspace(0.3, 1.0, 3), groups=groups,
                  error_score='raise')

    train_sizes_inc, train_scores_inc, test_scores_inc = learning_curve(
        estimator, X, y, cv=cv, n_jobs=1, train_sizes=np.linspace(0.3, 1.0, 3),
        groups=groups, shuffle=True, random_state=2,
        exploit_incremental_learning=True)
    assert_array_almost_equal(train_scores_inc.mean(axis=1),
                              train_scores_batch.mean(axis=1))
    assert_array_almost_equal(test_scores_inc.mean(axis=1),
                              test_scores_batch.mean(axis=1)) 

def test_objectmapper(self):
        df = pdml.ModelFrame([])
        self.assertIs(df.linear_model.ARDRegression, lm.ARDRegression)
        self.assertIs(df.linear_model.BayesianRidge, lm.BayesianRidge)
        self.assertIs(df.linear_model.ElasticNet, lm.ElasticNet)
        self.assertIs(df.linear_model.ElasticNetCV, lm.ElasticNetCV)

        self.assertIs(df.linear_model.HuberRegressor, lm.HuberRegressor)

        self.assertIs(df.linear_model.Lars, lm.Lars)
        self.assertIs(df.linear_model.LarsCV, lm.LarsCV)
        self.assertIs(df.linear_model.Lasso, lm.Lasso)
        self.assertIs(df.linear_model.LassoCV, lm.LassoCV)
        self.assertIs(df.linear_model.LassoLars, lm.LassoLars)
        self.assertIs(df.linear_model.LassoLarsCV, lm.LassoLarsCV)
        self.assertIs(df.linear_model.LassoLarsIC, lm.LassoLarsIC)

        self.assertIs(df.linear_model.LinearRegression, lm.LinearRegression)
        self.assertIs(df.linear_model.LogisticRegression, lm.LogisticRegression)
        self.assertIs(df.linear_model.LogisticRegressionCV, lm.LogisticRegressionCV)
        self.assertIs(df.linear_model.MultiTaskLasso, lm.MultiTaskLasso)
        self.assertIs(df.linear_model.MultiTaskElasticNet, lm.MultiTaskElasticNet)
        self.assertIs(df.linear_model.MultiTaskLassoCV, lm.MultiTaskLassoCV)
        self.assertIs(df.linear_model.MultiTaskElasticNetCV, lm.MultiTaskElasticNetCV)

        self.assertIs(df.linear_model.OrthogonalMatchingPursuit, lm.OrthogonalMatchingPursuit)
        self.assertIs(df.linear_model.OrthogonalMatchingPursuitCV, lm.OrthogonalMatchingPursuitCV)
        self.assertIs(df.linear_model.PassiveAggressiveClassifier, lm.PassiveAggressiveClassifier)
        self.assertIs(df.linear_model.PassiveAggressiveRegressor, lm.PassiveAggressiveRegressor)

        self.assertIs(df.linear_model.Perceptron, lm.Perceptron)
        self.assertIs(df.linear_model.RandomizedLasso, lm.RandomizedLasso)
        self.assertIs(df.linear_model.RandomizedLogisticRegression, lm.RandomizedLogisticRegression)
        self.assertIs(df.linear_model.RANSACRegressor, lm.RANSACRegressor)
        self.assertIs(df.linear_model.Ridge, lm.Ridge)
        self.assertIs(df.linear_model.RidgeClassifier, lm.RidgeClassifier)
        self.assertIs(df.linear_model.RidgeClassifierCV, lm.RidgeClassifierCV)
        self.assertIs(df.linear_model.RidgeCV, lm.RidgeCV)
        self.assertIs(df.linear_model.SGDClassifier, lm.SGDClassifier)
        self.assertIs(df.linear_model.SGDRegressor, lm.SGDRegressor)
        self.assertIs(df.linear_model.TheilSenRegressor, lm.TheilSenRegressor) 

def test_classifier_correctness(loss):
    y_bin = y.copy()
    y_bin[y != 1] = -1

    clf1 = MyPassiveAggressive(
        C=1.0, loss=loss, fit_intercept=True, n_iter=2)
    clf1.fit(X, y_bin)

    for data in (X, X_csr):
        clf2 = PassiveAggressiveClassifier(
            C=1.0, loss=loss, fit_intercept=True, max_iter=2,
            shuffle=False, tol=None)
        clf2.fit(data, y_bin)

        assert_array_almost_equal(clf1.w, clf2.coef_.ravel(), decimal=2) 

def test_classifier_undefined_methods():
    clf = PassiveAggressiveClassifier(max_iter=100)
    for meth in ("predict_proba", "predict_log_proba", "transform"):
        assert_raises(AttributeError, lambda x: getattr(clf, x), meth)


# 0.23. warning about tol not having its correct default value. 

def get_baseline_pa(dataset,train_label_list,test_label_list,verbose=True):
    (X_train, Y_train), (X_test, Y_test) = dataset
    classifier = PassiveAggressiveClassifier(n_jobs=-1,fit_intercept=True)
    classifier.fit(X_train,train_label_list)
    accuracy = classifier.score(X_test,test_label_list)
    
    if verbose:
        print('Got baseline of %f with Passive Aggressive classifier'%accuracy)

    return accuracy