Python sklearn.neighbors.LocalOutlierFactor() Examples
The following are 20
code examples of sklearn.neighbors.LocalOutlierFactor().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
sklearn.neighbors
, or try the search function
.
Example #1
Source File: test_lof.py From Mastering-Elasticsearch-7.0 with MIT License | 7 votes |
def test_lof(): # Toy sample (the last two samples are outliers): X = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [5, 3], [-4, 2]] # Test LocalOutlierFactor: clf = neighbors.LocalOutlierFactor(n_neighbors=5) score = clf.fit(X).negative_outlier_factor_ assert_array_equal(clf._fit_X, X) # Assert largest outlier score is smaller than smallest inlier score: assert_greater(np.min(score[:-2]), np.max(score[-2:])) # Assert predict() works: clf = neighbors.LocalOutlierFactor(contamination=0.25, n_neighbors=5).fit(X) assert_array_equal(clf._predict(), 6 * [1] + 2 * [-1]) assert_array_equal(clf.fit_predict(X), 6 * [1] + 2 * [-1])
Example #2
Source File: test_lof.py From Mastering-Elasticsearch-7.0 with MIT License | 6 votes |
def test_lof_values(): # toy samples: X_train = [[1, 1], [1, 2], [2, 1]] clf1 = neighbors.LocalOutlierFactor(n_neighbors=2, contamination=0.1, novelty=True).fit(X_train) clf2 = neighbors.LocalOutlierFactor(n_neighbors=2, novelty=True).fit(X_train) s_0 = 2. * sqrt(2.) / (1. + sqrt(2.)) s_1 = (1. + sqrt(2)) * (1. / (4. * sqrt(2.)) + 1. / (2. + 2. * sqrt(2))) # check predict() assert_array_almost_equal(-clf1.negative_outlier_factor_, [s_0, s_1, s_1]) assert_array_almost_equal(-clf2.negative_outlier_factor_, [s_0, s_1, s_1]) # check predict(one sample not in train) assert_array_almost_equal(-clf1.score_samples([[2., 2.]]), [s_0]) assert_array_almost_equal(-clf2.score_samples([[2., 2.]]), [s_0]) # check predict(one sample already in train) assert_array_almost_equal(-clf1.score_samples([[1., 1.]]), [s_1]) assert_array_almost_equal(-clf2.score_samples([[1., 1.]]), [s_1])
Example #3
Source File: test_lof.py From Mastering-Elasticsearch-7.0 with MIT License | 6 votes |
def test_lof_precomputed(random_state=42): """Tests LOF with a distance matrix.""" # Note: smaller samples may result in spurious test success rng = np.random.RandomState(random_state) X = rng.random_sample((10, 4)) Y = rng.random_sample((3, 4)) DXX = metrics.pairwise_distances(X, metric='euclidean') DYX = metrics.pairwise_distances(Y, X, metric='euclidean') # As a feature matrix (n_samples by n_features) lof_X = neighbors.LocalOutlierFactor(n_neighbors=3, novelty=True) lof_X.fit(X) pred_X_X = lof_X._predict() pred_X_Y = lof_X.predict(Y) # As a dense distance matrix (n_samples by n_samples) lof_D = neighbors.LocalOutlierFactor(n_neighbors=3, algorithm='brute', metric='precomputed', novelty=True) lof_D.fit(DXX) pred_D_X = lof_D._predict() pred_D_Y = lof_D.predict(DYX) assert_array_almost_equal(pred_X_X, pred_D_X) assert_array_almost_equal(pred_X_Y, pred_D_Y)
Example #4
Source File: test_lof.py From twitter-stock-recommendation with MIT License | 6 votes |
def test_lof_precomputed(random_state=42): """Tests LOF with a distance matrix.""" # Note: smaller samples may result in spurious test success rng = np.random.RandomState(random_state) X = rng.random_sample((10, 4)) Y = rng.random_sample((3, 4)) DXX = metrics.pairwise_distances(X, metric='euclidean') DYX = metrics.pairwise_distances(Y, X, metric='euclidean') # As a feature matrix (n_samples by n_features) lof_X = neighbors.LocalOutlierFactor(n_neighbors=3) lof_X.fit(X) pred_X_X = lof_X._predict() pred_X_Y = lof_X._predict(Y) # As a dense distance matrix (n_samples by n_samples) lof_D = neighbors.LocalOutlierFactor(n_neighbors=3, algorithm='brute', metric='precomputed') lof_D.fit(DXX) pred_D_X = lof_D._predict() pred_D_Y = lof_D._predict(DYX) assert_array_almost_equal(pred_X_X, pred_D_X) assert_array_almost_equal(pred_X_Y, pred_D_Y)
Example #5
Source File: test_lof.py From twitter-stock-recommendation with MIT License | 6 votes |
def test_lof_performance(): # Generate train/test data rng = check_random_state(2) X = 0.3 * rng.randn(120, 2) X_train = X[:100] # Generate some abnormal novel observations X_outliers = rng.uniform(low=-4, high=4, size=(20, 2)) X_test = np.r_[X[100:], X_outliers] y_test = np.array([0] * 20 + [1] * 20) # fit the model clf = neighbors.LocalOutlierFactor().fit(X_train) # predict scores (the lower, the more normal) y_pred = -clf._decision_function(X_test) # check that roc_auc is good assert_greater(roc_auc_score(y_test, y_pred), .99)
Example #6
Source File: test_lof.py From Mastering-Elasticsearch-7.0 with MIT License | 6 votes |
def test_novelty_training_scores(): # check that the scores of the training samples are still accessible # when novelty=True through the negative_outlier_factor_ attribute X = iris.data # fit with novelty=False clf_1 = neighbors.LocalOutlierFactor() clf_1.fit(X) scores_1 = clf_1.negative_outlier_factor_ # fit with novelty=True clf_2 = neighbors.LocalOutlierFactor(novelty=True) clf_2.fit(X) scores_2 = clf_2.negative_outlier_factor_ assert_array_almost_equal(scores_1, scores_2)
Example #7
Source File: test_lof.py From Mastering-Elasticsearch-7.0 with MIT License | 6 votes |
def test_hasattr_prediction(): # check availability of prediction methods depending on novelty value. X = [[1, 1], [1, 2], [2, 1]] # when novelty=True clf = neighbors.LocalOutlierFactor(novelty=True) clf.fit(X) assert hasattr(clf, 'predict') assert hasattr(clf, 'decision_function') assert hasattr(clf, 'score_samples') assert not hasattr(clf, 'fit_predict') # when novelty=False clf = neighbors.LocalOutlierFactor(novelty=False) clf.fit(X) assert hasattr(clf, 'fit_predict') assert not hasattr(clf, 'predict') assert not hasattr(clf, 'decision_function') assert not hasattr(clf, 'score_samples')
Example #8
Source File: test_lof.py From twitter-stock-recommendation with MIT License | 6 votes |
def test_lof(): # Toy sample (the last two samples are outliers): X = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [5, 3], [-4, 2]] # Test LocalOutlierFactor: clf = neighbors.LocalOutlierFactor(n_neighbors=5) score = clf.fit(X).negative_outlier_factor_ assert_array_equal(clf._fit_X, X) # Assert largest outlier score is smaller than smallest inlier score: assert_greater(np.min(score[:-2]), np.max(score[-2:])) # Assert predict() works: clf = neighbors.LocalOutlierFactor(contamination=0.25, n_neighbors=5).fit(X) assert_array_equal(clf._predict(), 6 * [1] + 2 * [-1])
Example #9
Source File: test_lof.py From twitter-stock-recommendation with MIT License | 5 votes |
def test_n_neighbors_attribute(): X = iris.data clf = neighbors.LocalOutlierFactor(n_neighbors=500).fit(X) assert_equal(clf.n_neighbors_, X.shape[0] - 1) clf = neighbors.LocalOutlierFactor(n_neighbors=500) assert_warns_message(UserWarning, "n_neighbors will be set to (n_samples - 1)", clf.fit, X) assert_equal(clf.n_neighbors_, X.shape[0] - 1)
Example #10
Source File: lof.py From pyod with BSD 2-Clause "Simplified" License | 5 votes |
def fit(self, X, y=None): """Fit detector. y is ignored in unsupervised methods. Parameters ---------- X : numpy array of shape (n_samples, n_features) The input samples. y : Ignored Not used, present for API consistency by convention. Returns ------- self : object Fitted estimator. """ # validate inputs X and y (optional) X = check_array(X) self._set_n_classes(y) self.detector_ = LocalOutlierFactor(n_neighbors=self.n_neighbors, algorithm=self.algorithm, leaf_size=self.leaf_size, metric=self.metric, p=self.p, metric_params=self.metric_params, contamination=self.contamination, n_jobs=self.n_jobs) self.detector_.fit(X=X, y=y) # Invert decision_scores_. Outliers comes with higher outlier scores self.decision_scores_ = invert_order( self.detector_.negative_outlier_factor_) self._process_decision_scores() return self
Example #11
Source File: test_lof.py From twitter-stock-recommendation with MIT License | 5 votes |
def test_lof_values(): # toy samples: X_train = [[1, 1], [1, 2], [2, 1]] clf = neighbors.LocalOutlierFactor(n_neighbors=2).fit(X_train) s_0 = 2. * sqrt(2.) / (1. + sqrt(2.)) s_1 = (1. + sqrt(2)) * (1. / (4. * sqrt(2.)) + 1. / (2. + 2. * sqrt(2))) # check predict() assert_array_almost_equal(-clf.negative_outlier_factor_, [s_0, s_1, s_1]) # check predict(one sample not in train) assert_array_almost_equal(-clf._decision_function([[2., 2.]]), [s_0]) # # check predict(one sample already in train) assert_array_almost_equal(-clf._decision_function([[1., 1.]]), [s_1])
Example #12
Source File: lof.py From SecuML with GNU General Public License v2.0 | 5 votes |
def _get_pipeline(self): return [('scaler', StandardScaler()), ('model', LocalOutlierFactor(n_jobs=self.conf.n_jobs, novelty=True))]
Example #13
Source File: density_based.py From kenchi with BSD 3-Clause "New" or "Revised" License | 5 votes |
def _fit(self, X): self.estimator_ = LocalOutlierFactor( algorithm = self.algorithm, contamination = self.contamination, leaf_size = self.leaf_size, metric = self.metric, novelty = self.novelty, n_jobs = self.n_jobs, n_neighbors = self.n_neighbors, p = self.p, metric_params = self.metric_params ).fit(X) return self
Example #14
Source File: test_lof.py From Mastering-Elasticsearch-7.0 with MIT License | 5 votes |
def test_predicted_outlier_number(): # the number of predicted outliers should be equal to the number of # expected outliers unless there are ties in the abnormality scores. X = iris.data n_samples = X.shape[0] expected_outliers = 30 contamination = float(expected_outliers)/n_samples clf = neighbors.LocalOutlierFactor(contamination=contamination) y_pred = clf.fit_predict(X) num_outliers = np.sum(y_pred != 1) if num_outliers != expected_outliers: y_dec = clf.negative_outlier_factor_ check_outlier_corruption(num_outliers, expected_outliers, y_dec)
Example #15
Source File: test_lof.py From Mastering-Elasticsearch-7.0 with MIT License | 5 votes |
def test_novelty_true_common_tests(): # the common tests are run for the default LOF (novelty=False). # here we run these common tests for LOF when novelty=True check_estimator(neighbors.LocalOutlierFactor(novelty=True))
Example #16
Source File: test_lof.py From Mastering-Elasticsearch-7.0 with MIT License | 5 votes |
def test_novelty_errors(): X = iris.data # check errors for novelty=False clf = neighbors.LocalOutlierFactor() clf.fit(X) # predict, decision_function and score_samples raise ValueError for method in ['predict', 'decision_function', 'score_samples']: msg = ('{} is not available when novelty=False'.format(method)) assert_raises_regex(AttributeError, msg, getattr, clf, method) # check errors for novelty=True clf = neighbors.LocalOutlierFactor(novelty=True) msg = 'fit_predict is not available when novelty=True' assert_raises_regex(AttributeError, msg, getattr, clf, 'fit_predict')
Example #17
Source File: test_lof.py From Mastering-Elasticsearch-7.0 with MIT License | 5 votes |
def test_contamination(): X = [[1, 1], [1, 0]] clf = neighbors.LocalOutlierFactor(contamination=0.6) assert_raises(ValueError, clf.fit, X)
Example #18
Source File: test_lof.py From Mastering-Elasticsearch-7.0 with MIT License | 5 votes |
def test_n_neighbors_attribute(): X = iris.data clf = neighbors.LocalOutlierFactor(n_neighbors=500).fit(X) assert_equal(clf.n_neighbors_, X.shape[0] - 1) clf = neighbors.LocalOutlierFactor(n_neighbors=500) assert_warns_message(UserWarning, "n_neighbors will be set to (n_samples - 1)", clf.fit, X) assert_equal(clf.n_neighbors_, X.shape[0] - 1)
Example #19
Source File: test_lof.py From Mastering-Elasticsearch-7.0 with MIT License | 5 votes |
def test_lof_performance(): # Generate train/test data rng = check_random_state(2) X = 0.3 * rng.randn(120, 2) X_train = X[:100] # Generate some abnormal novel observations X_outliers = rng.uniform(low=-4, high=4, size=(20, 2)) X_test = np.r_[X[100:], X_outliers] y_test = np.array([0] * 20 + [1] * 20) # fit the model for novelty detection clf = neighbors.LocalOutlierFactor(novelty=True).fit(X_train) # predict scores (the lower, the more normal) y_pred = -clf.decision_function(X_test) # check that roc_auc is good assert_greater(roc_auc_score(y_test, y_pred), .99)
Example #20
Source File: create_dynamic_transforms.py From MOTSFusion with MIT License | 4 votes |
def remove_outliers(object_points): if len(object_points) > 100: points_t0 = object_points[:, 0] points_t1 = object_points[:, 1] mask = np.zeros(len(object_points), dtype=np.bool) # fit the model for outlier detection (default) for points in [points_t0, points_t1]: clf = LocalOutlierFactor(n_neighbors=20) clf.fit_predict(points) X_scores = clf.negative_outlier_factor_ X_scores = (X_scores.max() - X_scores) / (X_scores.max() - X_scores.min()) median_score = np.median(X_scores) mask = np.logical_or([X_scores[i] > median_score for i in range(len(points))], mask) # print(X_scores) # print('median_score ', mean_score) # plt.title("Local Outlier Factor (LOF)") # plt.scatter(points[:, 0], points[:, 2], color='k', s=3., label='Data points') # # plot circles with radius proportional to the outlier scores # plt.scatter(points[:, 0], points[:, 2], s=1000 * X_scores, edgecolors='r', # facecolors='none', label='Outlier scores') # plt.axis('tight') # plt.xlim((-5, 5)) # plt.ylim((-5, 5)) # legend = plt.legend(loc='upper left') # legend.legendHandles[0]._sizes = [10] # legend.legendHandles[1]._sizes = [20] # points = points[np.logical_not(mask)] # X_scores = X_scores[np.logical_not(mask)] # plt.title("Local Outlier Factor (LOF)") # plt.scatter(points[:, 0], points[:, 2], color='k', s=3., label='Data points') # # plot circles with radius proportional to the outlier scores # plt.scatter(points[:, 0], points[:, 2], s=1000 * X_scores, edgecolors='r', # facecolors='none', label='Outlier scores') # plt.axis('tight') # plt.xlim((-5, 5)) # plt.ylim((-5, 5)) # legend = plt.legend(loc='upper left') # legend.legendHandles[0]._sizes = [10] # legend.legendHandles[1]._sizes = [20] # plt.show() if len(object_points[np.logical_not(mask)]) > 10: object_points = object_points[np.logical_not(mask)] return object_points