How to use pyod - 10 common examples

model.fit(X_train)  # fit all models with X
    model.approximate(X_train)  # conduct model approximation if it is enabled
    predicted_labels = model.predict(X_test)  # predict labels
    predicted_scores = model.decision_function(X_test)  # predict scores
    predicted_probs = model.predict_proba(X_test)  # predict scores

    ###########################################################################
    # compared with other approaches
    evaluate_print('majority vote', y_test, majority_vote(predicted_labels))
    evaluate_print('average', y_test, average(predicted_scores))
    evaluate_print('maximization', y_test, maximization(predicted_scores))

    clf = LOF()
    clf.fit(X_train)
    evaluate_print('LOF', y_test, clf.decision_function(X_test))

    clf = IForest()
    clf.fit(X_train)
    evaluate_print('IForest', y_test, clf.decision_function(X_test))

for i in range(n_clf):
        k = k_list[i]

        clf = KNN(n_neighbors=k, method='largest')
        clf.fit(X_train_norm)

        train_scores[:, i] = clf.decision_scores_
        test_scores[:, i] = clf.decision_function(X_test_norm)

    # Decision scores have to be normalized before combination
    train_scores_norm, test_scores_norm = standardizer(train_scores,
                                                       test_scores)
    # Combination by average
    y_by_average = average(test_scores_norm)
    evaluate_print('Combination by Average', y_test, y_by_average)

    # Combination by max
    y_by_maximization = maximization(test_scores_norm)
    evaluate_print('Combination by Maximization', y_test, y_by_maximization)

    # Combination by max
    y_by_maximization = median(test_scores_norm)
    evaluate_print('Combination by Median', y_test, y_by_maximization)

    # Combination by aom
    y_by_aom = aom(test_scores_norm, n_buckets=5)
    evaluate_print('Combination by AOM', y_test, y_by_aom)

    # Combination by moa
    y_by_moa = moa(test_scores_norm, n_buckets=5)
    evaluate_print('Combination by MOA', y_test, y_by_moa)

clf = LOF()
    clf.fit(X_train)

    # get the prediction labels and outlier scores of the training data
    y_train_pred = clf.labels_  # binary labels (0: inliers, 1: outliers)
    y_train_scores = clf.decision_scores_  # raw outlier scores

    # get the prediction on the test data
    y_test_pred = clf.predict(X_test)  # outlier labels (0 or 1)
    y_test_scores = clf.decision_function(X_test)  # outlier scores

    # evaluate and print the results
    print("\nOn Training Data:")
    evaluate_print(clf_name, y_train, y_train_scores)
    print("\nOn Test Data:")
    evaluate_print(clf_name, y_test, y_test_scores)

    # visualize the results
    visualize(clf_name, X_train, y_train, X_test, y_test, y_train_pred,
              y_test_pred, show_figure=True, save_figure=False)

# train COF detector
    clf_name = 'COF'
    clf = COF(n_neighbors=30)
    clf.fit(X_train)

    # get the prediction labels and outlier scores of the training data
    y_train_pred = clf.labels_  # binary labels (0: inliers, 1: outliers)
    y_train_scores = clf.decision_scores_  # raw outlier scores

    # get the prediction on the test data
    y_test_pred = clf.predict(X_test)  # outlier labels (0 or 1)
    y_test_scores = clf.decision_function(X_test)  # outlier scores

    # evaluate and print the results
    print("\nOn Training Data:")
    evaluate_print(clf_name, y_train, y_train_scores)
    print("\nOn Test Data:")
    evaluate_print(clf_name, y_test, y_test_scores)

    # visualize the results
    visualize(clf_name, X_train, y_train, X_test, y_test, y_train_pred,
              y_test_pred, show_figure=True, save_figure=False)

clf = OCSVM()
    clf.fit(X_train)

    # get the prediction labels and outlier scores of the training data
    y_train_pred = clf.labels_  # binary labels (0: inliers, 1: outliers)
    y_train_scores = clf.decision_scores_  # raw outlier scores

    # get the prediction on the test data
    y_test_pred = clf.predict(X_test)  # outlier labels (0 or 1)
    y_test_scores = clf.decision_function(X_test)  # outlier scores

    # evaluate and print the results
    print("\nOn Training Data:")
    evaluate_print(clf_name, y_train, y_train_scores)
    print("\nOn Test Data:")
    evaluate_print(clf_name, y_test, y_test_scores)

    # visualize the results
    visualize(clf_name, X_train, y_train, X_test, y_test, y_train_pred,
              y_test_pred, show_figure=True, save_figure=False)

# train HBOS detector
    clf_name = 'HBOS'
    clf = HBOS()
    clf.fit(X_train)

    # get the prediction labels and outlier scores of the training data
    y_train_pred = clf.labels_  # binary labels (0: inliers, 1: outliers)
    y_train_scores = clf.decision_scores_  # raw outlier scores

    # get the prediction on the test data
    y_test_pred = clf.predict(X_test)  # outlier labels (0 or 1)
    y_test_scores = clf.decision_function(X_test)  # outlier scores

    # evaluate and print the results
    print("\nOn Training Data:")
    evaluate_print(clf_name, y_train, y_train_scores)
    print("\nOn Test Data:")
    evaluate_print(clf_name, y_test, y_test_scores)

    # visualize the results
    visualize(clf_name, X_train, y_train, X_test, y_test, y_train_pred,
              y_test_pred, show_figure=True, save_figure=False)

clf = SO_GAAL(contamination=contamination)
    clf.fit(X_train)

    # get the prediction labels and outlier scores of the training data
    y_train_pred = clf.labels_  # binary labels (0: inliers, 1: outliers)
    y_train_scores = clf.decision_scores_  # raw outlier scores

    # get the prediction on the test data
    y_test_pred = clf.predict(X_test)  # outlier labels (0 or 1)
    y_test_scores = clf.decision_function(X_test)  # outlier scores

    # evaluate and print the results
    print("\nOn Training Data:")
    evaluate_print(clf_name, y_train, y_train_scores)
    print("\nOn Test Data:")
    evaluate_print(clf_name, y_test, y_test_scores)

def _fit_fast(self):
        """Fast ABOD method. Only use n_neighbors for angle calculation.
        Internal use only
        """

        # make sure the n_neighbors is in the range
        check_parameter(self.n_neighbors, 1, self.n_train_)

        self.tree_ = KDTree(self.X_train_)

        neigh = NearestNeighbors(n_neighbors=self.n_neighbors)
        neigh.fit(self.X_train_)
        ind_arr = neigh.kneighbors(n_neighbors=self.n_neighbors,
                                   return_distance=False)

        for i in range(self.n_train_):
            curr_pt = self.X_train_[i, :]
            X_ind = ind_arr[i, :]
            self.decision_scores_[i, 0] = _calculate_wocs(curr_pt,
                                                          self.X_train_,
                                                          X_ind)
        return self

model = SUOD(base_estimators=base_estimators, n_jobs=6, bps_flag=True,
                 contamination=contamination, approx_flag_global=True)

    model.fit(X_train)  # fit all models with X
    model.approximate(X_train)  # conduct model approximation if it is enabled
    predicted_labels = model.predict(X_test)  # predict labels
    predicted_scores = model.decision_function(X_test)  # predict scores
    predicted_probs = model.predict_proba(X_test)  # predict scores

    ###########################################################################
    # compared with other approaches
    evaluate_print('majority vote', y_test, majority_vote(predicted_labels))
    evaluate_print('average', y_test, average(predicted_scores))
    evaluate_print('maximization', y_test, maximization(predicted_scores))

    clf = LOF()
    clf.fit(X_train)
    evaluate_print('LOF', y_test, clf.decision_function(X_test))

    clf = IForest()
    clf.fit(X_train)
    evaluate_print('IForest', y_test, clf.decision_function(X_test))

LOF(n_neighbors=15, contamination=contamination),
        LOF(n_neighbors=25, contamination=contamination),
        LOF(n_neighbors=35, contamination=contamination),
        LOF(n_neighbors=45, contamination=contamination),
        HBOS(contamination=contamination),
        PCA(contamination=contamination),
        OCSVM(contamination=contamination),
        KNN(n_neighbors=5, contamination=contamination),
        KNN(n_neighbors=15, contamination=contamination),
        KNN(n_neighbors=25, contamination=contamination),
        KNN(n_neighbors=35, contamination=contamination),
        KNN(n_neighbors=45, contamination=contamination),
        IForest(n_estimators=50, contamination=contamination),
        IForest(n_estimators=100, contamination=contamination),
        LSCP(detector_list=[LOF(contamination=contamination),
                            LOF(contamination=contamination)])
    ]

    model = SUOD(base_estimators=base_estimators, n_jobs=6, bps_flag=True,
                 contamination=contamination, approx_flag_global=True)

    model.fit(X_train)  # fit all models with X
    model.approximate(X_train)  # conduct model approximation if it is enabled
    predicted_labels = model.predict(X_test)  # predict labels
    predicted_scores = model.decision_function(X_test)  # predict scores
    predicted_probs = model.predict_proba(X_test)  # predict scores

    ###########################################################################
    # compared with other approaches
    evaluate_print('majority vote', y_test, majority_vote(predicted_labels))
    evaluate_print('average', y_test, average(predicted_scores))
    evaluate_print('maximization', y_test, maximization(predicted_scores))