Merge 97136bd into c2839e0

examples/alad_example.py

@@ -0,0 +1,70 @@
+# -*- coding: utf-8 -*-
+"""Example of using Adversarially Learned Anomaly Detection(ALAD) for outlier detection
+"""
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+
+# temporary solution for relative imports in case pyod is not installed
+# if pyod is installed, no need to use the following line
+sys.path.append(
+    os.path.abspath(os.path.join(os.path.dirname("__file__"), '..')))
+
+from pyod.models.alad import ALAD
+from pyod.utils.data import generate_data
+
+from pyod.utils.data import evaluate_print
+from pyod.utils.example import visualize
+
+if __name__ == "__main__":
+    contamination = 0.1  # percentage of outliers
+    n_train = 500  # number of training points
+    n_test = 200  # number of testing points
+
+    # Generate sample data
+    X_train, X_test, y_train, y_test = \
+        generate_data(n_train=n_train,
+                      n_test=n_test,
+                      n_features=2,
+                      contamination=contamination,
+                      random_state=42)
+
+    # train ALAD detector
+    clf_name = 'ALAD'
+    clf  = ALAD( epochs = 100,   latent_dim = 2,     
+                 learning_rate_disc = 0.0001,  
+                 learning_rate_gen = 0.0001,  
+                 dropout_rate = 0.2, 
+                 add_recon_loss = False, 
+                 lambda_recon_loss= 0.05, 
+                 add_disc_zz_loss = True,
+                 dec_layers=[ 75, 100 ], 
+                 enc_layers=[ 100, 75 ], 
+                 disc_xx_layers= [ 100, 75 ], 
+                 disc_zz_layers= [ 25, 25 ], 
+                 disc_xz_layers= [ 100, 75 ], 
+                 spectral_normalization = False, 
+                 activation_hidden_disc = 'tanh', activation_hidden_gen = 'tanh' , 
+                 preprocessing=True, batch_size = 200, 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)
+
+    # 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)