finish experiments

experiments/study_results/context.py

@@ -15,4 +15,5 @@
 import neural_networks.jdeodorant.detect_feature_envy as jdeodorant_fe
 
 import neural_networks.vote.detect  as vote
-import neural_networks.asci.predict as asci
+import neural_networks.asci.predict as asci
+import neural_networks.smad.predict as smad

experiments/study_results/perfs_feature_envy.py

@@ -1,4 +1,4 @@
-from context import nnUtils, incode, hist_fe, jdeodorant_fe, vote
+from context import nnUtils, incode, hist_fe, jdeodorant_fe, vote, asci, smad
 
 import numpy as np
 
@@ -17,6 +17,8 @@
 overall_prediction_hist = np.empty(shape=[0, 1])
 overall_prediction_jd = np.empty(shape=[0, 1])
 overall_prediction_vote = np.empty(shape=[0, 1])
+overall_prediction_asci = np.empty(shape=[0, 1])
+overall_prediction_smad = np.empty(shape=[0, 1])
 
 overall_labels = np.empty(shape=[0, 1])
 for system in systems:
@@ -40,6 +42,14 @@
 	prediction_vote = nnUtils.predictFromDetect('feature_envy', system, vote.detect('feature_envy', system))
 	overall_prediction_vote = np.concatenate((overall_prediction_vote, prediction_vote), axis=0)
 
+	# Compute performances for ASCI
+	prediction_asci = asci.predict('feature_envy', system)
+	overall_prediction_asci = np.concatenate((overall_prediction_asci, prediction_asci), axis=0)
+
+	# Compute performances for SMAD
+	prediction_smad = smad.predict('feature_envy', system)
+	overall_prediction_smad = np.concatenate((overall_prediction_smad, prediction_smad), axis=0)
+
 	# Print performances for the considered system
 	print(system)
 	print('           |precision  |recall  |f_measure')
@@ -52,6 +62,10 @@
 	print('-------------------------------------------')
 	print('Vote       |' + "{0:.3f}".format(nnUtils.precision(prediction_vote, labels)) + '      |' + "{0:.3f}".format(nnUtils.recall(prediction_vote, labels)) + '   |' + "{0:.3f}".format(nnUtils.f_measure(prediction_vote, labels)))
 	print('-------------------------------------------')
+	print('ASCI       |' + "{0:.3f}".format(nnUtils.precision(prediction_asci, labels)) + '      |' + "{0:.3f}".format(nnUtils.recall(prediction_asci, labels)) + '   |' + "{0:.3f}".format(nnUtils.f_measure(prediction_asci, labels)))
+	print('-------------------------------------------')
+	print('SMAD       |' + "{0:.3f}".format(nnUtils.precision(prediction_smad, labels)) + '      |' + "{0:.3f}".format(nnUtils.recall(prediction_smad, labels)) + '   |' + "{0:.3f}".format(nnUtils.f_measure(prediction_smad, labels)))
+	print('-------------------------------------------')
 
 	print('\n')
 
@@ -67,3 +81,7 @@
 print('-------------------------------------------')
 print('Vote       |' + "{0:.3f}".format(nnUtils.precision(overall_prediction_vote, overall_labels)) + '      |' + "{0:.3f}".format(nnUtils.recall(overall_prediction_vote, overall_labels)) + '   |' + "{0:.3f}".format(nnUtils.f_measure(overall_prediction_vote, overall_labels)))
 print('-------------------------------------------')
+print('ASCI       |' + "{0:.3f}".format(nnUtils.precision(overall_prediction_asci, overall_labels)) + '      |' + "{0:.3f}".format(nnUtils.recall(overall_prediction_asci, overall_labels)) + '   |' + "{0:.3f}".format(nnUtils.f_measure(overall_prediction_asci, overall_labels)))
+print('-------------------------------------------')
+print('SMAD       |' + "{0:.3f}".format(nnUtils.precision(overall_prediction_smad, overall_labels)) + '      |' + "{0:.3f}".format(nnUtils.recall(overall_prediction_smad, overall_labels)) + '   |' + "{0:.3f}".format(nnUtils.f_measure(overall_prediction_smad, overall_labels)))
+print('-------------------------------------------')

experiments/study_results/perfs_god_class.py

@@ -1,4 +1,4 @@
-from context import nnUtils, decor, hist_gc, jdeodorant_gc, vote, asci
+from context import nnUtils, decor, hist_gc, jdeodorant_gc, vote, asci, smad
 
 import numpy as np
 
@@ -18,6 +18,7 @@
 overall_prediction_jd = np.empty(shape=[0, 1])
 overall_prediction_vote = np.empty(shape=[0, 1])
 overall_prediction_asci = np.empty(shape=[0, 1])
+overall_prediction_smad = np.empty(shape=[0, 1])
 
 overall_labels = np.empty(shape=[0, 1])
 for system in systems:
@@ -45,6 +46,10 @@
 	prediction_asci = asci.predict('god_class', system)
 	overall_prediction_asci = np.concatenate((overall_prediction_asci, prediction_asci), axis=0)
 
+	# Compute performances for SMAD
+	prediction_smad = smad.predict('god_class', system)
+	overall_prediction_smad = np.concatenate((overall_prediction_smad, prediction_smad), axis=0)
+
 	# Print performances for the considered system
 	print(system)
 	print('           |precision  |recall  |f_measure')
@@ -59,6 +64,8 @@
 	print('-------------------------------------------')
 	print('ASCI       |' + "{0:.3f}".format(nnUtils.precision(prediction_asci, labels)) + '      |' + "{0:.3f}".format(nnUtils.recall(prediction_asci, labels)) + '   |' + "{0:.3f}".format(nnUtils.f_measure(prediction_asci, labels)))
 	print('-------------------------------------------')
+	print('SMAD       |' + "{0:.3f}".format(nnUtils.precision(prediction_smad, labels)) + '      |' + "{0:.3f}".format(nnUtils.recall(prediction_smad, labels)) + '   |' + "{0:.3f}".format(nnUtils.f_measure(prediction_smad, labels)))
+	print('-------------------------------------------')
 
 	print('\n')
 
@@ -76,3 +83,5 @@
 print('-------------------------------------------')
 print('ASCI       |' + "{0:.3f}".format(nnUtils.precision(overall_prediction_asci, overall_labels)) + '      |' + "{0:.3f}".format(nnUtils.recall(overall_prediction_asci, overall_labels)) + '   |' + "{0:.3f}".format(nnUtils.f_measure(overall_prediction_asci, overall_labels)))
 print('-------------------------------------------')
+print('SMAD       |' + "{0:.3f}".format(nnUtils.precision(overall_prediction_smad, overall_labels)) + '      |' + "{0:.3f}".format(nnUtils.recall(overall_prediction_smad, overall_labels)) + '   |' + "{0:.3f}".format(nnUtils.f_measure(overall_prediction_smad, overall_labels)))
+print('-------------------------------------------')

experiments/training/train_smad.py

@@ -28,7 +28,7 @@ def parse_args():
 	parser.add_argument("-beta", type=float, help="The L2 regularization scale to be used for training.")
 	parser.add_argument('-dense_sizes', nargs='+', type=int, help="The sizes of each (dense) hidden layer in the network.")
 	parser.add_argument("-n_net", type=int, default=10, help="The number of distinct networks to be trained and saved.")
-	parser.add_argument("-n_step", type=int, default=300, help="The number of training steps.")
+	parser.add_argument("-n_step", type=int, default=200, help="The number of training steps.")
 	parser.add_argument("-decay_step", type=int, default=100, help="The number of training steps after which the learning rate is decayed")
 	parser.add_argument("-lr_decay", type=float, default=0.5, help="The factor by which the learning rate is multiplied every 'decay_step' steps")
 	return parser.parse_args()