refactor models package: create separate modules for pauls and renes networks

main.py

@@ -87,10 +87,6 @@ def main():
     kernel_size = 3
     drop_out = 0.5
     filters = 128
-    hidden_dims = 100
-    vocabSize = 40
-    threshold = 3
-    minFlowsPerUser = 10
 
     char_dict = dataset.get_character_dict()
     user_flow_df = dataset.get_user_flow_data()
@@ -110,11 +106,11 @@ def main():
     client_labels = client_labels[idx]
     server_labels = server_tr[idx]
 
-    shared_cnn = models.get_embedding_network_rene(len(char_dict) + 1, args.embedding, args.domain_length,
+    shared_cnn = models.renes_networks.get_embedding(len(char_dict) + 1, args.embedding, args.domain_length,
-                                                   args.hidden_char_dims, args.domain_embedding, 0.5)
+                                                     args.hidden_char_dims, kernel_size, args.domain_embedding, 0.5)
     shared_cnn.summary()
 
-    model = models.get_top_cnn_rene(cnnDropout, flowFeatures, args.domain_embedding,
+    model = models.renes_networks.get_model(cnnDropout, flowFeatures, args.domain_embedding,
                                             args.window, args.domain_length, filters, kernel_size,
                                             cnnHiddenDims, shared_cnn)
     model.summary()

models.py

@@ -1,81 +0,0 @@
-import keras
-from keras.engine import Input, Model
-from keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dense, Dropout, Activation, TimeDistributed, MaxPool1D
-
-
-# designed by paul
-def get_embedding_network_paul(vocab_size, embedding_size, input_length, filters, kernel_size,
-                               hidden_dims, drop_out=0.5):
-    x = y = Input(shape=(input_length,))
-    y = Embedding(input_dim=vocab_size, output_dim=embedding_size)(y)
-    y = Conv1D(filters, kernel_size, activation='relu')(y)
-    y = GlobalMaxPooling1D()(y)
-    y = Dense(hidden_dims)(y)
-    y = Dropout(drop_out)(y)
-    y = Activation('relu')(y)
-    return Model(x, y)
-
-
-def get_embedding_network_rene(vocab_size, embedding_size, input_length,
-                               hidden_char_dims, hidden_dims, drop_out=0.5):
-    x = y = Input(shape=(input_length,))
-    y = Embedding(input_dim=vocab_size, output_dim=embedding_size, mask_zero=True)(y)
-    y = Conv1D(hidden_char_dims, kernel_size=5, activation='relu')(y)
-    y = MaxPool1D(pool_size=3, strides=1)(y)
-    y = Conv1D(hidden_char_dims, kernel_size=3, activation='relu')(y)
-    y = MaxPool1D(pool_size=3, strides=1)(y)
-    y = Conv1D(hidden_char_dims, kernel_size=3, activation='relu')(y)
-    y = GlobalMaxPooling1D()(y)
-    y = Dense(hidden_dims)(y)
-    y = Dropout(drop_out)(y)
-    y = Activation('relu')(y)
-    return Model(x, y)
-
-
-def get_full_model(vocabSize, embeddingSize, maxLen, domainFeatures, flowFeatures,
-                   filters, h1, h2, dropout, dense):
-    pass
-
-
-# designed by paul
-def get_top_cnn(cnnDropout, flow_features, domain_features, window_size, domain_length, cnn_dims, kernel_size,
-                dense_dim,
-                cnn):
-    ipt_domains = Input(shape=(window_size, domain_length), name="ipt_domains")
-    encoded = TimeDistributed(cnn)(ipt_domains)
-    ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows")
-    merged = keras.layers.concatenate([encoded, ipt_flows], -1)
-    # CNN processing a small slides of flow windows
-    # TODO: add more layers?
-    y = Conv1D(cnn_dims,
-               kernel_size,
-               activation='relu',
-               input_shape=(window_size, domain_features + flow_features))(merged)
-    # remove temporal dimension by global max pooling
-    y = GlobalMaxPooling1D()(y)
-    y = Dropout(cnnDropout)(y)
-    y = Dense(dense_dim, activation='relu')(y)
-    y1 = Dense(2, activation='softmax', name="client")(y)
-    y2 = Dense(2, activation='softmax', name="server")(y)
-
-    return Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2))
-
-
-def get_top_cnn_rene(cnnDropout, flow_features, domain_features, window_size, domain_length, cnn_dims, kernel_size,
-                     dense_dim, cnn):
-    ipt_domains = Input(shape=(window_size, domain_length), name="ipt_domains")
-    encoded = TimeDistributed(cnn)(ipt_domains)
-    ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows")
-    merged = keras.layers.concatenate([encoded, ipt_flows], -1)
-    # CNN processing a small slides of flow windows
-    # TODO: add more layers?
-    y = Conv1D(filters=cnn_dims, kernel_size=kernel_size, activation='relu',
-               input_shape=(window_size, domain_features + flow_features))(merged)
-    # remove temporal dimension by global max pooling
-    y = GlobalMaxPooling1D()(y)
-    y = Dropout(cnnDropout)(y)
-    y = Dense(dense_dim, activation='relu')(y)
-    y1 = Dense(2, activation='softmax', name="client")(y)
-    y2 = Dense(2, activation='softmax', name="server")(y)
-
-    return Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2))

models/__init__.py

@@ -0,0 +1,2 @@
+from . import pauls_networks
+from . import renes_networks

models/pauls_networks.py

@@ -0,0 +1,37 @@
+import keras
+from keras.engine import Input, Model
+from keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dense, Dropout, Activation, TimeDistributed
+
+
+def get_embedding(vocab_size, embedding_size, input_length,
+                  filters, kernel_size, hidden_dims, drop_out=0.5):
+    x = y = Input(shape=(input_length,))
+    y = Embedding(input_dim=vocab_size, output_dim=embedding_size)(y)
+    y = Conv1D(filters, kernel_size, activation='relu')(y)
+    y = GlobalMaxPooling1D()(y)
+    y = Dense(hidden_dims)(y)
+    y = Dropout(drop_out)(y)
+    y = Activation('relu')(y)
+    return Model(x, y)
+
+
+def get_model(cnnDropout, flow_features, domain_features, window_size, domain_length, cnn_dims, kernel_size,
+              dense_dim, cnn):
+    ipt_domains = Input(shape=(window_size, domain_length), name="ipt_domains")
+    encoded = TimeDistributed(cnn)(ipt_domains)
+    ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows")
+    merged = keras.layers.concatenate([encoded, ipt_flows], -1)
+    # CNN processing a small slides of flow windows
+    # TODO: add more layers?
+    y = Conv1D(cnn_dims,
+               kernel_size,
+               activation='relu',
+               input_shape=(window_size, domain_features + flow_features))(merged)
+    # remove temporal dimension by global max pooling
+    y = GlobalMaxPooling1D()(y)
+    y = Dropout(cnnDropout)(y)
+    y = Dense(dense_dim, activation='relu')(y)
+    y1 = Dense(2, activation='softmax', name="client")(y)
+    y2 = Dense(2, activation='softmax', name="server")(y)
+
+    return Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2))

models/renes_networks.py

@@ -0,0 +1,40 @@
+import keras
+from keras.engine import Input, Model
+from keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dense, Dropout, TimeDistributed, MaxPool1D
+
+
+def get_embedding(vocab_size, embedding_size, input_length,
+                  hidden_char_dims, kernel_size, hidden_dims, drop_out=0.5):
+    x = y = Input(shape=(input_length,))
+    y = Embedding(input_dim=vocab_size, output_dim=embedding_size)(y)
+    y = Conv1D(hidden_char_dims, kernel_size=5, activation='relu')(y)
+    y = MaxPool1D(pool_size=3, strides=1)(y)
+    y = Conv1D(hidden_char_dims, kernel_size=3, activation='relu')(y)
+    y = MaxPool1D(pool_size=3, strides=1)(y)
+    y = Conv1D(hidden_char_dims, kernel_size=3, activation='relu')(y)
+    y = GlobalMaxPooling1D()(y)
+    y = Dropout(drop_out)(y)
+    y = Dense(hidden_dims, activation="relu")(y)
+    return Model(x, y)
+
+
+def get_model(cnnDropout, flow_features, domain_features, window_size, domain_length, cnn_dims, kernel_size,
+              dense_dim, cnn):
+    ipt_domains = Input(shape=(window_size, domain_length), name="ipt_domains")
+    encoded = TimeDistributed(cnn)(ipt_domains)
+    ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows")
+    merged = keras.layers.concatenate([encoded, ipt_flows], -1)
+    # CNN processing a small slides of flow windows
+    # TODO: add more layers?
+    y = Conv1D(filters=cnn_dims, kernel_size=kernel_size, activation='relu',
+               input_shape=(window_size, domain_features + flow_features))(merged)
+    y = MaxPool1D(pool_size=3, strides=1)(y)
+    y = Conv1D(filters=cnn_dims, kernel_size=kernel_size, activation='relu')(y)
+    # remove temporal dimension by global max pooling
+    y = GlobalMaxPooling1D()(y)
+    y = Dropout(cnnDropout)(y)
+    y = Dense(dense_dim, activation='relu')(y)
+    y1 = Dense(2, activation='softmax', name="client")(y)
+    y2 = Dense(2, activation='softmax', name="server")(y)
+
+    return Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2))