refactor dataset generation

Makefile

@@ -1,3 +1,3 @@
 test:
-	python3 main.py --epochs 1 --batch 64
+	python3 main.py --epochs 1 --batch 64 --train data/rk_data.csv.gz --test data/rk_data.csv.gz
 

dataset.py

@@ -117,12 +117,27 @@ def create_dataset_from_flows(user_flow_df, char_dict, max_len, window_size=10,
             break
 
     print("create training dataset")
-    return create_dataset_from_lists(
+    domain_tr, flow_tr, hits_tr, names_tr, server_tr, trusted_hits_tr = create_dataset_from_lists(
         domains=domains, features=features, vocab=char_dict,
         max_len=max_len,
         use_cisco_features=use_cisco_features, urlSIPDIct=dict(),
         window_size=window_size)
 
+    # make client labels discrete with 4 different values
+    # TODO: use trusted_hits_tr for client classification too
+    client_labels = np.apply_along_axis(lambda x: discretize_label(x, 3), 0, np.atleast_2d(hits_tr))
+    # select only 1.0 and 0.0 from training data
+    pos_idx = np.where(client_labels == 1.0)[0]
+    neg_idx = np.where(client_labels == 0.0)[0]
+    idx = np.concatenate((pos_idx, neg_idx))
+    # choose selected sample to train on
+    domain_tr = domain_tr[idx]
+    flow_tr = flow_tr[idx]
+    client_labels = client_labels[idx]
+    server_labels = server_tr[idx]
+
+    return domain_tr, flow_tr, client_labels, server_labels
+
 
 def create_dataset_from_lists(domains, features, vocab, max_len,
                               use_cisco_features=False, urlSIPDIct=dict(),
@@ -185,9 +200,11 @@ def discretize_label(values, threshold):
         return 0.0
 
 
-def get_user_flow_data():
+def get_user_flow_data(csv_file):
-    df = pd.read_csv("data/rk_data.csv.gz")
+    df = pd.read_csv(csv_file)
-    df.drop("Unnamed: 0", 1, inplace=True)
+    keys = ["duration", "bytes_down", "bytes_up", "domain", "timeStamp", "server_ip", "user_hash", "virusTotalHits",
+            "serverLabel", "trustedHits"]
+    df = df[keys]
     df.set_index(keys=['user_hash'], drop=False, inplace=True)
     return df
 

main.py

@@ -1,6 +1,5 @@
 import argparse
 
-import numpy as np
 from keras.utils import np_utils
 
 import dataset
@@ -8,17 +7,20 @@ import models
 
 parser = argparse.ArgumentParser()
 
-parser.add_argument("--modes", action="store", dest="modes", nargs="+")
+# parser.add_argument("--modes", action="store", dest="modes", nargs="+")
+
+parser.add_argument("--train", action="store", dest="train_data",
+                    default="data/full_dataset.csv.tar.bz2")
+
+parser.add_argument("--test", action="store", dest="test_data",
+                    default="data/full_future_dataset.csv.tar.bz2")
 
-# parser.add_argument("--data", action="store", dest="data",
-#                     default="data/")
-#
 # parser.add_argument("--h5data", action="store", dest="h5data",
 #                     default="")
 #
-# parser.add_argument("--model", action="store", dest="model",
+parser.add_argument("--model", action="store", dest="model",
-#                     default="model_x")
+                    default="model_x")
-#
+
 # parser.add_argument("--pred", action="store", dest="pred",
 #                     default="")
 #
@@ -66,8 +68,7 @@ parser.add_argument("--domain_embd", action="store", dest="domain_embedding",
 #
 # parser.add_argument("--tmp", action="store_true", dest="tmp")
 #
-# parser.add_argument("--test", action="store", dest="test_image",
+# parser.add_argument("--test", action="store_true", dest="test")
-#                     default=6, choices=range(7), type=int)
 
 args = parser.parse_args()
 
@@ -82,37 +83,24 @@ def main():
     # parameter
     cnnDropout = 0.5
     cnnHiddenDims = 1024
-    flowFeatures = 3
     numCiscoFeatures = 30
     kernel_size = 3
     drop_out = 0.5
     filters = 128
 
     char_dict = dataset.get_character_dict()
-    user_flow_df = dataset.get_user_flow_data()
+    user_flow_df = dataset.get_user_flow_data(args.train_data)
 
     print("create training dataset")
-    domain_tr, flow_tr, hits_tr, names_tr, server_tr, trusted_hits_tr = dataset.create_dataset_from_flows(
+    domain_tr, flow_tr, client_tr, server_tr = dataset.create_dataset_from_flows(
         user_flow_df, char_dict,
         max_len=args.domain_length, window_size=args.window)
-    # make client labels discrete with 4 different values
-    # TODO: use trusted_hits_tr for client classification too
-    client_labels = np.apply_along_axis(lambda x: dataset.discretize_label(x, 3), 0, np.atleast_2d(hits_tr))
-    # select only 1.0 and 0.0 from training data
-    pos_idx = np.where(client_labels == 1.0)[0]
-    neg_idx = np.where(client_labels == 0.0)[0]
-    idx = np.concatenate((pos_idx, neg_idx))
-    # choose selected sample to train on
-    domain_tr = domain_tr[idx]
-    flow_tr = flow_tr[idx]
-    client_labels = client_labels[idx]
-    server_labels = server_tr[idx]
 
     shared_cnn = models.renes_networks.get_embedding(len(char_dict) + 1, args.embedding, args.domain_length,
                                                      args.hidden_char_dims, kernel_size, args.domain_embedding, 0.5)
     shared_cnn.summary()
 
-    model = models.renes_networks.get_model(cnnDropout, flowFeatures, args.domain_embedding,
+    model = models.renes_networks.get_model(cnnDropout, flow_tr.shape[-1], args.domain_embedding,
                                             args.window, args.domain_length, filters, kernel_size,
                                             cnnHiddenDims, shared_cnn)
     model.summary()
@@ -121,14 +109,23 @@ def main():
                   loss='binary_crossentropy',
                   metrics=['accuracy'])
 
-    client_labels = np_utils.to_categorical(client_labels, 2)
+    client_tr = np_utils.to_categorical(client_tr, 2)
-    server_labels = np_utils.to_categorical(server_labels, 2)
+    server_tr = np_utils.to_categorical(server_tr, 2)
     model.fit([domain_tr, flow_tr],
-              [client_labels, server_labels],
+              [client_tr, server_tr],
               batch_size=args.batch_size,
               epochs=args.epochs,
-              shuffle=True)
+              shuffle=True,
-    # TODO: for validation we use future data -> validation_data=(testData,testLabel))
+              validation_split=0.2)
+
+
+def test():
+    char_dict = dataset.get_character_dict()
+    user_flow_df = dataset.get_user_flow_data(args.test_data)
+    domain_val, flow_val, client_val, server_val = dataset.create_dataset_from_flows(
+        user_flow_df, char_dict,
+        max_len=args.domain_length, window_size=args.window)
+    # TODO: get model and exec model.evaluate(...)
 
 
 if __name__ == "__main__":