Ported the code to python 3.

gather_and_train.py

@@ -5,7 +5,6 @@
 import sys
 import json
 import utils
-from sklearn.externals import joblib
 
 
 # Read the configuration and start training.
@@ -65,7 +64,7 @@
 
                 i += 1
 
-        print "    {} pcap files".format(i)
+        print(f"    {i} pcap files")
 
         # Increment the label
         current_label += 1

predict.py

@@ -12,15 +12,15 @@
     sys.exit(1)
 
 elif os.path.exists('config.json') == False:
-    print "No configuration found"
+    print("No configuration found")
     sys.exit(1)
 
 elif os.path.exists('./classifier-nb.dmp') == False:
-    print "No classifier dump found; train first"
+    print("No classifier dump found; train first")
     sys.exit(1)
 
 elif os.path.exists(sys.argv[1]) == False:
-    print "The input file was not found"
+    print("The input file was not found")
     sys.exit(1)
 
 # Read the configuration and start training.
@@ -57,7 +57,7 @@
 # Run the prediction.
 prediction = classifier.predict([stream])
 
-print classifier.predict_proba([stream])
+print(classifier.predict_proba([stream]))
 
 # Print the results.
-print("[{}] Prediction: {}".format(prediction[0], base_labels[prediction[0] - 1]))
+print(f"[{prediction[0]}] Prediction: {base_labels[prediction[0] - 1]}")

utils.py

@@ -119,8 +119,11 @@ def read_pcap_file(file):
     ratio = float(incoming_packets) / (outgoing_packets if outgoing_packets != 0 else 1)
 
     # Print some details.
-    print "OUT: {}, IN: {}, TOTAL: {}, SIZE: {}, RATIO: {}".format(\
-        outgoing_packets, incoming_packets, total_number_of_packets, incoming_size, ratio)
+    print(f'OUT: {outgoing_packets},' +
+            f'IN: {incoming_packets},' +
+            f'TOTAL: {total_number_of_packets},' +
+            f'SIZE: {incoming_size},' +
+            f'RATIO: {ratio}')
 
     # Reverse the array to append the other information.
     sizes.reverse()