From 8334e9a84f328b59d09ab9e82af0af8849901cf2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20Knaebel?= <rknaebel@uni-potsdam.de>
Date: Fri, 30 Jun 2017 17:42:18 +0200
Subject: [PATCH] removed ys from training data generation

---
 dataset.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/dataset.py b/dataset.py
index 9c8364f..f9163be 100644
--- a/dataset.py
+++ b/dataset.py
@@ -110,6 +110,7 @@ def create_dataset_from_flows(user_flow_df, char_dict, maxLen, threshold=3, wind
 def create_dataset_from_lists(domains, dfs, vocab, maxLen, threshold=3,
                               use_cisco_features=False, urlSIPDIct=dict(),
                               window_size=10):
+    # TODO: check for hits vs vth consistency
     if 'hits' in dfs[0].keys():
         hitName = 'hits'
     elif 'virusTotalHits' in dfs[0].keys():
@@ -120,7 +121,6 @@ def create_dataset_from_lists(domains, dfs, vocab, maxLen, threshold=3,
     if use_cisco_features:
         numFeatures += numCiscoFeatures
     Xs = []
-    ys = []
     hits = []
     names = []
     servers = []
@@ -141,12 +141,11 @@ def create_dataset_from_lists(domains, dfs, vocab, maxLen, threshold=3,
                 Xs[ctr][i, :] = get_flow_features(dfs[i].iloc[j])
             ctr += 1
 
-        ys.append(discretize_label(dfs[i][hitName], threshold))
         hits.append(np.max(dfs[i][hitName]))
         names.append(np.unique(dfs[i]['user_hash']))
         servers.append(np.max(dfs[i]['serverLabel']))
         trusted_hits.append(np.max(dfs[i]['trustedHits']))
-    return Xs, np.array(ys), np.array(hits), np.array(names), np.array(servers), np.array(trusted_hits)
+    return Xs, np.array(hits), np.array(names), np.array(servers), np.array(trusted_hits)
 
 
 def discretize_label(values, threshold):