diff --git a/dataset.py b/dataset.py
index b1af606..f4a40e6 100644
--- a/dataset.py
+++ b/dataset.py
@@ -92,11 +92,18 @@ def get_flow_features(flow):
     return features
 
 
+def get_all_flow_features(features):
+    flows = np.stack(list(
+        map(lambda f: f[["duration", "bytes_up", "bytes_down"]], features))
+    )
+    return np.log1p(flows)
+
+
 def create_dataset_from_flows(user_flow_df, char_dict, max_len, window_size=10, use_cisco_features=False):
     domains = []
     features = []
     print("get chunks from user data frames")
-    for i, user_flow in tqdm(list(enumerate(get_flow_per_user(user_flow_df)))[:50]):
+    for i, user_flow in tqdm(list(enumerate(get_flow_per_user(user_flow_df)))):
         (domain_windows, feature_windows) = get_user_chunks(user_flow,
                                                             windowSize=window_size,
                                                             overlapping=False,