From d219cd5b5fe3a1ef7743021f5f5e4ea98f3ba5ca Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Simon=20Kl=C3=BCttermann?= <Simon.kluettermann@gmx.de>
Date: Sun, 19 Sep 2021 14:44:26 +0200
Subject: [PATCH] made stuff a bit more userfriendly

---
 main.py          | 19 +++++++++++++------
 requirements.txt |  4 ++++
 2 files changed, 17 insertions(+), 6 deletions(-)
 create mode 100644 requirements.txt

diff --git a/main.py b/main.py
index 8d35c0d..55b0ecb 100644
--- a/main.py
+++ b/main.py
@@ -1,14 +1,21 @@
+
+
+#data loading
 import numpy as np
-
-from stroo import *
-
-
 f=np.load("useragents.npz")
 
-model=train_model(f["train"],n=2)
 
+from stroo import train_model
+
+#understands pure strings
+#definitely not the best possible model
+#so if this is at least >0.55 (on more complicated data) we should be able to do something with it
+#also migth be included into an isolation forest
+model=train_model(f["train"],n=3)
+
+#calculate auc. Has disparity between normal, abnormal: np.mean(testy)~=0.065
 print(model.eval(f["testx"],f["testy"]))
-
+#in my tests reaches >0.99
 
 
 
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..ab89ee0
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,4 @@
+numpy
+keras
+tqdm
+sklearn