commit c4eb649d28ef05a9a586832f6ce0205777dd7c1c
Author: Simon Klüttermann <Simon.kluettermann@gmx.de>
Date:   Sun Sep 19 14:38:23 2021 +0200

    initial commit

diff --git a/__pycache__/stroo.cpython-39.pyc b/__pycache__/stroo.cpython-39.pyc
new file mode 100644
index 0000000..8d9d41b
Binary files /dev/null and b/__pycache__/stroo.cpython-39.pyc differ
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..8d35c0d
--- /dev/null
+++ b/main.py
@@ -0,0 +1,14 @@
+import numpy as np
+
+from stroo import *
+
+
+f=np.load("useragents.npz")
+
+model=train_model(f["train"],n=2)
+
+print(model.eval(f["testx"],f["testy"]))
+
+
+
+
diff --git a/stroo.py b/stroo.py
new file mode 100644
index 0000000..835bca0
--- /dev/null
+++ b/stroo.py
@@ -0,0 +1,103 @@
+
+from tqdm import tqdm
+from sortedcontainers import SortedList as slist
+
+import numpy as np
+
+from sklearn.metrics import roc_curve,auc
+import keras
+
+
+def ngrams(q,n=3):
+    return [q[i:i+n] for i in range(len(q)-n)]
+
+def multigramm(q,n=3):
+    ret=set()
+    print("listing ngrams")
+    for zw in tqdm(q):
+        ret=ret|set(ngrams(zw,n=n))
+    return list(ret)
+
+def ngramtrafo(q,gram,n=3):
+    ret=[]
+    gram=slist(gram)#speed up. Trust me, you want this
+    print("converting to vector")
+    for qq in tqdm(q):
+        g=ngrams(qq,n=n)
+        ac=[0 for i in range(len(gram))]
+        for gg in g:
+            try:
+                dex=gram.index(gg)
+            except:continue
+            if dex>0:ac[dex]=1
+        ret.append(ac)
+    return np.array(ret)
+
+
+
+class stroo():
+    """simple merge class for tf model and ngrams"""
+    def __init__(s,model,grams,n,m):
+        """model:tf object
+        grams: list of ngrams
+        n: len of each ngram
+        m: mean of trained data for tf model"""
+        
+        s.model=model
+        s.grams=grams
+        s.n=n
+        s.m=m
+
+    def predict(s,data):
+        """generate normality scores for the provided data"""
+        ng=ngramtrafo(data,s.grams, n=s.n)
+        p=s.model.predict(ng)
+        p=(p-s.m)**2
+        return p
+
+
+    def eval(s,x,y):
+        """evaluates a model by a list of strings x that are normal(y=0) or abnormal (y=1)"""
+        p=s.predict(x)
+        fpr,tpr,_=roc_curve(y,p)
+        return auc(fpr,tpr)
+
+
+
+def train_model(data,n=3):
+    """trains an oneoff network for a list of (normal) strings data by using (n)grams, returns a model"""
+    ngrams=multigramm(data,n=n)
+    data=ngramtrafo(data,ngrams,n=n)
+
+
+    #tensorflow stuff (not at all optimised)
+    inp=keras.Input(data.shape[1:])
+    q=inp
+    q=keras.layers.Dense(10,activation="relu",use_bias=False)(q)
+    q=keras.layers.Dense(4,activation="relu",use_bias=False)(q)
+    q=keras.layers.Dense(1,activation="relu",use_bias=False)(q)
+
+    model=keras.models.Model(inp,q)
+
+    model.compile("adam","mse")
+    model.fit(data,np.ones(len(data),dtype="float"),
+              batch_size=100,
+              epochs=50,
+              validation_split=0.1)
+
+    pm=np.mean(model.predict(data))
+
+    return stroo(model,ngrams,n=n,m=pm)
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/useragents.npz b/useragents.npz
new file mode 100644
index 0000000..65470c9
Binary files /dev/null and b/useragents.npz differ