Fix WAF notebook

python-waf/machine-learning-waf.ipynb

@@ -141,7 +141,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The operation may take a long time, 3-5 minutes depending on the computer performance. Uncomment the lines if you don't plan on using a pretrained model (pickle dump)."
+    "The operation may take a long time, 3-5 minutes depending on the computer performance."
    ]
   },
   {
@@ -159,15 +159,15 @@
    "outputs": [],
    "source": [
     "vectorizer = TfidfVectorizer(min_df = 0.0, analyzer=\"char\", sublinear_tf=True, ngram_range=(1,3)) # converting data to vectors\n",
-    "# X = vectorizer.fit_transform(queries)\n",
+    "X = vectorizer.fit_transform(queries)\n",
     "\n",
-    "# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # splitting data\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # splitting data\n",
     "\n",
     "badCount = len(badQueries)\n",
     "validCount = len(validQueries)\n",
     "\n",
     "lgs = LogisticRegression(solver='lbfgs', class_weight={1: 2 * validCount / badCount, 0: 1.0}) # class_weight='balanced')\n",
-    "# lgs.fit(X_train, y_train) # training our model"
+    "lgs.fit(X_train, y_train) # training our model"
    ]
   },
   {
@@ -199,7 +199,7 @@
     "        ('classifier', lgs)\n",
     "    ])\n",
     "\n",
-    "# pickle.dump(p, open('trained_waf_model', 'wb'))"
+    "pickle.dump(p, open('trained_waf_model', 'wb'))"
    ]
   },
   {
@@ -262,7 +262,7 @@
    },
    "outputs": [],
    "source": [
-    "!wget https://github.com/fisher85/ml-cybersecurity/blob/master/python-waf/trained_waf_model?raw=true -O trained_waf_model\n",
+    "# !wget https://github.com/fisher85/ml-cybersecurity/blob/master/python-waf/trained_waf_model?raw=true -O trained_waf_model\n",
     "p = pickle.load(open('trained_waf_model', 'rb'))"
    ]
   },