From d228b7d538b739ef9c4ff1276f9ae97393f02fa1 Mon Sep 17 00:00:00 2001
From: Daniel Glauche <62604194+dglauche@users.noreply.github.com>
Date: Fri, 23 Jun 2023 11:22:20 +0200
Subject: [PATCH] Update pretrained_dga_model_dsdl.ipynb

moving calculation of domain union out of loop to improve performance
---
 notebooks/pretrained_dga_model_dsdl.ipynb | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/notebooks/pretrained_dga_model_dsdl.ipynb b/notebooks/pretrained_dga_model_dsdl.ipynb
index 1d80c0c695..65f925de79 100644
--- a/notebooks/pretrained_dga_model_dsdl.ipynb
+++ b/notebooks/pretrained_dga_model_dsdl.ipynb
@@ -224,12 +224,9 @@
     "        p, lns = Counter(domain), float(len(domain))\n",
     "        return -sum( count/lns * math.log(count/lns, 2) for count in p.values())\n",
     "    \n",
-    "alexa_domains = domains['domain']\n",
     "\n",
-    "    \n",
     "def is_in_alexa1m(domain,domains):\n",
-    "    test_in_alexa_domains = set(alexa_domains) & domains\n",
-    "    return ((domain in test_in_alexa_domains))\n",
+    "    return ((domain in domains))\n",
     "\n",
     "    \n",
     "    \n",
@@ -241,8 +238,8 @@
     "    print (\"2. Done adding entropy\")\n",
     "    X_4 = df['domain'].map(lambda x: len(x))\n",
     "    print (\"3. Done adding length of domain\")\n",
-    "    domains = set(df['domain'])\n",
-    "    X_5 = df['domain'].map(lambda x: is_in_alexa1m(x,domains))\n",
+    "    to_check = set(domains['domain']) & set(df['domain'])\n",
+    "    X_5 = df['domain'].map(lambda x: is_in_alexa1m(x, to_check))\n",
     "    print (\"4. Done adding domain present in alexa domains\")\n",
     "    X_5 = X_5.astype(int)\n",
     "    input2 = np.c_[X_1,X_2,X_3,X_4,X_5] #\n",