Fixed loop ordering and path_to_class in JSON

CompressedTreeParser.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 138,
    "id": "938dec51",
    "metadata": {},
    "outputs": [],
@@ -22,31 +22,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 139,
    "id": "442624c7",
    "metadata": {},
    "outputs": [],
    "source": [
-    "Set1 = pd.read_csv('data.csv').values.tolist()\n",
+    "Set1 = pd.read_csv('data/combined/data.csv').values.tolist()\n",
     "X = [i[0:3] for i in Set1]\n",
     "Y =[i[3] for i in Set1]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 142,
    "id": "12ad454d",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'0': 20, '1': 20, '2': 9, '3': 20, '4': 0, '5': 13, '6': 20, '7': 0, '8': 12, '9': 4, '10': 20, '11': 4, '12': 1, '13': 16, '14': 20, '15': 2, '16': 20, '17': 0, '18': 20, '19': 20, '20': 20, '21': 20, '22': 20, '23': 1, '24': 2, '25': 20, '26': 13, '27': 11, '28': 20, '29': 20}\n"
+     ]
+    }
+   ],
    "source": [
     "predict_Yt = []\n",
     "index=0\n",
-    "original_tree = open('tree.json', 'r')\n",
-    "original_tree = json.load(original_tree)\n",
-    "path_to_class = {}\n",
-    "for i in range(len(original_tree[\"paths\"])):\n",
-    "    path = original_tree[\"paths\"][i]\n",
-    "    path_to_class[path[\"id\"]] = path[\"classification\"]\n",
+    "\n",
     "with open('compressed_tree.json', 'r') as file:\n",
     "    data = json.load(file)\n",
     "    classes = data[\"classes\"]\n",
@@ -54,7 +57,9 @@
     "        counter = 0\n",
     "        class_set = []\n",
     "        paths_set = []\n",
-    "        for feature in reversed(data['layers']): #Have to reverse this list due to structure of the data.csv file and how it aligns with the compressed tree layers\n",
+    "        features = [\"protocol\", \"src\", \"dst\"]\n",
+    "        for feature in features:\n",
+    "            if feature in data[\"layers\"]:\n",
     "                for node in data['layers'][feature]:\n",
     "                    if node['min'] is None:\n",
     "                        if x[counter] <= node['max']:\n",
@@ -85,9 +90,13 @@
     "\n",
     "        #predict_Yt.append(list(result))\n",
     "        #print(result)\n",
+    "        if len(paths) != 1:\n",
+    "            print(paths)\n",
+    "            print(x)\n",
+    "            print(result)\n",
     "        assert len(paths) == 1\n",
     "        path = list(paths)[0]\n",
-    "        pred = path_to_class[path]\n",
+    "        pred = data[\"path_to_class\"][str(path)]\n",
     "        pred_class = classes[pred]\n",
     "        predict_Yt.append(pred_class)\n",
     "        \n",
@@ -96,7 +105,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 143,
    "id": "8b4c56b6",
    "metadata": {},
    "outputs": [
@@ -104,7 +113,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "0.8451332670948943\n"
+      "0.8410252791654538\n"
      ]
     }
    ],

TreeCompress.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 73,
    "id": "ec310f34",
    "metadata": {},
    "outputs": [],
@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 74,
    "id": "5b54797e",
    "metadata": {},
    "outputs": [],
@@ -28,7 +28,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 75,
    "id": "a38fdb8a",
    "metadata": {},
    "outputs": [],
@@ -60,7 +60,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 76,
    "id": "2fd4f738",
    "metadata": {},
    "outputs": [],
@@ -83,7 +83,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 77,
    "id": "98cde024",
    "metadata": {},
    "outputs": [],
@@ -123,7 +123,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 78,
    "id": "b6fbadbf",
    "metadata": {},
    "outputs": [],
@@ -183,7 +183,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 79,
    "id": "0a767971",
    "metadata": {},
    "outputs": [],
@@ -213,16 +213,22 @@
     "\tcompressed_layers[feature_name].append({\"min\": lower, \"max\": upper, \"paths\": paths, \"classes\": classes})\n",
     "\t#print(\"=\"*40)\n",
     "\n",
+    "path_to_class = {}\n",
+    "for i in range(len(tree[\"paths\"])):\n",
+    "    path = tree[\"paths\"][i]\n",
+    "    path_to_class[path[\"id\"]] = path[\"classification\"]\n",
+    "\n",
     "compressed_tree = {\n",
     "\t\"paths\": path_ids,\n",
     "\t\"classes\": path_classes,\n",
     "\t\"layers\": compressed_layers,\n",
+    "    \"path_to_class\": path_to_class,\n",
     "}"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 80,
    "id": "561b0bc1",
    "metadata": {},
    "outputs": [],
@@ -241,7 +247,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "switch",
+   "display_name": "cs216",
    "language": "python",
    "name": "python3"
   },
@@ -255,7 +261,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.7"
+   "version": "3.13.3"
   }
  },
  "nbformat": 4,