Files
IdealRMT-DecisionTrees/CompressedTreeParser.ipynb
2025-06-12 05:37:48 +00:00

185 lines
6.5 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "938dec51",
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import argparse\n",
"from sklearn.tree import DecisionTreeClassifier, plot_tree, _tree\n",
"from sklearn.metrics import accuracy_score\n",
"from sklearn.tree import export_graphviz\n",
"import pydotplus\n",
"from matplotlib import pyplot as plt\n",
"from labels import mac_to_label\n",
"import json\n",
"import math"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "442624c7",
"metadata": {},
"outputs": [],
"source": [
"Set1 = pd.read_csv('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,
"id": "12ad454d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"here1\n",
" protocl src dst classfication\n",
"0 6 40234 5228 other\n",
"1 6 40234 5228 other\n",
"2 6 443 46330 Dropcam\n",
"3 6 3063 443 other\n",
"4 1 0 0 Netatmo Camera\n",
"... ... ... ... ...\n",
"2419339 6 443 47940 Dropcam\n",
"2419340 6 47940 443 other\n",
"2419341 6 443 47940 Dropcam\n",
"2419342 0 0 0 iHome PowerPlug\n",
"2419343 0 0 0 other\n",
"\n",
"[2419344 rows x 4 columns]\n",
"{8, 20}\n",
"{13}\n",
"[6, 40234, 5228]\n",
"other\n"
]
}
],
"source": [
"predict_Yt = []\n",
"index=0\n",
"with open('compressed_tree.json', 'r') as file:\n",
" data = json.load(file)\n",
" classes = data[\"classes\"]\n",
" for x in X:\n",
" 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",
" for node in data['layers'][feature]:\n",
" if node['min'] is None:\n",
" if x[counter] <= node['max']:\n",
" class_set.append(node['classes'])\n",
" paths_set.append(node[\"paths\"])\n",
" break #is this an issue?\n",
" else:\n",
" continue\n",
" elif node['max'] is None:\n",
" if node['min'] < x[counter]:\n",
" class_set.append(node['classes'])\n",
" paths_set.append(node[\"paths\"])\n",
" break #is this an issue?\n",
" else:\n",
" continue\n",
" elif node['min'] < x[counter] and x[counter] <= node['max']:\n",
" class_set.append(node['classes'])\n",
" paths_set.append(node[\"paths\"])\n",
" break #is this an issue?\n",
"\n",
" counter += 1\n",
" result = set(class_set[0])\n",
" paths = set(paths_set[0])\n",
" for s in class_set[1:]:\n",
" result.intersection_update(s)\n",
" for s in paths_set[1:]:\n",
" paths.intersection_update(s)\n",
"\n",
" #predict_Yt.append(list(result))\n",
" #print(result)\n",
" if len(result) == 1:\n",
" prediction = list(result)[0]\n",
" pred_class = classes[prediction]\n",
" predict_Yt.append(pred_class)\n",
" elif len(paths) == 1:\n",
" print(\"here1\")\n",
" print(pd.read_csv('data.csv'))\n",
" print(result)\n",
" print(paths)\n",
" print(x)\n",
" print(Y[index])\n",
" break\n",
" predict_Yt.append(None)\n",
" else:\n",
" print(\"here2\")\n",
" print(pd.read_csv('data.csv'))\n",
" print(result)\n",
" print(paths)\n",
" print(x)\n",
" print(Y[index])\n",
" break\n",
" predict_Yt.append(None)\n",
" \n",
" index += 1"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "8b4c56b6",
"metadata": {},
"outputs": [
{
"ename": "IndexError",
"evalue": "list index out of range",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mIndexError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[4]\u001b[39m\u001b[32m, line 3\u001b[39m\n\u001b[32m 1\u001b[39m correct = \u001b[32m0\u001b[39m\n\u001b[32m 2\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(\u001b[38;5;28mlen\u001b[39m(Y)):\n\u001b[32m----> \u001b[39m\u001b[32m3\u001b[39m prediction = \u001b[43mpredict_Yt\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\n\u001b[32m 4\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m prediction != \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m Y[i] == prediction:\n\u001b[32m 5\u001b[39m correct += \u001b[32m1\u001b[39m\n",
"\u001b[31mIndexError\u001b[39m: list index out of range"
]
}
],
"source": [
"correct = 0\n",
"for i in range(len(Y)):\n",
" prediction = predict_Yt[i]\n",
" if prediction != None and Y[i] == prediction:\n",
" correct += 1\n",
"\n",
"print(correct / len(Y))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}