First try boundary nudging

Merge pull request #5 from ltcptgeneral/Parser
Fix range bug in TreeCompress, update parser to autofail non-singular…
2025-09-06 23:37:23 +00:00 · 2025-06-11 16:55:23 -07:00 · 2025-06-11 12:11:39 -07:00 · 2025-06-11 19:10:19 +00:00 · 2025-06-11 11:28:38 -07:00 · 2025-06-11 18:28:18 +00:00
6 changed files with 314 additions and 79 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,5 @@
 data.*
 __pycache__
-*.json
+*.json
+.DS_Store
+.ipynb_checkpoints/
--- a/CompressedTreeParser.ipynb
+++ b/CompressedTreeParser.ipynb
@@ -0,0 +1,128 @@
+{
+ "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": [],
+   "source": [
+    "predict_Yt = []\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",
+    "        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",
+    "                        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",
+    "                        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",
+    "                    break #is this an issue?\n",
+    "\n",
+    "            counter += 1\n",
+    "        result = set(class_set[0])\n",
+    "        for s in class_set[1:]:\n",
+    "            result.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",
+    "        else:\n",
+    "            predict_Yt.append(None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "8b4c56b6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.8448217242194891\n"
+     ]
+    }
+   ],
+   "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
+}
--- a/DecisionTree.ipynb
+++ b/DecisionTree.ipynb
--- a/ExtractDataset.ipynb
+++ b/ExtractDataset.ipynb
@@ -89,7 +89,7 @@
 ],
 "metadata": {
  "kernelspec": {
-   "display_name": "switch",
+   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
@@ -103,7 +103,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.12.7"
+   "version": "3.12.9"
  }
 },
 "nbformat": 4,
--- a/TreeCompress.ipynb
+++ b/TreeCompress.ipynb
@@ -38,14 +38,14 @@
    "i = 0\n",
    "\n",
    "path_ids = set()\n",
-    "path_classes = set()\n",
+    "path_classes = tree[\"classes\"]\n",
    "\n",
    "# for each path in the tree\n",
    "for path in paths:\n",
    "\t# assign a path id \n",
    "\tpath[\"id\"] = i\n",
    "\tpath_ids.add(i)\n",
-    "\tpath_classes.add(path[\"classification\"])\n",
+    "\t#path_classes.add(path[\"classification\"])\n",
    "\ti += 1\t\n",
    "\t# for each condition\n",
    "\tconditions = path[\"conditions\"]\n",
@@ -86,41 +86,7 @@
   "execution_count": 5,
   "id": "98cde024",
   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'dst': {'min': None, 'max': 578}, 'src': {'min': None, 'max': 60}, 'protocl': {'min': None, 'max': 0}}\n",
-      "{'dst': {'min': None, 'max': 3031}, 'src': {'min': None, 'max': 60}, 'protocl': {'min': None, 'max': 0}}\n",
-      "{'dst': {'min': None, 'max': 3031}, 'src': {'min': None, 'max': 60}, 'protocl': {'min': 0, 'max': None}}\n",
-      "{'dst': {'min': None, 'max': 3031}, 'src': {'min': None, 'max': 60}, 'protocl': {'min': 1, 'max': None}}\n",
-      "{'dst': {'min': None, 'max': 3031}, 'src': {'min': None, 'max': 67}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': None, 'max': 101}, 'src': {'min': 67, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': None, 'max': 101}, 'src': {'min': 54978, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': None, 'max': 101}, 'src': {'min': 59817, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': None, 'max': 101}, 'src': {'min': 60043, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': None, 'max': 3031}, 'src': {'min': 67, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': None, 'max': 3031}, 'src': {'min': 130, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': None, 'max': 3031}, 'src': {'min': 1223, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 3031, 'max': None}, 'src': {'min': None, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 3067, 'max': None}, 'src': {'min': None, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 5110, 'max': None}, 'src': {'min': None, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 33925, 'max': None}, 'src': {'min': None, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 46329, 'max': None}, 'src': {'min': None, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 46331, 'max': None}, 'src': {'min': None, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 49152, 'max': None}, 'src': {'min': None, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 49157, 'max': None}, 'src': {'min': None, 'max': 283}, 'protocl': {'min': None, 'max': 11}}\n",
-      "{'dst': {'min': 49157, 'max': None}, 'src': {'min': None, 'max': 283}, 'protocl': {'min': 11, 'max': None}}\n",
-      "{'dst': {'min': 49157, 'max': None}, 'src': {'min': None, 'max': 4566}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 56320, 'max': None}, 'src': {'min': None, 'max': 4566}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 49157, 'max': None}, 'src': {'min': 4566, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 51848, 'max': None}, 'src': {'min': 4566, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 49157, 'max': None}, 'src': {'min': 5225, 'max': None}, 'protocl': {'min': None, 'max': None}}\n",
-      "{'dst': {'min': 53283, 'max': None}, 'src': {'min': 5225, 'max': None}, 'protocl': {'min': None, 'max': None}}\n"
-     ]
-    }
-   ],
+   "outputs": [],
   "source": [
    "# collapse all paths to ranges for each feature\n",
    "# because of how decision trees work, all conditions on a path must be true to reach the leaf node\n",
@@ -143,17 +109,16 @@
    "\t\tvalue = condition[\"value\"]\n",
    "\n",
    "\t\t# move the min/max for the corresponding feature in compressed\n",
-    "\t\tif operation == \"<=\" and compressed[feature][\"min\"] is None:\n",
+    "\t\tif operation == \"<=\" and compressed[feature][\"max\"] is None:\n",
    "\t\t\tcompressed[feature][\"max\"] = value\n",
-    "\t\telif operation == \">\" and compressed[feature][\"max\"] is None:\n",
+    "\t\telif operation == \">\" and compressed[feature][\"min\"] is None:\n",
    "\t\t\tcompressed[feature][\"min\"] = value\n",
-    "\t\telif operation == \"<=\" and value < compressed[feature][\"min\"]:\n",
+    "\t\telif operation == \"<=\" and value < compressed[feature][\"max\"]:\n",
    "\t\t\tcompressed[feature][\"max\"] = value\n",
-    "\t\telif operation == \">\" and value > compressed[feature][\"max\"]:\n",
+    "\t\telif operation == \">\" and value > compressed[feature][\"min\"]:\n",
    "\t\t\tcompressed[feature][\"min\"] = value\n",
    "\n",
-    "\tpath[\"compressed\"] = compressed\n",
-    "\tprint(compressed)"
+    "\tpath[\"compressed\"] = compressed"
   ]
  },
  {
@@ -276,7 +241,7 @@
 ],
 "metadata": {
  "kernelspec": {
-   "display_name": "switch",
+   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
@@ -290,7 +255,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.12.7"
+   "version": "3.12.9"
  }
 },
 "nbformat": 4,
--- a/TreeToRMT.ipynb
+++ b/TreeToRMT.ipynb
@@ -77,7 +77,7 @@
    "\t\t}\n",
    "\t\ttcam_bits += num_prefixes * prefix_width\n",
    "\n",
-    "\t\t# assume no pointer reuse for metadata storage\n",
+    "\t\t# assume basic pointer reuse for metadata storage\n",
    "\t\tram = {\n",
    "\t\t\t\"id\": f\"{layer}_meta\",\n",
    "\t\t\t\"step\": step,\n",
@@ -86,7 +86,7 @@
    "\t\t\t\"key_size\": math.ceil(math.log2(num_ranges)),\n",
    "\t\t\t\"data_size\": len(classes)\n",
    "\t\t}\n",
-    "\t\tram_bits += math.ceil(math.log2(num_ranges)) * len(classes)\n",
+    "\t\tram_bits += num_ranges * len(classes)\n",
    "\n",
    "\t\trmt.append(tcam)\n",
    "\t\trmt.append(ram)\n",
@@ -117,8 +117,8 @@
      "[1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]\n",
      "id mapping: \n",
      "[['dst_range', 'dst_meta'], ['src_range', 'src_meta'], ['protocl_range', 'protocl_meta'], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [], []]\n",
-      "TCAM bits: 13312\n",
-      "RAM bits:  110\n"
+      "TCAM bits: 13184\n",
+      "RAM bits:  504\n"
     ]
    }
   ],
@@ -182,9 +182,7 @@
    "\t\t\tmerge(prefix, prefixes)\n",
    "\t\telse:\n",
    "\t\t\tprefixes.append(prefix)\n",
-    "\treturn prefixes\n",
-    "\n",
-    "#convert_range(81, 1024, 16)"
+    "\treturn prefixes"
   ]
  },
  {
@@ -234,7 +232,7 @@
    "\t\t\t\"key_size\": math.ceil(math.log2(num_ranges)),\n",
    "\t\t\t\"data_size\": len(classes)\n",
    "\t\t}\n",
-    "\t\tram_bits += math.ceil(math.log2(num_ranges)) * len(classes)\n",
+    "\t\tram_bits += num_ranges * len(classes)\n",
    "\n",
    "\t\trmt.append(tcam)\n",
    "\t\trmt.append(ram)\n",
@@ -265,8 +263,8 @@
      "[1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]\n",
      "id mapping: \n",
      "[['dst_range', 'dst_meta'], ['src_range', 'src_meta'], ['protocl_range', 'protocl_meta'], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [], []]\n",
-      "TCAM bits: 3520\n",
-      "RAM bits:  110\n"
+      "TCAM bits: 3320\n",
+      "RAM bits:  504\n"
     ]
    }
   ],
@@ -339,7 +337,7 @@
    "\t\t\t\"key_size\": math.ceil(math.log2(num_ranges)),\n",
    "\t\t\t\"data_size\": len(classes)\n",
    "\t\t}\n",
-    "\t\tram_bits += math.ceil(math.log2(num_ranges)) * len(classes)\n",
+    "\t\tram_bits += num_ranges * len(classes)\n",
    "\n",
    "\t\trmt.append(tcam)\n",
    "\t\trmt.append(ram)\n",
@@ -370,8 +368,8 @@
      "[1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]\n",
      "id mapping: \n",
      "[['dst_range', 'dst_meta'], ['src_range', 'src_meta'], ['protocl_range', 'protocl_meta'], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [], []]\n",
-      "TCAM bits: 2120\n",
-      "RAM bits:  110\n"
+      "TCAM bits: 2152\n",
+      "RAM bits:  504\n"
     ]
    }
   ],
@@ -384,7 +382,7 @@
 ],
 "metadata": {
  "kernelspec": {
-   "display_name": "switch",
+   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
@@ -398,7 +396,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.12.7"
+   "version": "3.12.9"
  }
 },
 "nbformat": 4,
Author	SHA1	Message	Date
Nathan Huey	fda251f051	First try boundary nudging	2025-06-11 16:55:23 -07:00
Arthur Lu	afc882a569	Merge pull request #5 from ltcptgeneral/Parser Fix range bug in TreeCompress, update parser to autofail non-singular…	2025-06-11 12:11:39 -07:00
Arthur Lu	6de3807fe2	fix range bug in TreeCompress, update parser to autofail non-singular classifications	2025-06-11 19:10:19 +00:00
Arthur Lu	fc16d3c586	Merge pull request #4 from ltcptgeneral/Parser Eval compressed tree accuracy	2025-06-11 11:28:38 -07:00
Arthur Lu	7bee40ecf9	restore TreeCompress and TreeToRMT from main	2025-06-11 18:28:18 +00:00
krishpatel	e811171a73	Implemented working compressed tree parser to get classification accuracy	2025-06-11 11:10:49 -07:00
Arthur Lu	61a451b82d	fix counting issue in ram bits	2025-06-11 04:47:35 +00:00
Arthur Lu	c73de36c70	replace classes with class string instead of index	2025-06-11 04:41:32 +00:00