exercisev2_43_3.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "690e3648-8352-4576-a76a-885edac5f8ef",
   "metadata": {},
   "outputs": [],
   "source": [
    "import networkx as nx\n",
    "from gensim.models import Word2Vec\n",
    "from sklearn.manifold import TSNE\n",
    "from sklearn.cluster import KMeans\n",
    "from sklearn.metrics import normalized_mutual_info_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "0405b4a3-e629-483c-b912-15954165156a",
   "metadata": {},
   "outputs": [],
   "source": [
    "H = nx.read_edgelist(\"1/data.txt\", create_using = nx.Graph(), delimiter = \"\\t\", nodetype = int)\n",
    "G = nx.Graph()\n",
    "G.add_nodes_from(sorted(H.nodes))\n",
    "G.add_edges_from(H.edges)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "8623084e-dba5-49db-aa23-3582ec362681",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2, 2, 2, 3, 1, 2, 0, 2, 3, 0, 2, 1, 1, 1, 2, 2, 1, 2, 2, 3, 1, 1,\n",
       "       0, 1, 1, 2, 3, 1, 2, 1, 2, 0, 2, 2, 0, 2, 2, 0, 3, 2, 1, 0, 0, 1,\n",
       "       3, 0, 0, 1, 2, 1, 3, 0, 3, 2, 3, 0, 3, 3, 0, 0, 3, 1, 3, 3, 2, 1,\n",
       "       1, 0, 3, 2, 3, 3, 3, 0, 1, 2, 2, 2, 3, 0, 0, 3, 2, 3, 1, 0, 1, 1,\n",
       "       0, 0, 0, 1, 2, 3, 0, 0, 2, 3, 2, 1, 2, 1, 3, 1, 2, 1, 1, 1, 0, 0,\n",
       "       2, 1, 1, 3, 2, 0, 3, 3, 3, 0, 2, 0, 2, 3, 2, 0, 1, 3, 3, 3, 2, 2,\n",
       "       1, 3, 3, 1, 1, 1, 1, 2, 1, 2, 3, 2, 2, 3, 1, 1, 0, 3, 0, 2, 0, 2,\n",
       "       3, 1, 1, 0, 3, 1, 2, 0, 0, 1, 0, 2, 2, 1, 0, 0, 2, 0, 0, 2, 0, 2,\n",
       "       2, 1, 1, 2, 1, 2, 1, 0, 0, 2, 2, 2, 0, 2, 0, 1, 0, 3, 3, 1, 0, 3,\n",
       "       2, 1, 0, 3, 1, 2, 3, 1, 2, 2, 3, 0, 2, 1, 1, 2, 2, 1, 0, 0, 2, 0,\n",
       "       2, 1, 3, 2, 1, 1, 1, 3, 1, 3, 3, 1, 2, 1, 2, 1, 1, 0, 3, 1, 0, 1,\n",
       "       1, 2, 0, 0, 1, 2, 2, 2, 3, 2, 3, 0, 3, 3, 3, 3, 3, 0, 3, 2, 1, 1,\n",
       "       0, 0, 1, 1, 1, 3, 3, 0, 3, 1, 1, 1, 2, 1, 1, 1, 2, 0, 2, 1, 3, 0,\n",
       "       0, 0, 0, 0, 3, 3, 3, 1, 3, 0, 2, 3, 0, 3, 1, 2, 0, 0, 1, 2, 2, 3,\n",
       "       0, 3, 1, 3, 1, 0, 3, 3, 1, 0, 1, 3, 0, 2, 2, 2, 1, 1, 1, 3, 3, 2,\n",
       "       1, 1, 2, 1, 0, 3, 1, 2, 1, 3, 1, 1, 3, 1, 2, 1, 1, 1, 3, 0, 2, 3,\n",
       "       0, 2, 0, 2, 1, 1, 2, 1, 3, 2, 0, 3, 1, 0, 3, 2, 1, 2, 2, 2, 3, 2,\n",
       "       1, 1, 0, 0, 3, 0, 2, 3, 0, 1, 2, 1, 2, 2, 2, 1, 2, 0, 3, 2, 0, 2,\n",
       "       1, 3, 0, 3, 1, 0, 1, 1, 0, 3, 2, 3, 3, 2, 3, 2, 0, 3, 3, 1, 0, 0,\n",
       "       3, 1, 1, 0, 3, 2, 3, 2, 3, 3, 0, 1, 3, 2, 0, 1, 1, 0, 3, 3, 1, 0,\n",
       "       3, 3, 2, 3, 1, 1, 2, 0, 0, 2, 2, 3, 2, 1, 0, 0, 3, 0, 1, 2, 0, 0,\n",
       "       3, 1, 3, 2, 3, 3, 0, 1, 0, 2, 1, 1, 1, 3, 1, 2, 2, 3, 3, 3, 0, 3,\n",
       "       1, 1, 2, 3, 2, 3, 1, 0, 1, 0, 1, 0, 3, 3, 3, 0, 3, 1, 2, 1, 3, 0,\n",
       "       2, 3, 2, 3, 1, 2, 1, 0, 0, 2, 2, 3, 3, 0, 2, 2, 1, 2, 1, 0, 2, 3,\n",
       "       1, 0, 1, 1, 3, 2, 2, 1, 2, 1, 0, 3, 1, 2, 0, 1, 3, 0, 3, 0, 0, 2,\n",
       "       0, 3, 3, 1, 0, 0, 3, 2, 3, 1, 3, 3, 1, 1, 2, 1, 0, 3, 1, 1, 2, 2,\n",
       "       2, 1, 3, 2, 3, 0, 2, 1, 3, 0, 1, 1, 2, 0, 3, 3, 3, 0, 3, 0, 3, 2,\n",
       "       1, 2, 2, 2, 1, 0, 1, 0, 3, 0, 1, 0, 2, 2, 3, 3, 0, 1, 1, 1, 1, 2,\n",
       "       3, 2, 0, 3, 1, 1, 3, 3, 2, 1, 2, 2, 2, 3, 0, 3, 2, 1, 1, 0, 3, 3,\n",
       "       0, 0, 1, 0, 1, 1, 1, 0, 0, 2, 1, 3, 3, 1, 1, 3, 1, 0, 3, 2, 0, 1,\n",
       "       2, 3, 1, 0, 3, 3, 3, 1, 2, 0, 3, 1, 1, 1, 2, 2, 1, 2, 1, 0, 3, 0,\n",
       "       1, 2, 3, 3, 3, 0, 2, 2, 0, 3, 1, 1, 2, 1, 1, 3, 3, 1, 1, 2, 3, 3,\n",
       "       2, 2, 2, 0, 2, 3, 2, 1, 2, 1, 0, 1, 2, 2, 1, 2, 1, 1, 1, 0, 0, 2,\n",
       "       1, 2, 3, 2, 0, 1, 1, 0, 3, 0, 1, 2, 1, 0, 2, 0, 3, 3, 3, 0, 2, 2,\n",
       "       2, 1, 1, 3, 1, 1, 2, 3, 1, 2, 1, 1, 3, 3, 2, 1, 2, 0, 3, 0, 1, 0,\n",
       "       1, 2, 0, 2, 1, 1, 2, 0, 0, 2, 3, 0, 1, 3, 3, 0, 1, 2, 1, 1, 0, 1,\n",
       "       1, 0, 1, 1, 2, 1, 0, 3, 1, 0, 0, 3, 2, 0, 3, 1, 3, 0, 3, 1, 0, 3,\n",
       "       0, 2, 1, 2, 2, 1, 2, 0, 2, 3, 2, 0, 1, 0, 1, 2, 3, 1, 3, 0, 0, 1,\n",
       "       3, 1, 0, 1, 2, 1, 0, 2, 1, 1, 3, 2, 1, 1, 0, 2, 0, 1, 3, 2, 0, 0,\n",
       "       1, 2, 1, 1, 2, 0, 1, 1, 0, 3, 0, 3, 0, 1, 1, 1, 2, 3, 1, 3, 3, 0,\n",
       "       1, 1, 1, 1, 1, 2, 1, 1, 0, 2, 2, 1, 0, 2, 2, 1, 2, 1, 1, 3, 3, 2,\n",
       "       2, 3, 1, 3, 3, 1, 1, 2, 3, 0, 1, 3, 3, 1, 2, 2, 0, 3, 1, 1, 3, 1,\n",
       "       0, 0, 1, 1, 3, 0, 0, 1, 1, 2, 2, 0, 2, 3, 2, 0, 3, 2, 2, 1, 0, 2,\n",
       "       3, 0, 0, 0, 1, 3, 1, 2, 0, 2, 2, 2, 1, 2, 1, 2, 1, 2, 3, 0, 0, 0,\n",
       "       3, 1, 1, 2, 1, 1, 2, 2, 1, 0, 2, 3, 1, 3, 0, 3, 0, 2, 1, 1, 3, 1,\n",
       "       3, 1, 1, 1, 0, 3, 3, 3, 2, 1], dtype=int32)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rndwalks = list(nx.generate_random_paths(G, 10000, path_length = 6))\n",
    "model = Word2Vec(sentences = rndwalks, vector_size = 32, min_count = 1, workers = 8)\n",
    "\n",
    "nodemap = [None] * len(G.nodes)\n",
    "for k in model.wv.key_to_index:\n",
    "   nodemap[k] = model.wv.key_to_index[k]\n",
    "\n",
    "reducer = TSNE(n_components = 2, init = \"pca\")\n",
    "embeddings = reducer.fit_transform(model.wv.vectors[nodemap])\n",
    "reducer = KMeans(n_clusters = 4)\n",
    "clusters = reducer.fit(embeddings).labels_\n",
    "\n",
    "clusters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "f00c1779-b5c2-4f40-8ca7-dbf9ed52464c",
   "metadata": {},
   "outputs": [],
   "source": [
    "nodes = list(G.nodes)\n",
    "\n",
    "ground_truth = {}\n",
    "with open(\"1/nodes.txt\", 'r') as f:\n",
    "   for line in f:\n",
    "      fields = line.strip().split('\\t')\n",
    "      ground_truth[int(fields[0])] = int(fields[1])\n",
    "\n",
    "ground_truth = [ground_truth[i] for i in nodes]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f4cc816f-e8fb-4186-b82e-e20edcb23d2c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 0, 0, 1, 0, 0, 2, 0, 1, 2]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lp = list(nx.algorithms.community.asyn_lpa_communities(G))\n",
    "lp = {n: c for c in range(len(lp)) for n in lp[c]}\n",
    "lp_array = []\n",
    "for n in G.nodes:\n",
    "   lp_array.append(lp[n])\n",
    "\n",
    "lp_array[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "36cda6a2-2c92-497a-b237-59b47224fae0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9439976142363943\n",
      "0.8323939993712498\n"
     ]
    }
   ],
   "source": [
    "print(normalized_mutual_info_score(clusters, ground_truth))\n",
    "print(normalized_mutual_info_score(lp_array, ground_truth))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}