Stopdwords

Group-8-Retrieval-System/bm25_stopwords.ipynb

@@ -0,0 +1,252 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "PyTerrier 0.10.0 has loaded Terrier 5.8 (built by craigm on 2023-11-01 18:05) and terrier-helper 0.0.8\n",
+      "\n",
+      "No etc/terrier.properties, using terrier.default.properties for bootstrap configuration.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Imports\n",
+    "from tira.third_party_integrations import ensure_pyterrier_is_loaded, persist_and_normalize_run\n",
+    "from tira.rest_api_client import Client\n",
+    "\n",
+    "import pyterrier as pt\n",
+    "\n",
+    "# Create a REST client to the TIRA platform for retrieving the pre-indexed data.\n",
+    "ensure_pyterrier_is_loaded()\n",
+    "tira = Client()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The dataset: the union of the IR Anthology and the ACL Anthology\n",
+    "# This line creates an IRDSDataset object and registers it under the name provided as an argument.\n",
+    "dataset = 'antique-test-20230107-training'\n",
+    "\n",
+    "pt_dataset = pt.get_dataset('irds:ir-lab-sose-2024/ir-acl-anthology-20240504-training')\n",
+    "\n",
+    "# A (pre-built) PyTerrier index loaded from TIRA\n",
+    "index = tira.pt.index('ir-lab-sose-2024/tira-ir-starter/Index (tira-ir-starter-pyterrier)', pt_dataset)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bm25 = pt.BatchRetrieve(index, wmodel=\"BM25\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Stopwords"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def create_index(documents, stopwords):\n",
+    "    indexer = pt.IterDictIndexer(\"/tmp/index\", overwrite=True, meta={'docno': 100, 'text': 20480}, stopwords=customStopwords)\n",
+    "    index_ref = indexer.index(documents)\n",
+    "    return pt.IndexFactory.of(index_ref)\n",
+    "\n",
+    "customStopwords =[\n",
+    "    'i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', 'your', 'yours', \n",
+    "    'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', 'her', 'hers', 'herself', \n",
+    "    'it', 'its', 'itself', 'they', 'them', 'their', 'theirs', 'themselves', 'what', 'which', \n",
+    "    'who', 'whom', 'this', 'that', 'these', 'those', 'am', 'is', 'are', 'was', 'were', 'be', \n",
+    "    'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', 'did', 'doing', 'a', 'an', \n",
+    "    'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', 'at', 'by', \n",
+    "    'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during', 'before', \n",
+    "    'after', 'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', \n",
+    "    'under', 'again', 'further', 'then', 'once', 'here', 'there', 'when', 'where', 'why', \n",
+    "    'how', 'all', 'any', 'both', 'each', 'few', 'more', 'most', 'other', 'some', 'such', \n",
+    "    'no', 'nor', 'not', 'only', 'own', 'same', 'so', 'than', 'too', 'very', 's', 't', 'can', \n",
+    "    'will', 'just', 'don', 'should', 'now'\n",
+    "]\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "ir-lab-sose-2024/ir-acl-anthology-20240504-training documents:  71%|███████   | 90005/126958 [00:22<00:08, 4212.71it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "19:23:10.931 [ForkJoinPool-1-worker-3] WARN org.terrier.structures.indexing.Indexer - Adding an empty document to the index (2020.mir_conference-2020.1) - further warnings are suppressed\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "ir-lab-sose-2024/ir-acl-anthology-20240504-training documents: 100%|██████████| 126958/126958 [00:31<00:00, 4002.84it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "19:23:24.124 [ForkJoinPool-1-worker-3] WARN org.terrier.structures.indexing.Indexer - Indexed 3 empty documents\n"
+     ]
+    }
+   ],
+   "source": [
+    "index = create_index(pt_dataset.get_corpus_iter(), customStopwords)\n",
+    "\n",
+    "bm25_stopwords = pt.BatchRetrieve(index, wmodel=\"BM25\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Evaluation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>name</th>\n",
+       "      <th>recall_1000</th>\n",
+       "      <th>ndcg_cut_5</th>\n",
+       "      <th>ndcg_cut.10</th>\n",
+       "      <th>recip_rank</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>BM25_Stopwords</td>\n",
+       "      <td>0.83441</td>\n",
+       "      <td>0.382805</td>\n",
+       "      <td>0.367656</td>\n",
+       "      <td>0.581239</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             name  recall_1000  ndcg_cut_5  ndcg_cut.10  recip_rank\n",
+       "0  BM25_Stopwords      0.83441    0.382805     0.367656    0.581239"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pt.Experiment(\n",
+    "    retr_systems=[bm25_stopwords],\n",
+    "    topics=pt_dataset.get_topics('text'),\n",
+    "    qrels=pt_dataset.get_qrels(),\n",
+    "    names=['BM25_Stopwords'],\n",
+    "    eval_metrics=['recall_1000', 'ndcg_cut_5', 'ndcg_cut.10', 'recip_rank']\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "run = bm25_stopwords(pt_dataset.get_topics('text'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The run file is normalized outside the TIRA sandbox, I will store it at \"../runs\".\n",
+      "Done. run file is stored under \"../runs/run.txt\".\n"
+     ]
+    }
+   ],
+   "source": [
+    "persist_and_normalize_run(run, system_name='bm25-baseline', default_output='../runs')"
+   ]
+  }
+ ],
+ "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}