fix run

tira-io · Jun 24, 2024 · ca8070a · ca8070a
1 parent 00fb24b
commit ca8070a
Show file tree

Hide file tree

Showing 2 changed files with 188,694 additions and 12 deletions.
diff --git a/final/Final.ipynb b/final/Final.ipynb
@@ -9,9 +9,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 3,
    "metadata": {},
-   "outputs": [],
+   "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",
@@ -38,7 +48,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -61,9 +71,38 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 5,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "ir-benchmarks/antique-test-20230107-training documents:   0%|          | 1828/403666 [00:02<03:26, 1943.99it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "14:24:05.530 [ForkJoinPool-1-worker-3] WARN org.terrier.structures.indexing.Indexer - Adding an empty document to the index (2824443_2) - further warnings are suppressed\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "ir-benchmarks/antique-test-20230107-training documents: 100%|██████████| 403666/403666 [00:41<00:00, 9720.29it/s] \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "14:24:49.744 [ForkJoinPool-1-worker-3] WARN org.terrier.structures.indexing.Indexer - Indexed 1570 empty documents\n"
+     ]
+    }
+   ],
    "source": [
     "def create_index(documents, stopwords):\n",
     "    indexer = pt.IterDictIndexer(\"/tmp/index\", overwrite=True, meta={'docno': 100, 'text': 20480}, stopwords=stopwords)\n",
@@ -99,7 +138,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -108,7 +147,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -130,7 +169,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -146,7 +185,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -198,7 +237,7 @@
        "0    0.928343  "
       ]
      },
-     "execution_count": 14,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -215,10 +254,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {},
-   "outputs": [],
+   "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": [
+    "run = bm25(pt_dataset.get_topics('text'))\n",
     "persist_and_normalize_run(run, system_name='bm25-baseline', default_output='../runs')"
    ]
   }