Update sinrvec_fr.ipynb (#116)

adding min_freq=0 for documents preprocessing
SINr-Embeddings · Nov 29, 2024 · 6756b0b · 6756b0b
1 parent ae6413d
commit 6756b0b
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/notebooks/sinrvec_fr.ipynb b/notebooks/sinrvec_fr.ipynb
@@ -835,14 +835,14 @@
     "                                  './train_#DOC#.txt'),\n",
     "                                  \".\", n_jobs=8)\n",
     "vrt_maker.do_txt_to_vrt(separator=separator)\n",
-    "docs_train = ppcs.extract_text('./train_#DOC#.vrt', min_length_doc=-1)\n",
+    "docs_train = ppcs.extract_text('./train_#DOC#.vrt', min_freq=0, min_length_doc=-1)\n",
     "\n",
     "vrt_maker = ppcs.VRTMaker(ppcs.Corpus(ppcs.Corpus.REGISTER_WEB,\n",
     "                                  ppcs.Corpus.LANGUAGE_EN,\n",
     "                                  './test_#DOC#.txt'),\n",
     "                                  \".\", n_jobs=8)\n",
     "vrt_maker.do_txt_to_vrt(separator=separator)\n",
-    "docs_test = ppcs.extract_text('./test_#DOC#.vrt', min_length_doc=-1)"
+    "docs_test = ppcs.extract_text('./test_#DOC#.vrt', min_freq=0, min_length_doc=-1)"
    ]
   },
   {