From da3edf34fcc99b9f7c1e58a9416c399d0473c601 Mon Sep 17 00:00:00 2001
From: Ludovic Moncla <moncla.ludovic@gmail.com>
Date: Fri, 9 Sep 2022 19:09:20 +0200
Subject: [PATCH] Update Tutoriel-geoparsing.ipynb

---
 Tutoriel-geoparsing.ipynb | 123 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 119 insertions(+), 4 deletions(-)

diff --git a/Tutoriel-geoparsing.ipynb b/Tutoriel-geoparsing.ipynb
index 84bf715..81392cd 100644
--- a/Tutoriel-geoparsing.ipynb
+++ b/Tutoriel-geoparsing.ipynb
@@ -184,19 +184,51 @@
     "\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Importer la librairie `Stanza` et télécharger le modèles pré-entrainé pour le français : "
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "import stanza\n",
+    "\n",
+    "stanza.download('fr')"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "stanza_parser = stanza.Pipeline(lang='fr', processors='tokenize,ner')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc = stanza_parser(content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for ent in doc.ents:\n",
+    "    print(ent.text, ent.type)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -205,19 +237,102 @@
     "### 5.2 SpaCy NER"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Installer le modèle français pré-entrainé de `spaCy` :"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "!python -m spacy download fr_core_news_sm"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Importer la librarie `spaCy` :"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "import spacy"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Charger le modèle français pré-entrainé de `spaCy`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "spacy_parser = spacy.load('fr_core_news_sm')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Executer la reconnaissance d'entités nommées :"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc = spacy_parser(content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Afficher la liste des entités nommées repérées :"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for ent in doc.ents:\n",
+    "    print(ent.text, ent.label_)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Afficher de manière graphique les entités nommées avec `displaCy` :"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "displacy.render(doc, style=\"ent\", jupyter=True) "
+   ]
   },
   {
    "cell_type": "markdown",
-- 
GitLab