From e40bf56fe9553eeea43fc4eff77fc8ef13fd3b2b Mon Sep 17 00:00:00 2001
From: William Bouchard <william.bouchard.2@umontreal.ca>
Date: Sun, 30 Mar 2025 16:27:12 +0000
Subject: [PATCH] Ajout de KeywordURNVerif.ipynb
---
jupyter/KeywordURNVerif.ipynb | 446 ++++++++++++++++++++++++++++++++++
1 file changed, 446 insertions(+)
create mode 100644 jupyter/KeywordURNVerif.ipynb
diff --git a/jupyter/KeywordURNVerif.ipynb b/jupyter/KeywordURNVerif.ipynb
new file mode 100644
index 0000000..cb0c144
--- /dev/null
+++ b/jupyter/KeywordURNVerif.ipynb
@@ -0,0 +1,446 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "d8c7db35",
+ "metadata": {},
+ "source": [
+ "# KeywordURNVerif\n",
+ "## Script pour extraire les keywords de l'API qui n'ont pas d'URN\n",
+ "\n",
+ "Pour extraire tous les keywords: get_no_urn_keywords()\n",
+ "\n",
+ "Pour filtrer par catégorie: filter_by_category(get_no_urn_keywords(), *Catégorie*)\n",
+ "\n",
+ "Par défaut, les fonctions exportent les résultats en CSV, mais on peut désactiver l'export en ajoutant le paramètre \"csv_export = False\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "20d7b5dd",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import requests\n",
+ "import pandas as pd"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "219b1ee7",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "API_URL = \"https://anthologiagraeca.org/api/keywords/\" "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "8cf7cb82",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#Fonction qui permet de récupérer tous les keywords depuis l'API dans un DataFrame\n",
+ "def get_api_data():\n",
+ " data = []\n",
+ " url = API_URL\n",
+ " \n",
+ " while url:\n",
+ " response = requests.get(url) \n",
+ " if response.status_code == 200:\n",
+ " page_data = response.json()\n",
+ " data.extend(page_data['results']) \n",
+ " url = page_data.get('next')\n",
+ " else:\n",
+ " print(f\"Erreur API : {response.status_code}\")\n",
+ " return pd.DataFrame() # Retourne un DataFrame vide en cas d'erreur\n",
+ " return pd.DataFrame(data)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "a9cbe306",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Fonction pour extraire le nom d'une liste de noms selon la priorité de la langue\n",
+ "def get_name(names):\n",
+ " #On préfère le français, puis l'anglais, etc.\n",
+ " priority_order = [\"fra\", \"eng\", \"grc\", \"ita\", \"lat\"]\n",
+ " \n",
+ " # Chercher le premier nom dans l'ordre de priorité\n",
+ " for name in names:\n",
+ " for language in priority_order:\n",
+ " if name[\"language\"] == language: return name[\"name\"]\n",
+ " \n",
+ " return None # Retourne None si aucun nom dans les langues prioritaires a été trouvé"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "f851d63b",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Fonction pour obtenir le nom en français à partir des noms de catégorie (il y a toujours une version en fr)\n",
+ "def get_category_name(category):\n",
+ " # Chercher dans la clé \"names\" pour obtenir le nom en français\n",
+ " for name in category.get(\"names\", []):\n",
+ " if name[\"language\"] == \"fra\":\n",
+ " return name[\"name\"]\n",
+ " return None # Si aucun nom en français n'est trouvé"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "379a5f10",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Fonction pour extraire l'URN\n",
+ "def get_urn(alternative_urns):\n",
+ " if alternative_urns:\n",
+ " return alternative_urns[0].get(\"urn\", None)\n",
+ " return None # Retourne None si l'URN n'est pas présente"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "76fcd266",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Retourne les keywords qui n'ont pas d'URN\n",
+ "def get_no_urn_keywords(csv_export = True):\n",
+ " # Cherche tous les keywords\n",
+ " keywords = get_api_data()\n",
+ " \n",
+ " #Simplifie leur structure et vérifie l'URN\n",
+ " keywords[\"category_name\"] = keywords[\"category\"].apply(get_category_name)\n",
+ " keywords[\"name\"] = keywords[\"names\"].apply(get_name)\n",
+ " keywords[\"alternative_urn\"] = keywords[\"alternative_urns\"].apply(get_urn)\n",
+ " \n",
+ " # On ne veut pas TOUT garder du keyword\n",
+ " columns_to_keep = ['id', 'url', 'category_name', 'name', 'alternative_urn']\n",
+ " keywords_filtered = keywords[columns_to_keep]\n",
+ " \n",
+ " # On garde seulement les keywords qui n'ont pas d'URN\n",
+ " keywords_filtered_no_urn = keywords_filtered[keywords_filtered[\"alternative_urn\"].isna()]\n",
+ " \n",
+ " # On exporte en CSV\n",
+ " if csv_export: keywords_filtered_no_urn.to_csv(\"keywords_no_urn.csv\", index=False, encoding=\"utf-8\")\n",
+ " \n",
+ " return keywords_filtered_no_urn"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "a66ebdee",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Retourne les keywords selon la catégorie demandée\n",
+ "def filter_by_category(keywords, category, csv_export = True):\n",
+ " \n",
+ " # Filtrer les lignes où la catégorie correspond\n",
+ " filtered_keywords = keywords[keywords[\"category_name\"]==category]\n",
+ " \n",
+ " #On exporte en CSV\n",
+ " if csv_export: filtered_keywords.to_csv(category+\"_no_urn.csv\", index=False, encoding=\"utf-8\")\n",
+ " \n",
+ " return filtered_keywords"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "ad7dd6ed",
+ "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>id</th>\n",
+ " <th>url</th>\n",
+ " <th>category_name</th>\n",
+ " <th>name</th>\n",
+ " <th>alternative_urn</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>34</th>\n",
+ " <td>35</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/35/</td>\n",
+ " <td>Poètes cités</td>\n",
+ " <td>Euphemus</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43</th>\n",
+ " <td>44</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/44/</td>\n",
+ " <td>Poètes cités</td>\n",
+ " <td>Parthenis</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45</th>\n",
+ " <td>46</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/46/</td>\n",
+ " <td>Poètes cités</td>\n",
+ " <td>Polyclitus</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>950</th>\n",
+ " <td>1139</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/1139/</td>\n",
+ " <td>Poètes cités</td>\n",
+ " <td>Tellen</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id url category_name \\\n",
+ "34 35 https://anthologiagraeca.org/api/keywords/35/ Poètes cités \n",
+ "43 44 https://anthologiagraeca.org/api/keywords/44/ Poètes cités \n",
+ "45 46 https://anthologiagraeca.org/api/keywords/46/ Poètes cités \n",
+ "950 1139 https://anthologiagraeca.org/api/keywords/1139/ Poètes cités \n",
+ "\n",
+ " name alternative_urn \n",
+ "34 Euphemus None \n",
+ "43 Parthenis None \n",
+ "45 Polyclitus None \n",
+ "950 Tellen None "
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "#Exemple d'utilisation\n",
+ "filter_by_category(get_no_urn_keywords(csv_export=False), \"Poètes cités\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "d8a35789",
+ "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>id</th>\n",
+ " <th>url</th>\n",
+ " <th>category_name</th>\n",
+ " <th>name</th>\n",
+ " <th>alternative_urn</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>2</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/2/</td>\n",
+ " <td>Parcours de lecture</td>\n",
+ " <td>Méléagre amoureux</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>5</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/5/</td>\n",
+ " <td>Parcours de lecture</td>\n",
+ " <td>Serments d'amour</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>6</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/6/</td>\n",
+ " <td>Peuples, lieux</td>\n",
+ " <td>Megarians</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>19</th>\n",
+ " <td>20</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/20/</td>\n",
+ " <td>Personnes citées</td>\n",
+ " <td>Diocles</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>22</th>\n",
+ " <td>23</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/23/</td>\n",
+ " <td>Motifs</td>\n",
+ " <td>Fleurs</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1083</th>\n",
+ " <td>1296</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/1296/</td>\n",
+ " <td>Personnes citées</td>\n",
+ " <td>Menestratos</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1085</th>\n",
+ " <td>1298</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/1298/</td>\n",
+ " <td>Personnes citées</td>\n",
+ " <td>Eumécius</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1086</th>\n",
+ " <td>1299</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/1299/</td>\n",
+ " <td>Personnes citées</td>\n",
+ " <td>Chairémon</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1087</th>\n",
+ " <td>1300</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/1300/</td>\n",
+ " <td>Personnes citées</td>\n",
+ " <td>Tityos</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1088</th>\n",
+ " <td>1301</td>\n",
+ " <td>https://anthologiagraeca.org/api/keywords/1301/</td>\n",
+ " <td>Personnes citées</td>\n",
+ " <td>Conon</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>706 rows × 5 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id url \\\n",
+ "1 2 https://anthologiagraeca.org/api/keywords/2/ \n",
+ "4 5 https://anthologiagraeca.org/api/keywords/5/ \n",
+ "5 6 https://anthologiagraeca.org/api/keywords/6/ \n",
+ "19 20 https://anthologiagraeca.org/api/keywords/20/ \n",
+ "22 23 https://anthologiagraeca.org/api/keywords/23/ \n",
+ "... ... ... \n",
+ "1083 1296 https://anthologiagraeca.org/api/keywords/1296/ \n",
+ "1085 1298 https://anthologiagraeca.org/api/keywords/1298/ \n",
+ "1086 1299 https://anthologiagraeca.org/api/keywords/1299/ \n",
+ "1087 1300 https://anthologiagraeca.org/api/keywords/1300/ \n",
+ "1088 1301 https://anthologiagraeca.org/api/keywords/1301/ \n",
+ "\n",
+ " category_name name alternative_urn \n",
+ "1 Parcours de lecture Méléagre amoureux None \n",
+ "4 Parcours de lecture Serments d'amour None \n",
+ "5 Peuples, lieux Megarians None \n",
+ "19 Personnes citées Diocles None \n",
+ "22 Motifs Fleurs None \n",
+ "... ... ... ... \n",
+ "1083 Personnes citées Menestratos None \n",
+ "1085 Personnes citées Eumécius None \n",
+ "1086 Personnes citées Chairémon None \n",
+ "1087 Personnes citées Tityos None \n",
+ "1088 Personnes citées Conon None \n",
+ "\n",
+ "[706 rows x 5 columns]"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "get_no_urn_keywords()"
+ ]
+ }
+ ],
+ "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": "3.10.12"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
--
GitLab