fix persons if no idref

dataesr · Dec 7, 2022 · 00fb064 · 00fb064
1 parent 816519c
commit 00fb064
Showing 1 changed file with 18 additions and 9 deletions.
diff --git a/Etoiles_Europe.ipynb b/Etoiles_Europe.ipynb
@@ -72,7 +72,7 @@
     "etoiles = etoiles.assign(person =  etoiles[\"prenom\"] +\" \"+ etoiles[\"nom\"])\n",
     "\n",
     "# etoiles = etoiles.assign(type_de_prix = \"Etoiles de l'Europe\")\n",
-    "etoiles = etoiles.assign(edition=str(edition), type_de_prix=\"Etoiles de l'Europe\", edition=str(an), person=etoiles[\"prenom\"] +\" \"+ etoiles[\"nom\"])"
+    "etoiles = etoiles.assign(type_de_prix=\"Etoiles de l'Europe\", edition=str(an), person=etoiles[\"prenom\"] +\" \"+ etoiles[\"nom\"])"
    ]
   },
   {
@@ -93,17 +93,22 @@
     "# # fonction de match des personnes pour récupérer le idref\n",
     "counter = 0\n",
     "for e in et:\n",
-    "    print(e['person'])\n",
     "    try:\n",
     "        response = pydref.identify(e['person'])\n",
     "    except:\n",
     "        print(f\"erreur pour {e['person']} on attend 5s.\")\n",
     "        time.sleep(5)\n",
     "        continue\n",
-    "    counter += 1\n",
-    "    print(counter, end=',')\n",
-    "    e['idref'] = response.get('idref')\n",
-    "    del(e['person'])"
+    "    if not response.get('idref'):\n",
+    "        print(f\"NO idref:{e['person']}\" )\n",
+    "    else:\n",
+    "        counter += 1\n",
+    "        print(counter)\n",
+    "        e['idref'] = response.get('idref')\n",
+    "    \n",
+    "        \n",
+    "#     del(e['person'])\n",
+    "    "
    ]
   },
   {
@@ -134,7 +139,8 @@
     "        if re.search(r'^f', e['sexe']):\n",
     "            e['sexe'] = 'femme'\n",
     "            e['sexe_code'] = '2'\n",
-    "        e['sexe'] = e['sexe'].capitalize()"
+    "        e['sexe'] = e['sexe'].capitalize()\n",
+    "\n"
    ]
   },
   {
@@ -385,8 +391,11 @@
     "export.to_csv(PATH + \"etoiles_europe_2013-\" + str(an) + \".csv\", sep=\";\", \n",
     "              encoding=\"ANSI\", na_rep=\"\", index=False, line_terminator='\\r')\n",
     "\n",
-    "export.to_csv(PATH + \"open data/fr-esr-etoile-de-l-europe.csv\", sep=\";\", \n",
-    "              encoding=\"ANSI\", na_rep=\"\", index=False, line_terminator='\\r')"
+    "'''VERIFIER dans le fichier CSV qu\\'il ne manque pas des infos existantes comme les idref non trouvés et sauver ce fichier\n",
+    "à nouveau dans le dossier OPENDATA sous le nom fr-esr-etoile-de-l-europe.csv'''\n",
+    "\n",
+    "# export.to_csv(PATH + \"open data/fr-esr-etoile-de-l-europe.csv\", sep=\";\", \n",
+    "#               encoding=\"ANSI\", na_rep=\"\", index=False, line_terminator='\\r')"
    ]
   }
  ],