diff --git a/notebooks/Predicted_super_domains_to_normclass.ipynb b/notebooks/Predicted_super_domains_to_normclass.ipynb
index d0d76dc7fbc9ad6355b4af1975e4f41496a42df9..46a0ffad1239d1c55f3ef42c1ddba7f990727f12 100644
--- a/notebooks/Predicted_super_domains_to_normclass.ipynb
+++ b/notebooks/Predicted_super_domains_to_normclass.ipynb
@@ -360,7 +360,65 @@
},
{
"cell_type": "code",
- "execution_count": 18,
+ "execution_count": 40,
+ "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>0</th>\n",
+ " <th>1</th>\n",
+ " <th>2</th>\n",
+ " <th>3</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Économie rustique</td>\n",
+ " <td>Droit Jurisprudence</td>\n",
+ " <td>Agriculture</td>\n",
+ " <td>Histoire naturelle</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " 0 1 2 3\n",
+ "0 Économie rustique Droit Jurisprudence Agriculture Histoire naturelle"
+ ]
+ },
+ "execution_count": 40,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.DataFrame([np.insert(g['super_domain_bert'].values,0,n)])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 41,
"metadata": {},
"outputs": [
{
@@ -1034,7 +1092,21 @@
"Droit saxon Histoire\n",
"Droit | Droit ecclésiastique Droit Jurisprudence\n",
"Droit | Histoire moderne Droit Jurisprudence\n",
- "Droit | Littérature | Commerce Belles-lettres\n",
+ "Droit | Littérature | Commerce Belles-lettres\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/var/folders/qv/x3jfzb6x2s5cpb2_8lw4g06m0000gn/T/ipykernel_73946/3752465403.py:5: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.\n",
+ " df2 = df2.append(pd.DataFrame([np.insert(g['super_domain_bert'].values,0,n)]), ignore_index=True)\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
"Droit | Médecine Philosophie\tDroit Jurisprudence\n",
"Droits honorifiques Droit Jurisprudence\n",
"Dynamique Physique\n",
@@ -2856,9 +2928,237 @@
}
],
"source": [
+ "df2 = pd.DataFrame()\n",
+ "\n",
"for n, g in dfg:\n",
" print(n, '\\t'.join(g['super_domain_bert'].values))\n",
- " "
+ " df2 = df2.append(pd.DataFrame([np.insert(g['super_domain_bert'].values,0,n)]), ignore_index=True)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 42,
+ "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>0</th>\n",
+ " <th>1</th>\n",
+ " <th>2</th>\n",
+ " <th>3</th>\n",
+ " <th>4</th>\n",
+ " <th>5</th>\n",
+ " <th>6</th>\n",
+ " <th>7</th>\n",
+ " <th>8</th>\n",
+ " <th>9</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Abus des langues</td>\n",
+ " <td>Philosophie</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Accord de sons</td>\n",
+ " <td>Belles-lettres</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Acoustique</td>\n",
+ " <td>Physique</td>\n",
+ " <td>Belles-lettres</td>\n",
+ " <td>Médecine</td>\n",
+ " <td>Médecine</td>\n",
+ " <td>Physique</td>\n",
+ " <td>Médecine</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Agonistique</td>\n",
+ " <td>Histoire</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Agriculture décorative</td>\n",
+ " <td>Agriculture</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2480</th>\n",
+ " <td>terme usité parmi les Maréchaux</td>\n",
+ " <td>Chasse</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2481</th>\n",
+ " <td>vaisselle d'étain</td>\n",
+ " <td>Métiers</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2482</th>\n",
+ " <td>Ébénisterie</td>\n",
+ " <td>Métiers</td>\n",
+ " <td>Métiers</td>\n",
+ " <td>Musique</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2483</th>\n",
+ " <td>Ébénisterie | Tapisserie</td>\n",
+ " <td>Métiers</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2484</th>\n",
+ " <td>Économie rustique</td>\n",
+ " <td>Droit Jurisprudence</td>\n",
+ " <td>Agriculture</td>\n",
+ " <td>Histoire naturelle</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>2485 rows × 10 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " 0 1 2 \\\n",
+ "0 Abus des langues Philosophie NaN \n",
+ "1 Accord de sons Belles-lettres NaN \n",
+ "2 Acoustique Physique Belles-lettres \n",
+ "3 Agonistique Histoire NaN \n",
+ "4 Agriculture décorative Agriculture NaN \n",
+ "... ... ... ... \n",
+ "2480 terme usité parmi les Maréchaux Chasse NaN \n",
+ "2481 vaisselle d'étain Métiers NaN \n",
+ "2482 Ébénisterie Métiers Métiers \n",
+ "2483 Ébénisterie | Tapisserie Métiers NaN \n",
+ "2484 Économie rustique Droit Jurisprudence Agriculture \n",
+ "\n",
+ " 3 4 5 6 7 8 9 \n",
+ "0 NaN NaN NaN NaN NaN NaN NaN \n",
+ "1 NaN NaN NaN NaN NaN NaN NaN \n",
+ "2 Médecine Médecine Physique Médecine NaN NaN NaN \n",
+ "3 NaN NaN NaN NaN NaN NaN NaN \n",
+ "4 NaN NaN NaN NaN NaN NaN NaN \n",
+ "... ... ... ... ... ... ... ... \n",
+ "2480 NaN NaN NaN NaN NaN NaN NaN \n",
+ "2481 NaN NaN NaN NaN NaN NaN NaN \n",
+ "2482 Musique NaN NaN NaN NaN NaN NaN \n",
+ "2483 NaN NaN NaN NaN NaN NaN NaN \n",
+ "2484 Histoire naturelle NaN NaN NaN NaN NaN NaN \n",
+ "\n",
+ "[2485 rows x 10 columns]"
+ ]
+ },
+ "execution_count": 42,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df2"
]
},
{