From cb0b695f407feb1c688aece313293156dff278d5 Mon Sep 17 00:00:00 2001
From: Ludovic Moncla <moncla.ludovic@gmail.com>
Date: Mon, 16 Jan 2023 15:04:30 +0100
Subject: [PATCH] Update Classification_Zero-Shot-Learning.ipynb
---
.../Classification_Zero-Shot-Learning.ipynb | 269 ++++++++++++++++--
1 file changed, 247 insertions(+), 22 deletions(-)
diff --git a/notebooks/Classification_Zero-Shot-Learning.ipynb b/notebooks/Classification_Zero-Shot-Learning.ipynb
index 673bab2..a42e4f4 100644
--- a/notebooks/Classification_Zero-Shot-Learning.ipynb
+++ b/notebooks/Classification_Zero-Shot-Learning.ipynb
@@ -123,7 +123,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
@@ -138,7 +138,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@@ -146,7 +146,170 @@
"id": "LRKJzWmf3pCg",
"outputId": "686c3ef4-8267-4266-95af-7193725aadca"
},
- "outputs": [],
+ "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>volume</th>\n",
+ " <th>numero</th>\n",
+ " <th>head</th>\n",
+ " <th>normClass</th>\n",
+ " <th>classEDdA</th>\n",
+ " <th>author</th>\n",
+ " <th>id_enccre</th>\n",
+ " <th>domaine_enccre</th>\n",
+ " <th>ensemble_domaine_enccre</th>\n",
+ " <th>content</th>\n",
+ " <th>contentWithoutClass</th>\n",
+ " <th>firstParagraph</th>\n",
+ " <th>nb_word</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>11</td>\n",
+ " <td>2973</td>\n",
+ " <td>ORNIS</td>\n",
+ " <td>Commerce</td>\n",
+ " <td>Comm.</td>\n",
+ " <td>unsigned</td>\n",
+ " <td>v11-1767-0</td>\n",
+ " <td>commerce</td>\n",
+ " <td>Commerce</td>\n",
+ " <td>ORNIS, s. m. toile des Indes, (Comm.) sortes d...</td>\n",
+ " <td>ORNIS, s. m. toile des Indes, () sortes de\\nto...</td>\n",
+ " <td>ORNIS, s. m. toile des Indes, () sortes de\\nto...</td>\n",
+ " <td>45</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>3</td>\n",
+ " <td>3525</td>\n",
+ " <td>COMPRENDRE</td>\n",
+ " <td>Philosophie</td>\n",
+ " <td>terme de Philosophie,</td>\n",
+ " <td>Diderot</td>\n",
+ " <td>v3-1722-0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>* COMPRENDRE, v. act. terme de Philosophie,\\nc...</td>\n",
+ " <td>* COMPRENDRE, v. act. \\nc'est appercevoir la l...</td>\n",
+ " <td>* COMPRENDRE, v. act. \\nc'est appercevoir la l...</td>\n",
+ " <td>92</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>1</td>\n",
+ " <td>2560</td>\n",
+ " <td>ANCRE</td>\n",
+ " <td>Marine</td>\n",
+ " <td>Marine</td>\n",
+ " <td>d'Alembert & Diderot</td>\n",
+ " <td>v1-1865-0</td>\n",
+ " <td>marine</td>\n",
+ " <td>Marine</td>\n",
+ " <td>ANCRE, s. f. (Marine.) est un instrument de fe...</td>\n",
+ " <td>ANCRE, s. f. (.) est un instrument de fer\\nABC...</td>\n",
+ " <td>ANCRE, s. f. (.) est un instrument de fer\\nABC...</td>\n",
+ " <td>3327</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>16</td>\n",
+ " <td>4241</td>\n",
+ " <td>VAKEBARO</td>\n",
+ " <td>Géographie moderne</td>\n",
+ " <td>Géog. mod.</td>\n",
+ " <td>unsigned</td>\n",
+ " <td>v16-2587-0</td>\n",
+ " <td>géographie</td>\n",
+ " <td>Géographie</td>\n",
+ " <td>VAKEBARO, (Géog. mod.) vallée du royaume\\nd'Es...</td>\n",
+ " <td>VAKEBARO, () vallée du royaume\\nd'Espagne dans...</td>\n",
+ " <td>VAKEBARO, () vallée du royaume\\nd'Espagne dans...</td>\n",
+ " <td>34</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>8</td>\n",
+ " <td>3281</td>\n",
+ " <td>INSPECTEUR</td>\n",
+ " <td>Histoire ancienne</td>\n",
+ " <td>Hist. anc.</td>\n",
+ " <td>unsigned</td>\n",
+ " <td>v8-2533-0</td>\n",
+ " <td>histoire</td>\n",
+ " <td>Histoire</td>\n",
+ " <td>INSPECTEUR, s. m. inspector ; (Hist. anc.) cel...</td>\n",
+ " <td>INSPECTEUR, s. m. inspector ; () celui \\nà qui...</td>\n",
+ " <td>INSPECTEUR, s. m. inspector ; () celui \\nà qui...</td>\n",
+ " <td>102</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " volume numero head normClass classEDdA \\\n",
+ "0 11 2973 ORNIS Commerce Comm. \n",
+ "1 3 3525 COMPRENDRE Philosophie terme de Philosophie, \n",
+ "2 1 2560 ANCRE Marine Marine \n",
+ "3 16 4241 VAKEBARO Géographie moderne Géog. mod. \n",
+ "4 8 3281 INSPECTEUR Histoire ancienne Hist. anc. \n",
+ "\n",
+ " author id_enccre domaine_enccre ensemble_domaine_enccre \\\n",
+ "0 unsigned v11-1767-0 commerce Commerce \n",
+ "1 Diderot v3-1722-0 NaN NaN \n",
+ "2 d'Alembert & Diderot v1-1865-0 marine Marine \n",
+ "3 unsigned v16-2587-0 géographie Géographie \n",
+ "4 unsigned v8-2533-0 histoire Histoire \n",
+ "\n",
+ " content \\\n",
+ "0 ORNIS, s. m. toile des Indes, (Comm.) sortes d... \n",
+ "1 * COMPRENDRE, v. act. terme de Philosophie,\\nc... \n",
+ "2 ANCRE, s. f. (Marine.) est un instrument de fe... \n",
+ "3 VAKEBARO, (Géog. mod.) vallée du royaume\\nd'Es... \n",
+ "4 INSPECTEUR, s. m. inspector ; (Hist. anc.) cel... \n",
+ "\n",
+ " contentWithoutClass \\\n",
+ "0 ORNIS, s. m. toile des Indes, () sortes de\\nto... \n",
+ "1 * COMPRENDRE, v. act. \\nc'est appercevoir la l... \n",
+ "2 ANCRE, s. f. (.) est un instrument de fer\\nABC... \n",
+ "3 VAKEBARO, () vallée du royaume\\nd'Espagne dans... \n",
+ "4 INSPECTEUR, s. m. inspector ; () celui \\nà qui... \n",
+ "\n",
+ " firstParagraph nb_word \n",
+ "0 ORNIS, s. m. toile des Indes, () sortes de\\nto... 45 \n",
+ "1 * COMPRENDRE, v. act. \\nc'est appercevoir la l... 92 \n",
+ "2 ANCRE, s. f. (.) est un instrument de fer\\nABC... 3327 \n",
+ "3 VAKEBARO, () vallée du royaume\\nd'Espagne dans... 34 \n",
+ "4 INSPECTEUR, s. m. inspector ; () celui \\nà qui... 102 "
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"df = pd.read_csv(input_path + test_set_path, sep=\"\\t\")\n",
"df.head()"
@@ -154,16 +317,27 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 4,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(15854, 13)"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
@@ -174,7 +348,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
@@ -183,18 +357,77 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 7,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(13441, 13)"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 8,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['Commerce',\n",
+ " 'Marine',\n",
+ " 'Géographie',\n",
+ " 'Histoire',\n",
+ " 'Belles-lettres - Poésie',\n",
+ " 'Economie domestique',\n",
+ " 'Droit - Jurisprudence',\n",
+ " 'Médecine - Chirurgie',\n",
+ " 'Militaire (Art) - Guerre - Arme',\n",
+ " 'Beaux-arts',\n",
+ " 'Antiquité',\n",
+ " 'Histoire naturelle',\n",
+ " 'Grammaire',\n",
+ " 'Philosophie',\n",
+ " 'Arts et métiers',\n",
+ " 'Pharmacie',\n",
+ " 'Religion',\n",
+ " 'Pêche',\n",
+ " 'Anatomie',\n",
+ " 'Architecture',\n",
+ " 'Musique',\n",
+ " 'Jeu',\n",
+ " 'Caractères',\n",
+ " 'Métiers',\n",
+ " 'Physique - [Sciences physico-mathématiques]',\n",
+ " 'Maréchage - Manège',\n",
+ " 'Chimie',\n",
+ " 'Blason',\n",
+ " 'Chasse',\n",
+ " 'Mathématiques',\n",
+ " 'Médailles',\n",
+ " 'Superstition',\n",
+ " 'Agriculture - Economie rustique',\n",
+ " 'Mesure',\n",
+ " 'Monnaie',\n",
+ " 'Minéralogie',\n",
+ " 'Politique',\n",
+ " 'Spectacle']"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"classes = df[column_class].unique().tolist()\n",
"classes"
@@ -218,7 +451,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
@@ -259,7 +492,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
@@ -318,15 +551,7 @@
"metadata": {},
"outputs": [],
"source": [
- "df[column_text].tolist()[0]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
+ "# test\n",
"premise = df[column_text].tolist()[0]\n",
"\n",
"true_probs = zero_shot_prediction(premise, classes)\n",
--
GitLab