Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add chapter 10 #549

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
65 changes: 65 additions & 0 deletions course/fr/chapter10/section2.ipynb
Original file line number Diff line number Diff line change
@@ -0,0 +1,65 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "kK8kfIfqrgrc"
},
"source": [
"# Configurez votre instance Argilla"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "cGOYFrYyrgrd"
},
"outputs": [],
"source": [
"!pip install argilla"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "mWB23rrFrgrf"
},
"outputs": [],
"source": [
"import argilla as rg\n",
"\n",
"HF_TOKEN = \"...\" # uniquement pour les spaces privés\n",
"\n",
"client = rg.Argilla(\n",
" api_url=\"...\",\n",
" api_key=\"...\",\n",
" headers={\"Authorization\": f\"Bearer {HF_TOKEN}\"}, # uniquement pour les spaces privés\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "UVHJPCFKrgrg"
},
"outputs": [],
"source": [
"client.me"
]
}
],
"metadata": {
"colab": {
"name": "Set up your Argilla instance",
"provenance": []
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
115 changes: 115 additions & 0 deletions course/fr/chapter10/section3.ipynb
Original file line number Diff line number Diff line change
@@ -0,0 +1,115 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Chargez votre jeu de données dans Argilla"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install argilla datasets"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import argilla as rg\n",
"\n",
"HF_TOKEN = \"...\" # uniquement pour les spaces privés\n",
"\n",
"client = rg.Argilla(\n",
" api_url=\"...\",\n",
" api_key=\"...\",\n",
" headers={\"Authorization\": f\"Bearer {HF_TOKEN}\"}, # uniquement pour les spaces privés\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'text': Value(dtype='string', id=None),\n",
" 'label': Value(dtype='int64', id=None),\n",
" 'label_text': Value(dtype='string', id=None)}"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from datasets import load_dataset\n",
"\n",
"data = load_dataset(\"SetFit/ag_news\", split=\"train\")\n",
"data.features"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"settings = rg.Settings(\n",
" fields=[rg.TextField(name=\"text\")],\n",
" questions=[\n",
" rg.LabelQuestion(\n",
" name=\"label\", title=\"Classifier le texte :\", labels=data.unique(\"label_text\")\n",
" ),\n",
" rg.SpanQuestion(\n",
" name=\"entities\",\n",
" title=\"Surligner toutes les entités présentes dans le texte :\",\n",
" labels=[\"PERSON\", \"ORG\", \"LOC\", \"EVENT\"],\n",
" field=\"text\",\n",
" ),\n",
" ],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"dataset = rg.Dataset(name=\"ag_news\", settings=settings)\n",
"\n",
"dataset.create()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"dataset.records.log(data, mapping={\"label_text\": \"label\"})"
]
}
],
"metadata": {
"colab": {
"name": "Load your dataset to Argilla",
"provenance": []
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
95 changes: 95 additions & 0 deletions course/fr/chapter10/section5.ipynb
Original file line number Diff line number Diff line change
@@ -0,0 +1,95 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Utilisez votre jeu de données annoté"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install argilla"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import argilla as rg\n",
"\n",
"HF_TOKEN = \"...\" # uniquement pour les spaces privés\n",
"\n",
"client = rg.Argilla(\n",
" api_url=\"...\",\n",
" api_key=\"...\",\n",
" headers={\"Authorization\": f\"Bearer {HF_TOKEN}\"}, # uniquement pour les spaces privés\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"dataset = client.datasets(name=\"ag_news\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"status_filter = rg.Query(filter=rg.Filter([(\"status\", \"==\", \"completed\")]))\n",
"\n",
"filtered_records = dataset.records(status_filter)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"filtered_records.to_datasets().push_to_hub(\"argilla/ag_news_annotated\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"dataset.to_hub(repo_id=\"argilla/ag_news_annotated\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"dataset = rg.Dataset.from_hub(repo_id=\"argilla/ag_news_annotated\")"
]
}
],
"metadata": {
"colab": {
"name": "Use your annotated dataset",
"provenance": []
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 4
}