course/videos/load_custom_dataset.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook regroups the code sample of the video below, which is a part of the [Hugging Face course](https://huggingface.co/course)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "cellView": "form"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/HyQgpJTkRdE?rel=0&amp;controls=0&amp;showinfo=0\" frameborder=\"0\" allowfullscreen></iframe>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#@title\n",
    "from IPython.display import HTML\n",
    "\n",
    "HTML('<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/HyQgpJTkRdE?rel=0&amp;controls=0&amp;showinfo=0\" frameborder=\"0\" allowfullscreen></iframe>')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Install the Transformers and Datasets libraries to run this notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "! pip install datasets transformers[sentencepiece]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!wget https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import load_dataset\n",
    "\n",
    "local_csv_dataset = load_dataset(\"csv\", data_files=\"winequality-white.csv\", sep=\";\")\n",
    "local_csv_dataset[\"train\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the dataset from the URL directly\n",
    "dataset_url = \"https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv\"\n",
    "remote_csv_dataset = load_dataset(\"csv\", data_files=dataset_url, sep=\";\")\n",
    "remote_csv_dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset_url = \"https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt\"\n",
    "text_dataset = load_dataset(\"text\", data_files=dataset_url)\n",
    "text_dataset[\"train\"][:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset_url = \"https://raw.githubusercontent.com/hirupert/sede/main/data/sede/train.jsonl\"\n",
    "json_lines_dataset = load_dataset(\"json\", data_files=dataset_url)\n",
    "json_lines_dataset[\"train\"][:2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset_url = \"https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v2.0.json\"\n",
    "json_dataset = load_dataset(\"json\", data_files=dataset_url, field=\"data\")\n",
    "json_dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://rajpurkar.github.io/SQuAD-explorer/dataset/\"\n",
    "data_files = {\"train\": f\"{url}train-v2.0.json\", \"validation\": f\"{url}dev-v2.0.json\"}\n",
    "json_dataset = load_dataset(\"json\", data_files=data_files, field=\"data\")\n",
    "json_dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "Loading a custom dataset",
   "provenance": []
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}