course/videos/datasets_and_dataframes.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/tfcY1067A5Q?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/tfcY1067A5Q?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": [
    "from datasets import load_dataset\n",
    "\n",
    "dataset = load_dataset(\"swiss_judgment_prediction\", \"all_languages\", split=\"train\")\n",
    "dataset[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Convert the output format to pandas.DataFrame\n",
    "dataset.set_format(\"pandas\")\n",
    "dataset[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset.__getitem__(0)\n",
    "\n",
    "dataset.set_format(\"pandas\")\n",
    "\n",
    "dataset.__getitem__(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = dataset.to_pandas()\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# How are languages distributed across regions?\n",
    "df.groupby(\"region\")[\"language\"].value_counts()\n",
    "\n",
    "# Which legal area is most common?\n",
    "df[\"legal area\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "# Load a pretrained tokenizer\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n",
    "# Tokenize the `text` column\n",
    "dataset.map(lambda x : tokenizer(x[\"text\"]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Reset back to Arrow format\n",
    "dataset.reset_format()\n",
    "# Now we can tokenize!\n",
    "dataset.map(lambda x : tokenizer(x[\"text\"]))"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Datasets + DataFrames = ❤️",
   "provenance": []
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}