course/videos/datasets_overview

{ "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/_BZearw7f0w?rel=0&controls=0&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/_BZearw7f0w?rel=0&controls=0&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": [ { "name": "stderr", "output_type": "stream", "text": [ "Reusing dataset glue (/home/sgugger/.cache/huggingface/datasets/glue/mrpc/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad)\n" ] }, { "data": { "text/plain": [ "DatasetDict({\n", " train: Dataset({\n", " features: ['sentence1', 'sentence2', 'label', 'idx'],\n", " num_rows: 3668\n", " })\n", " validation: Dataset({\n", " features: ['sentence1', 'sentence2', 'label', 'idx'],\n", " num_rows: 408\n", " })\n", " test: Dataset({\n", " features: ['sentence1', 'sentence2', 'label', 'idx'],\n", " num_rows: 1725\n", " })\n", "})" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from datasets import load_dataset\n", "\n", "raw_datasets = load_dataset(\"glue\", \"mrpc\")\n", "raw_datasets" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Dataset({\n", " features: ['sentence1', 'sentence2', 'label', 'idx'],\n", " num_rows: 3668\n", "})" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_datasets[\"train\"]" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'idx': 6,\n", " 'label': 0,\n", " 'sentence1': 'The Nasdaq had a weekly gain of 17.27 , or 1.2 percent , closing at 1,520.15 on Friday .',\n", " 'sentence2': 'The tech-laced Nasdaq Composite .IXIC rallied 30.46 points , or 2.04 percent , to 1,520.15 .'}" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_datasets[\"train\"][6]" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'idx': [0, 1, 2, 3, 4],\n", " 'label': [1, 0, 1, 0, 1],\n", " 'sentence1': ['Amrozi accused his brother , whom he called \" the witness \" , of deliberately distorting his evidence .',\n", " \"Yucaipa owned Dominick 's before selling the chain to Safeway in 1998 for $ 2.5 billion .\",\n", " 'They had published an advertisement on the Internet on June 10 , offering the cargo for sale , he added .',\n", " 'Around 0335 GMT , Tab shares were up 19 cents , or 4.4 % , at A $ 4.56 , having earlier set a record high of A $ 4.57 .',\n", " 'The stock rose $ 2.11 , or about 11 percent , to close Friday at $ 21.51 on the New York Stock Exchange .'],\n", " 'sentence2': ['Referring to him as only \" the witness \" , Amrozi accused his brother of deliberately distorting his evidence .',\n", " \"Yucaipa bought Dominick 's in 1995 for $ 693 million and sold it to Safeway for $ 1.8 billion in 1998 .\",\n", " \"On June 10 , the ship 's owners had published an advertisement on the Internet , offering the explosives for sale .\",\n", " 'Tab shares jumped 20 cents , or 4.6 % , to set a record closing high at A $ 4.57 .',\n", " 'PG & E Corp. shares jumped $ 1.63 or 8 percent to $ 21.03 on the New York Stock Exchange on Friday .']}" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_datasets[\"train\"][:5]" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'sentence1': Value(dtype='string', id=None),\n", " 'sentence2': Value(dtype='string', id=None),\n", " 'label': ClassLabel(num_classes=2, names=['not_equivalent', 'equivalent'], names_file=None, id=None),\n", " 'idx': Value(dtype='int32', id=None)}" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_datasets[\"train\"].features" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "9b3c52a30cf04ee3a23967aa3e03ebaa", "version_major": 2, "version_minor": 0 }, "text/plain": [ "HBox(children=(FloatProgress(value=0.0, max=3668.0), HTML(value='')))" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "05b0adf634ee4eedb107a5c9eb4e1d06", "version_major": 2, "version_minor": 0 }, "text/plain": [ "HBox(children=(FloatProgress(value=0.0, max=408.0), HTML(value='')))" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "1d3817f39edb4190ae89b2a6cc0f7a2c", "version_major": 2, "version_minor": 0 }, "text/plain": [ "HBox(children=(FloatProgress(value=0.0, max=1725.0), HTML(value='')))" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "{'train': ['attention_mask', 'idx', 'input_ids', 'label', 'sentence1', 'sentence2', 'token_type_ids'], 'validation': ['attention_mask', 'idx', 'input_ids', 'label', 'sentence1', 'sentence2', 'token_type_ids'], 'test': ['attention_mask', 'idx', 'input_ids', 'label', 'sentence1', 'sentence2', 'token_type_ids']}\n" ] } ], "source": [ "from transformers import AutoTokenizer\n", "\n", "checkpoint = \"bert-base-cased\"\n", "tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n", "\n", "def tokenize_function(example):\n", " return tokenizer(\n", " example[\"sentence1\"], example[\"sentence2\"], padding=\"max_length\", truncation=True, max_length=128\n", " )\n", "\n", "tokenized_datasets = raw_datasets.map(tokenize_function)\n", "print(tokenized_datasets.column_names)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Loading cached processed dataset at /home/sgugger/.cache/huggingface/datasets/glue/mrpc/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad/cache-2b2682faffe74c3f.arrow\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "a982bbb10e9648fe94b80ab7f25e4ca0", "version_major": 2, "version_minor": 0 }, "text/plain": [ "HBox(children=(FloatProgress(value=0.0, max=1.0), HTML(value='')))" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stderr", "output_type": "stream", "text": [ "Loading cached processed dataset at /home/sgugger/.cache/huggingface/datasets/glue/mrpc/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad/cache-754363c6c40d803c.arrow\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n" ] } ], "source": [ "from transformers import AutoTokenizer\n", "\n", "checkpoint = \"bert-base-cased\"\n", "tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n", "\n", "def tokenize_function(examples):\n", " return tokenizer(\n", " examples[\"sentence1\"], examples[\"sentence2\"], padding=\"max_length\", truncation=True, max_length=128\n", " )\n", "\n", "tokenized_datasets = raw_datasets.map(tokenize_function, batched=True)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Dataset({\n", " features: ['attention_mask', 'input_ids', 'labels', 'token_type_ids'],\n", " num_rows: 3668\n", "})" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tokenized_datasets = tokenized_datasets.remove_columns([\"idx\", \"sentence1\", \"sentence2\"])\n", "tokenized_datasets = tokenized_datasets.rename_column(\"label\", \"labels\")\n", "tokenized_datasets = tokenized_datasets.with_format(\"torch\")\n", "tokenized_datasets[\"train\"]" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "small_train_dataset = tokenized_datasets[\"train\"].select(range(100))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "colab": { "name": "Hugging Face Datasets overview (Pytorch)", "provenance": [] } }, "nbformat": 4, "nbformat_minor": 4 }

course/videos/datasets_overview_pt.ipynb (388 lines of code) (raw):