{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Lecture 1:  pipeline()\nThis course will teach you about natural language processing (NLP) using libraries from the Hugging Face ecosystem — 🤗 Transformers, 🤗 Datasets, 🤗 Tokenizers, and 🤗 Accelerate — as well as the Hugging Face Hub\n\n# 1 fill-mask                                                            \n# 2 ner (named entity recognition)                                                                   \n# 3 question-answering                                                              \n# 4 sentiment-analysis                                                    \n# 5 summarization                                                          \n# 6 text-generation                                                               \n# 7 translation                                                                      \n# 8 zero-shot-classification                                                           ","metadata":{}},{"cell_type":"markdown","source":"# Sentiment analysis","metadata":{}},{"cell_type":"code","source":"from transformers import pipeline\nclf = pipeline('sentiment-analysis')\n# clf(\"I appreciate your like and comments\")\n# clf(\"I don't like when my students don't like my videos\")\nclf(\"sky is blue\")","metadata":{"execution":{"iopub.status.busy":"2023-10-02T10:00:25.282261Z","iopub.execute_input":"2023-10-02T10:00:25.282636Z","iopub.status.idle":"2023-10-02T10:00:26.050289Z","shell.execute_reply.started":"2023-10-02T10:00:25.282609Z","shell.execute_reply":"2023-10-02T10:00:26.049244Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Pipeline\nIn the context of transformers and natural language processing (NLP), a \"pipeline\" refers to a sequence of processing steps that are applied to text data to perform various NLP tasks. Each step in the pipeline represents a specific processing task, and the output of one step becomes the input for the next step. Pipelines are used in transformers to streamline and automate the process of text analysis and NLP tasks. Here's a brief explanation of why pipelines are used and what they typically consist of:\n\n# Note:\nBy default, this pipeline selects a particular pretrained model that has been fine-tuned for sentiment analysis in English. The model is downloaded and cached when you create the classifier object. If you rerun the command, the cached model will be used instead and there is no need to download the model again.\n\nThere are three main steps involved when you pass some text to a pipeline:\n\nThe text is preprocessed into a format the model can understand.\nThe preprocessed inputs are passed to the model.\nThe predictions of the model are post-processed, so you can make sense of them.\n\n![image.png](attachment:aacab735-1c89-49d3-b8d5-30f843963f1f.png)\n\n# Why We Use Pipelines in Transformers:\n\nSimplicity: Pipelines simplify the process of applying various NLP tasks to text data. Instead of manually configuring and running each task separately, you can define a single pipeline with all the required steps.\n\nEfficiency: Pipelines are efficient because they allow you to reuse pre-trained transformer models and avoid redundant computations. The same transformer model can be used for multiple tasks in a pipeline.\n\nConsistency: Pipelines ensure that each task is executed consistently with the same pre-processing and post-processing steps, reducing the chance of errors and inconsistencies in results.\n\nEase of Deployment: When deploying NLP models for real-world applications, pipelines make it easier to manage and maintain the entire processing flow, from input data to output results.","metadata":{},"attachments":{"aacab735-1c89-49d3-b8d5-30f843963f1f.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"# Zero-shot-classification","metadata":{}},{"cell_type":"code","source":"from transformers import pipeline\n\nclassifier = pipeline(\"zero-shot-classification\")\nclassifier(\n    \"This is a course about the Transformers library\",\n    candidate_labels=[\"education\", \"politics\", \"business\"],\n)","metadata":{"execution":{"iopub.status.busy":"2023-10-02T10:43:49.686510Z","iopub.execute_input":"2023-10-02T10:43:49.687618Z","iopub.status.idle":"2023-10-02T10:44:09.537050Z","shell.execute_reply.started":"2023-10-02T10:43:49.687576Z","shell.execute_reply":"2023-10-02T10:44:09.536044Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# text-generation\nText generation\nNow let’s see how to use a pipeline to generate some text. The main idea here is that you provide a prompt and the model will auto-complete it by generating the remaining text. This is similar to the predictive text feature that is found on many phones. Text generation involves randomness, so it’s normal if you don’t get the same results as shown below.","metadata":{}},{"cell_type":"code","source":"from transformers import pipeline\ngen = pipeline('text-generation')\ngen(\"In this course we will teach you\")","metadata":{"execution":{"iopub.status.busy":"2023-10-02T10:46:20.284801Z","iopub.execute_input":"2023-10-02T10:46:20.285181Z","iopub.status.idle":"2023-10-02T10:46:28.340595Z","shell.execute_reply.started":"2023-10-02T10:46:20.285152Z","shell.execute_reply":"2023-10-02T10:46:28.339660Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Using any model from the Hub in a pipeline\nThe previous examples used the default model for the task at hand, but you can also choose a particular model from the Hub to use in a pipeline for a specific task — say, text generation. Go to the Model Hub and click on the corresponding tag on the left to display only the supported models for that task. You should get to a page like this one.","metadata":{}},{"cell_type":"code","source":"from transformers import pipeline\n\ngenerator = pipeline(\"text-generation\", model=\"distilgpt2\")\ngenerator(\n\"in this course we will teach you\",\nmax_length =30,\nnum_return_sequences=2\n)","metadata":{"execution":{"iopub.status.busy":"2023-10-02T10:51:08.947876Z","iopub.execute_input":"2023-10-02T10:51:08.948250Z","iopub.status.idle":"2023-10-02T10:51:17.775315Z","shell.execute_reply.started":"2023-10-02T10:51:08.948221Z","shell.execute_reply":"2023-10-02T10:51:17.774289Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Mask filling\nThe next pipeline you’ll try is fill-mask. The idea of this task is to fill in the blanks in a given text:","metadata":{}},{"cell_type":"code","source":"from transformers import pipeline\n\nunmasker = pipeline(\"fill-mask\")\nunmasker(\"This course will teach you all about <mask> models.\", top_k=5)","metadata":{"execution":{"iopub.status.busy":"2023-10-02T10:55:17.011009Z","iopub.execute_input":"2023-10-02T10:55:17.011388Z","iopub.status.idle":"2023-10-02T10:55:18.944004Z","shell.execute_reply.started":"2023-10-02T10:55:17.011347Z","shell.execute_reply":"2023-10-02T10:55:18.943008Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Named entity recognition\nNamed entity recognition (NER) is a task where the model has to find which parts of the input text correspond to entities such as persons, locations, or organizations. Let’s look at an example:","metadata":{}},{"cell_type":"code","source":"from transformers import pipeline\n\nner = pipeline(\"ner\", grouped_entities=True)\nner(\"My name is Sylvain and I work at Hugging Face in Brooklyn.\")","metadata":{"execution":{"iopub.status.busy":"2023-10-02T10:57:17.965873Z","iopub.execute_input":"2023-10-02T10:57:17.966212Z","iopub.status.idle":"2023-10-02T10:57:48.597428Z","shell.execute_reply.started":"2023-10-02T10:57:17.966186Z","shell.execute_reply":"2023-10-02T10:57:48.596104Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Question answering\nThe question-answering pipeline answers questions using information from a given context:","metadata":{}},{"cell_type":"code","source":"from transformers import pipeline\n\nquestion_answerer = pipeline(\"question-answering\")\nquestion_answerer(\n    question=\"Asman ka rang kia he?\",\n    context=\"Asman ka rang nila he. Asan bahut uncha he ju humy nila dikhai deta he\"\n)","metadata":{"execution":{"iopub.status.busy":"2023-10-02T11:07:13.249250Z","iopub.execute_input":"2023-10-02T11:07:13.249968Z","iopub.status.idle":"2023-10-02T11:07:14.765241Z","shell.execute_reply.started":"2023-10-02T11:07:13.249936Z","shell.execute_reply":"2023-10-02T11:07:14.764129Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Summarization\nSummarization is the task of reducing a text into a shorter text while keeping all (or most) of the important aspects referenced in the text. Here’s an example:","metadata":{}},{"cell_type":"code","source":"from transformers import pipeline\n\nsummarizer = pipeline(\"summarization\")\nsummarizer(\n    \"\"\"\n    America has changed dramatically during recent years. Not only has the number of \n    graduates in traditional engineering disciplines such as mechanical, civil, \n    electrical, chemical, and aeronautical engineering declined, but in most of \n    the premier American universities engineering curricula now concentrate on \n    and encourage largely the study of engineering science. As a result, there \n    are declining offerings in engineering subjects dealing with infrastructure, \n    the environment, and related issues, and greater concentration on high \n    technology subjects, largely supporting increasingly complex scientific \n    developments. While the latter is important, it should not be at the expense \n    of more traditional engineering.\n\n    Rapidly developing economies such as China and India, as well as other \n    industrial countries in Europe and Asia, continue to encourage and advance \n    the teaching of engineering. Both China and India, respectively, graduate \n    six and eight times as many traditional engineers as does the United States. \n    Other industrial countries at minimum maintain their output, while America \n    suffers an increasingly serious decline in the number of engineering graduates \n    and a lack of well-educated engineers.\n\"\"\"\n)","metadata":{"execution":{"iopub.status.busy":"2023-10-02T11:09:36.038951Z","iopub.execute_input":"2023-10-02T11:09:36.039344Z","iopub.status.idle":"2023-10-02T11:10:00.615779Z","shell.execute_reply.started":"2023-10-02T11:09:36.039298Z","shell.execute_reply":"2023-10-02T11:10:00.614725Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Translation\nFor translation, you can use a default model if you provide a language pair in the task name (such as \"translation_en_to_fr\"), but the easiest way is to pick the model you want to use on the Model Hub. Here we’ll try translating from French to English:","metadata":{}},{"cell_type":"code","source":"from transformers import pipeline\n\ntranslator = pipeline(\"translation\", model=\"Helsinki-NLP/opus-mt-fr-en\")\ntranslator(\"Ce cours est produit par Hugging Face.\")","metadata":{"execution":{"iopub.status.busy":"2023-10-02T11:12:50.700159Z","iopub.execute_input":"2023-10-02T11:12:50.700584Z","iopub.status.idle":"2023-10-02T11:13:05.494861Z","shell.execute_reply.started":"2023-10-02T11:12:50.700553Z","shell.execute_reply":"2023-10-02T11:13:05.493833Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}