From d81e7561715fb991665da1d3d30b5399f2d40e9b Mon Sep 17 00:00:00 2001 From: AnjanaRita Date: Mon, 22 Nov 2021 14:31:23 +0530 Subject: [PATCH] adds usage example. --- .gitignore | 148 ++++++++++++++++++++++++++++++++++++++++--- notebook/usage.ipynb | 82 ++++++++++++++++++++++++ 2 files changed, 221 insertions(+), 9 deletions(-) create mode 100644 notebook/usage.ipynb diff --git a/.gitignore b/.gitignore index 2e77bae..fef0fd4 100644 --- a/.gitignore +++ b/.gitignore @@ -1,12 +1,142 @@ -*.log -*.pyc -.cache/ -.coverage -.idea/ -.vscode/ -zeroshot_topics.egg-info/ +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python build/ +develop-eggs/ dist/ -docs/build/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py,cover +.hypothesis/ +.pytest_cache/ +cover/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +.pybuilder/ +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +# For a library or package, you might want to ignore these files since the code is +# intended to run in multiple environments; otherwise, check them in: +# .python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +#Pipfile.lock + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# SageMath parsed files +*.sage.py + +# Environments +.env +.venv +env/ venv/ -wheelhouse/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# pytype static type analyzer +.pytype/ + +# Cython debug symbols +cython_debug/ + +#others +nohup.out +.DS_Store \ No newline at end of file diff --git a/notebook/usage.ipynb b/notebook/usage.ipynb new file mode 100644 index 0000000..bfb59d7 --- /dev/null +++ b/notebook/usage.ipynb @@ -0,0 +1,82 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "id": "2b26c142-ae31-46e6-ae90-de31716026b6", + "metadata": {}, + "outputs": [], + "source": [ + "from zeroshot_topics import ZeroShotTopicFinder" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "071e82f4-9509-429b-83c9-29abdc2f8b6d", + "metadata": {}, + "outputs": [], + "source": [ + "zsmodel = ZeroShotTopicFinder()" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "9dedf400-f7c7-4451-b58d-96b4a9b90ffd", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/rita/opt/anaconda3/lib/python3.8/site-packages/transformers/tokenization_utils_base.py:2227: UserWarning: `max_length` is ignored when `padding`=`True`.\n", + " warnings.warn(\"`max_length` is ignored when `padding`=`True`.\")\n" + ] + }, + { + "data": { + "text/plain": [ + "['Vertebrate']" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "text = \"\"\"Dinosaurs are a varied group of animals from taxonomic, morphological and ecological standpoints. Birds, at over 10,700 living species, \n", + "are among the most diverse group of vertebrates. Using fossil evidence, paleontologists have identified over 900 distinct genera and more than\n", + "1,000 different species of non-avian dinosaurs. Dinosaurs are represented on every continent by both extant species (birds) and fossil remains.\n", + "Through the first half of the 20th century, before birds were recognized as dinosaurs, most of the scientific community believed dinosaurs to have\n", + "been sluggish and cold-blooded. Most research conducted since the 1970s, however, has indicated that dinosaurs were active animals with elevated\n", + "metabolisms and numerous adaptations for social interaction. Some were herbivorous, others carnivorous. \n", + "Evidence suggests that all dinosaurs were egg-laying; and that nest-building was a trait shared by many dinosaurs, both avian and non-avian. \"\"\"\n", + "\n", + "zsmodel.find_topic(text, n_topic=1)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.8" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}