Deployed ea540e8 with MkDocs version: 1.3.0
This commit is contained in:
parent
2c0fafb925
commit
54400a8829
52 changed files with 14526 additions and 502 deletions
11
great_ai_example-main/Dockerfile
Normal file
11
great_ai_example-main/Dockerfile
Normal file
|
|
@ -0,0 +1,11 @@
|
|||
FROM test
|
||||
|
||||
COPY requirements.txt .
|
||||
RUN pip install --no-cache-dir ./great_ai
|
||||
|
||||
COPY mongo.ini .
|
||||
COPY deploy.ipynb .
|
||||
|
||||
# RUN python3 -m large_file --backend s3 -secrets ~/.aws/credentials --cache my_first_file.json:3 my_second_file my_folder:0
|
||||
|
||||
CMD ["deploy.ipynb"]
|
||||
23
great_ai_example-main/README.md
Normal file
23
great_ai_example-main/README.md
Normal file
|
|
@ -0,0 +1,23 @@
|
|||
# Train a domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)
|
||||
|
||||
|
||||
|
||||
## Install
|
||||
|
||||
### System dependencies
|
||||
|
||||
Make sure you have `python3`, `pip`, and `venv` installed.
|
||||
> On Ubuntu, execute: `sudo apt install -y python3 python3-pip python3-venv`
|
||||
|
||||
### Install dependencies
|
||||
```sh
|
||||
python3 -m venv --copies .env
|
||||
source .env/bin/activate
|
||||
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
## Execute
|
||||
|
||||
- [Part 1](src/data.ipynb)
|
||||
- [Part 2](src/train.ipynb)
|
||||
- [Part 3](src/deploy.ipynb)
|
||||
1
great_ai_example-main/diagrams/scope-data.svg
Normal file
1
great_ai_example-main/diagrams/scope-data.svg
Normal file
File diff suppressed because one or more lines are too long
|
After Width: | Height: | Size: 14 KiB |
1
great_ai_example-main/diagrams/scope-deploy.svg
Normal file
1
great_ai_example-main/diagrams/scope-deploy.svg
Normal file
File diff suppressed because one or more lines are too long
|
After Width: | Height: | Size: 14 KiB |
1
great_ai_example-main/diagrams/scope-train.svg
Normal file
1
great_ai_example-main/diagrams/scope-train.svg
Normal file
File diff suppressed because one or more lines are too long
|
After Width: | Height: | Size: 14 KiB |
1
great_ai_example-main/diagrams/scope.svg
Normal file
1
great_ai_example-main/diagrams/scope.svg
Normal file
File diff suppressed because one or more lines are too long
|
After Width: | Height: | Size: 14 KiB |
31
great_ai_example-main/format.sh
Normal file
31
great_ai_example-main/format.sh
Normal file
|
|
@ -0,0 +1,31 @@
|
|||
#!/bin/sh
|
||||
|
||||
set -e
|
||||
|
||||
echo "Installing dependencies if necessary"
|
||||
python3 -m pip install --upgrade autoflake isort black[jupyter] mypy flake8
|
||||
|
||||
echo "Formatting and checking $1"
|
||||
|
||||
cd $1
|
||||
|
||||
echo Running autoflake
|
||||
python3 -m autoflake --expand-star-imports --remove-all-unused-imports --ignore-init-module-imports --remove-unused-variables --in-place -r .
|
||||
|
||||
echo Running isort
|
||||
python3 -m isort --profile black --skip .env .
|
||||
|
||||
echo Running black
|
||||
python3 -m black . --exclude .env
|
||||
|
||||
if ls *.py 1> /dev/null 2>&1; then
|
||||
echo Running mypy
|
||||
python3 -m mypy --namespace-packages --ignore-missing-imports --install-types --non-interactive --disallow-untyped-defs --disallow-incomplete-defs --pretty --follow-imports=silent --exclude=external/ --exclude=/build/ .
|
||||
fi
|
||||
|
||||
echo Running Flake8
|
||||
python3 -m flake8 . --count --show-source --statistics --exclude=__init__.py,.env,external --ignore=E501,E722,E402,W503,E203
|
||||
|
||||
cd -
|
||||
|
||||
echo "Finished formatting"
|
||||
467
great_ai_example-main/index.html
Normal file
467
great_ai_example-main/index.html
Normal file
|
|
@ -0,0 +1,467 @@
|
|||
|
||||
<!doctype html>
|
||||
<html lang="en" class="no-js">
|
||||
<head>
|
||||
|
||||
<meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width,initial-scale=1">
|
||||
|
||||
|
||||
|
||||
<link rel="icon" href="../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.3.0, mkdocs-material-8.3.9">
|
||||
|
||||
|
||||
|
||||
<title>Train a domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus) - GreatAI documentation</title>
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/stylesheets/main.1d29e8d0.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/stylesheets/palette.cbb835fc.min.css">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
||||
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
|
||||
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/_mkdocstrings.css">
|
||||
|
||||
<script>__md_scope=new URL("..",location),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="" data-md-color-accent="">
|
||||
|
||||
|
||||
|
||||
<script>var palette=__md_get("__palette");if(palette&&"object"==typeof palette.color)for(var key of Object.keys(palette.color))document.body.setAttribute("data-md-color-"+key,palette.color[key])</script>
|
||||
|
||||
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
|
||||
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
|
||||
<label class="md-overlay" for="__drawer"></label>
|
||||
<div data-md-component="skip">
|
||||
|
||||
|
||||
<a href="#train-a-domain-classifier-on-the-semantic-scholar-dataset" class="md-skip">
|
||||
Skip to content
|
||||
</a>
|
||||
|
||||
</div>
|
||||
<div data-md-component="announce">
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
<header class="md-header" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href=".." title="GreatAI documentation" class="md-header__button md-logo" aria-label="GreatAI documentation" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z"/></svg>
|
||||
|
||||
</a>
|
||||
<label class="md-header__button md-icon" for="__drawer">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2Z"/></svg>
|
||||
</label>
|
||||
<div class="md-header__title" data-md-component="header-title">
|
||||
<div class="md-header__ellipsis">
|
||||
<div class="md-header__topic">
|
||||
<span class="md-ellipsis">
|
||||
GreatAI documentation
|
||||
</span>
|
||||
</div>
|
||||
<div class="md-header__topic" data-md-component="header-topic">
|
||||
<span class="md-ellipsis">
|
||||
|
||||
Train a domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)
|
||||
|
||||
</span>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<form class="md-header__option" data-md-component="palette">
|
||||
|
||||
|
||||
|
||||
<input class="md-option" data-md-color-media="" data-md-color-scheme="default" data-md-color-primary="" data-md-color-accent="" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_1">
|
||||
|
||||
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_2" hidden>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12 20 8.69Z"/></svg>
|
||||
</label>
|
||||
|
||||
|
||||
|
||||
|
||||
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="" data-md-color-accent="" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_2">
|
||||
|
||||
<label class="md-header__button md-icon" title="Switch to light mode" for="__palette_1" hidden>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12c0-2.42-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12 20 8.69Z"/></svg>
|
||||
</label>
|
||||
|
||||
|
||||
</form>
|
||||
|
||||
|
||||
|
||||
<label class="md-header__button md-icon" for="__search">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
|
||||
</label>
|
||||
<div class="md-search" data-md-component="search" role="dialog">
|
||||
<label class="md-search__overlay" for="__search"></label>
|
||||
<div class="md-search__inner" role="search">
|
||||
<form class="md-search__form" name="search">
|
||||
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
|
||||
<label class="md-search__icon md-icon" for="__search">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"/></svg>
|
||||
</label>
|
||||
<nav class="md-search__options" aria-label="Search">
|
||||
|
||||
<button type="reset" class="md-search__icon md-icon" aria-label="Clear" tabindex="-1">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41Z"/></svg>
|
||||
</button>
|
||||
</nav>
|
||||
|
||||
</form>
|
||||
<div class="md-search__output">
|
||||
<div class="md-search__scrollwrap" data-md-scrollfix>
|
||||
<div class="md-search-result" data-md-component="search-result">
|
||||
<div class="md-search-result__meta">
|
||||
Initializing search
|
||||
</div>
|
||||
<ol class="md-search-result__list"></ol>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
<div class="md-header__source">
|
||||
<a href="https://github.com/schmelczer/great-ai" title="Go to repository" class="md-source" data-md-component="source">
|
||||
<div class="md-source__icon md-icon">
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.1.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2022 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
|
||||
</div>
|
||||
<div class="md-source__repository">
|
||||
GitHub
|
||||
</div>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
</nav>
|
||||
|
||||
</header>
|
||||
|
||||
<div class="md-container" data-md-component="container">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<main class="md-main" data-md-component="main">
|
||||
<div class="md-main__inner md-grid">
|
||||
|
||||
|
||||
|
||||
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
|
||||
<div class="md-sidebar__scrollwrap">
|
||||
<div class="md-sidebar__inner">
|
||||
|
||||
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href=".." title="GreatAI documentation" class="md-nav__button md-logo" aria-label="GreatAI documentation" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z"/></svg>
|
||||
|
||||
</a>
|
||||
GreatAI documentation
|
||||
</label>
|
||||
|
||||
<div class="md-nav__source">
|
||||
<a href="https://github.com/schmelczer/great-ai" title="Go to repository" class="md-source" data-md-component="source">
|
||||
<div class="md-source__icon md-icon">
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.1.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2022 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
|
||||
</div>
|
||||
<div class="md-source__repository">
|
||||
GitHub
|
||||
</div>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
<ul class="md-nav__list" data-md-scrollfix>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href=".." class="md-nav__link">
|
||||
Home
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../tutorials/" class="md-nav__link">
|
||||
Tutorials
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../how-to-guides/" class="md-nav__link">
|
||||
How-To Guides
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../reference/" class="md-nav__link">
|
||||
Reference
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../explanation/" class="md-nav__link">
|
||||
Explanation
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../simple-mag/train/" class="md-nav__link">
|
||||
Train a field of study (domain) classification of sentences on the MAG dataset
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
|
||||
<div class="md-sidebar__scrollwrap">
|
||||
<div class="md-sidebar__inner">
|
||||
|
||||
|
||||
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<label class="md-nav__title" for="__toc">
|
||||
<span class="md-nav__icon md-icon"></span>
|
||||
Table of contents
|
||||
</label>
|
||||
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#install" class="md-nav__link">
|
||||
Install
|
||||
</a>
|
||||
|
||||
<nav class="md-nav" aria-label="Install">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#system-dependencies" class="md-nav__link">
|
||||
System dependencies
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#install-dependencies" class="md-nav__link">
|
||||
Install dependencies
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#execute" class="md-nav__link">
|
||||
Execute
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
</nav>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
<div class="md-content" data-md-component="content">
|
||||
<article class="md-content__inner md-typeset">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<a href="https://github.com/schmelczer/great-ai/edit/main/docs/great_ai_example-main/README.md" title="Edit this page" class="md-content__button md-icon">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20.71 7.04c.39-.39.39-1.04 0-1.41l-2.34-2.34c-.37-.39-1.02-.39-1.41 0l-1.84 1.83 3.75 3.75M3 17.25V21h3.75L17.81 9.93l-3.75-3.75L3 17.25Z"/></svg>
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
<h1 id="train-a-domain-classifier-on-the-semantic-scholar-dataset">Train a domain classifier on the <a href="https://api.semanticscholar.org/corpus">semantic scholar dataset</a></h1>
|
||||
<p><img alt="steps" src="diagrams/scope.svg" /></p>
|
||||
<h2 id="install">Install</h2>
|
||||
<h3 id="system-dependencies">System dependencies</h3>
|
||||
<p>Make sure you have <code>python3</code>, <code>pip</code>, and <code>venv</code> installed.</p>
|
||||
<blockquote>
|
||||
<p>On Ubuntu, execute: <code>sudo apt install -y python3 python3-pip python3-venv</code></p>
|
||||
</blockquote>
|
||||
<h3 id="install-dependencies">Install dependencies</h3>
|
||||
<pre><code class="language-sh">python3 -m venv --copies .env
|
||||
source .env/bin/activate
|
||||
|
||||
pip install -r requirements.txt
|
||||
</code></pre>
|
||||
<h2 id="execute">Execute</h2>
|
||||
<ul>
|
||||
<li><a href="src/data/">Part 1</a></li>
|
||||
<li><a href="src/train/">Part 2</a></li>
|
||||
<li><a href="src/deploy/">Part 3</a></li>
|
||||
</ul>
|
||||
|
||||
<hr>
|
||||
<div class="md-source-file">
|
||||
<small>
|
||||
|
||||
Last update:
|
||||
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date">July 8, 2022</span>
|
||||
|
||||
|
||||
</small>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
</article>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</main>
|
||||
|
||||
<footer class="md-footer">
|
||||
|
||||
<div class="md-footer-meta md-typeset">
|
||||
<div class="md-footer-meta__inner md-grid">
|
||||
<div class="md-copyright">
|
||||
|
||||
|
||||
Made with
|
||||
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
|
||||
Material for MkDocs
|
||||
</a>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</footer>
|
||||
|
||||
</div>
|
||||
<div class="md-dialog" data-md-component="dialog">
|
||||
<div class="md-dialog__inner md-typeset"></div>
|
||||
</div>
|
||||
<script id="__config" type="application/json">{"base": "..", "features": [], "search": "../assets/javascripts/workers/search.b97dbffb.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.config.lang": "en", "search.config.pipeline": "trimmer, stopWordFilter", "search.config.separator": "[\\s\\-]+", "search.placeholder": "Search", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version.title": "Select version"}}</script>
|
||||
|
||||
|
||||
<script src="../assets/javascripts/bundle.6c7ad80a.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
4
great_ai_example-main/requirements.txt
Normal file
4
great_ai_example-main/requirements.txt
Normal file
|
|
@ -0,0 +1,4 @@
|
|||
great_ai
|
||||
notebook
|
||||
nbformat
|
||||
nbconvert
|
||||
265
great_ai_example-main/src/data/data.ipynb
Normal file
265
great_ai_example-main/src/data/data.ipynb
Normal file
|
|
@ -0,0 +1,265 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Train a domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)\n",
|
||||
"> Part 1: obtain and clean data\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"> The blue boxes show the steps implemented in this notebook.\n",
|
||||
"\n",
|
||||
"### Extract\n",
|
||||
"\n",
|
||||
"This can be achieved by downloading a public dataset (such as in this case), or by having a Data Engineer setup and give us access to the organisation's data.\n",
|
||||
"\n",
|
||||
"In this case, we download the semantic scholar dataset from a public S3 bucket."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"MAX_CHUNK_COUNT = 1"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Processing 1 out of the 6002 available chunks'"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import urllib.request\n",
|
||||
"from random import shuffle\n",
|
||||
"\n",
|
||||
"manifest = (\n",
|
||||
" urllib.request.urlopen(\n",
|
||||
" \"https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/manifest.txt\"\n",
|
||||
" )\n",
|
||||
" .read()\n",
|
||||
" .decode()\n",
|
||||
") # a list of available chunks separated by '\\n' characters\n",
|
||||
"\n",
|
||||
"lines = manifest.split()\n",
|
||||
"shuffle(lines)\n",
|
||||
"chunks = lines[:MAX_CHUNK_COUNT]\n",
|
||||
"\n",
|
||||
"f\"Processing {len(chunks)} out of the {len(manifest.split())} available chunks\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Transform\n",
|
||||
"\n",
|
||||
"- Filter out non-English abstracts using `great_ai.utilities.predict_language`\n",
|
||||
"- Project it to only keep the necessary components (text and labels), clean the textual content using `great_ai.utilities.clean`\n",
|
||||
"- We will speed up processing using `great_ai.utilities.parallel_map`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Spacy model en_core_web_sm not found locally, downloading...\n",
|
||||
"Collecting en-core-web-sm==3.3.0\n",
|
||||
" Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.3.0/en_core_web_sm-3.3.0-py3-none-any.whl (12.8 MB)\n",
|
||||
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 12.8/12.8 MB 3.6 MB/s eta 0:00:00\n",
|
||||
"Requirement already satisfied: spacy<3.4.0,>=3.3.0.dev0 in ./.env/lib/python3.10/site-packages (from en-core-web-sm==3.3.0) (3.3.1)\n",
|
||||
"Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (4.64.0)\n",
|
||||
"Requirement already satisfied: wasabi<1.1.0,>=0.9.1 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (0.9.1)\n",
|
||||
"Requirement already satisfied: srsly<3.0.0,>=2.4.3 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.4.3)\n",
|
||||
"Requirement already satisfied: typer<0.5.0,>=0.3.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (0.4.1)\n",
|
||||
"Requirement already satisfied: setuptools in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (59.6.0)\n",
|
||||
"Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.0.7)\n",
|
||||
"Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (1.0.2)\n",
|
||||
"Requirement already satisfied: blis<0.8.0,>=0.4.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (0.7.8)\n",
|
||||
"Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (1.0.7)\n",
|
||||
"Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.9 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.0.9)\n",
|
||||
"Requirement already satisfied: requests<3.0.0,>=2.13.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.28.0)\n",
|
||||
"Requirement already satisfied: numpy>=1.15.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (1.23.0)\n",
|
||||
"Requirement already satisfied: cymem<2.1.0,>=2.0.2 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.0.6)\n",
|
||||
"Requirement already satisfied: pathy>=0.3.5 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (0.6.1)\n",
|
||||
"Requirement already satisfied: jinja2 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.1.2)\n",
|
||||
"Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.3.0)\n",
|
||||
"Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.9.0,>=1.7.4 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (1.8.2)\n",
|
||||
"Requirement already satisfied: preshed<3.1.0,>=3.0.2 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.0.6)\n",
|
||||
"Requirement already satisfied: thinc<8.1.0,>=8.0.14 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (8.0.17)\n",
|
||||
"Requirement already satisfied: packaging>=20.0 in ./.env/lib/python3.10/site-packages (from spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (21.3)\n",
|
||||
"Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in ./.env/lib/python3.10/site-packages (from packaging>=20.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.0.9)\n",
|
||||
"Requirement already satisfied: smart-open<6.0.0,>=5.0.0 in ./.env/lib/python3.10/site-packages (from pathy>=0.3.5->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (5.2.1)\n",
|
||||
"Requirement already satisfied: typing-extensions>=3.7.4.3 in ./.env/lib/python3.10/site-packages (from pydantic!=1.8,!=1.8.1,<1.9.0,>=1.7.4->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (4.2.0)\n",
|
||||
"Requirement already satisfied: charset-normalizer~=2.0.0 in ./.env/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.0.12)\n",
|
||||
"Requirement already satisfied: certifi>=2017.4.17 in ./.env/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2022.6.15)\n",
|
||||
"Requirement already satisfied: idna<4,>=2.5 in ./.env/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (3.3)\n",
|
||||
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.env/lib/python3.10/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (1.26.9)\n",
|
||||
"Requirement already satisfied: click<9.0.0,>=7.1.1 in ./.env/lib/python3.10/site-packages (from typer<0.5.0,>=0.3.0->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (8.1.3)\n",
|
||||
"Requirement already satisfied: MarkupSafe>=2.0 in ./.env/lib/python3.10/site-packages (from jinja2->spacy<3.4.0,>=3.3.0.dev0->en-core-web-sm==3.3.0) (2.1.1)\n",
|
||||
"Installing collected packages: en-core-web-sm\n",
|
||||
"Successfully installed en-core-web-sm-3.3.0\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[38;5;226m2022-06-25 14:21:57,983 | WARNING | Limiting concurrency to 1 because there are only 1 chunks\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:21:57,984 | INFO | Starting parallel map (concurrency: 1, chunk size: 1)\u001b[0m\n",
|
||||
"\u001b[38;5;226m2022-06-25 14:21:57,984 | WARNING | Running in series, there is no reason for parallelism\u001b[0m\n",
|
||||
"100%|██████████| 1/1 [03:26<00:00, 206.86s/it]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from typing import List, Tuple\n",
|
||||
"import json\n",
|
||||
"import gzip\n",
|
||||
"from great_ai import parallel_map, clean, is_english, predict_language\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def preprocess_chunk(chunk_key: str) -> List[Tuple[str, List[str]]]:\n",
|
||||
" # Extract\n",
|
||||
" response = urllib.request.urlopen(\n",
|
||||
" f\"https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/{chunk_key}\"\n",
|
||||
" ) # a gzipped JSON Lines file\n",
|
||||
"\n",
|
||||
" decompressed = gzip.decompress(response.read())\n",
|
||||
" decoded = decompressed.decode()\n",
|
||||
" chunk = [json.loads(line) for line in decoded.split(\"\\n\") if line]\n",
|
||||
"\n",
|
||||
" # Transform\n",
|
||||
" return [\n",
|
||||
" (\n",
|
||||
" clean(\n",
|
||||
" f'{c[\"title\"]} {c[\"paperAbstract\"]} {c[\"journalName\"]} {c[\"venue\"]}',\n",
|
||||
" convert_to_ascii=True,\n",
|
||||
" ), # The text is cleaned to remove PDF extraction, web scraping, and other common artifacts\n",
|
||||
" c[\"fieldsOfStudy\"],\n",
|
||||
" ) # Create pairs of `(text, [...domains])`\n",
|
||||
" for c in chunk\n",
|
||||
" if c[\"fieldsOfStudy\"] and is_english(predict_language(c[\"paperAbstract\"]))\n",
|
||||
" ]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"preprocessed_chunks = parallel_map(preprocess_chunk, chunks)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from itertools import chain\n",
|
||||
"\n",
|
||||
"preprocessed_data = list(chain(*preprocessed_chunks))\n",
|
||||
"X, y = zip(\n",
|
||||
" *preprocessed_data\n",
|
||||
") # X is the input, y is the expected (ground truth) output"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load\n",
|
||||
"\n",
|
||||
"Upload the dataset (or a part of it) to a central repository using `great_ai.add_ground_truth`. This step automatically tags each datapoint with a split label according to the ratios we set. Additional tags can be also given.\n",
|
||||
"\n",
|
||||
"#### Production-ready backend\n",
|
||||
"\n",
|
||||
"The MongoDB driver is automatically configured if `mongo.ini` exists with the following scheme:\n",
|
||||
"\n",
|
||||
"```ini\n",
|
||||
"mongo_connection_string=mongodb://localhost:27017/\n",
|
||||
"mongo_database=my_great_ai_db\n",
|
||||
"```\n",
|
||||
"> You can install MongoDB from [here](https://www.mongodb.com/docs/manual/installation) or [use it as a service](https://www.mongodb.com/cloud/atlas/register)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[38;5;226m2022-06-25 14:25:24,989 | WARNING | Environment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,990 | INFO | Found credentials file (/data/projects/great_ai_example/mongo.ini), initialising MongodbDriver\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,991 | INFO | Found credentials file (/data/projects/great_ai_example/mongo.ini), initialising LargeFileMongo\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,992 | INFO | Settings: configured ✅\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,993 | INFO | 🔩 tracing_database: MongodbDriver\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,994 | INFO | 🔩 large_file_implementation: LargeFileMongo\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,994 | INFO | 🔩 is_production: False\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,995 | INFO | 🔩 should_log_exception_stack: True\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,996 | INFO | 🔩 prediction_cache_size: 512\u001b[0m\n",
|
||||
"\u001b[38;5;39m2022-06-25 14:25:24,997 | INFO | 🔩 dashboard_table_size: 50\u001b[0m\n",
|
||||
"\u001b[38;5;226m2022-06-25 14:25:24,998 | WARNING | You still need to check whether you follow all best practices before trusting your deployment.\u001b[0m\n",
|
||||
"\u001b[38;5;226m2022-06-25 14:25:24,998 | WARNING | > Find out more at https://se-ml.github.io/practices/\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from great_ai import add_ground_truth\n",
|
||||
"\n",
|
||||
"add_ground_truth(X, y, train_split_ratio=0.8, test_split_ratio=0.2)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Next: [Part 2](train.ipynb)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.10.4 ('.env': venv)",
|
||||
"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": "3.10.4"
|
||||
},
|
||||
"orig_nbformat": 4,
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "c1f394f9662881005685eeb18d8f9f77079b1b8b9a5ece1f825bfa01fcb7f52f"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
1950
great_ai_example-main/src/data/index.html
Normal file
1950
great_ai_example-main/src/data/index.html
Normal file
File diff suppressed because one or more lines are too long
239
great_ai_example-main/src/deploy/deploy.ipynb
Normal file
239
great_ai_example-main/src/deploy/deploy.ipynb
Normal file
File diff suppressed because one or more lines are too long
1857
great_ai_example-main/src/deploy/index.html
Normal file
1857
great_ai_example-main/src/deploy/index.html
Normal file
File diff suppressed because one or more lines are too long
2
great_ai_example-main/src/mongo.ini
Normal file
2
great_ai_example-main/src/mongo.ini
Normal file
|
|
@ -0,0 +1,2 @@
|
|||
mongo_connection_string=mongodb://localhost:27017/ # change this
|
||||
mongo_database=great_ai_example # this will be automatically created
|
||||
2470
great_ai_example-main/src/train/index.html
Normal file
2470
great_ai_example-main/src/train/index.html
Normal file
File diff suppressed because one or more lines are too long
1811
great_ai_example-main/src/train/train.ipynb
Normal file
1811
great_ai_example-main/src/train/train.ipynb
Normal file
File diff suppressed because it is too large
Load diff
Loading…
Add table
Add a link
Reference in a new issue