decile-team · Aziz-Shameem · Jun 7, 2021 · Jun 7, 2021 · Jun 7, 2021 · Jun 7, 2021
diff --git a/.gitignore b/.gitignore
@@ -1 +1,23 @@
-./data/
+__pycache__/
+*.py[cod]
+data/
+docs/build/
+
+*.so
+
+bin/
+build/
+develop-eggs/
+dist/
+eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+pip-log.txt
+pip-delete-this-directory.txt
diff --git a/.readthedocs.yml b/.readthedocs.yml
@@ -0,0 +1,16 @@
+# .readthedocs.yml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: docs/source/conf.py
+
+# Optionally set the version of Python and requirements required to build your docs
+python:
+  version: 3.6
+  install:
+    - requirements: docs/requirements.txt
diff --git a/LICENSE.txt b/LICENSE.txt
@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2021- decile.org
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
diff --git a/README.md b/README.md
@@ -1 +1,119 @@
-# spear
+
+<!-- [![](https://tokei.rs/b1/github/decile-team/spear?category=code)](https://github.com/decile-team/spear) -->
+[![Lines of code](https://img.shields.io/tokei/lines/github/decile-team/spear)]()
+![visitors](https://visitor-badge.glitch.me/badge?page_id=decile-team/spear)
+![PyPI](https://img.shields.io/pypi/v/spear)
+[![docs](https://readthedocs.org/projects/spear-decile/badge)](https://spear-decile.readthedocs.io/)
+[![license](https://img.shields.io/badge/License-MIT-blue.svg)](https://github.com/decile-team/spear/blob/main/LICENSE.txt)
+[![website](https://img.shields.io/badge/website-online-green)](https://decile.org/)
+
+<!-- ![GitHub repo size](https://img.shields.io/github/repo-size/decile-team/spear) -->
+
+<p align="center">
+    <br>
+        <img src="https://github.com/decile-team/spear/blob/main/spear_logo.png" width="540" height="150"/>
+    </br>
+</p>
+
+## Semi-Supervised Data Programming for Data Efficient Machine Learning
+SPEAR is a library for data programming with semi-supervision. The package implements several recent data programming approaches including facility to programmatically label and build training data.
+
+### Pipeline
+* Design Labeling functions(LFs)
+* generate pickle file containing labels by passing raw data to LFs
+* Use one of the Label Aggregators(LA) to get final labels
+
+<p align="center">
+    <br>
+        <img src="https://github.com/decile-team/spear/blob/main/spear_pipeline.svg" width="1000" height="300" />
+    </br>
+</p>
+
+
+### SPEAR provides functionality such as 
+* development of LFs/rules/heuristics for quick labeling
+* compare against several data programming approaches
+* compare against semi-supervised data programming approaches
+* use subset selection to make best use of the annotation efforts
+* facility to store and save data in [pickle file](https://spear-decile.readthedocs.io/en/latest/index.html#spear.utils.data_editor.get_data)
+
+#### Labelling Functions (LFs)
+* discrete LFs - Users can define LFs that return discrete labels
+* continuous LFs - return continuous scores/confidence to the labels assigned
+
+#### Approaches Implemented
+You can read [this paper](https://arxiv.org/pdf/2008.09887.pdf) to know about below approaches
+* Only-L 
+* Learning to Reweight
+* Posterior Regularization
+* Imply Loss
+* CAGE
+* Joint Learning
+
+Data folder for SMS & TREC can be found [here](https://drive.google.com/file/d/1CJZ73nNa7Ho0BOSDgGx9CRvXoepVSpet/view?usp=sharing). This folder needs to be placed in the same directory as notebooks folder is in, to run the notebooks or examples.
+
+Direct download of the zip file can be done via wget using `gdown` library . 
+```bash
+pip install gdown
+gdown 1CJZ73nNa7Ho0BOSDgGx9CRvXoepVSpet
+```
+
+## Installation
+* Install Submodlib library
+`pip install -i https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ submodlib`
+#### Method 1
+To install latest version of SPEAR package using PyPI:
+ ```python 
+ pip install decile-spear
+ ```
+#### Method 2    
+SPEAR requires Python 3.6 or later. First install [submodlib](https://github.com/decile-team/submodlib#setup). Then install SPEAR:
+
+```bash
+git clone https://github.com/decile-team/spear.git
+cd spear
+pip install -r requirements/requirements.txt
+```
+
+## Citation
+```bibtex
+@misc{abhishek2021spear,
+      title={SPEAR : Semi-supervised Data Programming in Python}, 
+      author={Guttu Sai Abhishek and Harshad Ingole and Parth Laturia and Vineeth Dorna and Ayush Maheshwari and Ganesh Ramakrishnan and Rishabh Iyer},
+      year={2021},
+      eprint={2108.00373},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```
+
+### Quick Links
+* [SPEAR tutorials](https://github.com/decile-team/spear/tree/main/notebooks)
+* [SPEAR documentation](https://spear-decile.readthedocs.io/)
+* [Demonstration of Cage and Joint Learning using SPEAR](https://youtu.be/qdukvO3B8YU)
+* [Demonstration of Imply Loss, Learn2Reweight using SPEAR](https://youtu.be/SN9YYK4FlU0)
+* SMS SPAM: [CAGE colab](https://colab.research.google.com/drive/1vec-Q-xO9wQtM3p_CZ7237gCq0xIR9b9?usp=sharing), [JL colab](https://colab.research.google.com/drive/1HqkqQ8ytWjP9on3du-vVB07IQvo8Li3W?usp=sharing)
+* [DECILE website](https://decile.org)
+* [SubModLib - Summarize massive datasets using submodular optimization](https://github.com/decile-team/submodlib)
+* [DISTIL- Deep Diversified Interactive Learning](https://github.com/decile-team/distil)
+* [CORDS- COResets and Data Subset Selection](https://github.com/decile-team/cords)
+
+
+
+### Acknowledgment
+SPEAR takes inspiration, builds upon, and uses pieces of code from several open source codebases. These include [Snorkel](https://github.com/snorkel-team/snorkel), [Snuba](https://github.com/HazyResearch/reef)  & [Imply Loss](https://github.com/awasthiabhijeet/Learning-From-Rules). Also, SPEAR uses [SUBMODLIB](https://github.com/decile-team/submodlib) for subset selection, which is provided by [DECILE](https://decile.org/) too.
+
+### Team
+SPEAR is created and maintained by [Ayush](https://www.cse.iitb.ac.in/~ayusham), [Abhishek](https://www.linkedin.com/in/guttu-sai-abhishek/), [Vineeth](https://www.cse.iitb.ac.in/~vineethdorna/), [Harshad](https://www.cse.iitb.ac.in/~harshadingole/), [Parth](https://www.cse.iitb.ac.in/~parthlaturia/), [Pankaj](https://www.linkedin.com/in/pankaj-singh-b000894a/), [Rishabh Iyer](https://www.rishiyer.com), and [Ganesh Ramakrishnan](https://www.cse.iitb.ac.in/~ganesh/). We look forward to have SPEAR more community driven. Please use it and contribute to it for your research, and feel free to use it for your commercial projects. We will add the major contributors here.
+
+
+## Publications
+[1] Abhishek et al. [SPEAR : Semi-supervised Data Programming in Python](https://arxiv.org/abs/2108.00373), Demonstration Paper.
+
+[2] Maheshwari et al. [Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programming](https://arxiv.org/abs/2109.11410), In Findings of ACL (Long Paper) 2022.
+
+[3] Maheshwari, Ayush, et al. [Data Programming using Semi-Supervision and Subset Selection](https://arxiv.org/abs/2008.09887), In Findings of ACL (Long Paper) 2021.
+
+[4] Chatterjee, Oishik, Ganesh Ramakrishnan, and Sunita Sarawagi. [Data Programming using Continuous and Quality-Guided Labeling Functions](https://arxiv.org/abs/1911.09860), In AAAI 2020.
+
+[5] Sahay, Atul, et al. [Rule augmented unsupervised constituency parsing](https://arxiv.org/abs/2105.10193), In Findings of ACL (Short Paper) 2021.
diff --git a/docs/make.bat b/docs/make.bat
@@ -10,8 +10,6 @@ if "%SPHINXBUILD%" == "" (
 set SOURCEDIR=source
 set BUILDDIR=build
 
-if "%1" == "" goto help
-
 %SPHINXBUILD% >NUL 2>NUL
 if errorlevel 9009 (
 	echo.
@@ -21,10 +19,12 @@ if errorlevel 9009 (
 	echo.may add the Sphinx directory to PATH.
 	echo.
 	echo.If you don't have Sphinx installed, grab it from
-	echo.http://sphinx-doc.org/
+	echo.https://www.sphinx-doc.org/
 	exit /b 1
 )
 
+if "%1" == "" goto help
+
 %SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
 goto end
 

diff --git a/docs/requirements.txt b/docs/requirements.txt
@@ -0,0 +1,9 @@
+sphinx-rtd-theme==0.5.1
+sphinxcontrib-applehelp==1.0.2
+sphinxcontrib-bibtex==2.2.0
+sphinxcontrib-devhelp==1.0.2
+sphinxcontrib-htmlhelp==1.0.3
+sphinxcontrib-jsmath==1.0.1
+sphinxcontrib-napoleon==0.7
+sphinxcontrib-qthelp==1.0.3
+sphinxcontrib-serializinghtml==1.1.4
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -14,13 +14,13 @@
 import sys
 sys.path.insert(0, os.path.abspath('../..'))
 
+
 master_doc = 'index'
-autodoc_mock_imports = ["torch", "sklearn", "utils_jl", "models", "tensorflow", "snorkel", "my_checkmate", "my_checkpoints","my_config", "my_data_feeder_utils", "my_data_types",  "my_gen_cross_entropy_utils", "my_pr_utils", "my_test", "my_train", "my_utils"]
 # -- Project information -----------------------------------------------------
 
 project = 'SPEAR(DECILE)'
-copyright = '2021, Ganesh_Ramakrishnan, Ayush_Maheshwari, Guttu_Sai_Abhishek, Harshad_Ingole, Parth_Laturia, Vineeth_Dorna'
-author = 'Ganesh_Ramakrishnan, Ayush_Maheshwari, Guttu_Sai_Abhishek, Harshad_Ingole, Parth_Laturia, Vineeth_Dorna'
+copyright = '2021 DECILE'
+author = 'Ayush_Maheshwari, Guttu_Sai_Abhishek, Harshad_Ingole, Parth_Laturia, Vineeth_Dorna'
 
 # The full version, including alpha/beta/rc tags
 release = '0.0.1'
@@ -42,9 +42,7 @@
     #'numpydoc'
     'sphinxcontrib.napoleon',
     'sphinxcontrib.bibtex'
-# 'rinoh.frontend.sphinx'
 ]
-
 bibtex_bibfiles = ['refs.bib']
 
 # Add any paths that contain templates here, relative to this directory.
@@ -61,13 +59,11 @@
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'sphinx_rtd_theme' #'alabaster'
+html_theme = 'sphinx_rtd_theme'
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-#html_static_path = ['_static']
-html_static_path = []
+html_static_path = ['_static']
 
-#below line makes functions to print in order they were defined in files. added by abhishek
-autodoc_member_order = 'bysource'
+autodoc_member_order = 'bysource'