├── .gitignore ├── LICENSE ├── MANIFEST.in ├── README.rst ├── assets ├── img_example1.jpg └── img_example2.jpg ├── pigeon ├── __init__.py ├── __version__.py └── annotate.py └── setup.py /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | *ipynb 3 | 4 | # Byte-compiled / optimized / DLL files 5 | __pycache__/ 6 | *.py[cod] 7 | *$py.class 8 | 9 | # C extensions 10 | *.so 11 | 12 | # Distribution / packaging 13 | .Python 14 | build/ 15 | develop-eggs/ 16 | dist/ 17 | downloads/ 18 | eggs/ 19 | .eggs/ 20 | lib/ 21 | lib64/ 22 | parts/ 23 | sdist/ 24 | var/ 25 | wheels/ 26 | *.egg-info/ 27 | .installed.cfg 28 | *.egg 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | .hypothesis/ 50 | 51 | # Translations 52 | *.mo 53 | *.pot 54 | 55 | # Django stuff: 56 | *.log 57 | local_settings.py 58 | 59 | # Flask stuff: 60 | instance/ 61 | .webassets-cache 62 | 63 | # Scrapy stuff: 64 | .scrapy 65 | 66 | # Sphinx documentation 67 | docs/_build/ 68 | 69 | # PyBuilder 70 | target/ 71 | 72 | # Jupyter Notebook 73 | .ipynb_checkpoints 74 | 75 | # pyenv 76 | .python-version 77 | 78 | # celery beat schedule file 79 | celerybeat-schedule 80 | 81 | # SageMath parsed files 82 | *.sage.py 83 | 84 | # Environments 85 | .env 86 | .venv 87 | env/ 88 | venv/ 89 | ENV/ 90 | 91 | # Spyder project settings 92 | .spyderproject 93 | .spyproject 94 | 95 | # Rope project settings 96 | .ropeproject 97 | 98 | # mkdocs documentation 99 | /site 100 | 101 | # mypy 102 | .mypy_cache/ 103 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright 2017 Anastasis Germanidis 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include README.rst LICENSE 2 | -------------------------------------------------------------------------------- /README.rst: -------------------------------------------------------------------------------- 1 | 🐦 pigeon - Quickly annotate data on Jupyter 2 | ======================== 3 | 4 | Pigeon is a simple widget that lets you quickly annotate a dataset of 5 | unlabeled examples from the comfort of your Jupyter notebook. 6 | 7 | Pigeon currently supports annotation for classification tasks (set of 8 | labels), regression tasks (int/float range), or captioning tasks 9 | (variable-length text). Anything that can be displayed on Jupyter 10 | (text, images, audio, graphs, etc.) can be displayed by pigeon 11 | by providing the appropriate :code:`display_fn` argument. 12 | 13 | Installation 14 | ----- 15 | 16 | .. code-block:: bash 17 | 18 | pip install pigeon-jupyter 19 | 20 | Examples 21 | ----- 22 | 23 | - Text classification 24 | 25 | Code: 26 | 27 | .. code-block:: python 28 | 29 | from pigeon import annotate 30 | annotations = annotate( 31 | ['I love this movie', 'I was really disappointed by the book'], 32 | options=['positive', 'negative'] 33 | ) 34 | 35 | 36 | Preview: 37 | 38 | .. image:: http://i.imgur.com/00ry4Li.gif 39 | 40 | - Image classification 41 | 42 | Code: 43 | 44 | .. code-block:: python 45 | 46 | from pigeon import annotate 47 | from IPython.display import display, Image 48 | 49 | annotations = annotate( 50 | ['assets/img_example1.jpg', 'assets/img_example2.jpg'], 51 | options=['cat', 'dog', 'horse'], 52 | display_fn=lambda filename: display(Image(filename)) 53 | ) 54 | 55 | Preview: 56 | 57 | .. image:: http://i.imgur.com/PiE3eDt.gif 58 | -------------------------------------------------------------------------------- /assets/img_example1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/agermanidis/pigeon/fa5760b2e24b5ec3f268da59ed7ffddf76318d58/assets/img_example1.jpg -------------------------------------------------------------------------------- /assets/img_example2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/agermanidis/pigeon/fa5760b2e24b5ec3f268da59ed7ffddf76318d58/assets/img_example2.jpg -------------------------------------------------------------------------------- /pigeon/__init__.py: -------------------------------------------------------------------------------- 1 | from .annotate import * 2 | -------------------------------------------------------------------------------- /pigeon/__version__.py: -------------------------------------------------------------------------------- 1 | __title__ = 'pigeon' 2 | __description__ = 'Quickly annotate data on Jupyter.' 3 | __url__ = 'https://github.com/agermanidis/pigeon' 4 | __version__ = '0.1.0' 5 | __author__ = 'Anastasis Germanidis' 6 | __author_email__ = 'agermanidis@gmail.com' 7 | __license__ = 'Apache 2.0' 8 | __copyright__ = 'Copyright 2017 Anastasis Germanidis' 9 | -------------------------------------------------------------------------------- /pigeon/annotate.py: -------------------------------------------------------------------------------- 1 | import random 2 | import functools 3 | from IPython.display import display, clear_output 4 | from ipywidgets import Button, Dropdown, HTML, HBox, IntSlider, FloatSlider, Textarea, Output 5 | 6 | def annotate(examples, 7 | options=None, 8 | shuffle=False, 9 | include_skip=True, 10 | display_fn=display): 11 | """ 12 | Build an interactive widget for annotating a list of input examples. 13 | 14 | Parameters 15 | ---------- 16 | examples: list(any), list of items to annotate 17 | options: list(any) or tuple(start, end, [step]) or None 18 | if list: list of labels for binary classification task (Dropdown or Buttons) 19 | if tuple: range for regression task (IntSlider or FloatSlider) 20 | if None: arbitrary text input (TextArea) 21 | shuffle: bool, shuffle the examples before annotating 22 | include_skip: bool, include option to skip example while annotating 23 | display_fn: func, function for displaying an example to the user 24 | 25 | Returns 26 | ------- 27 | annotations : list of tuples, list of annotated examples (example, label) 28 | """ 29 | examples = list(examples) 30 | if shuffle: 31 | random.shuffle(examples) 32 | 33 | annotations = [] 34 | current_index = -1 35 | 36 | def set_label_text(): 37 | nonlocal count_label 38 | count_label.value = '{} examples annotated, {} examples left'.format( 39 | len(annotations), len(examples) - current_index 40 | ) 41 | 42 | def show_next(): 43 | nonlocal current_index 44 | current_index += 1 45 | set_label_text() 46 | if current_index >= len(examples): 47 | for btn in buttons: 48 | btn.disabled = True 49 | print('Annotation done.') 50 | return 51 | with out: 52 | clear_output(wait=True) 53 | display_fn(examples[current_index]) 54 | 55 | def add_annotation(annotation): 56 | annotations.append((examples[current_index], annotation)) 57 | show_next() 58 | 59 | def skip(btn): 60 | show_next() 61 | 62 | count_label = HTML() 63 | set_label_text() 64 | display(count_label) 65 | 66 | if type(options) == list: 67 | task_type = 'classification' 68 | elif type(options) == tuple and len(options) in [2, 3]: 69 | task_type = 'regression' 70 | elif options is None: 71 | task_type = 'captioning' 72 | else: 73 | raise Exception('Invalid options') 74 | 75 | buttons = [] 76 | 77 | if task_type == 'classification': 78 | use_dropdown = len(options) > 5 79 | 80 | if use_dropdown: 81 | dd = Dropdown(options=options) 82 | display(dd) 83 | btn = Button(description='submit') 84 | def on_click(btn): 85 | add_annotation(dd.value) 86 | btn.on_click(on_click) 87 | buttons.append(btn) 88 | 89 | else: 90 | for label in options: 91 | btn = Button(description=label) 92 | def on_click(label, btn): 93 | add_annotation(label) 94 | btn.on_click(functools.partial(on_click, label)) 95 | buttons.append(btn) 96 | 97 | elif task_type == 'regression': 98 | target_type = type(options[0]) 99 | if target_type == int: 100 | cls = IntSlider 101 | else: 102 | cls = FloatSlider 103 | if len(options) == 2: 104 | min_val, max_val = options 105 | slider = cls(min=min_val, max=max_val) 106 | else: 107 | min_val, max_val, step_val = options 108 | slider = cls(min=min_val, max=max_val, step=step_val) 109 | display(slider) 110 | btn = Button(description='submit') 111 | def on_click(btn): 112 | add_annotation(slider.value) 113 | btn.on_click(on_click) 114 | buttons.append(btn) 115 | 116 | else: 117 | ta = Textarea() 118 | display(ta) 119 | btn = Button(description='submit') 120 | def on_click(btn): 121 | add_annotation(ta.value) 122 | btn.on_click(on_click) 123 | buttons.append(btn) 124 | 125 | if include_skip: 126 | btn = Button(description='skip') 127 | btn.on_click(skip) 128 | buttons.append(btn) 129 | 130 | box = HBox(buttons) 131 | display(box) 132 | 133 | out = Output() 134 | display(out) 135 | 136 | show_next() 137 | 138 | return annotations 139 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | import io 5 | import os 6 | import sys 7 | from shutil import rmtree 8 | 9 | from setuptools import find_packages, setup, Command 10 | 11 | NAME = 'pigeon-jupyter' 12 | DESCRIPTION = 'Quickly annotate data on Jupyter notebooks.' 13 | URL = 'https://github.com/agermanidis/pigeon' 14 | EMAIL = 'agermanidis@gmail.com' 15 | AUTHOR = 'Anastasis Germanidis' 16 | 17 | REQUIRED = [ 18 | 'ipywidgets' 19 | ] 20 | 21 | here = os.path.abspath(os.path.dirname(__file__)) 22 | 23 | with io.open(os.path.join(here, 'README.rst'), encoding='utf-8') as f: 24 | long_description = '\n' + f.read() 25 | 26 | about = {} 27 | with open(os.path.join(here, 'pigeon', '__version__.py')) as f: 28 | exec(f.read(), about) 29 | 30 | 31 | class PublishCommand(Command): 32 | """Support setup.py publish.""" 33 | 34 | description = 'Build and publish the package.' 35 | user_options = [] 36 | 37 | @staticmethod 38 | def status(s): 39 | """Prints things in bold.""" 40 | print('\033[1m{0}\033[0m'.format(s)) 41 | 42 | def initialize_options(self): 43 | pass 44 | 45 | def finalize_options(self): 46 | pass 47 | 48 | def run(self): 49 | try: 50 | self.status('Removing previous builds…') 51 | rmtree(os.path.join(here, 'dist')) 52 | except FileNotFoundError: 53 | pass 54 | 55 | self.status('Building Source and Wheel (universal) distribution…') 56 | os.system('{0} setup.py sdist bdist_wheel --universal'.format(sys.executable)) 57 | 58 | self.status('Uploading the package to PyPi via Twine…') 59 | os.system('twine upload dist/*') 60 | 61 | sys.exit() 62 | 63 | setup( 64 | name=NAME, 65 | version=about['__version__'], 66 | description=DESCRIPTION, 67 | long_description=long_description, 68 | author=AUTHOR, 69 | author_email=EMAIL, 70 | url=URL, 71 | packages=['pigeon'], 72 | install_requires=REQUIRED, 73 | include_package_data=True, 74 | license='Apache 2.0', 75 | classifiers=[ 76 | # Trove classifiers 77 | # Full list: https://pypi.python.org/pypi?%3Aaction=list_classifiers 78 | 'Programming Language :: Python', 79 | 'Programming Language :: Python :: 3', 80 | 'Programming Language :: Python :: 3.3', 81 | 'Programming Language :: Python :: 3.4', 82 | 'Programming Language :: Python :: 3.5', 83 | 'Programming Language :: Python :: 3.6', 84 | 'Topic :: Scientific/Engineering :: Artificial Intelligence', 85 | 'Framework :: Jupyter' 86 | ], 87 | # $ setup.py publish support. 88 | cmdclass={ 89 | 'publish': PublishCommand, 90 | }, 91 | ) 92 | --------------------------------------------------------------------------------