├── .gitignore ├── Dockerfile ├── LICENSE ├── README.md ├── file_cache.py └── writing_code_for_nlp_research.pdf /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | *.egg-info/ 24 | .installed.cfg 25 | *.egg 26 | MANIFEST 27 | 28 | # PyInstaller 29 | # Usually these files are written by a python script from a template 30 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 31 | *.manifest 32 | *.spec 33 | 34 | # Installer logs 35 | pip-log.txt 36 | pip-delete-this-directory.txt 37 | 38 | # Unit test / coverage reports 39 | htmlcov/ 40 | .tox/ 41 | .coverage 42 | .coverage.* 43 | .cache 44 | nosetests.xml 45 | coverage.xml 46 | *.cover 47 | .hypothesis/ 48 | .pytest_cache/ 49 | 50 | # Translations 51 | *.mo 52 | *.pot 53 | 54 | # Django stuff: 55 | *.log 56 | local_settings.py 57 | db.sqlite3 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 | env.bak/ 91 | venv.bak/ 92 | 93 | # Spyder project settings 94 | .spyderproject 95 | .spyproject 96 | 97 | # Rope project settings 98 | .ropeproject 99 | 100 | # mkdocs documentation 101 | /site 102 | 103 | # mypy 104 | .mypy_cache/ 105 | -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- 1 | FROM python:3.6.3-jessie 2 | 3 | ENV LC_ALL=C.UTF-8 4 | ENV LANG=C.UTF-8 5 | 6 | 7 | # This specifies where the current working 8 | # directory is when we start copying files in. 9 | WORKDIR /stage 10 | 11 | # Install base packages like gcc, git etc. 12 | RUN apt-get update --fix-missing && apt-get install -y \ 13 | bzip2 \ 14 | ca-certificates \ 15 | curl \ 16 | gcc \ 17 | git \ 18 | libc-dev \ 19 | libglib2.0-0 \ 20 | libsm6 \ 21 | libxext6 \ 22 | libxrender1 \ 23 | wget \ 24 | libevent-dev \ 25 | build-essential && \ 26 | rm -rf /var/lib/apt/lists/* 27 | 28 | #### Add your code in here! #### 29 | 30 | # Example commands: 31 | # 32 | # Copies a directory into the dockerfile. 33 | # COPY folder/ folder/ 34 | # 35 | # Installs some requirements. Remember to COPY the 36 | # requirements.txt file into the Docker image first! 37 | # RUN pip install -r requirements.txt 38 | 39 | 40 | # Optional argument to set an environment variable with the Git SHA 41 | ARG SOURCE_COMMIT 42 | ENV SOURCE_COMMIT $SOURCE_COMMIT 43 | 44 | # This exposes port 8000 to outside of the Docker container. 45 | # This is helful if you want to run a model server or something. 46 | EXPOSE 8000 47 | 48 | 49 | # You could change this to actually run your training script. 50 | # Currently, it just runs a shell inside the container. 51 | CMD ["/bin/bash"] 52 | -------------------------------------------------------------------------------- /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 [yyyy] [name of copyright owner] 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 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # writing-code-for-nlp-research-emnlp2018 2 | A companion repository for the "Writing code for NLP Research" Tutorial at EMNLP 2018 3 | -------------------------------------------------------------------------------- /file_cache.py: -------------------------------------------------------------------------------- 1 | """ 2 | Utilities for working with the local dataset cache. 3 | """ 4 | 5 | import os 6 | import logging 7 | import shutil 8 | import tempfile 9 | import json 10 | from urllib.parse import urlparse 11 | from pathlib import Path 12 | from typing import Optional, Tuple, Union, IO, Callable 13 | from hashlib import sha256 14 | from functools import wraps 15 | 16 | import requests 17 | 18 | logger = logging.getLogger(__name__) # pylint: disable=invalid-name 19 | 20 | CACHE_ROOT = Path(os.getenv('RESEARCH_CACHE_ROOT', Path.home() / '.research')) 21 | DATASET_CACHE = str(CACHE_ROOT / "datasets") 22 | 23 | 24 | def cached_path(url_or_filename: Union[str, Path], cache_dir: str = None) -> str: 25 | """ 26 | Given something that might be a URL (or might be a local path), 27 | determine which. If it's a URL, download the file and cache it, and 28 | return the path to the cached file. If it's already a local path, 29 | make sure the file exists and then return the path. 30 | """ 31 | if cache_dir is None: 32 | cache_dir = DATASET_CACHE 33 | if isinstance(url_or_filename, Path): 34 | url_or_filename = str(url_or_filename) 35 | 36 | parsed = urlparse(url_or_filename) 37 | 38 | if parsed.scheme in ('http', 'https'): 39 | # URL, so get it from the cache (downloading if necessary) 40 | return get_from_cache(url_or_filename, cache_dir) 41 | elif os.path.exists(url_or_filename): 42 | # File, and it exists. 43 | return url_or_filename 44 | elif parsed.scheme == '': 45 | # File, but it doesn't exist. 46 | raise FileNotFoundError("file {} not found".format(url_or_filename)) 47 | else: 48 | # Something unknown 49 | raise ValueError("unable to parse {} as a URL or as a local path".format(url_or_filename)) 50 | 51 | 52 | def url_to_filename(url: str, etag: str = None) -> str: 53 | """ 54 | Convert `url` into a hashed filename in a repeatable way. 55 | If `etag` is specified, append its hash to the url's, delimited 56 | by a period. 57 | """ 58 | url_bytes = url.encode('utf-8') 59 | url_hash = sha256(url_bytes) 60 | filename = url_hash.hexdigest() 61 | 62 | if etag: 63 | etag_bytes = etag.encode('utf-8') 64 | etag_hash = sha256(etag_bytes) 65 | filename += '.' + etag_hash.hexdigest() 66 | 67 | return filename 68 | 69 | 70 | def filename_to_url(filename: str, cache_dir: str = None) -> Tuple[str, str]: 71 | """ 72 | Return the url and etag (which may be ``None``) stored for `filename`. 73 | Raise ``FileNotFoundError`` if `filename` or its stored metadata do not exist. 74 | """ 75 | if cache_dir is None: 76 | cache_dir = DATASET_CACHE 77 | 78 | cache_path = os.path.join(cache_dir, filename) 79 | if not os.path.exists(cache_path): 80 | raise FileNotFoundError("file {} not found".format(cache_path)) 81 | 82 | meta_path = cache_path + '.json' 83 | if not os.path.exists(meta_path): 84 | raise FileNotFoundError("file {} not found".format(meta_path)) 85 | 86 | with open(meta_path) as meta_file: 87 | metadata = json.load(meta_file) 88 | url = metadata['url'] 89 | etag = metadata['etag'] 90 | 91 | return url, etag 92 | 93 | def http_get(url: str, temp_file: IO) -> None: 94 | req = requests.get(url, stream=True) 95 | content_length = req.headers.get('Content-Length') 96 | total = int(content_length) if content_length is not None else None 97 | for chunk in req.iter_content(chunk_size=1024): 98 | if chunk: # filter out keep-alive new chunks 99 | temp_file.write(chunk) 100 | 101 | 102 | def get_from_cache(url: str, cache_dir: str = None) -> str: 103 | """ 104 | Given a URL, look for the corresponding dataset in the local cache. 105 | If it's not there, download it. Then return the path to the cached file. 106 | """ 107 | if cache_dir is None: 108 | cache_dir = DATASET_CACHE 109 | 110 | os.makedirs(cache_dir, exist_ok=True) 111 | 112 | response = requests.head(url, allow_redirects=True) 113 | if response.status_code != 200: 114 | raise IOError("HEAD request failed for url {} with status code {}" 115 | .format(url, response.status_code)) 116 | etag = response.headers.get("ETag") 117 | 118 | filename = url_to_filename(url, etag) 119 | 120 | # get cache path to put the file 121 | cache_path = os.path.join(cache_dir, filename) 122 | 123 | if not os.path.exists(cache_path): 124 | # Download to temporary file, then copy to cache dir once finished. 125 | # Otherwise you get corrupt cache entries if the download gets interrupted. 126 | with tempfile.NamedTemporaryFile() as temp_file: 127 | logger.info("%s not found in cache, downloading to %s", url, temp_file.name) 128 | 129 | # GET file object 130 | http_get(url, temp_file) 131 | 132 | # we are copying the file before closing it, so flush to avoid truncation 133 | temp_file.flush() 134 | # shutil.copyfileobj() starts at the current position, so go to the start 135 | temp_file.seek(0) 136 | 137 | logger.info("copying %s to cache at %s", temp_file.name, cache_path) 138 | with open(cache_path, 'wb') as cache_file: 139 | shutil.copyfileobj(temp_file, cache_file) 140 | 141 | logger.info("creating metadata file for %s", cache_path) 142 | meta = {'url': url, 'etag': etag} 143 | meta_path = cache_path + '.json' 144 | with open(meta_path, 'w') as meta_file: 145 | json.dump(meta, meta_file) 146 | 147 | logger.info("removing temp file %s", temp_file.name) 148 | 149 | return cache_path 150 | 151 | -------------------------------------------------------------------------------- /writing_code_for_nlp_research.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/writing-code-for-nlp-research-emnlp2018/514afeaa47d6f2498d59e2d6d083d32be8f94c89/writing_code_for_nlp_research.pdf --------------------------------------------------------------------------------