├── .dockerignore ├── .gitignore ├── .gitmodules ├── Dockerfile ├── Introduction.ipynb ├── README.md ├── bin └── get_wikidata.sh ├── ch02 ├── .gitignore ├── Weakly Supervised Learning - Stack Overflow Tag Labeler.ipynb ├── emr_bootstrap.sh ├── get_questions.spark.py ├── images │ └── kim_cnn_model_architecture.png └── xml_to_parquet.spark.py ├── ch03 ├── Introducing Snorkel.ipynb └── images │ ├── labeling_function_api.png │ ├── snorkel_apis_0.9.5.png │ └── snorkel_tutorial_functions.png ├── ch04 ├── .gitignore ├── Chapter 4 - Github Embeddings.ipynb ├── Chapter 4 - Transfer Learning.ipynb ├── PREREQUISITES.md └── bert.sh ├── ch05 ├── Distant Supervision.ipynb ├── Snorkel.ipynb ├── bad_tags.spark.py ├── label.spark.py └── split_tags.spark.py ├── conda.env.yaml ├── conda.pip.requirements.txt ├── conda.requirements.txt ├── data ├── .exists └── amazon_github_repos.json.bz2 ├── docker-compose.yml ├── download.sh ├── lib └── utils.py ├── paths.json ├── requirements.dev.in ├── requirements.in └── settings.json /.dockerignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/.dockerignore -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/.gitmodules -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/Dockerfile -------------------------------------------------------------------------------- /Introduction.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/Introduction.ipynb -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/README.md -------------------------------------------------------------------------------- /bin/get_wikidata.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/bin/get_wikidata.sh -------------------------------------------------------------------------------- /ch02/.gitignore: -------------------------------------------------------------------------------- 1 | models 2 | -------------------------------------------------------------------------------- /ch02/Weakly Supervised Learning - Stack Overflow Tag Labeler.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch02/Weakly Supervised Learning - Stack Overflow Tag Labeler.ipynb -------------------------------------------------------------------------------- /ch02/emr_bootstrap.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch02/emr_bootstrap.sh -------------------------------------------------------------------------------- /ch02/get_questions.spark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch02/get_questions.spark.py -------------------------------------------------------------------------------- /ch02/images/kim_cnn_model_architecture.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch02/images/kim_cnn_model_architecture.png -------------------------------------------------------------------------------- /ch02/xml_to_parquet.spark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch02/xml_to_parquet.spark.py -------------------------------------------------------------------------------- /ch03/Introducing Snorkel.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch03/Introducing Snorkel.ipynb -------------------------------------------------------------------------------- /ch03/images/labeling_function_api.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch03/images/labeling_function_api.png -------------------------------------------------------------------------------- /ch03/images/snorkel_apis_0.9.5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch03/images/snorkel_apis_0.9.5.png -------------------------------------------------------------------------------- /ch03/images/snorkel_tutorial_functions.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch03/images/snorkel_tutorial_functions.png -------------------------------------------------------------------------------- /ch04/.gitignore: -------------------------------------------------------------------------------- 1 | models 2 | -------------------------------------------------------------------------------- /ch04/Chapter 4 - Github Embeddings.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch04/Chapter 4 - Github Embeddings.ipynb -------------------------------------------------------------------------------- /ch04/Chapter 4 - Transfer Learning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch04/Chapter 4 - Transfer Learning.ipynb -------------------------------------------------------------------------------- /ch04/PREREQUISITES.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch04/PREREQUISITES.md -------------------------------------------------------------------------------- /ch04/bert.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch04/bert.sh -------------------------------------------------------------------------------- /ch05/Distant Supervision.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch05/Distant Supervision.ipynb -------------------------------------------------------------------------------- /ch05/Snorkel.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch05/Snorkel.ipynb -------------------------------------------------------------------------------- /ch05/bad_tags.spark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch05/bad_tags.spark.py -------------------------------------------------------------------------------- /ch05/label.spark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch05/label.spark.py -------------------------------------------------------------------------------- /ch05/split_tags.spark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/ch05/split_tags.spark.py -------------------------------------------------------------------------------- /conda.env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/conda.env.yaml -------------------------------------------------------------------------------- /conda.pip.requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/conda.pip.requirements.txt -------------------------------------------------------------------------------- /conda.requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/conda.requirements.txt -------------------------------------------------------------------------------- /data/.exists: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /data/amazon_github_repos.json.bz2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/data/amazon_github_repos.json.bz2 -------------------------------------------------------------------------------- /docker-compose.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/docker-compose.yml -------------------------------------------------------------------------------- /download.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/download.sh -------------------------------------------------------------------------------- /lib/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/lib/utils.py -------------------------------------------------------------------------------- /paths.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/paths.json -------------------------------------------------------------------------------- /requirements.dev.in: -------------------------------------------------------------------------------- 1 | nbstripout 2 | pip-tools 3 | -------------------------------------------------------------------------------- /requirements.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/requirements.in -------------------------------------------------------------------------------- /settings.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rjurney/weakly_supervised_learning_code/HEAD/settings.json --------------------------------------------------------------------------------