├── .gitignore ├── LICENSE.txt ├── README.md ├── Session 1 - Text Analysis Overview.ipynb ├── Session 2 - Information Extraction.ipynb ├── Session 3 - Text Classification.ipynb ├── Session 3 Appendix - PyLDAVis.ipynb ├── figures ├── s1_discourse.png ├── s1_growing_corpora.png ├── s1_ngrams.png ├── s1_preprocessing.png ├── s2_constituency_parsing.jpg ├── s2_dependency_parsing.jpg ├── s2_email_graph.png ├── s2_keyphrase_rank_graph.png ├── s2_ner.png ├── s3_bag_of_words.png ├── s3_classification.png ├── s3_classification_pipeline.png ├── s3_clustering.png ├── s3_cosine_distance.png ├── s3_cross_validation.png ├── s3_distance_table.png ├── s3_distributed_representation.png ├── s3_edit_distance.png ├── s3_feature_space.png ├── s3_frequency_encoding.png ├── s3_jaccard.png ├── s3_mahalanobis.png ├── s3_minkowski.png ├── s3_one_hot_encoding.png ├── s3_precision_recall.jpg ├── s3_pyldavis.png ├── s3_regression.png ├── s3_socher_sentiment.png ├── s3_text_pipelines.png ├── s3_tfidf_encoding.png ├── s3_topic_modeling.png └── s3_vector_encoding.png ├── requirements.txt ├── slides ├── figures ├── graphs.pdf └── intro.pdf ├── slideshow.sh └── utils ├── __init__.py ├── download.py ├── normalize.py ├── reader.py └── wapo.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/LICENSE.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/README.md -------------------------------------------------------------------------------- /Session 1 - Text Analysis Overview.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/Session 1 - Text Analysis Overview.ipynb -------------------------------------------------------------------------------- /Session 2 - Information Extraction.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/Session 2 - Information Extraction.ipynb -------------------------------------------------------------------------------- /Session 3 - Text Classification.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/Session 3 - Text Classification.ipynb -------------------------------------------------------------------------------- /Session 3 Appendix - PyLDAVis.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/Session 3 Appendix - PyLDAVis.ipynb -------------------------------------------------------------------------------- /figures/s1_discourse.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s1_discourse.png -------------------------------------------------------------------------------- /figures/s1_growing_corpora.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s1_growing_corpora.png -------------------------------------------------------------------------------- /figures/s1_ngrams.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s1_ngrams.png -------------------------------------------------------------------------------- /figures/s1_preprocessing.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s1_preprocessing.png -------------------------------------------------------------------------------- /figures/s2_constituency_parsing.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s2_constituency_parsing.jpg -------------------------------------------------------------------------------- /figures/s2_dependency_parsing.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s2_dependency_parsing.jpg -------------------------------------------------------------------------------- /figures/s2_email_graph.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s2_email_graph.png -------------------------------------------------------------------------------- /figures/s2_keyphrase_rank_graph.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s2_keyphrase_rank_graph.png -------------------------------------------------------------------------------- /figures/s2_ner.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s2_ner.png -------------------------------------------------------------------------------- /figures/s3_bag_of_words.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_bag_of_words.png -------------------------------------------------------------------------------- /figures/s3_classification.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_classification.png -------------------------------------------------------------------------------- /figures/s3_classification_pipeline.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_classification_pipeline.png -------------------------------------------------------------------------------- /figures/s3_clustering.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_clustering.png -------------------------------------------------------------------------------- /figures/s3_cosine_distance.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_cosine_distance.png -------------------------------------------------------------------------------- /figures/s3_cross_validation.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_cross_validation.png -------------------------------------------------------------------------------- /figures/s3_distance_table.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_distance_table.png -------------------------------------------------------------------------------- /figures/s3_distributed_representation.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_distributed_representation.png -------------------------------------------------------------------------------- /figures/s3_edit_distance.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_edit_distance.png -------------------------------------------------------------------------------- /figures/s3_feature_space.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_feature_space.png -------------------------------------------------------------------------------- /figures/s3_frequency_encoding.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_frequency_encoding.png -------------------------------------------------------------------------------- /figures/s3_jaccard.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_jaccard.png -------------------------------------------------------------------------------- /figures/s3_mahalanobis.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_mahalanobis.png -------------------------------------------------------------------------------- /figures/s3_minkowski.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_minkowski.png -------------------------------------------------------------------------------- /figures/s3_one_hot_encoding.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_one_hot_encoding.png -------------------------------------------------------------------------------- /figures/s3_precision_recall.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_precision_recall.jpg -------------------------------------------------------------------------------- /figures/s3_pyldavis.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_pyldavis.png -------------------------------------------------------------------------------- /figures/s3_regression.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_regression.png -------------------------------------------------------------------------------- /figures/s3_socher_sentiment.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_socher_sentiment.png -------------------------------------------------------------------------------- /figures/s3_text_pipelines.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_text_pipelines.png -------------------------------------------------------------------------------- /figures/s3_tfidf_encoding.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_tfidf_encoding.png -------------------------------------------------------------------------------- /figures/s3_topic_modeling.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_topic_modeling.png -------------------------------------------------------------------------------- /figures/s3_vector_encoding.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/figures/s3_vector_encoding.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/requirements.txt -------------------------------------------------------------------------------- /slides/figures: -------------------------------------------------------------------------------- 1 | ../figures -------------------------------------------------------------------------------- /slides/graphs.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/slides/graphs.pdf -------------------------------------------------------------------------------- /slides/intro.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/slides/intro.pdf -------------------------------------------------------------------------------- /slideshow.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/slideshow.sh -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /utils/download.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/utils/download.py -------------------------------------------------------------------------------- /utils/normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/utils/normalize.py -------------------------------------------------------------------------------- /utils/reader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/utils/reader.py -------------------------------------------------------------------------------- /utils/wapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DistrictDataLabs/brookings-nlp/HEAD/utils/wapo.py --------------------------------------------------------------------------------