├── .gitignore ├── README.md ├── conda_env.yml ├── conda_env_medcat.yml ├── condition_histogram.ipynb ├── config.py ├── data ├── Names_2010Census.csv ├── icd_9_conversion.txt └── yob1950.txt ├── experiments ├── MLM │ ├── common.py │ ├── condition_given_name.py │ └── first_name_given_last_name.py ├── cosine_similarity │ ├── bert_cosine_sim.py │ └── word_embedding_cosine_sim.py ├── generation │ ├── generate_text.py │ ├── name_condition_extraction.py │ └── name_extraction.py ├── metrics.py ├── parse_results.py ├── probing │ ├── FullBERT_single_condition_probing.py │ ├── LR_single_condition_probing.py │ ├── all_conditions_probing.py │ ├── common.py │ └── names_probing.py ├── statistics_name_sentence.py └── utilities.py ├── how_many_names.py ├── setup_scripts ├── name_insertion.sh ├── notes_preprocessing_and_name_insertion.py ├── notes_preprocessing_functions.py ├── setup.sh ├── subject_id_to_icd9.py ├── subject_id_to_medcat_finalize.py ├── subject_id_to_medcat_preprocess.py ├── subject_id_to_name.py ├── subject_id_to_notes_original.py └── template_only_notes.py └── training_scripts ├── convert_to_tf.py ├── create_BERT_tfrecords.py ├── create_BERT_tfrecords.sh ├── tpu_download_BERT.sh ├── tpu_train_BERT.sh └── train_word_embeddings.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/README.md -------------------------------------------------------------------------------- /conda_env.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/conda_env.yml -------------------------------------------------------------------------------- /conda_env_medcat.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/conda_env_medcat.yml -------------------------------------------------------------------------------- /condition_histogram.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/condition_histogram.ipynb -------------------------------------------------------------------------------- /config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/config.py -------------------------------------------------------------------------------- /data/Names_2010Census.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/data/Names_2010Census.csv -------------------------------------------------------------------------------- /data/icd_9_conversion.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/data/icd_9_conversion.txt -------------------------------------------------------------------------------- /data/yob1950.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/data/yob1950.txt -------------------------------------------------------------------------------- /experiments/MLM/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/MLM/common.py -------------------------------------------------------------------------------- /experiments/MLM/condition_given_name.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/MLM/condition_given_name.py -------------------------------------------------------------------------------- /experiments/MLM/first_name_given_last_name.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/MLM/first_name_given_last_name.py -------------------------------------------------------------------------------- /experiments/cosine_similarity/bert_cosine_sim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/cosine_similarity/bert_cosine_sim.py -------------------------------------------------------------------------------- /experiments/cosine_similarity/word_embedding_cosine_sim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/cosine_similarity/word_embedding_cosine_sim.py -------------------------------------------------------------------------------- /experiments/generation/generate_text.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/generation/generate_text.py -------------------------------------------------------------------------------- /experiments/generation/name_condition_extraction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/generation/name_condition_extraction.py -------------------------------------------------------------------------------- /experiments/generation/name_extraction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/generation/name_extraction.py -------------------------------------------------------------------------------- /experiments/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/metrics.py -------------------------------------------------------------------------------- /experiments/parse_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/parse_results.py -------------------------------------------------------------------------------- /experiments/probing/FullBERT_single_condition_probing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/probing/FullBERT_single_condition_probing.py -------------------------------------------------------------------------------- /experiments/probing/LR_single_condition_probing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/probing/LR_single_condition_probing.py -------------------------------------------------------------------------------- /experiments/probing/all_conditions_probing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/probing/all_conditions_probing.py -------------------------------------------------------------------------------- /experiments/probing/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/probing/common.py -------------------------------------------------------------------------------- /experiments/probing/names_probing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/probing/names_probing.py -------------------------------------------------------------------------------- /experiments/statistics_name_sentence.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/statistics_name_sentence.py -------------------------------------------------------------------------------- /experiments/utilities.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/experiments/utilities.py -------------------------------------------------------------------------------- /how_many_names.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/how_many_names.py -------------------------------------------------------------------------------- /setup_scripts/name_insertion.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/setup_scripts/name_insertion.sh -------------------------------------------------------------------------------- /setup_scripts/notes_preprocessing_and_name_insertion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/setup_scripts/notes_preprocessing_and_name_insertion.py -------------------------------------------------------------------------------- /setup_scripts/notes_preprocessing_functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/setup_scripts/notes_preprocessing_functions.py -------------------------------------------------------------------------------- /setup_scripts/setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/setup_scripts/setup.sh -------------------------------------------------------------------------------- /setup_scripts/subject_id_to_icd9.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/setup_scripts/subject_id_to_icd9.py -------------------------------------------------------------------------------- /setup_scripts/subject_id_to_medcat_finalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/setup_scripts/subject_id_to_medcat_finalize.py -------------------------------------------------------------------------------- /setup_scripts/subject_id_to_medcat_preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/setup_scripts/subject_id_to_medcat_preprocess.py -------------------------------------------------------------------------------- /setup_scripts/subject_id_to_name.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/setup_scripts/subject_id_to_name.py -------------------------------------------------------------------------------- /setup_scripts/subject_id_to_notes_original.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/setup_scripts/subject_id_to_notes_original.py -------------------------------------------------------------------------------- /setup_scripts/template_only_notes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/setup_scripts/template_only_notes.py -------------------------------------------------------------------------------- /training_scripts/convert_to_tf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/training_scripts/convert_to_tf.py -------------------------------------------------------------------------------- /training_scripts/create_BERT_tfrecords.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/training_scripts/create_BERT_tfrecords.py -------------------------------------------------------------------------------- /training_scripts/create_BERT_tfrecords.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/training_scripts/create_BERT_tfrecords.sh -------------------------------------------------------------------------------- /training_scripts/tpu_download_BERT.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/training_scripts/tpu_download_BERT.sh -------------------------------------------------------------------------------- /training_scripts/tpu_train_BERT.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/training_scripts/tpu_train_BERT.sh -------------------------------------------------------------------------------- /training_scripts/train_word_embeddings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/elehman16/exposing_patient_data_release/HEAD/training_scripts/train_word_embeddings.py --------------------------------------------------------------------------------