cehrbert-data 0.1.2__tar.gz → 0.2.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (146) hide show
  1. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/PKG-INFO +1 -1
  2. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data.egg-info/PKG-INFO +1 -1
  3. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data.egg-info/SOURCES.txt +2 -0
  4. cehrbert_data-0.2.0/src/cehrbert_data.egg-info/scm_file_list.json +141 -0
  5. cehrbert_data-0.2.0/src/cehrbert_data.egg-info/scm_version.json +8 -0
  6. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/.github/workflows/python-build.yml +0 -0
  7. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/.github/workflows/tests.yml +0 -0
  8. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/.gitignore +0 -0
  9. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/.pre-commit-config.yaml +0 -0
  10. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/LICENSE +0 -0
  11. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/README.md +0 -0
  12. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/pyproject.toml +0 -0
  13. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept/._SUCCESS.crc +0 -0
  14. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept/.part-00000-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet.crc +0 -0
  15. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept/.part-00003-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet.crc +0 -0
  16. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept/.part-00010-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet.crc +0 -0
  17. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept/_SUCCESS +0 -0
  18. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept/part-00000-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet +0 -0
  19. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept/part-00003-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet +0 -0
  20. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept/part-00010-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet +0 -0
  21. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/._SUCCESS.crc +0 -0
  22. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/.part-00000-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc +0 -0
  23. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/.part-00002-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc +0 -0
  24. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/.part-00006-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc +0 -0
  25. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/.part-00011-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc +0 -0
  26. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/.part-00013-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc +0 -0
  27. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/_SUCCESS +0 -0
  28. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/part-00000-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet +0 -0
  29. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/part-00002-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet +0 -0
  30. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/part-00006-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet +0 -0
  31. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/part-00011-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet +0 -0
  32. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_ancestor/part-00013-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet +0 -0
  33. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_relationship/._SUCCESS.crc +0 -0
  34. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_relationship/.part-00000-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc +0 -0
  35. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_relationship/.part-00002-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc +0 -0
  36. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_relationship/.part-00007-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc +0 -0
  37. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_relationship/.part-00012-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc +0 -0
  38. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_relationship/_SUCCESS +0 -0
  39. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_relationship/part-00000-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet +0 -0
  40. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_relationship/part-00002-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet +0 -0
  41. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_relationship/part-00007-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet +0 -0
  42. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/concept_relationship/part-00012-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet +0 -0
  43. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/condition_occurrence/._SUCCESS.crc +0 -0
  44. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/condition_occurrence/.part-00000-4eff03a1-cdcf-4c89-b0cd-9ce590b9b1eb-c000.snappy.parquet.crc +0 -0
  45. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/condition_occurrence/_SUCCESS +0 -0
  46. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/condition_occurrence/part-00000-4eff03a1-cdcf-4c89-b0cd-9ce590b9b1eb-c000.snappy.parquet +0 -0
  47. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/drug_exposure/._SUCCESS.crc +0 -0
  48. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/drug_exposure/.part-00000-10bbf1a4-a7da-416e-9703-58609c7edfad-c000.snappy.parquet.crc +0 -0
  49. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/drug_exposure/_SUCCESS +0 -0
  50. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/drug_exposure/part-00000-10bbf1a4-a7da-416e-9703-58609c7edfad-c000.snappy.parquet +0 -0
  51. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/observation_period/._SUCCESS.crc +0 -0
  52. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/observation_period/.part-00000-694316e5-cc95-49f1-9fad-5a7f377e2602-c000.snappy.parquet.crc +0 -0
  53. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/observation_period/_SUCCESS +0 -0
  54. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/observation_period/part-00000-694316e5-cc95-49f1-9fad-5a7f377e2602-c000.snappy.parquet +0 -0
  55. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/person/._SUCCESS.crc +0 -0
  56. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/person/.part-00000-7d789011-f361-48da-af6f-cfe102978b3a-c000.snappy.parquet.crc +0 -0
  57. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/person/_SUCCESS +0 -0
  58. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/person/part-00000-7d789011-f361-48da-af6f-cfe102978b3a-c000.snappy.parquet +0 -0
  59. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/procedure_occurrence/._SUCCESS.crc +0 -0
  60. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/procedure_occurrence/.part-00000-e73003c1-aed5-41c0-b2d4-eaccaccf044a-c000.snappy.parquet.crc +0 -0
  61. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/procedure_occurrence/_SUCCESS +0 -0
  62. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/procedure_occurrence/part-00000-e73003c1-aed5-41c0-b2d4-eaccaccf044a-c000.snappy.parquet +0 -0
  63. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/visit_occurrence/._SUCCESS.crc +0 -0
  64. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/visit_occurrence/.part-00000-e874b5f1-bf9e-4cb9-93bf-c309a47b0476-c000.snappy.parquet.crc +0 -0
  65. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/visit_occurrence/_SUCCESS +0 -0
  66. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/sample_data/omop_sample/visit_occurrence/part-00000-e874b5f1-bf9e-4cb9-93bf-c309a47b0476-c000.snappy.parquet +0 -0
  67. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/scripts/extract_features_bert.sh +0 -0
  68. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/scripts/extract_features_gpt.sh +0 -0
  69. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/scripts/process_cohorts.sh +0 -0
  70. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/setup.cfg +0 -0
  71. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/__init__.py +0 -0
  72. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/__init__.py +0 -0
  73. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/apps/__init__.py +0 -0
  74. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/apps/generate_included_concept_list.py +0 -0
  75. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/apps/generate_training_data.py +0 -0
  76. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/__init__.py +0 -0
  77. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/atrial_fibrillation.py +0 -0
  78. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/cabg.py +0 -0
  79. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/coronary_artery_disease.py +0 -0
  80. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/covid.py +0 -0
  81. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/covid_inpatient.py +0 -0
  82. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/death.py +0 -0
  83. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/heart_failure.py +0 -0
  84. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/ischemic_stroke.py +0 -0
  85. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/last_visit_discharged_home.py +0 -0
  86. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/query_builder.py +0 -0
  87. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/spark_app_base.py +0 -0
  88. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/type_two_diabietes.py +0 -0
  89. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/ventilation.py +0 -0
  90. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/config/__init__.py +0 -0
  91. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/config/output_names.py +0 -0
  92. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/const/__init__.py +0 -0
  93. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/const/__pycache__/__init__.cpython-311.pyc +0 -0
  94. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/const/__pycache__/common.cpython-311.pyc +0 -0
  95. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/const/artificial_tokens.py +0 -0
  96. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/const/common.py +0 -0
  97. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/decorators/__init__.py +0 -0
  98. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/decorators/artificial_time_token_decorator.py +0 -0
  99. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/decorators/clinical_event_decorator.py +0 -0
  100. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/decorators/death_event_decorator.py +0 -0
  101. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/decorators/demographic_event_decorator.py +0 -0
  102. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/decorators/patient_event_decorator_base.py +0 -0
  103. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/decorators/prediction_token_decorator.py +0 -0
  104. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/decorators/token_priority.py +0 -0
  105. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/__init__.py +0 -0
  106. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/afib_ischemic_stroke.py +0 -0
  107. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/cad_cabg_cohort.py +0 -0
  108. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/cad_hf_cohort.py +0 -0
  109. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/copd_readmission.py +0 -0
  110. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/covid_death.py +0 -0
  111. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/covid_ventilation.py +0 -0
  112. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/discharge_home_death.py +0 -0
  113. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/hf_readmission.py +0 -0
  114. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/hospitalization.py +0 -0
  115. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/hospitalization_mortality.py +0 -0
  116. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/readmission.py +0 -0
  117. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/prediction_cohorts/t2dm_hf_cohort.py +0 -0
  118. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/queries/__init__.py +0 -0
  119. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/queries/measurement_queries.py +0 -0
  120. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/__init__.py +0 -0
  121. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/connect_omop_visit.py +0 -0
  122. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/convert_prediction_time_to_local.py +0 -0
  123. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/convert_prediction_time_to_str.py +0 -0
  124. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/download_omop_tables.py +0 -0
  125. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/ehrshot_to_omop.py +0 -0
  126. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/extract_features.py +0 -0
  127. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/prepare_ehrshot_cohorts.py +0 -0
  128. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/sample_omop_tables.py +0 -0
  129. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/update_omop_visit.py +0 -0
  130. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/utils/__init__.py +0 -0
  131. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/utils/logging_utils.py +0 -0
  132. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/utils/spark_parse_args.py +0 -0
  133. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/utils/spark_utils.py +0 -0
  134. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data/utils/vocab_utils.py +0 -0
  135. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data.egg-info/dependency_links.txt +0 -0
  136. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data.egg-info/requires.txt +0 -0
  137. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/src/cehrbert_data.egg-info/top_level.txt +0 -0
  138. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/tests/__init__.py +0 -0
  139. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/tests/integration_tests/__init__.py +0 -0
  140. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/tests/integration_tests/test_generate_training_data.py +0 -0
  141. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/tests/integration_tests/test_hf_readmission.py +0 -0
  142. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/tests/integration_tests/test_hf_readmission_cohort_meds.py +0 -0
  143. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/tests/pyspark_test_base.py +0 -0
  144. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/tests/unit_tests/__init__.py +0 -0
  145. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/tests/unit_tests/test_ehrshot_to_omop.py +0 -0
  146. {cehrbert_data-0.1.2 → cehrbert_data-0.2.0}/tests/unit_tests/test_spark_utils.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: cehrbert_data
3
- Version: 0.1.2
3
+ Version: 0.2.0
4
4
  Summary: The Spark ETL tools for generating the CEHR-BERT and CEHR-GPT pre-training and finetuning data
5
5
  Author-email: Chao Pang <chaopang229@gmail.com>, Xinzhuo Jiang <xj2193@cumc.columbia.edu>, Krishna Kalluri <kk3326@cumc.columbia.edu>, Nishanth Parameshwar Pavinkurve <np2689@cumc.columbia.edu>, Karthik Natarajan <kn2174@cumc.columbia.edu>
6
6
  License: MIT License
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: cehrbert_data
3
- Version: 0.1.2
3
+ Version: 0.2.0
4
4
  Summary: The Spark ETL tools for generating the CEHR-BERT and CEHR-GPT pre-training and finetuning data
5
5
  Author-email: Chao Pang <chaopang229@gmail.com>, Xinzhuo Jiang <xj2193@cumc.columbia.edu>, Krishna Kalluri <kk3326@cumc.columbia.edu>, Nishanth Parameshwar Pavinkurve <np2689@cumc.columbia.edu>, Karthik Natarajan <kn2174@cumc.columbia.edu>
6
6
  License: MIT License
@@ -68,6 +68,8 @@ src/cehrbert_data.egg-info/PKG-INFO
68
68
  src/cehrbert_data.egg-info/SOURCES.txt
69
69
  src/cehrbert_data.egg-info/dependency_links.txt
70
70
  src/cehrbert_data.egg-info/requires.txt
71
+ src/cehrbert_data.egg-info/scm_file_list.json
72
+ src/cehrbert_data.egg-info/scm_version.json
71
73
  src/cehrbert_data.egg-info/top_level.txt
72
74
  src/cehrbert_data/apps/__init__.py
73
75
  src/cehrbert_data/apps/generate_included_concept_list.py
@@ -0,0 +1,141 @@
1
+ {
2
+ "files": [
3
+ ".github/workflows/python-build.yml",
4
+ ".github/workflows/tests.yml",
5
+ ".gitignore",
6
+ ".pre-commit-config.yaml",
7
+ "LICENSE",
8
+ "README.md",
9
+ "pyproject.toml",
10
+ "sample_data/omop_sample/concept/._SUCCESS.crc",
11
+ "sample_data/omop_sample/concept/.part-00000-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet.crc",
12
+ "sample_data/omop_sample/concept/.part-00003-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet.crc",
13
+ "sample_data/omop_sample/concept/.part-00010-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet.crc",
14
+ "sample_data/omop_sample/concept/_SUCCESS",
15
+ "sample_data/omop_sample/concept/part-00000-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet",
16
+ "sample_data/omop_sample/concept/part-00003-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet",
17
+ "sample_data/omop_sample/concept/part-00010-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet",
18
+ "sample_data/omop_sample/concept_ancestor/._SUCCESS.crc",
19
+ "sample_data/omop_sample/concept_ancestor/.part-00000-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc",
20
+ "sample_data/omop_sample/concept_ancestor/.part-00002-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc",
21
+ "sample_data/omop_sample/concept_ancestor/.part-00006-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc",
22
+ "sample_data/omop_sample/concept_ancestor/.part-00011-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc",
23
+ "sample_data/omop_sample/concept_ancestor/.part-00013-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc",
24
+ "sample_data/omop_sample/concept_ancestor/_SUCCESS",
25
+ "sample_data/omop_sample/concept_ancestor/part-00000-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet",
26
+ "sample_data/omop_sample/concept_ancestor/part-00002-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet",
27
+ "sample_data/omop_sample/concept_ancestor/part-00006-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet",
28
+ "sample_data/omop_sample/concept_ancestor/part-00011-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet",
29
+ "sample_data/omop_sample/concept_ancestor/part-00013-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet",
30
+ "sample_data/omop_sample/concept_relationship/._SUCCESS.crc",
31
+ "sample_data/omop_sample/concept_relationship/.part-00000-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc",
32
+ "sample_data/omop_sample/concept_relationship/.part-00002-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc",
33
+ "sample_data/omop_sample/concept_relationship/.part-00007-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc",
34
+ "sample_data/omop_sample/concept_relationship/.part-00012-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc",
35
+ "sample_data/omop_sample/concept_relationship/_SUCCESS",
36
+ "sample_data/omop_sample/concept_relationship/part-00000-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet",
37
+ "sample_data/omop_sample/concept_relationship/part-00002-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet",
38
+ "sample_data/omop_sample/concept_relationship/part-00007-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet",
39
+ "sample_data/omop_sample/concept_relationship/part-00012-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet",
40
+ "sample_data/omop_sample/condition_occurrence/._SUCCESS.crc",
41
+ "sample_data/omop_sample/condition_occurrence/.part-00000-4eff03a1-cdcf-4c89-b0cd-9ce590b9b1eb-c000.snappy.parquet.crc",
42
+ "sample_data/omop_sample/condition_occurrence/_SUCCESS",
43
+ "sample_data/omop_sample/condition_occurrence/part-00000-4eff03a1-cdcf-4c89-b0cd-9ce590b9b1eb-c000.snappy.parquet",
44
+ "sample_data/omop_sample/drug_exposure/._SUCCESS.crc",
45
+ "sample_data/omop_sample/drug_exposure/.part-00000-10bbf1a4-a7da-416e-9703-58609c7edfad-c000.snappy.parquet.crc",
46
+ "sample_data/omop_sample/drug_exposure/_SUCCESS",
47
+ "sample_data/omop_sample/drug_exposure/part-00000-10bbf1a4-a7da-416e-9703-58609c7edfad-c000.snappy.parquet",
48
+ "sample_data/omop_sample/observation_period/._SUCCESS.crc",
49
+ "sample_data/omop_sample/observation_period/.part-00000-694316e5-cc95-49f1-9fad-5a7f377e2602-c000.snappy.parquet.crc",
50
+ "sample_data/omop_sample/observation_period/_SUCCESS",
51
+ "sample_data/omop_sample/observation_period/part-00000-694316e5-cc95-49f1-9fad-5a7f377e2602-c000.snappy.parquet",
52
+ "sample_data/omop_sample/person/._SUCCESS.crc",
53
+ "sample_data/omop_sample/person/.part-00000-7d789011-f361-48da-af6f-cfe102978b3a-c000.snappy.parquet.crc",
54
+ "sample_data/omop_sample/person/_SUCCESS",
55
+ "sample_data/omop_sample/person/part-00000-7d789011-f361-48da-af6f-cfe102978b3a-c000.snappy.parquet",
56
+ "sample_data/omop_sample/procedure_occurrence/._SUCCESS.crc",
57
+ "sample_data/omop_sample/procedure_occurrence/.part-00000-e73003c1-aed5-41c0-b2d4-eaccaccf044a-c000.snappy.parquet.crc",
58
+ "sample_data/omop_sample/procedure_occurrence/_SUCCESS",
59
+ "sample_data/omop_sample/procedure_occurrence/part-00000-e73003c1-aed5-41c0-b2d4-eaccaccf044a-c000.snappy.parquet",
60
+ "sample_data/omop_sample/visit_occurrence/._SUCCESS.crc",
61
+ "sample_data/omop_sample/visit_occurrence/.part-00000-e874b5f1-bf9e-4cb9-93bf-c309a47b0476-c000.snappy.parquet.crc",
62
+ "sample_data/omop_sample/visit_occurrence/_SUCCESS",
63
+ "sample_data/omop_sample/visit_occurrence/part-00000-e874b5f1-bf9e-4cb9-93bf-c309a47b0476-c000.snappy.parquet",
64
+ "scripts/extract_features_bert.sh",
65
+ "scripts/extract_features_gpt.sh",
66
+ "scripts/process_cohorts.sh",
67
+ "src/__init__.py",
68
+ "src/cehrbert_data/__init__.py",
69
+ "src/cehrbert_data/apps/__init__.py",
70
+ "src/cehrbert_data/apps/generate_included_concept_list.py",
71
+ "src/cehrbert_data/apps/generate_training_data.py",
72
+ "src/cehrbert_data/cohorts/__init__.py",
73
+ "src/cehrbert_data/cohorts/atrial_fibrillation.py",
74
+ "src/cehrbert_data/cohorts/cabg.py",
75
+ "src/cehrbert_data/cohorts/coronary_artery_disease.py",
76
+ "src/cehrbert_data/cohorts/covid.py",
77
+ "src/cehrbert_data/cohorts/covid_inpatient.py",
78
+ "src/cehrbert_data/cohorts/death.py",
79
+ "src/cehrbert_data/cohorts/heart_failure.py",
80
+ "src/cehrbert_data/cohorts/ischemic_stroke.py",
81
+ "src/cehrbert_data/cohorts/last_visit_discharged_home.py",
82
+ "src/cehrbert_data/cohorts/query_builder.py",
83
+ "src/cehrbert_data/cohorts/spark_app_base.py",
84
+ "src/cehrbert_data/cohorts/type_two_diabietes.py",
85
+ "src/cehrbert_data/cohorts/ventilation.py",
86
+ "src/cehrbert_data/config/__init__.py",
87
+ "src/cehrbert_data/config/output_names.py",
88
+ "src/cehrbert_data/const/__init__.py",
89
+ "src/cehrbert_data/const/__pycache__/__init__.cpython-311.pyc",
90
+ "src/cehrbert_data/const/__pycache__/common.cpython-311.pyc",
91
+ "src/cehrbert_data/const/artificial_tokens.py",
92
+ "src/cehrbert_data/const/common.py",
93
+ "src/cehrbert_data/decorators/__init__.py",
94
+ "src/cehrbert_data/decorators/artificial_time_token_decorator.py",
95
+ "src/cehrbert_data/decorators/clinical_event_decorator.py",
96
+ "src/cehrbert_data/decorators/death_event_decorator.py",
97
+ "src/cehrbert_data/decorators/demographic_event_decorator.py",
98
+ "src/cehrbert_data/decorators/patient_event_decorator_base.py",
99
+ "src/cehrbert_data/decorators/prediction_token_decorator.py",
100
+ "src/cehrbert_data/decorators/token_priority.py",
101
+ "src/cehrbert_data/prediction_cohorts/__init__.py",
102
+ "src/cehrbert_data/prediction_cohorts/afib_ischemic_stroke.py",
103
+ "src/cehrbert_data/prediction_cohorts/cad_cabg_cohort.py",
104
+ "src/cehrbert_data/prediction_cohorts/cad_hf_cohort.py",
105
+ "src/cehrbert_data/prediction_cohorts/copd_readmission.py",
106
+ "src/cehrbert_data/prediction_cohorts/covid_death.py",
107
+ "src/cehrbert_data/prediction_cohorts/covid_ventilation.py",
108
+ "src/cehrbert_data/prediction_cohorts/discharge_home_death.py",
109
+ "src/cehrbert_data/prediction_cohorts/hf_readmission.py",
110
+ "src/cehrbert_data/prediction_cohorts/hospitalization.py",
111
+ "src/cehrbert_data/prediction_cohorts/hospitalization_mortality.py",
112
+ "src/cehrbert_data/prediction_cohorts/readmission.py",
113
+ "src/cehrbert_data/prediction_cohorts/t2dm_hf_cohort.py",
114
+ "src/cehrbert_data/queries/__init__.py",
115
+ "src/cehrbert_data/queries/measurement_queries.py",
116
+ "src/cehrbert_data/tools/__init__.py",
117
+ "src/cehrbert_data/tools/connect_omop_visit.py",
118
+ "src/cehrbert_data/tools/convert_prediction_time_to_local.py",
119
+ "src/cehrbert_data/tools/convert_prediction_time_to_str.py",
120
+ "src/cehrbert_data/tools/download_omop_tables.py",
121
+ "src/cehrbert_data/tools/ehrshot_to_omop.py",
122
+ "src/cehrbert_data/tools/extract_features.py",
123
+ "src/cehrbert_data/tools/prepare_ehrshot_cohorts.py",
124
+ "src/cehrbert_data/tools/sample_omop_tables.py",
125
+ "src/cehrbert_data/tools/update_omop_visit.py",
126
+ "src/cehrbert_data/utils/__init__.py",
127
+ "src/cehrbert_data/utils/logging_utils.py",
128
+ "src/cehrbert_data/utils/spark_parse_args.py",
129
+ "src/cehrbert_data/utils/spark_utils.py",
130
+ "src/cehrbert_data/utils/vocab_utils.py",
131
+ "tests/__init__.py",
132
+ "tests/integration_tests/__init__.py",
133
+ "tests/integration_tests/test_generate_training_data.py",
134
+ "tests/integration_tests/test_hf_readmission.py",
135
+ "tests/integration_tests/test_hf_readmission_cohort_meds.py",
136
+ "tests/pyspark_test_base.py",
137
+ "tests/unit_tests/__init__.py",
138
+ "tests/unit_tests/test_ehrshot_to_omop.py",
139
+ "tests/unit_tests/test_spark_utils.py"
140
+ ]
141
+ }
@@ -0,0 +1,8 @@
1
+ {
2
+ "tag": "0.2.0",
3
+ "distance": 0,
4
+ "node": "gcf5a5dd7ffecc8eacae72535f68284aa150f42cb",
5
+ "dirty": false,
6
+ "branch": "HEAD",
7
+ "node_date": "2026-03-01"
8
+ }
File without changes
File without changes
File without changes
File without changes