cehrbert-data 0.1.1__tar.gz → 0.2.0__tar.gz

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cehrbert_data
-Version: 0.1.1
+Version: 0.2.0
 Summary: The Spark ETL tools for generating the CEHR-BERT and CEHR-GPT pre-training and finetuning data
 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>
 License: MIT License

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data/apps/generate_included_concept_list.py

@@ -53,7 +53,11 @@ def main(
     The function processes patient event data across various domain tables, excludes low-frequency
     concepts, and saves the filtered concepts to a specified output folder.
     """
-    spark = SparkSession.builder.appName("Generate concept list").getOrCreate()
+    spark = (
+        SparkSession.builder.appName("Generate concept list")
+        .config("spark.sql.session.timeZone", "UTC")
+        .getOrCreate()
+    )
 
     # Exclude measurement from domain_table_list if exists because we need to process measurement
     # in a different way

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data/apps/generate_training_data.py

@@ -54,7 +54,11 @@ def main(
         duplicate_records: bool = False,
         disconnect_problem_list_records: bool = False,
 ):
-    spark = SparkSession.builder.appName("Generate CEHR-BERT Training Data").getOrCreate()
+    spark = (
+        SparkSession.builder.appName("Generate CEHR-BERT Training Data")
+        .config("spark.sql.session.timeZone", "UTC")
+        .getOrCreate()
+    )
 
     logger = logging.getLogger(__name__)
     logger.info(
@@ -120,6 +124,7 @@ def main(
         "person_id",
         "discharged_to_concept_id",
     )
+
     person = preprocess_domain_table(spark, input_folder, PERSON)
     birth_datetime_udf = F.coalesce("birth_datetime", F.concat("year_of_birth", F.lit("-01-01")).cast("timestamp"))
     person = person.select(
@@ -128,22 +133,12 @@ def main(
         "race_concept_id",
         "gender_concept_id",
     )
-
     visit_occurrence_person = visit_occurrence.join(person, "person_id").withColumn(
         "age",
         F.ceil(F.months_between(F.col("visit_start_date"), F.col("birth_datetime")) / F.lit(12)),
     )
     visit_occurrence_person = visit_occurrence_person.drop("birth_datetime")
 
-    death = preprocess_domain_table(spark, input_folder, DEATH) if include_death else None
-
-    if include_concept_list and patient_ehr_events:
-        # Filter out concepts
-        qualified_concepts = preprocess_domain_table(spark, input_folder, "qualified_concept_list")
-        patient_ehr_events = patient_ehr_events.join(
-            qualified_concepts.select("standard_concept_id"), "standard_concept_id"
-        )
-
     patient_ehr_events = (
         patient_ehr_events.join(visit_occurrence_person, "visit_occurrence_id")
         .select(
@@ -153,10 +148,12 @@ def main(
         .withColumn("cohort_member_id", F.col("person_id"))
     )
 
-    # Apply the age security measure
-    # We only keep the patient records, whose corresponding age is less than 90
-    if apply_age_filter:
-        patient_ehr_events = patient_ehr_events.where(F.col("age") < 90)
+    if include_concept_list and patient_ehr_events:
+        # Filter out concepts
+        qualified_concepts = preprocess_domain_table(spark, input_folder, "qualified_concept_list")
+        patient_ehr_events = patient_ehr_events.join(
+            qualified_concepts.select("standard_concept_id"), "standard_concept_id"
+        )
 
     if not continue_from_events:
         patient_ehr_events.write.mode("overwrite").parquet(os.path.join(output_folder, "all_patient_events"))
@@ -164,24 +161,21 @@ def main(
     patient_ehr_events = spark.read.parquet(os.path.join(output_folder, "all_patient_events"))
     if should_construct_artificial_visits:
         # Construct artificial visits or re-link the visits for the problem list events
-        patient_ehr_events, visit_occurrence_person = construct_artificial_visits(
+        patient_ehr_events, visit_occurrence = construct_artificial_visits(
             patient_ehr_events,
-            visit_occurrence_person,
+            visit_occurrence,
             spark=spark,
             persistence_folder=output_folder,
             duplicate_records=duplicate_records,
             disconnect_problem_list_records=disconnect_problem_list_records
         )
-        # Update age if some of the ehr_records have been re-associated with the new visits
-        patient_ehr_events = patient_ehr_events.join(
-            person.select("person_id", "birth_datetime"),
-            "person_id",
-        ).join(
-            visit_occurrence_person.select("visit_occurrence_id", "visit_start_date"), "visit_occurrence_id"
-        ).withColumn(
-            "age",
-            F.ceil(F.months_between(F.col("visit_start_date"), F.col("birth_datetime")) / F.lit(12))
-        ).drop("visit_start_date", "birth_datetime")
+
+    death = preprocess_domain_table(spark, input_folder, DEATH) if include_death else None
+
+    # Apply the age security measure
+    # We only keep the patient records, whose corresponding age is less than 90
+    if apply_age_filter:
+        patient_ehr_events = patient_ehr_events.where(F.col("age") < 90)
 
     if is_new_patient_representation:
         patient_sequence_data = create_sequence_data_with_att(

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data/cohorts/spark_app_base.py

@@ -137,7 +137,11 @@ class BaseCohortBuilder(ABC):
         # Validate if the data folders exist
         validate_date_folder(self._input_folder, self._query_builder.get_dependency_list())
 
-        self.spark = SparkSession.builder.appName(f"Generate {self._query_builder.get_cohort_name()}").getOrCreate()
+        self.spark = (
+            SparkSession.builder.appName(f"Generate {self._query_builder.get_cohort_name()}")
+            .config("spark.sql.session.timeZone", "UTC")
+            .getOrCreate()
+        )
 
         self._dependency_dict = instantiate_dependencies(
             self.spark, self._input_folder, self._query_builder.get_dependency_list()
@@ -409,7 +413,11 @@ class NestedCohortBuilder:
             f"disconnect_problem_list_records: {disconnect_problem_list_records}\n"
         )
 
-        self.spark = SparkSession.builder.appName(f"Generate {self._cohort_name}").getOrCreate()
+        self.spark = (
+            SparkSession.builder.appName(f"Generate {self._cohort_name}")
+            .config("spark.sql.session.timeZone", "UTC")
+            .getOrCreate()
+        )
         self._dependency_dict = instantiate_dependencies(self.spark, self._input_folder, DEFAULT_DEPENDENCY)
 
         # Validate the input and output folders

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/connect_omop_visit.py

@@ -226,7 +226,11 @@ def step_2_connect_outpatient_to_inpatient(
 
 
 def main(args):
-    spark = SparkSession.builder.appName("Clean up visit_occurrence").getOrCreate()
+    spark = (
+        SparkSession.builder.appName("Clean up visit_occurrence")
+        .config("spark.sql.session.timeZone", "UTC")
+        .getOrCreate()
+    )
     visit_occurrence = spark.read.parquet(os.path.join(args.input_folder, "visit_occurrence"))
     visit_occurrence_step_1, in_to_in_visit_mapping = step_1_consolidate_inpatient_visits(
         spark,

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/convert_prediction_time_to_str.py

@@ -26,9 +26,10 @@ def convert_file(file_pair):
         # Read with Polars
         df = pl.read_parquet(input_file)
 
-        # Convert datetime to string (ISO format)
+        # Convert datetime to string (ISO format) in UTC to avoid timezone issues
         df = df.with_columns([
             pl.col("prediction_time")
+            .dt.convert_time_zone("UTC")
             .cast(pl.Datetime("us"))
             .dt.strftime("%Y-%m-%d %H:%M:%S.%f")
             .alias("prediction_time")

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/download_omop_tables.py

@@ -107,7 +107,11 @@ if __name__ == "__main__":
     )
 
     ARGS = parser.parse_args()
-    spark = SparkSession.builder.appName("Download OMOP tables").getOrCreate()
+    spark = (
+        SparkSession.builder.appName("Download OMOP tables")
+        .config("spark.sql.session.timeZone", "UTC")
+        .getOrCreate()
+    )
     domain_table_list = ARGS.domain_table_list
     credential_path = ARGS.credential_path
     download_folder = ARGS.output_folder

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/ehrshot_to_omop.py

@@ -784,7 +784,11 @@ def drop_duplicate_visits(data: DataFrame) -> DataFrame:
 
 
 def main(args):
-    spark = SparkSession.builder.appName("Convert EHRShot Data").getOrCreate()
+    spark = (
+        SparkSession.builder.appName("Convert EHRShot Data")
+        .config("spark.sql.session.timeZone", "UTC")
+        .getOrCreate()
+    )
 
     logger.info(
         f"ehr_shot_file: {args.ehr_shot_file}\n"

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/extract_features.py

@@ -71,6 +71,7 @@ def main(args):
         "spark.sql.legacy.parquet.int96RebaseModeInWrite",
         "CORRECTED"
     )
+    spark.conf.set("spark.sql.session.timeZone", "UTC")
 
     cohort_dir = os.path.expanduser(args.cohort_dir)
     is_parquet = False

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/sample_omop_tables.py

@@ -23,6 +23,7 @@ def main(args):
         .config("spark.sql.legacy.parquet.int96RebaseModeInWrite", "CORRECTED")
         .config("spark.sql.legacy.parquet.datetimeRebaseModeInRead", "CORRECTED")
         .config("spark.sql.legacy.parquet.datetimeRebaseModeInWrite", "CORRECTED")
+        .config("spark.sql.session.timeZone", "UTC")
         .getOrCreate()
     )
     patient_sample = spark.read.parquet(args.person_sample)

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data/tools/update_omop_visit.py

@@ -7,7 +7,11 @@ from pyspark.sql import SparkSession
 from pyspark.sql import functions as f
 
 def main(args):
-    spark = SparkSession.builder.appName("Clean up visit_occurrence").getOrCreate()
+    spark = (
+        SparkSession.builder.appName("Clean up visit_occurrence")
+        .config("spark.sql.session.timeZone", "UTC")
+        .getOrCreate()
+    )
     visit_mapping = spark.read.parquet(
         os.path.join(args.output_folder, "visit_mapping")
     )

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data/utils/spark_utils.py

@@ -44,7 +44,7 @@ DOMAIN_KEY_FIELDS = {
             "condition_concept_id",
             "condition_start_date",
             "condition_start_datetime",
-            "condition"
+            "condition_occurrence"
         )
     ],
     "procedure_occurrence_id": [
@@ -52,7 +52,7 @@ DOMAIN_KEY_FIELDS = {
             "procedure_concept_id",
             "procedure_date",
             "procedure_datetime",
-            "procedure"
+            "procedure_occurrence"
         )
     ],
     "drug_exposure_id": [
@@ -60,7 +60,7 @@ DOMAIN_KEY_FIELDS = {
             "drug_concept_id",
             "drug_exposure_start_date",
             "drug_exposure_start_datetime",
-            "drug"
+            "drug_exposure"
         )
     ],
     "measurement_id": [
@@ -84,13 +84,13 @@ DOMAIN_KEY_FIELDS = {
             "device_concept_id",
             "device_exposure_start_date",
             "device_exposure_start_datetime",
-            "device"
+            "device_exposure"
         )
     ],
     "death_date": [("cause_concept_id", "death_date", "death_datetime", "death")],
     "visit_concept_id": [
-        ("visit_concept_id", "visit_start_date", "visit"),
-        ("discharged_to_concept_id", "visit_end_date", "visit"),
+        ("visit_concept_id", "visit_start_date", "visit_occurrence"),
+        ("discharged_to_concept_id", "visit_end_date", "visit_occurrence"),
     ],
 }
 
@@ -180,7 +180,7 @@ def extract_events_by_domain(
     ) in get_key_fields(domain_table):
 
         if is_domain_numeric(domain_table_name):
-            concept = kwargs.get("concept")
+            concept: DataFrame = kwargs.get("concept")
             spark = kwargs.get("spark", None)
             persistence_folder = kwargs.get("persistence_folder", None)
             refresh = kwargs.get("refresh_measurement", False)
@@ -210,7 +210,7 @@ def extract_events_by_domain(
             domain_records = domain_table.where(F.col(date_field).isNotNull()).where(
                 F.col(concept_id_field).isNotNull()
             )
-            datetime_field_udf = F.to_timestamp(F.coalesce(datetime_field, date_field), "yyyy-MM-dd HH:mm:ss")
+            datetime_field_udf = F.to_timestamp(F.coalesce(datetime_field, date_field))
             domain_records = (
                 domain_records.where(F.col(concept_id_field).cast("string") != "0")
                 .withColumn("date", F.to_date(F.col(date_field)))
@@ -222,17 +222,13 @@ def extract_events_by_domain(
                 domain_records["date"].cast("date"),
                 domain_records["datetime"].cast(T.TimestampType()),
                 domain_records["visit_occurrence_id"],
-                F.lit(domain_table_name).alias("domain"),
+                F.lit(domain_table_name.split("_")[0]).alias("domain"),
                 F.lit(None).cast("string").alias("event_group_id"),
                 F.lit(None).cast("float").alias("number_as_value"),
                 F.lit(None).cast("string").alias("concept_as_value"),
                 F.col("unit") if domain_has_unit(domain_records) else F.lit(NA).alias("unit"),
             ).distinct()
 
-            # Remove "Patient Died" from condition_occurrence
-            if domain_table_name == "condition_occurrence":
-                domain_records = domain_records.where("condition_concept_id != 4216643")
-
         if ehr_events is None:
             ehr_events = domain_records
         else:

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cehrbert_data
-Version: 0.1.1
+Version: 0.2.0
 Summary: The Spark ETL tools for generating the CEHR-BERT and CEHR-GPT pre-training and finetuning data
 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>
 License: MIT License

{cehrbert_data-0.1.1 → cehrbert_data-0.2.0}/src/cehrbert_data.egg-info/SOURCES.txt

@@ -68,6 +68,8 @@ src/cehrbert_data.egg-info/PKG-INFO
 src/cehrbert_data.egg-info/SOURCES.txt
 src/cehrbert_data.egg-info/dependency_links.txt
 src/cehrbert_data.egg-info/requires.txt
+src/cehrbert_data.egg-info/scm_file_list.json
+src/cehrbert_data.egg-info/scm_version.json
 src/cehrbert_data.egg-info/top_level.txt
 src/cehrbert_data/apps/__init__.py
 src/cehrbert_data/apps/generate_included_concept_list.py

cehrbert_data-0.2.0/src/cehrbert_data.egg-info/scm_file_list.json

@@ -0,0 +1,141 @@
+{
+  "files": [
+    ".github/workflows/python-build.yml",
+    ".github/workflows/tests.yml",
+    ".gitignore",
+    ".pre-commit-config.yaml",
+    "LICENSE",
+    "README.md",
+    "pyproject.toml",
+    "sample_data/omop_sample/concept/._SUCCESS.crc",
+    "sample_data/omop_sample/concept/.part-00000-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept/.part-00003-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept/.part-00010-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept/_SUCCESS",
+    "sample_data/omop_sample/concept/part-00000-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet",
+    "sample_data/omop_sample/concept/part-00003-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet",
+    "sample_data/omop_sample/concept/part-00010-4b12270c-f6c8-4b59-8e0f-fd588bd79386-c000.snappy.parquet",
+    "sample_data/omop_sample/concept_ancestor/._SUCCESS.crc",
+    "sample_data/omop_sample/concept_ancestor/.part-00000-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept_ancestor/.part-00002-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept_ancestor/.part-00006-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept_ancestor/.part-00011-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept_ancestor/.part-00013-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept_ancestor/_SUCCESS",
+    "sample_data/omop_sample/concept_ancestor/part-00000-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet",
+    "sample_data/omop_sample/concept_ancestor/part-00002-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet",
+    "sample_data/omop_sample/concept_ancestor/part-00006-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet",
+    "sample_data/omop_sample/concept_ancestor/part-00011-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet",
+    "sample_data/omop_sample/concept_ancestor/part-00013-eafbd8be-3337-46da-89d3-20f79c2565d4-c000.snappy.parquet",
+    "sample_data/omop_sample/concept_relationship/._SUCCESS.crc",
+    "sample_data/omop_sample/concept_relationship/.part-00000-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept_relationship/.part-00002-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept_relationship/.part-00007-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept_relationship/.part-00012-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/concept_relationship/_SUCCESS",
+    "sample_data/omop_sample/concept_relationship/part-00000-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet",
+    "sample_data/omop_sample/concept_relationship/part-00002-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet",
+    "sample_data/omop_sample/concept_relationship/part-00007-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet",
+    "sample_data/omop_sample/concept_relationship/part-00012-5752b472-8ba7-4189-ab69-8c92e46443aa-c000.snappy.parquet",
+    "sample_data/omop_sample/condition_occurrence/._SUCCESS.crc",
+    "sample_data/omop_sample/condition_occurrence/.part-00000-4eff03a1-cdcf-4c89-b0cd-9ce590b9b1eb-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/condition_occurrence/_SUCCESS",
+    "sample_data/omop_sample/condition_occurrence/part-00000-4eff03a1-cdcf-4c89-b0cd-9ce590b9b1eb-c000.snappy.parquet",
+    "sample_data/omop_sample/drug_exposure/._SUCCESS.crc",
+    "sample_data/omop_sample/drug_exposure/.part-00000-10bbf1a4-a7da-416e-9703-58609c7edfad-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/drug_exposure/_SUCCESS",
+    "sample_data/omop_sample/drug_exposure/part-00000-10bbf1a4-a7da-416e-9703-58609c7edfad-c000.snappy.parquet",
+    "sample_data/omop_sample/observation_period/._SUCCESS.crc",
+    "sample_data/omop_sample/observation_period/.part-00000-694316e5-cc95-49f1-9fad-5a7f377e2602-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/observation_period/_SUCCESS",
+    "sample_data/omop_sample/observation_period/part-00000-694316e5-cc95-49f1-9fad-5a7f377e2602-c000.snappy.parquet",
+    "sample_data/omop_sample/person/._SUCCESS.crc",
+    "sample_data/omop_sample/person/.part-00000-7d789011-f361-48da-af6f-cfe102978b3a-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/person/_SUCCESS",
+    "sample_data/omop_sample/person/part-00000-7d789011-f361-48da-af6f-cfe102978b3a-c000.snappy.parquet",
+    "sample_data/omop_sample/procedure_occurrence/._SUCCESS.crc",
+    "sample_data/omop_sample/procedure_occurrence/.part-00000-e73003c1-aed5-41c0-b2d4-eaccaccf044a-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/procedure_occurrence/_SUCCESS",
+    "sample_data/omop_sample/procedure_occurrence/part-00000-e73003c1-aed5-41c0-b2d4-eaccaccf044a-c000.snappy.parquet",
+    "sample_data/omop_sample/visit_occurrence/._SUCCESS.crc",
+    "sample_data/omop_sample/visit_occurrence/.part-00000-e874b5f1-bf9e-4cb9-93bf-c309a47b0476-c000.snappy.parquet.crc",
+    "sample_data/omop_sample/visit_occurrence/_SUCCESS",
+    "sample_data/omop_sample/visit_occurrence/part-00000-e874b5f1-bf9e-4cb9-93bf-c309a47b0476-c000.snappy.parquet",
+    "scripts/extract_features_bert.sh",
+    "scripts/extract_features_gpt.sh",
+    "scripts/process_cohorts.sh",
+    "src/__init__.py",
+    "src/cehrbert_data/__init__.py",
+    "src/cehrbert_data/apps/__init__.py",
+    "src/cehrbert_data/apps/generate_included_concept_list.py",
+    "src/cehrbert_data/apps/generate_training_data.py",
+    "src/cehrbert_data/cohorts/__init__.py",
+    "src/cehrbert_data/cohorts/atrial_fibrillation.py",
+    "src/cehrbert_data/cohorts/cabg.py",
+    "src/cehrbert_data/cohorts/coronary_artery_disease.py",
+    "src/cehrbert_data/cohorts/covid.py",
+    "src/cehrbert_data/cohorts/covid_inpatient.py",
+    "src/cehrbert_data/cohorts/death.py",
+    "src/cehrbert_data/cohorts/heart_failure.py",
+    "src/cehrbert_data/cohorts/ischemic_stroke.py",
+    "src/cehrbert_data/cohorts/last_visit_discharged_home.py",
+    "src/cehrbert_data/cohorts/query_builder.py",
+    "src/cehrbert_data/cohorts/spark_app_base.py",
+    "src/cehrbert_data/cohorts/type_two_diabietes.py",
+    "src/cehrbert_data/cohorts/ventilation.py",
+    "src/cehrbert_data/config/__init__.py",
+    "src/cehrbert_data/config/output_names.py",
+    "src/cehrbert_data/const/__init__.py",
+    "src/cehrbert_data/const/__pycache__/__init__.cpython-311.pyc",
+    "src/cehrbert_data/const/__pycache__/common.cpython-311.pyc",
+    "src/cehrbert_data/const/artificial_tokens.py",
+    "src/cehrbert_data/const/common.py",
+    "src/cehrbert_data/decorators/__init__.py",
+    "src/cehrbert_data/decorators/artificial_time_token_decorator.py",
+    "src/cehrbert_data/decorators/clinical_event_decorator.py",
+    "src/cehrbert_data/decorators/death_event_decorator.py",
+    "src/cehrbert_data/decorators/demographic_event_decorator.py",
+    "src/cehrbert_data/decorators/patient_event_decorator_base.py",
+    "src/cehrbert_data/decorators/prediction_token_decorator.py",
+    "src/cehrbert_data/decorators/token_priority.py",
+    "src/cehrbert_data/prediction_cohorts/__init__.py",
+    "src/cehrbert_data/prediction_cohorts/afib_ischemic_stroke.py",
+    "src/cehrbert_data/prediction_cohorts/cad_cabg_cohort.py",
+    "src/cehrbert_data/prediction_cohorts/cad_hf_cohort.py",
+    "src/cehrbert_data/prediction_cohorts/copd_readmission.py",
+    "src/cehrbert_data/prediction_cohorts/covid_death.py",
+    "src/cehrbert_data/prediction_cohorts/covid_ventilation.py",
+    "src/cehrbert_data/prediction_cohorts/discharge_home_death.py",
+    "src/cehrbert_data/prediction_cohorts/hf_readmission.py",
+    "src/cehrbert_data/prediction_cohorts/hospitalization.py",
+    "src/cehrbert_data/prediction_cohorts/hospitalization_mortality.py",
+    "src/cehrbert_data/prediction_cohorts/readmission.py",
+    "src/cehrbert_data/prediction_cohorts/t2dm_hf_cohort.py",
+    "src/cehrbert_data/queries/__init__.py",
+    "src/cehrbert_data/queries/measurement_queries.py",
+    "src/cehrbert_data/tools/__init__.py",
+    "src/cehrbert_data/tools/connect_omop_visit.py",
+    "src/cehrbert_data/tools/convert_prediction_time_to_local.py",
+    "src/cehrbert_data/tools/convert_prediction_time_to_str.py",
+    "src/cehrbert_data/tools/download_omop_tables.py",
+    "src/cehrbert_data/tools/ehrshot_to_omop.py",
+    "src/cehrbert_data/tools/extract_features.py",
+    "src/cehrbert_data/tools/prepare_ehrshot_cohorts.py",
+    "src/cehrbert_data/tools/sample_omop_tables.py",
+    "src/cehrbert_data/tools/update_omop_visit.py",
+    "src/cehrbert_data/utils/__init__.py",
+    "src/cehrbert_data/utils/logging_utils.py",
+    "src/cehrbert_data/utils/spark_parse_args.py",
+    "src/cehrbert_data/utils/spark_utils.py",
+    "src/cehrbert_data/utils/vocab_utils.py",
+    "tests/__init__.py",
+    "tests/integration_tests/__init__.py",
+    "tests/integration_tests/test_generate_training_data.py",
+    "tests/integration_tests/test_hf_readmission.py",
+    "tests/integration_tests/test_hf_readmission_cohort_meds.py",
+    "tests/pyspark_test_base.py",
+    "tests/unit_tests/__init__.py",
+    "tests/unit_tests/test_ehrshot_to_omop.py",
+    "tests/unit_tests/test_spark_utils.py"
+  ]
+}

cehrbert_data-0.2.0/src/cehrbert_data.egg-info/scm_version.json

@@ -0,0 +1,8 @@
+{
+  "tag": "0.2.0",
+  "distance": 0,
+  "node": "gcf5a5dd7ffecc8eacae72535f68284aa150f42cb",
+  "dirty": false,
+  "branch": "HEAD",
+  "node_date": "2026-03-01"
+}