upgraded cehrbert_data to v0.0.3

pyproject.toml

@@ -58,7 +58,7 @@ dependencies = [
     "Werkzeug==3.0.1",
     "wandb==0.17.8",
     "xgboost==2.0.3",
-    "cehrbert_data==0.0.1"
+    "cehrbert_data==0.0.3"
 ]
 
 [tool.setuptools_scm]

src/cehrbert/data_generators/hf_data_generator/hf_dataset_mapping.py

@@ -8,13 +8,14 @@
 
 import numpy as np
 import pandas as pd
-from cehrbert_data.decorators.patient_event_decorator import get_att_function
+from cehrbert_data.const.common import NA
+from cehrbert_data.decorators.patient_event_decorator_base import get_att_function
 from datasets.formatting.formatting import LazyBatch
 from dateutil.relativedelta import relativedelta
 from meds.schema import birth_code, death_code
 from pandas import Series
 
-from cehrbert.models.hf_models.tokenization_hf_cehrbert import NA, CehrBertTokenizer
+from cehrbert.models.hf_models.tokenization_hf_cehrbert import CehrBertTokenizer
 from cehrbert.runners.hf_runner_argument_dataclass import DataTrainingArguments
 
 birth_codes = [birth_code, "MEDS_BIRTH"]

src/cehrbert/models/hf_models/tokenization_hf_cehrbert.py

@@ -8,6 +8,7 @@
 
 import numpy as np
 import transformers
+from cehrbert_data.const.common import NA
 from datasets import Dataset, DatasetDict
 from tokenizers import Tokenizer
 from tokenizers.models import WordLevel
@@ -16,7 +17,7 @@
 from tqdm import tqdm
 from transformers.tokenization_utils_base import PushToHubMixin
 
-from cehrbert.models.hf_models.tokenization_utils import NA, agg_helper, agg_statistics, map_statistics
+from cehrbert.models.hf_models.tokenization_utils import agg_helper, agg_statistics, map_statistics
 from cehrbert.runners.hf_runner_argument_dataclass import DataTrainingArguments
 
 PAD_TOKEN = "[PAD]"

src/cehrbert/models/hf_models/tokenization_utils.py

@@ -4,9 +4,9 @@
 from functools import partial
 from typing import Any, Dict
 
-from cehrbert.utils.stat_utils import TruncatedOnlineStatistics
+from cehrbert_data.const.common import NA
 
-NA = "N/A"
+from cehrbert.utils.stat_utils import TruncatedOnlineStatistics
 
 
 def load_json_file(json_file):

src/cehrbert/runners/hf_runner_argument_dataclass.py

@@ -2,7 +2,7 @@
 from enum import Enum
 from typing import Any, Dict, List, Literal, Optional
 
-from cehrbert_data.decorators.patient_event_decorator import AttType
+from cehrbert_data.decorators.patient_event_decorator_base import AttType
 
 from cehrbert.data_generators.hf_data_generator.meds_to_cehrbert_conversion_rules import (
     MedsToBertMimic4,

tests/unit_tests/data_generators/hf_data_generator/hf_med_to_cehrbert_mapping_test.py

@@ -1,7 +1,7 @@
 import unittest
 from datetime import datetime
 
-from cehrbert_data.decorators.patient_event_decorator import AttType
+from cehrbert_data.decorators.patient_event_decorator_base import AttType
 
 from cehrbert.data_generators.hf_data_generator.hf_dataset_mapping import MedToCehrBertDatasetMapping
 from cehrbert.med_extension.schema_extension import CehrBertPatient, Event, Visit