Standardized schema naming convention and fixed another typo.

README.md

@@ -85,7 +85,7 @@ In addition, it can contain any number of custom properties to further enrich ob
 function below generates a pyarrow schema for a given set of custom properties.
 
 ```python
-def data_schema(custom_properties=[]):
+def data(custom_properties=[]):
     return pa.schema(
         [
             ("patient_id", pa.int64()),
@@ -181,17 +181,15 @@ DatasetMetadata = TypedDict(
 #### The code metadata schema.
 
 ```python
-def code_metadata_schema(custom_per_code_properties=[]): 
-    code_metadata = pa.schema(
+def code_metadata(custom_per_code_properties=[]): 
+    return pa.schema(
         [
             ("code", pa.string()),
             ("description", pa.string()),
             ("parent_codes", pa.list(pa.string()),
         ] + custom_per_code_properties
     )
 
-    return code_metadata
-
 # Python type for the above schema
 
 CodeMetadata = TypedDict("CodeMetadata", {"code": str, "description": str, "parent_codes": List[str]}, total=False)

src/meds/__init__.py

@@ -1,14 +1,14 @@
 from meds._version import __version__  # noqa
 
 from .schema import (
-    data_schema, label, Label, train_split, tuning_split, held_out_split, patient_split, code_metadata,
+    data, label, Label, train_split, tuning_split, held_out_split, patient_split, code_metadata,
     dataset_metadata, CodeMetadata, DatasetMetadata, birth_code, death_code
 )
 
 
 # List all objects that we want to export
 _exported_objects = {
-    'data_schema': data_schema,
+    'data': data,
     'label': label,
     'Label': Label,
     'train_split': train_split,

src/meds/schema.py

@@ -26,7 +26,7 @@
 birth_code = "MEDS_BIRTH"
 death_code = "MEDS_DEATH"
 
-def data_schema(custom_properties=[]):
+def data(custom_properties=[]):
     return pa.schema(
         [
             ("patient_id", pa.int64()),
@@ -126,17 +126,15 @@ def data_schema(custom_properties=[]):
 # The code metadata schema.
 # This is a parquet schema.
 
-def code_metadata_schema(custom_per_code_properties=[]): 
-    code_metadata = pa.schema(
+def code_metadata(custom_per_code_properties=[]): 
+    return pa.schema(
         [
             ("code", pa.string()),
             ("description", pa.string()),
             ("parent_codes", pa.list(pa.string())),
         ] + custom_per_code_properties
     )
 
-    return code_metadata
-
 # Python type for the above schema
 
 CodeMetadata = TypedDict("CodeMetadata", {"code": str, "description": str, "parent_codes": List[str]}, total=False)