hccinfhir 0.2.1__py3-none-any.whl → 0.2.3__py3-none-any.whl

hccinfhir/hccinfhir.py

@@ -1,4 +1,4 @@
-from typing import List, Dict, Any, Union, Optional, Tuple, Set
+from typing import List, Dict, Any, Union, Optional, Tuple, Set, Iterable
 from hccinfhir.extractor import extract_sld_list
 from hccinfhir.filter import apply_filter
 from hccinfhir.model_calculate import calculate_raf
@@ -184,16 +184,16 @@ class HCCInFHIR:
         # Create new result with service data included
         return raf_result.model_copy(update={'service_level_data': standardized_data})
         
-    def calculate_from_diagnosis(self, diagnosis_codes: List[str],
+    def calculate_from_diagnosis(self, diagnosis_codes: Iterable[str],
                                demographics: Union[Demographics, Dict[str, Any]],
                                prefix_override: Optional[PrefixOverride] = None,
                                maci: float = 0.0,
                                norm_factor: float = 1.0,
                                frailty_score: float = 0.0) -> RAFResult:
-        """Calculate RAF scores from a list of diagnosis codes.
+        """Calculate RAF scores from diagnosis codes.
 
         Args:
-            diagnosis_codes: List of diagnosis codes
+            diagnosis_codes: Iterable of diagnosis codes (list, tuple, numpy array, etc.)
             demographics: Demographics information
             prefix_override: Optional prefix to override auto-detected demographic prefix.
                 Use when demographic categorization is incorrect (e.g., ESRD patients with orec=0).
@@ -201,14 +201,14 @@ class HCCInFHIR:
             norm_factor: Normalization factor (default 1.0)
             frailty_score: Frailty adjustment score (default 0.0)
 
-        Raises:
-            ValueError: If diagnosis_codes is empty or not a list
+        Returns:
+            RAFResult object containing calculated scores
         """
-        if not isinstance(diagnosis_codes, list):
-            raise ValueError("diagnosis_codes must be a list")
-        
+        # Convert to list to ensure consistent handling downstream
+        diagnosis_list = list(diagnosis_codes) if diagnosis_codes is not None else []
+
         demographics = self._ensure_demographics(demographics)
         raf_result = self._calculate_raf_from_demographics_and_dx_codes(
-            diagnosis_codes, demographics, prefix_override, maci, norm_factor, frailty_score
+            diagnosis_list, demographics, prefix_override, maci, norm_factor, frailty_score
         )
         return raf_result

hccinfhir/model_calculate.py

@@ -1,11 +1,11 @@
 from typing import List, Union, Dict, Tuple, Set, Optional
-from hccinfhir.datamodels import ModelName, RAFResult, PrefixOverride
+from hccinfhir.datamodels import ModelName, RAFResult, PrefixOverride, HCCDetail
 from hccinfhir.model_demographics import categorize_demographics
 from hccinfhir.model_dx_to_cc import apply_mapping
 from hccinfhir.model_hierarchies import apply_hierarchies
 from hccinfhir.model_coefficients import apply_coefficients
 from hccinfhir.model_interactions import apply_interactions
-from hccinfhir.defaults import dx_to_cc_default, hierarchies_default, is_chronic_default, coefficients_default
+from hccinfhir.defaults import dx_to_cc_default, hierarchies_default, is_chronic_default, coefficients_default, labels_default
 
 def calculate_raf(diagnosis_codes: List[str],
                   model_name: ModelName = "CMS-HCC Model V28",
@@ -23,6 +23,7 @@ def calculate_raf(diagnosis_codes: List[str],
                   is_chronic_mapping: Dict[Tuple[str, ModelName], bool] = is_chronic_default,
                   hierarchies_mapping: Dict[Tuple[str, ModelName], Set[str]] = hierarchies_default,
                   coefficients_mapping: Dict[Tuple[str, ModelName], float] = coefficients_default,
+                  labels_mapping: Dict[Tuple[str, ModelName], str] = labels_default,
                   prefix_override: Optional[PrefixOverride] = None,
                   maci: float = 0.0,
                   norm_factor: float = 1.0,
@@ -47,6 +48,7 @@ def calculate_raf(diagnosis_codes: List[str],
         is_chronic_mapping: Mapping of HCCs to a chronic flag for the selected model; defaults to packaged mappings.
         hierarchies_mapping: Mapping of parent HCCs to child HCCs for hierarchical rules; defaults to packaged 2026 mappings.
         coefficients_mapping: Mapping of coefficient names to values; defaults to packaged 2026 mappings.
+        labels_mapping: Mapping of (cc, model_name) to human-readable HCC labels; defaults to packaged 2026 mappings.
         prefix_override: Optional prefix to override auto-detected demographic prefix.
             Use when demographic categorization from orec/crec is incorrect.
             Common values: 'DI_' (ESRD Dialysis), 'DNE_' (ESRD Dialysis New Enrollee),
@@ -136,6 +138,19 @@ def calculate_raf(diagnosis_codes: List[str],
     risk_score_hcc = risk_score - risk_score_demographics
     risk_score_payment = risk_score * (1 - maci) / norm_factor + frailty_score
 
+    # Build HCC details with labels and chronic status
+    hcc_details = []
+    for hcc in hcc_set:
+        label = labels_mapping.get((hcc, model_name))
+        is_chronic = is_chronic_mapping.get((hcc, model_name), False)
+        coef = coefficients.get(hcc)
+        hcc_details.append(HCCDetail(
+            hcc=hcc,
+            label=label,
+            is_chronic=is_chronic,
+            coefficient=coef
+        ))
+
     return RAFResult(
         risk_score=risk_score,
         risk_score_demographics=risk_score_demographics,
@@ -143,6 +158,7 @@ def calculate_raf(diagnosis_codes: List[str],
         risk_score_hcc=risk_score_hcc,
         risk_score_payment=risk_score_payment,
         hcc_list=list(hcc_set),
+        hcc_details=hcc_details,
         cc_to_dx=cc_to_dx,
         coefficients=coefficients,
         interactions=interactions,

hccinfhir/sample_files/sample_834_02.txt

@@ -0,0 +1 @@
+ISA*00*          *00*          *ZZ*CADHCS_5010_834*30*999999991      *250124*1927*^*00501*000000001*0*P*:~GS*BE*CADHCS_5010_834*999999991*20250124*192730*10000001*X*005010X220A1~ST*834*0001*005010X220A1~BGN*00*DHCS834-DA-20250124-Sample PACE-001*20250124*19273000****2~QTY*TO*1~N1*P5*California Department of Health Care Services.........*FI*999999990~N1*IN*Sample PACE Inc.*FI*999999991~INS*Y*18*001*AI*A*E**AC~REF*0F*randomParticipantID~REF*1L*randomCIN1~REF*17*;;202501;~REF*23*4;20200101;;~REF*3H*19;10;randomCaseNum1;;~REF*6O*;W;Y;;60;~REF*ZZ*01051;41609;;;;30451;41651;;;~NM1*IL*1*randomLastName*randomFirstName*A~PER*IP**TE*randomPhone~N3*randomStreetAddress1~N4*LOS ANGELES CA*CA*90019**CY*19~DMG*D8*randomDoB*F**7~LUI*LD*SPA**7~HD*021**LTC*010;51~DTP*348*D8*20250101~DTP*349*D8*20250131~REF*17*N;;;;;;;;;;;;;1~REF*9V*9;9;0~REF*CE*10;401;;;;;;~REF*RB*10~REF*ZX*19~REF*ZZ*;;10~SE*29*0001~GE*1*10000001~IEA*1*000000001~

hccinfhir/sample_files/sample_834_03.txt

@@ -0,0 +1 @@
+ISA*00*          *00*          *ZZ*CADHCS_5010_834*30*999999992      *250812*1936*^*00501*000000002*0*P*:~GS*BE*CADHCS_5010_834*999999992*20250812*193641*10000002*X*005010X220A1~ST*834*0001*005010X220A1~BGN*00*DHCS834-DA-20250812-Sample South LA PACE-957-001*20250812*19364100****2~QTY*TO*1~N1*P5*California Department of Health Care Services.........*FI*999999990~N1*IN*Sample South LA PACE Inc.*FI*999999992~INS*Y*18*001*AI*A*C**AC~REF*0F*randomMemberId~REF*1L*randomCIN2~REF*17*;;202508;~REF*23*2;20200201;;;~REF*3H*19;60;randomCaseNum2;;~REF*6O*;W;Y;;08;~REF*DX*H9999;006;20250201;;;~REF*F6*randomMbi~REF*QQ*;;202001;202001~REF*ZZ*95701;;;;;35201;;;;~NM1*IL*1*randomLastName*randomFirstName~PER*IP**TE*randomPhone~N3*randomAddress1~N4*LONG BEACH CA*CA*90813**CY*19~DMG*D8*randomDoB*F**7~LUI*LD*SPA**7~HD*021**LTC*957;01~DTP*348*D8*20250801~DTP*349*D8*20250831~REF*17*F;;;;;;;;;;;;;1~REF*9V*2;2;2~REF*CE*60;401;80;401;;;;~REF*RB*60~REF*ZX*19~REF*ZZ*;;10~SE*32*0001~GE*1*10000002~IEA*1*000000002~

hccinfhir/sample_files/sample_834_04.txt

@@ -0,0 +1 @@
+ISA*00*          *00*          *ZZ*CADHCS_5010_834*30*999999992      *251022*2000*^*00501*000000003*0*P*:~GS*BE*CADHCS_5010_834*999999992*20251022*200019*10000003*X*005010X220A1~ST*834*0001*005010X220A1~BGN*00*DHCS834-DA-20251022-Sample South LA PACE-957-001*20251022*20001900****2~QTY*TO*1~N1*P5*California Department of Health Care Services.........*FI*999999990~N1*IN*Sample South LA PACE Inc.*FI*999999992~INS*Y*18*001*AI*A*C**AC~REF*0F*randomMemberId~REF*1L*randomCIN3~REF*17*202605;;202510;~REF*23*2;20200301;;;~REF*3H*19;16;randomCode;;08~REF*6O*;A;Y;;29;~REF*DX*H9999;001;20251101;;;~REF*F6*randomMbi~REF*QQ*;;202002;202002~REF*ZZ*95701;;;;;20101;;;;~NM1*IL*1*randomLastName*randomFirstName~PER*IP**TE*randomPhone~N3*randomAddress1~N4*LOS ANGELES CA*CA*90044**CY*19~DMG*D8*randomDoB*F**:RET:2054-5~HD*021**LTC*957;01~DTP*348*D8*20251001~DTP*349*D8*20251031~REF*17*F;;;;1~REF*9V*3;2;2~REF*CE*16;401;80;401;;;;~REF*RB*16~REF*ZX*19~REF*ZZ*;;10~SE*31*0001~GE*1*10000003~IEA*1*000000003~

hccinfhir/sample_files/sample_834_05.txt

@@ -0,0 +1 @@
+ISA*00*          *00*          *ZZ*CADHCS_5010_834*30*999999992      *251023*1959*^*00501*000000004*0*P*:~GS*BE*CADHCS_5010_834*999999992*20251023*195928*10000004*X*005010X220A1~ST*834*0001*005010X220A1~BGN*00*DHCS834-DA-20251023-Sample South LA PACE-957-001*20251023*19592800****2~QTY*TO*1~N1*P5*California Department of Health Care Services.........*FI*999999990~N1*IN*Sample South LA PACE Inc.*FI*999999992~INS*Y*18*001*AI*A*C**AC~REF*0F*randomMemberId~REF*1L*randomCIN4~REF*17*202601;;202510;~REF*23*6;20200401;20200101;;~REF*3H*19;17;randomId1;;07~REF*6O*;W;Y;;19;~REF*DX*H9999;006;20230401;;;~REF*F6*randomId2~REF*QQ*;;202003;202003~REF*ZZ*957P4;;;;;;;;;~NM1*IL*1*randomLastName*randomFirstName~PER*IP**TE*randomPhone~N3*randomAddress1~N4*LONG BEACH CA*CA*90810**CY*19~DMG*D8*randomDoB*F**:RET:2135-2~HD*001**LTC*957;P4~DTP*348*D8*20251001~DTP*349*D8*20250930~AMT*R*1237~REF*17*F;;;;1~REF*9V*3;1;0~REF*CE*17;501;2K;691;;;;~REF*ZX*19~REF*ZZ*;;10~SE*31*0001~GE*1*10000004~IEA*1*000000004~

hccinfhir/sample_files/sample_834_06.txt

@@ -0,0 +1 @@
+ISA*00*          *00*          *ZZ*CADHCS_5010_834*30*999999991      *250206*2008*^*00501*000000005*0*P*:~GS*BE*CADHCS_5010_834*999999991*20250206*200823*10000005*X*005010X220A1~ST*834*0001*005010X220A1~BGN*00*DHCS834-DA-20250206-Sample PACE-001*20250206*20082300****2~QTY*TO*2~N1*P5*California Department of Health Care Services.........*FI*999999990~N1*IN*Sample PACE Inc.*FI*999999991~INS*Y*18*001*AI*A*E**AC~REF*0F*randomMemberId~REF*1L*randomCIN5~REF*17*;;202502;~REF*23*3;20200501;;~REF*3H*19;60;randomCaseNum1;;~REF*6O*;A;Y;D;67;~REF*Q4*randomProviderId;~REF*ZZ*01059;;;;;010S1;;;;~NM1*IL*1*randomLName1*randomFName1~PER*IP**TE*randomPhone1~N3*randomFullAddress1~N4*LOS ANGELES CA*CA*90037**CY*19~DMG*D8*randomDoB1*F**:RET:2054-5~NM1*31*1~N3*randomAddress~N4*LOS ANGELES CA*CA*90037~HD*001**LTC*010;59~DTP*348*D8*20250201~DTP*349*D8*20250131~REF*17*N;;;;;;;;;;;;;1~REF*CE*60;001;80;891;;;;~REF*RB*60~REF*ZX*19~REF*ZZ*;;10~HD*021**LTC*010;S1~DTP*348*D8*20250101~DTP*349*D8*20250131~REF*17*N;;;;;;;;;;;;;1~REF*CE*60;401;80;891;;;;~REF*RB*60~REF*ZX*19~REF*ZZ*;;11~INS*Y*18*001*AI*A*C**AC~REF*0F*randomMemberId2~REF*1L*randomCIN6~REF*17*;;202502;~REF*23*9;20200601;;~REF*3H*19;10;randomCaseNum2;;~REF*6O*;A;Y;;25;~REF*DX*;;;S5617;D635;20240901~REF*F6*randomId1~REF*QQ*;;202004;202004~REF*ZZ*01001;;;;;30401;;;;~NM1*IL*1*randomLName2*randomFName2*M~PER*IP**TE*randomPhone2~N3*randomAddress2~N4*LOS ANGELES CA*CA*90029**CY*19~DMG*D8*randomDoB2*M**:RET:2135-2~HD*021**LTC*010;01~DTP*348*D8*20250201~DTP*349*D8*20250228~REF*17*D;;;;;;;;;;;;;1~REF*9V*2;2;2~REF*CE*10;401;9G;999;80;401;;~REF*RB*10~REF*ZX*19~REF*ZZ*;;10~SE*64*0001~GE*1*10000005~IEA*1*000000005~

hccinfhir/utils.py

@@ -244,4 +244,71 @@ def load_coefficients(file_path: str) -> Dict[Tuple[str, ModelName], float]:
         except (ValueError, IndexError):
             continue  # Skip malformed lines
 
-    return coefficients
+    return coefficients
+
+
+def load_labels(file_path: str) -> Dict[Tuple[str, ModelName], str]:
+    """
+    Load HCC labels from a CSV file.
+    Expected format: cc,label,model_domain,model_version,...
+
+    Args:
+        file_path: Filename or path to the CSV file
+
+    Returns:
+        Dictionary mapping (cc, model_name) to label string
+
+    Raises:
+        FileNotFoundError: If file cannot be found
+        RuntimeError: If file cannot be loaded or parsed
+    """
+    labels: Dict[Tuple[str, ModelName], str] = {}
+
+    try:
+        resolved_path = resolve_data_file(file_path)
+        with open(resolved_path, "r", encoding="utf-8") as file:
+            content = file.read()
+    except FileNotFoundError as e:
+        raise FileNotFoundError(f"Could not load labels: {e}")
+    except Exception as e:
+        raise RuntimeError(f"Error loading labels file '{file_path}': {e}")
+
+    for line in content.splitlines()[1:]:  # Skip header
+        try:
+            parts = line.strip().split(',')
+            if len(parts) < 4:
+                continue
+            cc_raw, label, model_domain, model_version = parts[0], parts[1], parts[2], parts[3]
+
+            # Strip HCC prefix if present to get just the number
+            cc = cc_raw.replace('HCC', '').replace('RxHCC', '')
+
+            # Handle quoted labels with commas
+            if label.startswith('"'):
+                # Find closing quote
+                label_parts = [label]
+                for i, p in enumerate(parts[2:], start=2):
+                    if p.endswith('"'):
+                        label_parts.append(p)
+                        # Recalculate domain and version after the quoted label
+                        model_domain = parts[i + 1] if len(parts) > i + 1 else ''
+                        model_version = parts[i + 2] if len(parts) > i + 2 else ''
+                        break
+                    label_parts.append(p)
+                label = ','.join(label_parts).strip('"')
+
+            # Construct model name based on domain
+            if model_domain == 'ESRD':
+                model_name = f"CMS-HCC {model_domain} Model {model_version}"
+            elif model_domain == 'RxHCC':
+                model_name = f"{model_domain} Model {model_version}"
+            else:
+                model_name = f"{model_domain} Model {model_version}"
+
+            key = (cc, model_name)
+            if key not in labels:
+                labels[key] = label
+        except (ValueError, IndexError):
+            continue  # Skip malformed lines
+
+    return labels

{hccinfhir-0.2.1.dist-info → hccinfhir-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: hccinfhir
-Version: 0.2.1
+Version: 0.2.3
 Summary: HCC Algorithm for FHIR Resources
 Project-URL: Homepage, https://github.com/mimilabs/hccinfhir
 Project-URL: Issues, https://github.com/mimilabs/hccinfhir/issues
@@ -10,6 +10,7 @@ Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Requires-Python: >=3.8
 Requires-Dist: pydantic>=2.10.3
+Requires-Dist: typing-extensions>=4.6.0
 Description-Content-Type: text/markdown
 
 # HCCInFHIR
@@ -62,6 +63,7 @@ print(f"HCCs: {result.hcc_list}")
   - [Demographic Prefix Override](#demographic-prefix-override)
   - [Custom File Path Resolution](#custom-file-path-resolution)
   - [Batch Processing](#batch-processing)
+  - [Large-Scale Processing with Databricks](#large-scale-processing-with-databricks)
   - [Converting to Dictionaries](#converting-to-dictionaries)
 - [Sample Data](#sample-data)
 - [Testing](#testing)
@@ -78,7 +80,7 @@ print(f"HCCs: {result.hcc_list}")
 - **Custom Data Files**: Full support for custom coefficients, mappings, and hierarchies
 - **Flexible File Resolution**: Absolute paths, relative paths, or bundled data files
 - **Type-Safe**: Built on Pydantic with full type hints
-- **Well-Tested**: 155 comprehensive tests covering all features
+- **Well-Tested**: 189 comprehensive tests covering all features
 
 ## 📊 Data Sources & Use Cases
 
@@ -834,6 +836,146 @@ with open("risk_scores.json", "w") as f:
     json.dump(results, f, indent=2)
 ```
 
+### Large-Scale Processing with Databricks
+
+For processing millions of beneficiaries, use PySpark's `pandas_udf` for distributed computation. The hccinfhir logic is well-suited for batch operations with clear, simple transformations.
+
+**Performance Benchmark**:
+
+![Databricks Performance Chart](hccinfhir_pandas_udf_performance_chart.png)
+
+*Tested with ACO data on Databricks Runtime 17.3 LTS, Worker: i3.4xlarge (122GB, 16 cores)*
+
+The chart shows execution time varies based on condition complexity - members with more diagnoses require additional internal processing loops. While the relationship isn't perfectly linear, **1 million members can be processed in under 2 minutes** with this configuration.
+
+```python
+from pyspark.sql import SparkSession
+from pyspark.sql.types import StructType, StructField, FloatType, ArrayType, StringType
+from pyspark.sql import functions as F
+from pyspark.sql.functions import pandas_udf
+import pandas as pd
+
+from hccinfhir import HCCInFHIR, Demographics
+
+# Define the return schema
+hcc_schema = StructType([
+    StructField("risk_score", FloatType(), True),
+    StructField("risk_score_demographics", FloatType(), True),
+    StructField("risk_score_chronic_only", FloatType(), True),
+    StructField("risk_score_hcc", FloatType(), True),
+    StructField("hcc_list", ArrayType(StringType()), True)
+])
+
+# Initialize processor (will be serialized to each executor)
+hcc_processor = HCCInFHIR(model_name="CMS-HCC Model V28")
+
+# Create the pandas UDF
+@pandas_udf(hcc_schema)
+def calculate_hcc(
+    age_series: pd.Series,
+    sex_series: pd.Series,
+    diagnosis_series: pd.Series
+) -> pd.DataFrame:
+    results = []
+
+    for age, sex, diagnosis_codes in zip(age_series, sex_series, diagnosis_series):
+        try:
+            demographics = Demographics(age=int(age), sex=sex)
+
+            # diagnosis_codes can be passed directly - accepts any iterable including numpy arrays
+            result = hcc_processor.calculate_from_diagnosis(diagnosis_codes, demographics)
+
+            results.append({
+                'risk_score': float(result.risk_score),
+                'risk_score_demographics': float(result.risk_score_demographics),
+                'risk_score_chronic_only': float(result.risk_score_chronic_only),
+                'risk_score_hcc': float(result.risk_score_hcc),
+                'hcc_list': result.hcc_list
+            })
+        except Exception as e:
+            # Log error and return nulls for failed rows
+            print(f"ERROR processing row: {e}")
+            results.append({
+                'risk_score': None,
+                'risk_score_demographics': None,
+                'risk_score_chronic_only': None,
+                'risk_score_hcc': None,
+                'hcc_list': None
+            })
+
+    return pd.DataFrame(results)
+
+# Apply the UDF to your DataFrame
+# Assumes df has columns: age, patient_gender, diagnosis_codes (array of strings)
+df = df.withColumn(
+    "hcc_results",
+    calculate_hcc(
+        F.col("age"),
+        F.col("patient_gender"),
+        F.col("diagnosis_codes")
+    )
+)
+
+# Expand the struct into separate columns
+df = df.select(
+    "*",
+    F.col("hcc_results.risk_score").alias("risk_score"),
+    F.col("hcc_results.risk_score_demographics").alias("risk_score_demographics"),
+    F.col("hcc_results.risk_score_chronic_only").alias("risk_score_chronic_only"),
+    F.col("hcc_results.risk_score_hcc").alias("risk_score_hcc"),
+    F.col("hcc_results.hcc_list").alias("hcc_list")
+).drop("hcc_results")
+```
+
+**Performance Tips**:
+- **Repartition** your DataFrame before applying the UDF to balance workload across executors
+- **Cache** the processor initialization by defining it at module level
+- **Batch size**: pandas_udf processes data in batches; Spark handles optimal batch sizing automatically
+- **Install hccinfhir** on all cluster nodes: `%pip install hccinfhir` in a notebook cell or add to cluster init script
+
+**Extended Schema with Demographics**:
+
+```python
+# Include additional demographic parameters
+@pandas_udf(hcc_schema)
+def calculate_hcc_full(
+    age_series: pd.Series,
+    sex_series: pd.Series,
+    dual_status_series: pd.Series,
+    diagnosis_series: pd.Series
+) -> pd.DataFrame:
+    results = []
+
+    for age, sex, dual_status, diagnosis_codes in zip(
+        age_series, sex_series, dual_status_series, diagnosis_series
+    ):
+        try:
+            demographics = Demographics(
+                age=int(age),
+                sex=sex,
+                dual_elgbl_cd=dual_status if dual_status else "00"
+            )
+            result = hcc_processor.calculate_from_diagnosis(diagnosis_codes, demographics)
+
+            results.append({
+                'risk_score': float(result.risk_score),
+                'risk_score_demographics': float(result.risk_score_demographics),
+                'risk_score_chronic_only': float(result.risk_score_chronic_only),
+                'risk_score_hcc': float(result.risk_score_hcc),
+                'hcc_list': result.hcc_list
+            })
+        except Exception as e:
+            results.append({
+                'risk_score': None,
+                'risk_score_demographics': None,
+                'risk_score_chronic_only': None,
+                'risk_score_hcc': None,
+                'hcc_list': None
+            })
+
+    return pd.DataFrame(results)
+```
+
 ### Converting to Dictionaries
 
 All Pydantic models support dictionary conversion for JSON serialization, database storage, or legacy code:
@@ -895,8 +1037,8 @@ result = processor.run([eob], demographics)  # Note: [eob] not eob
 claim = get_837_sample(0)  # Cases 0-12 (returns string)
 claims = get_837_sample_list([0, 1, 2])  # Returns list
 
-# X12 834 enrollment samples
-enrollment_834 = get_834_sample(1)  # Currently only case 1 available (returns string)
+# X12 834 enrollment samples (6 CA DHCS scenarios)
+enrollment_834 = get_834_sample(1)  # Cases 1-6 available (returns string)
 
 # List all available samples
 info = list_available_samples()
@@ -914,7 +1056,7 @@ hatch shell
 # Install in development mode
 pip install -e .
 
-# Run all tests (155 tests)
+# Run all tests (189 tests)
 pytest tests/
 
 # Run specific test file

{hccinfhir-0.2.1.dist-info → hccinfhir-0.2.3.dist-info}/RECORD

@@ -1,21 +1,21 @@
-hccinfhir/__init__.py,sha256=CKpYTUSzZdP3s1eB74w5JTe9OS3MtcvuUkv6ymgSyic,1085
+hccinfhir/__init__.py,sha256=3aFYtjTklZJg3wIlnMJNgfDBaDCfKXVlYsacdsZ9L4I,1113
 hccinfhir/constants.py,sha256=C4Vyjtzgyd4Jm2I2X6cTYQZLe-jAMC8boUcy-7OXQDQ,8473
-hccinfhir/datamodels.py,sha256=NULDYb57R61v4EklOI_AAIuC1-OkLFH1InbAad48dZM,10601
-hccinfhir/defaults.py,sha256=tMNym0R6Nr6ibKTqOu6N1vLcdekL0ZmHyDNIOCOMsP4,1292
+hccinfhir/datamodels.py,sha256=xGh9E5RVi4vONhtIZw2XiaFwVLc5UK027trY31YMUWc,15457
+hccinfhir/defaults.py,sha256=aKdXPhf9bYUzpGvXM1GIXZaKxqkKInt3v9meLB9fWog,1394
 hccinfhir/extractor.py,sha256=xL9c2VT-e2I7_c8N8j4Og42UEgVuCzyn9WFp3ntM5Ro,1822
-hccinfhir/extractor_834.py,sha256=dIqovUOWm_7k_c6sUqTIzQua_kTQ8dLGy3-4-LECW3Y,18855
+hccinfhir/extractor_834.py,sha256=zH2nOUJvIJvbDLf6HJWmwCw2yAjT-6RCJyuH4kmIKIQ,27862
 hccinfhir/extractor_837.py,sha256=fGsvBTWIj9dsHLGGR67AdlYDSsFi5qnSVlTgwkL1f-E,15334
 hccinfhir/extractor_fhir.py,sha256=wUN3vTm1oTZ-KvfcDebnpQMxAC-7YlRKv12Wrv3p85A,8490
 hccinfhir/filter.py,sha256=j_yD2g6RBXVUV9trKkWzsQ35x3fRvfKUPvEXKUefI64,2007
-hccinfhir/hccinfhir.py,sha256=rCnExvxZGKi1vLD4cHQ0nzPAGV6e-8C15MtJ2p7zAAk,11160
-hccinfhir/model_calculate.py,sha256=KSeZjKYBCfBYYIWOIckDg941OC8050MX2F7BZ2l3V8g,7663
+hccinfhir/hccinfhir.py,sha256=NydnH3WBvuyskn76hY70LpUS6XuIEoax_kip1mgfpHw,11225
+hccinfhir/model_calculate.py,sha256=_TUWNVUsBym0pre3wltXvRuipQaONQ0QBfWPFNAeDsQ,8347
 hccinfhir/model_coefficients.py,sha256=5n3QzHX6FJ3MlO0cV9NS7Bqt-lxzVvT_M3zFaWq6Gng,4685
 hccinfhir/model_demographics.py,sha256=nImKtJCq1HkR9w2GU8aikybJFgow71CPufBRV8Jn7fM,8932
 hccinfhir/model_dx_to_cc.py,sha256=Yjc6xKI-jMXsbOzS_chc4NI15Bwagb7BwZZ8cKQaTbk,1540
 hccinfhir/model_hierarchies.py,sha256=cboUnSHZZfOxA8QZKV4QIE-32duElssML32OqYT-65g,1542
 hccinfhir/model_interactions.py,sha256=g6jK27Xu8RQUHS3lk4sk2v6w6wqd52mdbGn0BsnR7Pk,21394
 hccinfhir/samples.py,sha256=2VSWS81cv9EnaHqK7sd6CjwG6FUI9E--5wHgD000REI,9952
-hccinfhir/utils.py,sha256=9ki4o1wXyAYYr8BR9Skkz0PKL_1H_HYNV4LalEsASE0,8260
+hccinfhir/utils.py,sha256=hQgHjuOcEQcnxemTZwqFBHWvLC5-C1Gup9cDXEYlZjE,10770
 hccinfhir/data/__init__.py,sha256=SGiSkpGrnxbvtEFMMlk82NFHOE50hFXcgKwKUSuVZUg,45
 hccinfhir/data/hcc_is_chronic.csv,sha256=Bwd-RND6SdEsKP-assoBaXnjUJAuDXhSkwWlymux72Y,19701
 hccinfhir/data/hcc_is_chronic_without_esrd_model.csv,sha256=eVVI4_8mQNkiBiNO3kattfT_zfcV18XgmiltdzZEXSo,17720
@@ -29,8 +29,14 @@ hccinfhir/data/ra_eligible_cpt_hcpcs_2025.csv,sha256=-tMvv2su5tsSbGUh6fZZCMUEkXI
 hccinfhir/data/ra_eligible_cpt_hcpcs_2026.csv,sha256=EYGN7k_rgCpJe59lL_yNInUcCkdETDWGSFTXII3LZ0Y,40497
 hccinfhir/data/ra_hierarchies_2025.csv,sha256=HQSPNloe6mvvwMgv8ZwYAfWKkT2b2eUvm4JQy6S_mVQ,13045
 hccinfhir/data/ra_hierarchies_2026.csv,sha256=A6ZQZb0rpRWrySBB_KA5S4PGtMxWuzB2guU3aBE09v0,19596
+hccinfhir/data/ra_labels_2026.csv,sha256=YstfP7s-3ZwjP4I_GYPPj3_yn-PQK3Q0Q_MVYZhsfjY,50248
 hccinfhir/sample_files/__init__.py,sha256=SGiSkpGrnxbvtEFMMlk82NFHOE50hFXcgKwKUSuVZUg,45
 hccinfhir/sample_files/sample_834_01.txt,sha256=J2HMXfY6fAFpV36rvLQ3QymRRS2TPqf3TQY6CNS7TrE,1627
+hccinfhir/sample_files/sample_834_02.txt,sha256=vSvjM69kKfOW9e-8dvlO9zDcRPpOD7LmekLu68z4aB4,926
+hccinfhir/sample_files/sample_834_03.txt,sha256=pD4UTUFCEHxKu3bz3ZZdWo5b8Y1UWTXAo7PmFjWsukU,999
+hccinfhir/sample_files/sample_834_04.txt,sha256=1Cv8kN7At1ce60kXBGlMr5DhLMsuw2clnVDi02mvBJA,991
+hccinfhir/sample_files/sample_834_05.txt,sha256=hjQ5SEgj0cCNZyWas1-sVL9gm8m3rC4R65JHIcbAPRk,993
+hccinfhir/sample_files/sample_834_06.txt,sha256=oC3e4UMmmhVKXI8eB7SlLyJ8kZX4NemlzI_WGznO-48,1659
 hccinfhir/sample_files/sample_837_0.txt,sha256=eggrD259uHa05z2dfxWBpUDseSDp_AQcLyN_adpHyTw,5295
 hccinfhir/sample_files/sample_837_1.txt,sha256=E155MdemSDYoXokuTXUZ6Br_RGGedYv5t5dh-eMRmuk,1322
 hccinfhir/sample_files/sample_837_10.txt,sha256=zSJXI78vHAksA7FFQEVLvepefdpMM2_AexLyoDimV3Q,1129
@@ -48,7 +54,7 @@ hccinfhir/sample_files/sample_eob_1.json,sha256=_NGSVR2ysFpx-DcTvyga6dFCzhQ8Vi9f
 hccinfhir/sample_files/sample_eob_2.json,sha256=FcnJcx0ApOczxjJ_uxVLzCep9THfNf4xs9Yf7hxk8e4,1769
 hccinfhir/sample_files/sample_eob_200.ndjson,sha256=CxpjeQ1DCMUzZILaM68UEhfxO0p45YGhDDoCZeq8PxU,1917986
 hccinfhir/sample_files/sample_eob_3.json,sha256=4BW4wOMBEEU9RDfJR15rBEvk0KNHyuMEh3e055y87Hc,2306
-hccinfhir-0.2.1.dist-info/METADATA,sha256=FrzAPidGEXS8l-1vO_QRlemPZegXavDpn--TkmwQBxY,31674
-hccinfhir-0.2.1.dist-info/WHEEL,sha256=C2FUgwZgiLbznR-k0b_5k3Ai_1aASOXDss3lzCUsUug,87
-hccinfhir-0.2.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-hccinfhir-0.2.1.dist-info/RECORD,,
+hccinfhir-0.2.3.dist-info/METADATA,sha256=YHHcOAObdo2gWJtPmP6y05-EXeXHpuE40W1pdUXlydw,37132
+hccinfhir-0.2.3.dist-info/WHEEL,sha256=C2FUgwZgiLbznR-k0b_5k3Ai_1aASOXDss3lzCUsUug,87
+hccinfhir-0.2.3.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+hccinfhir-0.2.3.dist-info/RECORD,,