hccinfhir 0.1.0__tar.gz → 0.1.2__tar.gz

{hccinfhir-0.1.0 → hccinfhir-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: hccinfhir
-Version: 0.1.0
+Version: 0.1.2
 Summary: HCC Algorithm for FHIR Resources
 Project-URL: Homepage, https://github.com/mimilabs/hccinfhir
 Project-URL: Issues, https://github.com/mimilabs/hccinfhir/issues
@@ -69,6 +69,34 @@ result = calculate_raf(
 
 For more details on the SLD format, see the `datamodels.py` file.
 
+## Sample Data
+
+The package includes comprehensive sample data for testing and demonstration purposes:
+
+```python
+from hccinfhir import (
+    get_eob_sample,
+    get_eob_sample_list,
+    get_837_sample,
+    get_837_sample_list,
+    list_available_samples
+)
+
+# Get individual EOB samples (cases 1, 2, or 3)
+eob_data = get_eob_sample(1)
+
+# Get multiple EOB samples (up to 200 available)
+eob_list = get_eob_sample_list(limit=10)
+
+# Get 837 claim samples (cases 0 through 11)
+claim_data = get_837_sample(0)
+
+# Get information about available samples
+info = list_available_samples()
+```
+
+For detailed usage examples, see the `examples/sample_data_usage.py` file.
+
 ## Core Components
 
 ### 1. Extractor Module
@@ -182,10 +210,12 @@ Each method returns a RAFResult containing:
 - Processed service level data (when applicable)
 
 ## Testing
+
+After installing `hatch`
 ```bash
-$ python3 -m hatch shell
-$ python3 -m pip install -e .
-$ python3 -m pytest tests/*
+$ hatch shell
+$ pip install -e .
+$ pytest tests/*
 ``` 
 
 ## Dependencies
@@ -267,45 +297,93 @@ $ python3 -m pytest tests/*
 
 ## Data Files
 
-`ra_dx_to_cc_mapping_2025.csv`
+`ra_dx_to_cc_mapping_2026.csv`
 ```sql
-SELECT diagnosis_code, cc, model_name 
-FROM ra_dx_to_cc_mapping 
-WHERE year = 2025 and model_type = 'Initial';
+WITH latest_years AS (
+  SELECT 
+    model_name,
+    MAX(year) as latest_year
+  FROM mimi_ws_1.cmspayment.ra_dx_to_cc_mapping 
+  WHERE model_type = 'Initial'
+    AND year <= 2026  -- Don't go beyond 2026
+  GROUP BY model_name
+)
+SELECT 
+  r.diagnosis_code, 
+  r.cc, 
+  r.model_name
+FROM mimi_ws_1.cmspayment.ra_dx_to_cc_mapping r
+INNER JOIN latest_years l 
+  ON r.model_name = l.model_name 
+  AND r.year = l.latest_year
+WHERE r.model_type = 'Initial'
+ORDER BY r.model_name, r.diagnosis_code;
 ```
 
-`ra_hierarchies_2025.csv`
+`ra_hierarchies_2026.csv`
 ```sql
-SELECT cc_parent, 
-  cc_child, 
-  model_domain, 
-  model_version, 
-  model_fullname
-FROM ra_hierarchies
-WHERE eff_last_date > '2025-01-01';
+WITH latest_dates AS (
+  SELECT 
+    model_domain,
+    model_version,
+    model_fullname,
+    MAX(eff_last_date) as latest_eff_last_date
+  FROM mimi_ws_1.cmspayment.ra_hierarchies 
+  GROUP BY model_domain, model_version, model_fullname
+)
+SELECT 
+  r.cc_parent, 
+  r.cc_child, 
+  r.model_domain, 
+  r.model_version, 
+  r.model_fullname
+FROM mimi_ws_1.cmspayment.ra_hierarchies r
+INNER JOIN latest_dates l 
+  ON r.model_domain = l.model_domain 
+  AND r.model_version = l.model_version
+  AND r.model_fullname = l.model_fullname
+  AND r.eff_last_date = l.latest_eff_last_date
+ORDER BY r.model_domain, r.model_version, r.model_fullname, r.cc_parent, r.cc_child;
 ```
 
-`ra_coefficients_2025.csv`
+`ra_coefficients_2026.csv`
 ```sql
-SELECT coefficient, value, model_domain, model_version 
-FROM ra_coefficients 
-WHERE eff_last_date > '2025-01-01';
+WITH preferred_records AS (
+  SELECT 
+    model_domain,
+    model_version,
+    MAX(eff_last_date) as latest_eff_last_date
+  FROM mimi_ws_1.cmspayment.ra_coefficients
+  GROUP BY model_domain, model_version
+)
+SELECT 
+  r.coefficient,
+  r.value, 
+  r.model_domain, 
+  r.model_version
+FROM mimi_ws_1.cmspayment.ra_coefficients r
+INNER JOIN preferred_records p
+  ON r.model_domain = p.model_domain 
+  AND r.model_version = p.model_version
+  AND r.eff_last_date = p.latest_eff_last_date
+ORDER BY r.model_domain, r.model_version, r.coefficient;
 ```   
 
-`ra_eligible_cpt_hcpcs_2025.csv`
+`ra_eligible_cpt_hcpcs_2026.csv`
 ```sql
 SELECT DISTINCT cpt_hcpcs_code
 FROM mimi_ws_1.cmspayment.ra_eligible_cpt_hcpcs
-WHERE is_included = 'yes' AND YEAR(mimi_src_file_date) = 2024;
+WHERE is_included = 'yes' AND YEAR(mimi_src_file_date) = 2025;
 ```
 
 ## Contributing
 Join us at [mimilabs](https://mimilabs.ai/signup). Reference data available in MIMILabs data lakehouse.
 
 ## Publishing (only for those maintainers...)
+Inside the hatch
 ```bash
-$ python3 -m hatch build
-$ python3 -m hatch publish
+$ hatch build
+$ hatch publish
 ```
 
 ## License

{hccinfhir-0.1.0 → hccinfhir-0.1.2}/README.md

@@ -55,6 +55,34 @@ result = calculate_raf(
 
 For more details on the SLD format, see the `datamodels.py` file.
 
+## Sample Data
+
+The package includes comprehensive sample data for testing and demonstration purposes:
+
+```python
+from hccinfhir import (
+    get_eob_sample,
+    get_eob_sample_list,
+    get_837_sample,
+    get_837_sample_list,
+    list_available_samples
+)
+
+# Get individual EOB samples (cases 1, 2, or 3)
+eob_data = get_eob_sample(1)
+
+# Get multiple EOB samples (up to 200 available)
+eob_list = get_eob_sample_list(limit=10)
+
+# Get 837 claim samples (cases 0 through 11)
+claim_data = get_837_sample(0)
+
+# Get information about available samples
+info = list_available_samples()
+```
+
+For detailed usage examples, see the `examples/sample_data_usage.py` file.
+
 ## Core Components
 
 ### 1. Extractor Module
@@ -168,10 +196,12 @@ Each method returns a RAFResult containing:
 - Processed service level data (when applicable)
 
 ## Testing
+
+After installing `hatch`
 ```bash
-$ python3 -m hatch shell
-$ python3 -m pip install -e .
-$ python3 -m pytest tests/*
+$ hatch shell
+$ pip install -e .
+$ pytest tests/*
 ``` 
 
 ## Dependencies
@@ -253,45 +283,93 @@ $ python3 -m pytest tests/*
 
 ## Data Files
 
-`ra_dx_to_cc_mapping_2025.csv`
+`ra_dx_to_cc_mapping_2026.csv`
 ```sql
-SELECT diagnosis_code, cc, model_name 
-FROM ra_dx_to_cc_mapping 
-WHERE year = 2025 and model_type = 'Initial';
+WITH latest_years AS (
+  SELECT 
+    model_name,
+    MAX(year) as latest_year
+  FROM mimi_ws_1.cmspayment.ra_dx_to_cc_mapping 
+  WHERE model_type = 'Initial'
+    AND year <= 2026  -- Don't go beyond 2026
+  GROUP BY model_name
+)
+SELECT 
+  r.diagnosis_code, 
+  r.cc, 
+  r.model_name
+FROM mimi_ws_1.cmspayment.ra_dx_to_cc_mapping r
+INNER JOIN latest_years l 
+  ON r.model_name = l.model_name 
+  AND r.year = l.latest_year
+WHERE r.model_type = 'Initial'
+ORDER BY r.model_name, r.diagnosis_code;
 ```
 
-`ra_hierarchies_2025.csv`
+`ra_hierarchies_2026.csv`
 ```sql
-SELECT cc_parent, 
-  cc_child, 
-  model_domain, 
-  model_version, 
-  model_fullname
-FROM ra_hierarchies
-WHERE eff_last_date > '2025-01-01';
+WITH latest_dates AS (
+  SELECT 
+    model_domain,
+    model_version,
+    model_fullname,
+    MAX(eff_last_date) as latest_eff_last_date
+  FROM mimi_ws_1.cmspayment.ra_hierarchies 
+  GROUP BY model_domain, model_version, model_fullname
+)
+SELECT 
+  r.cc_parent, 
+  r.cc_child, 
+  r.model_domain, 
+  r.model_version, 
+  r.model_fullname
+FROM mimi_ws_1.cmspayment.ra_hierarchies r
+INNER JOIN latest_dates l 
+  ON r.model_domain = l.model_domain 
+  AND r.model_version = l.model_version
+  AND r.model_fullname = l.model_fullname
+  AND r.eff_last_date = l.latest_eff_last_date
+ORDER BY r.model_domain, r.model_version, r.model_fullname, r.cc_parent, r.cc_child;
 ```
 
-`ra_coefficients_2025.csv`
+`ra_coefficients_2026.csv`
 ```sql
-SELECT coefficient, value, model_domain, model_version 
-FROM ra_coefficients 
-WHERE eff_last_date > '2025-01-01';
+WITH preferred_records AS (
+  SELECT 
+    model_domain,
+    model_version,
+    MAX(eff_last_date) as latest_eff_last_date
+  FROM mimi_ws_1.cmspayment.ra_coefficients
+  GROUP BY model_domain, model_version
+)
+SELECT 
+  r.coefficient,
+  r.value, 
+  r.model_domain, 
+  r.model_version
+FROM mimi_ws_1.cmspayment.ra_coefficients r
+INNER JOIN preferred_records p
+  ON r.model_domain = p.model_domain 
+  AND r.model_version = p.model_version
+  AND r.eff_last_date = p.latest_eff_last_date
+ORDER BY r.model_domain, r.model_version, r.coefficient;
 ```   
 
-`ra_eligible_cpt_hcpcs_2025.csv`
+`ra_eligible_cpt_hcpcs_2026.csv`
 ```sql
 SELECT DISTINCT cpt_hcpcs_code
 FROM mimi_ws_1.cmspayment.ra_eligible_cpt_hcpcs
-WHERE is_included = 'yes' AND YEAR(mimi_src_file_date) = 2024;
+WHERE is_included = 'yes' AND YEAR(mimi_src_file_date) = 2025;
 ```
 
 ## Contributing
 Join us at [mimilabs](https://mimilabs.ai/signup). Reference data available in MIMILabs data lakehouse.
 
 ## Publishing (only for those maintainers...)
+Inside the hatch
 ```bash
-$ python3 -m hatch build
-$ python3 -m hatch publish
+$ hatch build
+$ hatch publish
 ```
 
 ## License

hccinfhir-0.1.2/hccinfhir/__init__.py

@@ -0,0 +1,47 @@
+"""
+HCCInFHIR - HCC Algorithm for FHIR Resources
+
+A Python library for processing FHIR EOB resources and calculating HCC risk scores.
+"""
+
+# Main classes
+from .hccinfhir import HCCInFHIR
+from .extractor import extract_sld, extract_sld_list
+from .filter import apply_filter
+from .model_calculate import calculate_raf
+from .datamodels import Demographics, ServiceLevelData, RAFResult, ModelName
+
+# Sample data functions
+from .sample_utils import (
+    SampleData,
+    get_eob_sample,
+    get_eob_sample_list,
+    get_837_sample,
+    get_837_sample_list,
+    list_available_samples
+)
+
+__version__ = "0.1.2"
+__author__ = "Yubin Park"
+__email__ = "yubin.park@mimilabs.ai"
+
+__all__ = [
+    # Main classes
+    "HCCInFHIR",
+    "extract_sld",
+    "extract_sld_list", 
+    "apply_filter",
+    "calculate_raf",
+    "Demographics",
+    "ServiceLevelData",
+    "RAFResult",
+    "ModelName",
+    
+    # Sample data
+    "SampleData",
+    "get_eob_sample",
+    "get_eob_sample_list",
+    "get_837_sample",
+    "get_837_sample_list",
+    "list_available_samples"
+]