ins-pricing 0.5.0__py3-none-any.whl → 0.5.3__py3-none-any.whl

ins_pricing/utils/__init__.py

@@ -17,9 +17,9 @@ Example:
 from __future__ import annotations
 
 # =============================================================================
-# Logging utilities
-# =============================================================================
-from ins_pricing.utils.logging import get_logger, configure_logging
+# Logging utilities
+# =============================================================================
+from ins_pricing.utils.logging import get_logger, configure_logging, log_print
 
 # =============================================================================
 # Metric utilities (PSI, model evaluation)
@@ -78,9 +78,10 @@ from ins_pricing.utils.device import (
 )
 
 __all__ = [
-    # Logging
-    "get_logger",
-    "configure_logging",
+    # Logging
+    "get_logger",
+    "configure_logging",
+    "log_print",
     # Metrics
     "psi_numeric",
     "psi_categorical",

ins_pricing/utils/device.py

@@ -58,32 +58,53 @@ class GPUMemoryManager:
     _logger = get_logger("ins_pricing.gpu")
 
     @classmethod
-    def clean(cls, verbose: bool = False) -> None:
-        """Clean up GPU memory.
-
-        Args:
-            verbose: If True, log cleanup details
-        """
-        gc.collect()
-
-        if TORCH_AVAILABLE and torch.cuda.is_available():
-            torch.cuda.empty_cache()
-            torch.cuda.synchronize()
-            if verbose:
-                cls._logger.debug("CUDA cache cleared and synchronized")
-
-            # Optional: Force IPC collect for multi-process scenarios
-            if os.environ.get("BAYESOPT_CUDA_IPC_COLLECT", "0") == "1":
-                try:
-                    torch.cuda.ipc_collect()
-                    if verbose:
-                        cls._logger.debug("CUDA IPC collect performed")
-                except Exception:
-                    pass
+    def clean(
+        cls,
+        verbose: bool = False,
+        *,
+        synchronize: bool = True,
+        empty_cache: bool = True,
+    ) -> None:
+        """Clean up GPU memory.
+
+        Args:
+            verbose: If True, log cleanup details
+            synchronize: If True, synchronize CUDA device after cleanup
+            empty_cache: If True, clear CUDA cache
+        """
+        gc.collect()
+
+        if TORCH_AVAILABLE and torch.cuda.is_available():
+            if empty_cache:
+                torch.cuda.empty_cache()
+            if synchronize:
+                torch.cuda.synchronize()
+            if verbose:
+                if empty_cache and synchronize:
+                    cls._logger.debug("CUDA cache cleared and synchronized")
+                elif empty_cache:
+                    cls._logger.debug("CUDA cache cleared")
+                elif synchronize:
+                    cls._logger.debug("CUDA synchronized")
+
+            # Optional: Force IPC collect for multi-process scenarios
+            if os.environ.get("BAYESOPT_CUDA_IPC_COLLECT", "0") == "1":
+                try:
+                    torch.cuda.ipc_collect()
+                    if verbose:
+                        cls._logger.debug("CUDA IPC collect performed")
+                except Exception:
+                    pass
 
     @classmethod
     @contextmanager
-    def cleanup_context(cls, verbose: bool = False):
+    def cleanup_context(
+        cls,
+        verbose: bool = False,
+        *,
+        synchronize: bool = True,
+        empty_cache: bool = True,
+    ):
         """Context manager that cleans GPU memory on exit.
 
         Args:
@@ -95,7 +116,7 @@ class GPUMemoryManager:
         try:
             yield
         finally:
-            cls.clean(verbose=verbose)
+            cls.clean(verbose=verbose, synchronize=synchronize, empty_cache=empty_cache)
 
     @classmethod
     def move_model_to_cpu(cls, model: Any) -> Any:

ins_pricing/utils/logging.py

@@ -18,7 +18,7 @@ from __future__ import annotations
 import logging
 import os
 from functools import lru_cache
-from typing import Optional
+from typing import Optional, Union
 
 
 @lru_cache(maxsize=1)
@@ -72,3 +72,36 @@ def configure_logging(
         formatter = logging.Formatter(format_string)
         for handler in logger.handlers:
             handler.setFormatter(formatter)
+
+
+def log_print(
+    logger: logging.Logger,
+    *args,
+    level: Optional[Union[int, str]] = None,
+    **kwargs,
+) -> None:
+    """Print-like helper that routes messages to a logger.
+
+    This preserves basic print semantics (sep/end) while ignoring file/flush,
+    and it auto-detects severity when level is not provided.
+    """
+    sep = kwargs.get("sep", " ")
+    msg = sep.join(str(arg) for arg in args)
+    if not msg:
+        return
+
+    if level is None:
+        lowered = msg.lstrip().lower()
+        if lowered.startswith(("warn", "[warn]", "warning")):
+            level_value = logging.WARNING
+        elif lowered.startswith(("error", "[error]", "err")):
+            level_value = logging.ERROR
+        else:
+            level_value = logging.INFO
+    else:
+        if isinstance(level, str):
+            level_value = getattr(logging, level.upper(), logging.INFO)
+        else:
+            level_value = int(level)
+
+    logger.log(level_value, msg)

ins_pricing/utils/profiling.py

@@ -18,6 +18,10 @@ import time
 from contextlib import contextmanager
 from typing import Optional
 
+from ins_pricing.utils import get_logger
+
+_logger = get_logger("ins_pricing.utils.profiling")
+
 try:
     import psutil
     HAS_PSUTIL = True
@@ -96,7 +100,7 @@ def profile_section(
         if logger:
             logger.log(log_level, msg)
         else:
-            print(msg)
+            _logger.log(log_level, msg)
 
 
 def get_memory_info() -> dict:
@@ -250,7 +254,7 @@ def cleanup_memory(logger: Optional[logging.Logger] = None) -> None:
     if logger:
         logger.info(msg)
     else:
-        print(msg)
+        _logger.info(msg)
 
 
 class MemoryMonitor:
@@ -301,7 +305,7 @@ class MemoryMonitor:
         if self.logger:
             self.logger.info(msg)
         else:
-            print(msg)
+            _logger.info(msg)
 
         return self
 
@@ -323,7 +327,7 @@ class MemoryMonitor:
         if self.logger:
             self.logger.info(msg)
         else:
-            print(msg)
+            _logger.info(msg)
 
         # Check threshold and cleanup if needed
         if self.threshold_gb is not None:

{ins_pricing-0.5.0.dist-info → ins_pricing-0.5.3.dist-info}/METADATA

@@ -1,182 +1,182 @@
-Metadata-Version: 2.4
-Name: ins_pricing
-Version: 0.5.0
-Summary: Reusable modelling, pricing, governance, and reporting utilities.
-Author: meishi125478
-License: Proprietary
-Keywords: pricing,insurance,bayesopt,ml
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.9
-Classifier: License :: Other/Proprietary License
-Classifier: Operating System :: OS Independent
-Classifier: Intended Audience :: Developers
-Requires-Python: >=3.9
-Description-Content-Type: text/markdown
-Requires-Dist: numpy>=1.20
-Requires-Dist: pandas>=1.4
-Provides-Extra: bayesopt
-Requires-Dist: torch>=1.13; extra == "bayesopt"
-Requires-Dist: optuna>=3.0; extra == "bayesopt"
-Requires-Dist: xgboost>=1.6; extra == "bayesopt"
-Requires-Dist: scikit-learn>=1.1; extra == "bayesopt"
-Requires-Dist: statsmodels>=0.13; extra == "bayesopt"
-Requires-Dist: joblib>=1.2; extra == "bayesopt"
-Requires-Dist: matplotlib>=3.5; extra == "bayesopt"
-Provides-Extra: plotting
-Requires-Dist: matplotlib>=3.5; extra == "plotting"
-Requires-Dist: scikit-learn>=1.1; extra == "plotting"
-Provides-Extra: explain
-Requires-Dist: torch>=1.13; extra == "explain"
-Requires-Dist: shap>=0.41; extra == "explain"
-Requires-Dist: scikit-learn>=1.1; extra == "explain"
-Provides-Extra: geo
-Requires-Dist: contextily>=1.3; extra == "geo"
-Requires-Dist: matplotlib>=3.5; extra == "geo"
-Provides-Extra: gnn
-Requires-Dist: torch>=1.13; extra == "gnn"
-Requires-Dist: pynndescent>=0.5; extra == "gnn"
-Requires-Dist: torch-geometric>=2.3; extra == "gnn"
-Provides-Extra: all
-Requires-Dist: torch>=1.13; extra == "all"
-Requires-Dist: optuna>=3.0; extra == "all"
-Requires-Dist: xgboost>=1.6; extra == "all"
-Requires-Dist: scikit-learn>=1.1; extra == "all"
-Requires-Dist: statsmodels>=0.13; extra == "all"
-Requires-Dist: joblib>=1.2; extra == "all"
-Requires-Dist: matplotlib>=3.5; extra == "all"
-Requires-Dist: shap>=0.41; extra == "all"
-Requires-Dist: contextily>=1.3; extra == "all"
-Requires-Dist: pynndescent>=0.5; extra == "all"
-Requires-Dist: torch-geometric>=2.3; extra == "all"
-
-# Insurance-Pricing
-
-A reusable toolkit for insurance modeling, pricing, governance, and reporting.
-
-## Overview
-
-Insurance-Pricing (ins_pricing) is an enterprise-grade Python library designed for machine learning
-model training, pricing calculations, and model governance workflows in the insurance industry.
-
-### Core Modules
-
-| Module | Description |
-|--------|-------------|
-| modelling | ML model training (GLM, XGBoost, ResNet, FT-Transformer, GNN) and model interpretability |
-| pricing | Factor table construction, numeric binning, premium calibration, exposure calculation, PSI monitoring |
-| production | Model prediction, batch scoring, data drift detection, production metrics monitoring |
-| governance | Model registry, version management, approval workflows, audit logging |
-| reporting | Report generation (Markdown format), report scheduling |
-| utils | Data validation, performance profiling, device management, logging configuration |
-
-### Quick Start
-
-```python
-# Model training with Bayesian optimization
-from ins_pricing import bayesopt as ropt
-
-model = ropt.BayesOptModel(
-    train_data, test_data,
-    model_name='my_model',
-    resp_nme='target',
-    weight_nme='weight',
-    factor_nmes=feature_list,
-    cate_list=categorical_features,
-)
-model.bayesopt_xgb(max_evals=100)      # Train XGBoost
-model.bayesopt_resnet(max_evals=50)    # Train ResNet
-model.bayesopt_ft(max_evals=50)        # Train FT-Transformer
-
-# Pricing: build factor table
-from ins_pricing.pricing import build_factor_table
-factors = build_factor_table(
-    df,
-    factor_col='age_band',
-    loss_col='claim_amount',
-    exposure_col='exposure',
-)
-
-# Production: batch scoring
-from ins_pricing.production import batch_score
-scores = batch_score(model.trainers['xgb'].predict, df)
-
-# Model governance
-from ins_pricing.governance import ModelRegistry
-registry = ModelRegistry('models.json')
-registry.register(model_name, version, metrics=metrics)
-```
-
-### Project Structure
-
-```
-ins_pricing/
-  cli/                    # Command-line entry points
-  modelling/
-    core/bayesopt/         # ML model training core
-    explain/               # Model interpretability
-    plotting/              # Model visualization
-  pricing/                 # Insurance pricing module
-  production/              # Production deployment module
-  governance/              # Model governance
-  reporting/               # Report generation
-  utils/                   # Utilities
-  tests/                   # Test suite
-```
-
-### Installation
-
-```bash
-# Basic installation
-pip install ins_pricing
-
-# Full installation (all optional dependencies)
-pip install ins_pricing[all]
-
-# Install specific extras
-pip install ins_pricing[bayesopt]    # Model training
-pip install ins_pricing[explain]     # Model explanation
-pip install ins_pricing[plotting]    # Visualization
-pip install ins_pricing[gnn]         # Graph neural networks
-```
-
-#### Multi-platform and GPU notes
-
-- Install the correct PyTorch build for your platform/GPU before installing extras.
-- Torch Geometric requires platform-specific wheels; follow the official PyG install guide.
-- Multi-GPU uses torch.distributed/DataParallel where supported; Windows disables CUDA DDP.
-
----
-## PyPI Upload (scripts)
-
-This repo includes upload scripts for Windows and Linux/macOS.
-
-### Windows
-
-```cmd
-set TWINE_PASSWORD=your_pypi_token_here
-python -m build
-upload_to_pypi.bat
-```
-
-### Linux / macOS
-
-```bash
-chmod +x upload_to_pypi.sh
-export TWINE_PASSWORD='your_pypi_token_here'
-python -m build
-./upload_to_pypi.sh
-```
-
-### Makefile (if make is available)
-
-```bash
-make build
-make upload
-```
-
-### Tips
-
-- Never commit tokens to version control.
-- Use environment variables or secret managers to store credentials.
-- Test with TestPyPI before publishing when needed.
+Metadata-Version: 2.4
+Name: ins_pricing
+Version: 0.5.3
+Summary: Reusable modelling, pricing, governance, and reporting utilities.
+Author: meishi125478
+License: Proprietary
+Keywords: pricing,insurance,bayesopt,ml
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.9
+Classifier: License :: Other/Proprietary License
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Developers
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: numpy>=1.20
+Requires-Dist: pandas>=1.4
+Provides-Extra: bayesopt
+Requires-Dist: torch>=1.13; extra == "bayesopt"
+Requires-Dist: optuna>=3.0; extra == "bayesopt"
+Requires-Dist: xgboost>=1.6; extra == "bayesopt"
+Requires-Dist: scikit-learn>=1.1; extra == "bayesopt"
+Requires-Dist: statsmodels>=0.13; extra == "bayesopt"
+Requires-Dist: joblib>=1.2; extra == "bayesopt"
+Requires-Dist: matplotlib>=3.5; extra == "bayesopt"
+Provides-Extra: plotting
+Requires-Dist: matplotlib>=3.5; extra == "plotting"
+Requires-Dist: scikit-learn>=1.1; extra == "plotting"
+Provides-Extra: explain
+Requires-Dist: torch>=1.13; extra == "explain"
+Requires-Dist: shap>=0.41; extra == "explain"
+Requires-Dist: scikit-learn>=1.1; extra == "explain"
+Provides-Extra: geo
+Requires-Dist: contextily>=1.3; extra == "geo"
+Requires-Dist: matplotlib>=3.5; extra == "geo"
+Provides-Extra: gnn
+Requires-Dist: torch>=1.13; extra == "gnn"
+Requires-Dist: pynndescent>=0.5; extra == "gnn"
+Requires-Dist: torch-geometric>=2.3; extra == "gnn"
+Provides-Extra: all
+Requires-Dist: torch>=1.13; extra == "all"
+Requires-Dist: optuna>=3.0; extra == "all"
+Requires-Dist: xgboost>=1.6; extra == "all"
+Requires-Dist: scikit-learn>=1.1; extra == "all"
+Requires-Dist: statsmodels>=0.13; extra == "all"
+Requires-Dist: joblib>=1.2; extra == "all"
+Requires-Dist: matplotlib>=3.5; extra == "all"
+Requires-Dist: shap>=0.41; extra == "all"
+Requires-Dist: contextily>=1.3; extra == "all"
+Requires-Dist: pynndescent>=0.5; extra == "all"
+Requires-Dist: torch-geometric>=2.3; extra == "all"
+
+# Insurance-Pricing
+
+A reusable toolkit for insurance modeling, pricing, governance, and reporting.
+
+## Overview
+
+Insurance-Pricing (ins_pricing) is an enterprise-grade Python library designed for machine learning
+model training, pricing calculations, and model governance workflows in the insurance industry.
+
+### Core Modules
+
+| Module | Description |
+|--------|-------------|
+| modelling | ML model training (GLM, XGBoost, ResNet, FT-Transformer, GNN) and model interpretability |
+| pricing | Factor table construction, numeric binning, premium calibration, exposure calculation, PSI monitoring |
+| production | Model prediction, batch scoring, data drift detection, production metrics monitoring |
+| governance | Model registry, version management, approval workflows, audit logging |
+| reporting | Report generation (Markdown format), report scheduling |
+| utils | Data validation, performance profiling, device management, logging configuration |
+
+### Quick Start
+
+```python
+# Model training with Bayesian optimization
+from ins_pricing import bayesopt as ropt
+
+model = ropt.BayesOptModel(
+    train_data, test_data,
+    model_name='my_model',
+    resp_nme='target',
+    weight_nme='weight',
+    factor_nmes=feature_list,
+    cate_list=categorical_features,
+)
+model.bayesopt_xgb(max_evals=100)      # Train XGBoost
+model.bayesopt_resnet(max_evals=50)    # Train ResNet
+model.bayesopt_ft(max_evals=50)        # Train FT-Transformer
+
+# Pricing: build factor table
+from ins_pricing.pricing import build_factor_table
+factors = build_factor_table(
+    df,
+    factor_col='age_band',
+    loss_col='claim_amount',
+    exposure_col='exposure',
+)
+
+# Production: batch scoring
+from ins_pricing.production import batch_score
+scores = batch_score(model.trainers['xgb'].predict, df)
+
+# Model governance
+from ins_pricing.governance import ModelRegistry
+registry = ModelRegistry('models.json')
+registry.register(model_name, version, metrics=metrics)
+```
+
+### Project Structure
+
+```
+ins_pricing/
+  cli/                    # Command-line entry points
+  modelling/
+    core/bayesopt/         # ML model training core
+    explain/               # Model interpretability
+    plotting/              # Model visualization
+  pricing/                 # Insurance pricing module
+  production/              # Production deployment module
+  governance/              # Model governance
+  reporting/               # Report generation
+  utils/                   # Utilities
+  tests/                   # Test suite
+```
+
+### Installation
+
+```bash
+# Basic installation
+pip install ins_pricing
+
+# Full installation (all optional dependencies)
+pip install ins_pricing[all]
+
+# Install specific extras
+pip install ins_pricing[bayesopt]    # Model training
+pip install ins_pricing[explain]     # Model explanation
+pip install ins_pricing[plotting]    # Visualization
+pip install ins_pricing[gnn]         # Graph neural networks
+```
+
+#### Multi-platform and GPU notes
+
+- Install the correct PyTorch build for your platform/GPU before installing extras.
+- Torch Geometric requires platform-specific wheels; follow the official PyG install guide.
+- Multi-GPU uses torch.distributed/DataParallel where supported; Windows disables CUDA DDP.
+
+---
+## PyPI Upload (scripts)
+
+This repo includes upload scripts for Windows and Linux/macOS.
+
+### Windows
+
+```cmd
+set TWINE_PASSWORD=your_pypi_token_here
+python -m build
+upload_to_pypi.bat
+```
+
+### Linux / macOS
+
+```bash
+chmod +x upload_to_pypi.sh
+export TWINE_PASSWORD='your_pypi_token_here'
+python -m build
+./upload_to_pypi.sh
+```
+
+### Makefile (if make is available)
+
+```bash
+make build
+make upload
+```
+
+### Tips
+
+- Never commit tokens to version control.
+- Use environment variables or secret managers to store credentials.
+- Test with TestPyPI before publishing when needed.