ins-pricing 0.2.7__py3-none-any.whl → 0.2.9__py3-none-any.whl

ins_pricing/utils/validation.py

@@ -0,0 +1,427 @@
+"""Data validation utilities for ins_pricing.
+
+This module provides reusable validation functions to ensure data quality
+and provide clear error messages when validation fails.
+
+Example:
+    >>> import pandas as pd
+    >>> from ins_pricing.utils.validation import validate_required_columns
+    >>> df = pd.DataFrame({'a': [1, 2], 'b': [3, 4]})
+    >>> validate_required_columns(df, ['a', 'b'], df_name='my_data')
+    >>> # Raises DataValidationError if columns missing
+"""
+
+from __future__ import annotations
+
+from typing import Dict, List, Optional, Union
+
+import pandas as pd
+
+from ins_pricing.exceptions import DataValidationError
+
+
+def validate_required_columns(
+    df: pd.DataFrame,
+    required: List[str],
+    *,
+    df_name: str = "DataFrame"
+) -> None:
+    """Validate that DataFrame contains all required columns.
+
+    Args:
+        df: DataFrame to validate
+        required: List of required column names
+        df_name: Name of DataFrame for error messages (default: "DataFrame")
+
+    Raises:
+        DataValidationError: If any required columns are missing
+
+    Example:
+        >>> df = pd.DataFrame({'age': [25, 30], 'premium': [100, 200]})
+        >>> validate_required_columns(df, ['age', 'premium'], df_name='policy_data')
+        >>> validate_required_columns(df, ['age', 'claim'], df_name='policy_data')
+        Traceback (most recent call last):
+            ...
+        DataValidationError: policy_data missing required columns: ['claim']...
+    """
+    missing = [col for col in required if col not in df.columns]
+    if missing:
+        available_preview = list(df.columns)[:50]
+        raise DataValidationError(
+            f"{df_name} missing required columns: {missing}. "
+            f"Available columns (first 50): {available_preview}"
+        )
+
+
+def validate_column_types(
+    df: pd.DataFrame,
+    type_spec: Dict[str, Union[type, str]],
+    *,
+    coerce: bool = False,
+    df_name: str = "DataFrame"
+) -> pd.DataFrame:
+    """Validate and optionally coerce column data types.
+
+    Args:
+        df: DataFrame to validate
+        type_spec: Dictionary mapping column names to expected types.
+                  Types can be Python types (int, float, str) or pandas
+                  dtype strings ('int64', 'float64', 'object', 'category')
+        coerce: If True, attempt to convert columns to expected types.
+               If False, raise error on type mismatch (default: False)
+        df_name: Name of DataFrame for error messages
+
+    Returns:
+        DataFrame with validated (and possibly coerced) types
+
+    Raises:
+        DataValidationError: If column types don't match and coerce=False
+
+    Example:
+        >>> df = pd.DataFrame({'age': ['25', '30'], 'premium': [100.0, 200.0]})
+        >>> df = validate_column_types(
+        ...     df,
+        ...     {'age': 'int64', 'premium': 'float64'},
+        ...     coerce=True
+        ... )
+        >>> df['age'].dtype
+        dtype('int64')
+    """
+    df = df.copy() if coerce else df
+
+    for col, expected_type in type_spec.items():
+        if col not in df.columns:
+            continue
+
+        current_dtype = df[col].dtype
+
+        # Convert type spec to pandas dtype
+        if isinstance(expected_type, type):
+            if expected_type == int:
+                expected_dtype = 'int64'
+            elif expected_type == float:
+                expected_dtype = 'float64'
+            elif expected_type == str:
+                expected_dtype = 'object'
+            else:
+                expected_dtype = str(expected_type)
+        else:
+            expected_dtype = expected_type
+
+        # Check if types match
+        type_matches = (
+            str(current_dtype) == expected_dtype or
+            current_dtype.name == expected_dtype
+        )
+
+        if not type_matches:
+            if coerce:
+                try:
+                    df[col] = df[col].astype(expected_dtype)
+                except (ValueError, TypeError) as e:
+                    raise DataValidationError(
+                        f"{df_name}: Cannot convert column '{col}' from "
+                        f"{current_dtype} to {expected_dtype}: {e}"
+                    )
+            else:
+                raise DataValidationError(
+                    f"{df_name}: Column '{col}' has type {current_dtype}, "
+                    f"expected {expected_dtype}"
+                )
+
+    return df
+
+
+def validate_value_range(
+    df: pd.DataFrame,
+    col: str,
+    *,
+    min_val: Optional[float] = None,
+    max_val: Optional[float] = None,
+    df_name: str = "DataFrame"
+) -> None:
+    """Validate that numeric column values are within expected range.
+
+    Args:
+        df: DataFrame to validate
+        col: Column name to check
+        min_val: Minimum allowed value (inclusive), None for no minimum
+        max_val: Maximum allowed value (inclusive), None for no maximum
+        df_name: Name of DataFrame for error messages
+
+    Raises:
+        DataValidationError: If values are outside the specified range
+
+    Example:
+        >>> df = pd.DataFrame({'age': [25, 30, 150]})
+        >>> validate_value_range(df, 'age', min_val=0, max_val=120)
+        Traceback (most recent call last):
+            ...
+        DataValidationError: ...values outside range [0, 120]...
+    """
+    if col not in df.columns:
+        raise DataValidationError(
+            f"{df_name}: Column '{col}' not found for range validation"
+        )
+
+    if not pd.api.types.is_numeric_dtype(df[col]):
+        raise DataValidationError(
+            f"{df_name}: Column '{col}' is not numeric, cannot validate range"
+        )
+
+    violations = []
+
+    if min_val is not None:
+        below_min = df[col] < min_val
+        if below_min.any():
+            count = below_min.sum()
+            min_found = df.loc[below_min, col].min()
+            violations.append(
+                f"{count} values below minimum {min_val} (min found: {min_found})"
+            )
+
+    if max_val is not None:
+        above_max = df[col] > max_val
+        if above_max.any():
+            count = above_max.sum()
+            max_found = df.loc[above_max, col].max()
+            violations.append(
+                f"{count} values above maximum {max_val} (max found: {max_found})"
+            )
+
+    if violations:
+        range_str = f"[{min_val}, {max_val}]"
+        raise DataValidationError(
+            f"{df_name}: Column '{col}' has values outside range {range_str}: "
+            f"{'; '.join(violations)}"
+        )
+
+
+def validate_no_nulls(
+    df: pd.DataFrame,
+    columns: List[str],
+    *,
+    df_name: str = "DataFrame"
+) -> None:
+    """Validate that specified columns contain no null values.
+
+    Args:
+        df: DataFrame to validate
+        columns: List of column names to check for nulls
+        df_name: Name of DataFrame for error messages
+
+    Raises:
+        DataValidationError: If any specified columns contain null values
+
+    Example:
+        >>> df = pd.DataFrame({'age': [25, None, 30], 'premium': [100, 200, 300]})
+        >>> validate_no_nulls(df, ['age', 'premium'])
+        Traceback (most recent call last):
+            ...
+        DataValidationError: ...contains null values: age (1 nulls)...
+    """
+    null_info = []
+
+    for col in columns:
+        if col not in df.columns:
+            raise DataValidationError(
+                f"{df_name}: Column '{col}' not found for null validation"
+            )
+
+        null_count = df[col].isna().sum()
+        if null_count > 0:
+            null_info.append(f"{col} ({null_count} nulls)")
+
+    if null_info:
+        raise DataValidationError(
+            f"{df_name} contains null values: {', '.join(null_info)}"
+        )
+
+
+def validate_categorical_values(
+    df: pd.DataFrame,
+    col: str,
+    allowed_values: List[str],
+    *,
+    df_name: str = "DataFrame"
+) -> None:
+    """Validate that categorical column contains only allowed values.
+
+    Args:
+        df: DataFrame to validate
+        col: Column name to check
+        allowed_values: List of allowed values
+        df_name: Name of DataFrame for error messages
+
+    Raises:
+        DataValidationError: If column contains values not in allowed_values
+
+    Example:
+        >>> df = pd.DataFrame({'gender': ['M', 'F', 'X']})
+        >>> validate_categorical_values(df, 'gender', ['M', 'F'])
+        Traceback (most recent call last):
+            ...
+        DataValidationError: ...contains invalid values: ['X']...
+    """
+    if col not in df.columns:
+        raise DataValidationError(
+            f"{df_name}: Column '{col}' not found for categorical validation"
+        )
+
+    unique_values = df[col].dropna().unique()
+    invalid_values = [v for v in unique_values if v not in allowed_values]
+
+    if invalid_values:
+        raise DataValidationError(
+            f"{df_name}: Column '{col}' contains invalid values: {invalid_values}. "
+            f"Allowed values: {allowed_values}"
+        )
+
+
+def validate_positive(
+    df: pd.DataFrame,
+    columns: List[str],
+    *,
+    allow_zero: bool = False,
+    df_name: str = "DataFrame"
+) -> None:
+    """Validate that numeric columns contain only positive values.
+
+    Args:
+        df: DataFrame to validate
+        columns: List of column names to check
+        allow_zero: If True, allow zero values (default: False)
+        df_name: Name of DataFrame for error messages
+
+    Raises:
+        DataValidationError: If columns contain non-positive values
+
+    Example:
+        >>> df = pd.DataFrame({'premium': [100, -50, 200], 'exposure': [1, 0, 2]})
+        >>> validate_positive(df, ['premium', 'exposure'])
+        Traceback (most recent call last):
+            ...
+        DataValidationError: ...contains non-positive values...
+    """
+    violations = []
+
+    for col in columns:
+        if col not in df.columns:
+            raise DataValidationError(
+                f"{df_name}: Column '{col}' not found for positivity validation"
+            )
+
+        if not pd.api.types.is_numeric_dtype(df[col]):
+            raise DataValidationError(
+                f"{df_name}: Column '{col}' is not numeric"
+            )
+
+        if allow_zero:
+            invalid = df[col] < 0
+            msg = "negative"
+        else:
+            invalid = df[col] <= 0
+            msg = "non-positive"
+
+        if invalid.any():
+            count = invalid.sum()
+            min_val = df.loc[invalid, col].min()
+            violations.append(f"{col} ({count} {msg} values, min: {min_val})")
+
+    if violations:
+        raise DataValidationError(
+            f"{df_name} contains {msg} values: {', '.join(violations)}"
+        )
+
+
+def validate_dataframe_not_empty(
+    df: pd.DataFrame,
+    *,
+    df_name: str = "DataFrame"
+) -> None:
+    """Validate that DataFrame is not empty.
+
+    Args:
+        df: DataFrame to validate
+        df_name: Name of DataFrame for error messages
+
+    Raises:
+        DataValidationError: If DataFrame is empty
+
+    Example:
+        >>> df = pd.DataFrame()
+        >>> validate_dataframe_not_empty(df, df_name='train_data')
+        Traceback (most recent call last):
+            ...
+        DataValidationError: train_data is empty (0 rows)
+    """
+    if len(df) == 0:
+        raise DataValidationError(f"{df_name} is empty (0 rows)")
+
+
+def validate_date_range(
+    df: pd.DataFrame,
+    col: str,
+    *,
+    min_date: Optional[pd.Timestamp] = None,
+    max_date: Optional[pd.Timestamp] = None,
+    df_name: str = "DataFrame"
+) -> None:
+    """Validate that date column values are within expected range.
+
+    Args:
+        df: DataFrame to validate
+        col: Column name to check (should be datetime type)
+        min_date: Minimum allowed date, None for no minimum
+        max_date: Maximum allowed date, None for no maximum
+        df_name: Name of DataFrame for error messages
+
+    Raises:
+        DataValidationError: If dates are outside the specified range
+
+    Example:
+        >>> df = pd.DataFrame({'policy_date': pd.to_datetime(['2020-01-01', '2025-01-01'])})
+        >>> validate_date_range(
+        ...     df, 'policy_date',
+        ...     min_date=pd.Timestamp('2020-01-01'),
+        ...     max_date=pd.Timestamp('2023-12-31')
+        ... )
+        Traceback (most recent call last):
+            ...
+        DataValidationError: ...dates outside range...
+    """
+    if col not in df.columns:
+        raise DataValidationError(
+            f"{df_name}: Column '{col}' not found for date validation"
+        )
+
+    if not pd.api.types.is_datetime64_any_dtype(df[col]):
+        raise DataValidationError(
+            f"{df_name}: Column '{col}' is not datetime type"
+        )
+
+    violations = []
+
+    if min_date is not None:
+        before_min = df[col] < min_date
+        if before_min.any():
+            count = before_min.sum()
+            earliest = df.loc[before_min, col].min()
+            violations.append(
+                f"{count} dates before {min_date} (earliest: {earliest})"
+            )
+
+    if max_date is not None:
+        after_max = df[col] > max_date
+        if after_max.any():
+            count = after_max.sum()
+            latest = df.loc[after_max, col].max()
+            violations.append(
+                f"{count} dates after {max_date} (latest: {latest})"
+            )
+
+    if violations:
+        raise DataValidationError(
+            f"{df_name}: Column '{col}' has dates outside range: "
+            f"{'; '.join(violations)}"
+        )

ins_pricing-0.2.9.dist-info/METADATA

@@ -0,0 +1,149 @@
+Metadata-Version: 2.4
+Name: ins_pricing
+Version: 0.2.9
+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 (SHAP, permutation importance) |
+| **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
+```
+
+### Requirements
+
+- Python >= 3.9
+- Core dependencies: numpy >= 1.20, pandas >= 1.4
+
+### License
+
+Proprietary

{ins_pricing-0.2.7.dist-info → ins_pricing-0.2.9.dist-info}/RECORD

@@ -1,9 +1,9 @@
-ins_pricing/CHANGELOG_20260114.md,sha256=eRDstQ8mLPGv9MH70FnMUxwvp3RXT3ati_a0rkx4C88,7680
-ins_pricing/CODE_REVIEW_IMPROVEMENTS.md,sha256=eGQ1qtl8l84VvxvAnvzcV9Kk_FVPthAg1poq92k6vZU,17852
+ins_pricing/CHANGELOG.md,sha256=Z423KtXu_4_cL0T2C947K8F5hHjulRvoc3lRjH5nCVw,7618
 ins_pricing/README.md,sha256=pMOO1cU06oBfvm5d8gvAsQsJr9bfb6AKdpXlrx0AAxw,2727
+ins_pricing/RELEASE_NOTES_0.2.8.md,sha256=KIJzk1jbZbZPKjwnkPSDHO_2Ipv3SP3CzCNDdf07jI0,9331
 ins_pricing/__init__.py,sha256=46j1wCdLVrgrofeBwKl-3NXTxzjbTv-w3KjW-dyKGiY,2622
 ins_pricing/exceptions.py,sha256=5fZavPV4zNJ7wPC75L215KkHXX9pRrfDAYZOdSKJMGo,4778
-ins_pricing/setup.py,sha256=ERo1J0UQZunYcOPE8fqxzRyxKvpZBo-9lYRceaZmzFA,1702
+ins_pricing/setup.py,sha256=YXo6D3Tjgo6DwXI2SOufrvgYbHY2oCnT2dStGzA5Fuc,1702
 ins_pricing/cli/BayesOpt_entry.py,sha256=X3AiNQQh5ARcjVMM2vOKWPYPDIId40n_RPZA76pTGl4,558
 ins_pricing/cli/BayesOpt_incremental.py,sha256=_Klr5vvNoq_TbgwrH_T3f0a6cHmA9iVJMViiji6ahJY,35927
 ins_pricing/cli/Explain_Run.py,sha256=gEPQjqHiXyXlCTKjUzwSvbAn5_h74ABgb_sEGs-YHVE,664
@@ -34,7 +34,7 @@ ins_pricing/modelling/core/bayesopt/config_preprocess.py,sha256=2UpkcmhEk2V3uLv2
 ins_pricing/modelling/core/bayesopt/core.py,sha256=ewChb0s-on3ZWIcbCpJTJAaeHeo28nBzsFyvQ-zWHio,40926
 ins_pricing/modelling/core/bayesopt/model_explain_mixin.py,sha256=jCk1zPpwgwBBCndaq-A0_cQnc4RHueh2p5cAuE9ArTo,11620
 ins_pricing/modelling/core/bayesopt/model_plotting_mixin.py,sha256=lD0rUvWV4eWatmTzMrmAUm2Flj8uAOa3R9S2JyYV94k,21807
-ins_pricing/modelling/core/bayesopt/utils.py,sha256=db7QJjwDgJK6SKCzPHbftlRurZ9RNBxa4O672zZcUKs,57874
+ins_pricing/modelling/core/bayesopt/utils.py,sha256=5RKizpR3j6KwR87WqqaXPtgjQXWPW4vM75sIkx38SSM,57924
 ins_pricing/modelling/core/bayesopt/models/__init__.py,sha256=vFFCkGnO6rm50TbxR6QekKKQjq-NW4UFwog6fng8-p8,700
 ins_pricing/modelling/core/bayesopt/models/model_ft_components.py,sha256=0I0NiDf1D3cOhTRQwatsNTw9Julmxv5v3HZV8fTrvcQ,10989
 ins_pricing/modelling/core/bayesopt/models/model_ft_trainer.py,sha256=IJoBOYHo5uzLEpo4DZj1PsPXojmCKbMaoRudhB9IGBY,36531
@@ -51,7 +51,7 @@ ins_pricing/modelling/explain/__init__.py,sha256=CPoGzGu8TTO3FOXjxoXC13VkuIDCf3Y
 ins_pricing/modelling/explain/gradients.py,sha256=9TqCws_p49nFxVMcjVxe4KCZ7frezeL0uV_LCdoM5yo,11088
 ins_pricing/modelling/explain/metrics.py,sha256=K_xOY7ZrHWhbJ79RNB7eXN3VXeTe8vq68ZLH2BlZufA,5389
 ins_pricing/modelling/explain/permutation.py,sha256=TeVlhz7FWyPsaZwEP3BSLa0BZgdOq74coZqnadkGaPw,9333
-ins_pricing/modelling/explain/shap_utils.py,sha256=IkijzxBeawyDIXiVxUUkvcC0MrHnttSKsMYOjM-wt-k,4353
+ins_pricing/modelling/explain/shap_utils.py,sha256=70zRIHPPdoECFOFQeBTRxLZF-6sjaGJBNMIRS4_kmVI,10462
 ins_pricing/modelling/plotting/__init__.py,sha256=BBQKcE7IYUYObFrjpSnfNS6rmzc80Lae7oEqxKz-vEk,1058
 ins_pricing/modelling/plotting/common.py,sha256=_kFq7JMA0LnKIp4bqAFvr-24VaHjj9pegDMm1qP9_7Y,1439
 ins_pricing/modelling/plotting/curves.py,sha256=fEnoeHAVvLPI5HXadNLUoWygmHtNWCngynLdZK868NQ,18398
@@ -60,22 +60,26 @@ ins_pricing/modelling/plotting/geo.py,sha256=sRJTYOcAphNFM-oww4qbw9MoZneBCJtur96
 ins_pricing/modelling/plotting/importance.py,sha256=xs3l9uW_rCrakoA__fanIph6DK2jN_DugsKASAzteJU,3666
 ins_pricing/pricing/README.md,sha256=PEcyw5oDkqJHOqnNdzBdbbpZwG4SOlnhMwY-owwQ0GI,1064
 ins_pricing/pricing/__init__.py,sha256=XFplK3zkxPyNQZJd1Gn6_VvpwHLedMqxAd_Vn9tqsTE,881
-ins_pricing/pricing/calibration.py,sha256=9j_kDW5Fxb9weDMaaRJE0QjAhT98lL0Ifhls6VIRnY0,1158
+ins_pricing/pricing/calibration.py,sha256=cx9fbDoOnNEMGPH6Js1EDMfVwy9J7zf_90yuNwD7W6I,6196
 ins_pricing/pricing/data_quality.py,sha256=8FecBE60cABsTZE7HETuoKCEOXIrirGAFgg5wQCZrmU,4043
 ins_pricing/pricing/exposure.py,sha256=rw8kKZ_1QdeGTCm13ck9NXrRBPt6TunxRw2s_qkHYkg,2575
-ins_pricing/pricing/factors.py,sha256=RqZRXvW70rKkTIOxtK4MGeyDD3PrOFJ19hVc6rLYFzQ,2937
+ins_pricing/pricing/factors.py,sha256=1cqDqdXRLb9-yt-x60f0lPWdgAAOvk7slnawVIKcWDo,6573
 ins_pricing/pricing/monitoring.py,sha256=GnfF2g1C9KzDks9ELBykfAd0zzVBUvjuTWoffa7aGbI,613
 ins_pricing/pricing/rate_table.py,sha256=llDW95i7gR6cCtGFwcGqgpgFvOOPCURaJWmuQw1oce8,2473
 ins_pricing/production/__init__.py,sha256=plUjyiwxrzHDDgXKezyGp9UHOg7Mav4f0ryXYtNmbfs,885
 ins_pricing/production/drift.py,sha256=q_oE_h2NbVETTBkh9QUu8Y68ERuFFcrfKpOb3zBcvsA,383
 ins_pricing/production/monitoring.py,sha256=A6Hyc5WSKhFkDZOIrqmFteuDee75CdcwdTq644vrk-U,4836
 ins_pricing/production/predict.py,sha256=mJog-RGLHxIJxx4oh0D1gbhJwBZPQs1z1P6YTDfWtfg,21791
-ins_pricing/production/preprocess.py,sha256=R_QVbzjppF5XJtRJG3v3NWL0PdMS3rDn0-VETzUnkJI,2315
+ins_pricing/production/preprocess.py,sha256=cl20X0rVcKNCjVJswB8SdHffMgox6Qga4Ac29L6pW5g,9404
 ins_pricing/production/scoring.py,sha256=yFmMmbYb7w_RC4uZOCMnAjLMRcjXQWIuT1nsfu-bwuc,1379
 ins_pricing/reporting/README.md,sha256=kTVdB6pNewwh1HlCHrI2SzWTgprtQoQprLRQ2qLdgNA,486
 ins_pricing/reporting/__init__.py,sha256=Se5Cdomv9_RwkIDizkw1yx4iCMcjhjTHb4pZK6K895c,242
 ins_pricing/reporting/report_builder.py,sha256=53ZFqGUx2isAoigT5IDwvXkek67zN7-6IgKeGpJhO7c,2241
 ins_pricing/reporting/scheduler.py,sha256=9koG_1cmWvLqrS66uzMJuAlYI2VTkynV19ssB2TtcKU,1336
+ins_pricing/tests/governance/__init__.py,sha256=5Nxg4_dIxY_J58_x2QOXrrRgw6L51Md0Wnt5Up-chqg,39
+ins_pricing/tests/governance/test_audit.py,sha256=ubybXSTVILPN4VxQ2fMnG6oPNv4LjJJE3EsQ53NYdLU,1702
+ins_pricing/tests/governance/test_registry.py,sha256=TvkNMLHViNuopjjho6oETwZ9d6MNaNM1xbL6URPDKSk,4602
+ins_pricing/tests/governance/test_release.py,sha256=Cdo6prZ0xlioAP2AYHodzgASEIa6ZCLjbXW9Me2RGKk,2347
 ins_pricing/tests/modelling/conftest.py,sha256=0KUXnkTgIGEIsf0J4uzIx5Kq4JkDyFo81Mv0qvIzW9k,180
 ins_pricing/tests/modelling/test_cross_val_generic.py,sha256=iLZOFmdyrycB15lFWoQphkFlEjzZTozQXTLVOHLw2Qg,1721
 ins_pricing/tests/modelling/test_distributed_utils.py,sha256=9cStpDw7jPdQwmm0Po-G2tB04uzSR1CoOUZMLuB61yI,466
@@ -85,12 +89,24 @@ ins_pricing/tests/modelling/test_graph_cache.py,sha256=QEI5cLLtQ9_zwRR50KqUf8qxo
 ins_pricing/tests/modelling/test_plotting.py,sha256=4gJax72l40fQrjyJQLOgUmaT6xn6zXpujEaFNeHVwGw,1911
 ins_pricing/tests/modelling/test_plotting_library.py,sha256=SB5RjKTaPydK848V0xpqEaJtEWhRv6ZfnHmnnzjaPh4,4079
 ins_pricing/tests/modelling/test_preprocessor.py,sha256=FqbKltV803Pd-ZY1xBc4XF1T-INDuUliaVcMIDPmBxI,1438
+ins_pricing/tests/pricing/__init__.py,sha256=SVfgUYBlCmc4wjYLMRX5xPFgQZxTS3aHBOA_Cx1aJg4,36
+ins_pricing/tests/pricing/test_calibration.py,sha256=hLZuSWOH4t9WKcQ-2srvYp4P5ldr1Yh1dhl7s61vMp8,2420
+ins_pricing/tests/pricing/test_exposure.py,sha256=CrpSncVce-PGt2XzjOX6qV0SA22vKPUv1u8RlKQjt_g,2054
+ins_pricing/tests/pricing/test_factors.py,sha256=NTE7lz1RWChhoRt2K5003DoNRqG_Gu4X1Aauy2NexOg,5093
+ins_pricing/tests/pricing/test_rate_table.py,sha256=ICHfAQsC9TaxXbQVKM5AvBaJXRTVY723Vaz1XOWNMW8,1250
+ins_pricing/tests/production/__init__.py,sha256=WFWlvBVdjg-E-nKaiJ8VTKNELYufJusufpij1p1xwso,39
+ins_pricing/tests/production/test_monitoring.py,sha256=jettbaVLH4a3efLWeiQ6FFukGEw7mmz6_AeYhYX0caQ,11409
+ins_pricing/tests/production/test_predict.py,sha256=PNamNzb-KNbLtT8xbBkwWOcmJC1gXvxj2nnc7dR5fyc,8193
+ins_pricing/tests/production/test_preprocess.py,sha256=tsHYANwJjNlaSo8O4qiwqBvMOMtwmtZymRFm6UrODrE,11084
+ins_pricing/tests/production/test_scoring.py,sha256=fKz2tJomodrRt333apCrjtyJCwg9RHRbWm0lvcU6xm0,9848
 ins_pricing/utils/__init__.py,sha256=ovtolxOvlYp_1SOxZ35OPBdn7JB2O4idzRSQgIlzCvc,2339
 ins_pricing/utils/device.py,sha256=fePvqSaOkzHMBbrHCXAOCKRwdcR8YtiGI5K8Q3ljXJc,7543
 ins_pricing/utils/logging.py,sha256=_AKB4ErmvygwGLtu7Ai7ESemj6Hh8FTgh4cs8j_gVW4,2258
 ins_pricing/utils/metrics.py,sha256=zhKYgXgki8RDscjP_GO2lEgzrtMIZCqOX_aLpQzdw6k,8390
 ins_pricing/utils/paths.py,sha256=o_tBiclFvBci4cYg9WANwKPxrMcglEdOjDP-EZgGjdQ,8749
-ins_pricing-0.2.7.dist-info/METADATA,sha256=_0EKpRju1la9-IJXHHOaMQa8ncs1MsQkA5iB14_xOKU,3763
-ins_pricing-0.2.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-ins_pricing-0.2.7.dist-info/top_level.txt,sha256=haZuNQpHKNBEPZx3NjLnHp8pV3I_J9QG8-HyJn00FA0,12
-ins_pricing-0.2.7.dist-info/RECORD,,
+ins_pricing/utils/profiling.py,sha256=kmbykHLcYywlZxAf_aVU8HXID3zOvUcBoO5Q58AijhA,11132
+ins_pricing/utils/validation.py,sha256=4Tw9VUJPk0N-WO3YUqZP-xXRl1Xpubkm0vi3WzzZrv4,13348
+ins_pricing-0.2.9.dist-info/METADATA,sha256=uQLsM3-erzbt48qF7nt7_Orf18CF-aKkk4_5B4_yeMk,5397
+ins_pricing-0.2.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ins_pricing-0.2.9.dist-info/top_level.txt,sha256=haZuNQpHKNBEPZx3NjLnHp8pV3I_J9QG8-HyJn00FA0,12
+ins_pricing-0.2.9.dist-info/RECORD,,