serverlex 1.0.0__tar.gz → 1.2.0__tar.gz

serverlex-1.2.0/Clean.py

@@ -0,0 +1,2 @@
+from serverlex.preprocessing.clean import Clean
+__all__ = ["Clean"]

serverlex-1.2.0/DataCheck.py

@@ -0,0 +1,2 @@
+from serverlex.diagnostics.dataguard import DataGuard
+__all__ = ["DataGuard"]

serverlex-1.2.0/DriftDetector.py

@@ -0,0 +1,2 @@
+from serverlex.diagnostics.drift import DriftDetector
+__all__ = ["DriftDetector"]

serverlex-1.2.0/EnsembleBuilder.py

@@ -0,0 +1,2 @@
+from serverlex.modeling.ensemble import EnsembleBuilder
+__all__ = ["EnsembleBuilder"]

serverlex-1.2.0/Evaluation.py

@@ -0,0 +1,2 @@
+from serverlex.diagnostics.evaluation import ModelEvaluator
+__all__ = ["ModelEvaluator"]

serverlex-1.2.0/Explainability.py

@@ -0,0 +1,2 @@
+from serverlex.diagnostics.explainability import ModelExplainer
+__all__ = ["ModelExplainer"]

serverlex-1.2.0/FeatureSelector.py

@@ -0,0 +1,2 @@
+from serverlex.modeling.selector import FeatureSelector
+__all__ = ["FeatureSelector"]

serverlex-1.2.0/ModelDeployer.py

@@ -0,0 +1,2 @@
+from serverlex.serving.deployer import ModelDeployer
+__all__ = ["ModelDeployer"]

serverlex-1.2.0/ModelHyperparameter.py

@@ -0,0 +1,2 @@
+from serverlex.modeling.hyperparameter import ModelHyperparameter
+__all__ = ["ModelHyperparameter"]

{serverlex-1.0.0/serverlex.egg-info → serverlex-1.2.0}/PKG-INFO

@@ -1,8 +1,9 @@
 Metadata-Version: 2.4
 Name: serverlex
-Version: 1.0.0
-Summary: End-to-End Automated Data Cleaning, ML Preprocessing, Diagnostics, and Deployment Platform
+Version: 1.2.0
+Summary: Production-Safe ML Preprocessing, Diagnostics, Tuning, and Serving Platform
 Author: Serverlex Team
+License: MIT
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
@@ -15,23 +16,20 @@ Requires-Dist: scipy>=1.10.0
 Requires-Dist: matplotlib>=3.7.0
 Requires-Dist: scikit-learn>=1.3.0
 Requires-Dist: joblib>=1.3.0
-Dynamic: author
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: requires-dist
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: flake8>=6.0.0; extra == "dev"
 Dynamic: requires-python
-Dynamic: summary
 
 # Serverlex ⚡
 **The Production-Safe Machine Learning Preprocessing, Diagnostics, & Serving Platform**
 
 [![Python Version](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11-blue.svg)](https://www.python.org/)
-[![PyPI](https://img.shields.io/badge/pypi-coming%20soon-orange.svg)](https://pypi.org/)
+[![PyPI version](https://img.shields.io/pypi/v/serverlex.svg?color=blue)](https://pypi.org/project/serverlex/)
+[![PyPI Downloads](https://img.shields.io/pypi/dm/serverlex.svg)](https://pypi.org/project/serverlex/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Code Style](https://img.shields.io/badge/code%20style-flat%20%26%20clean-green.svg)](https://github.com/)
-
-> 🚀 **Coming Soon to PyPI!** Serverlex is currently undergoing final release preparations and will soon be installable with a simple `pip install serverlex`. Star this repository to get notified when the initial PyPI package is published!
+[![Code Style](https://img.shields.io/badge/code%20style-flat%20%26%20clean-green.svg)](https://github.com/Uwais-ML/Serverlex)
 
 **Serverlex** is an end-to-end Python library that takes raw, dirty data and transforms it into model-ready features, baseline benchmarks, tuned algorithms, and live production endpoints—all without data leakage or boilerplate code.
 
@@ -39,17 +37,18 @@ Dynamic: summary
 
 ## 📦 Installation
 
-### Coming Soon via PyPI:
+Install the official release directly from [PyPI](https://pypi.org/project/serverlex/):
+
 ```bash
 pip install serverlex
 ```
 
-### Current Installation (From GitHub / Source):
+### Or Install From Source / GitHub:
 ```bash
-# Direct from GitHub:
+# Latest development branch from GitHub:
 pip install git+https://github.com/Uwais-ML/Serverlex.git
 
-# Or install locally in editable mode:
+# Or clone and install in editable mode:
 git clone https://github.com/Uwais-ML/Serverlex.git
 cd Serverlex
 pip install -e .
@@ -163,17 +162,31 @@ print("Predicted Churn:", loaded_deployer.predict(raw_input)[0])
 
 | Module | Core Class | Primary Purpose |
 |---|---|---|
-| [`Clean.py`](Clean.py) | `Clean` | Headers, deduplication, IQR/Z-score outlier capping, format parsing. |
-| [`DataCheck.py`](DataCheck.py) | `DataGuard` | Pre-training safety audit (ID detection, target leakage, class imbalance). |
-| [`Visualization.py`](Visualization.py) | `Visualize` | EDA plots (missing, distribution, box, correlation) and real-time `plt.ion()`. |
-| [`Pipeline.py`](Pipeline.py) | `MLPipeline` | Leakage-free `fit`/`transform`, datetime extraction, encoding, scaling. |
-| [`FeatureSelector.py`](FeatureSelector.py) | `FeatureSelector` | Mutual Information ranking, collinearity pruning, variance threshold. |
-| [`ModelHyperparameter.py`](ModelHyperparameter.py) | `ModelHyperparameter` | Non-nested `GridSearchCV` and unbiased Nested Cross-Validation. |
-| [`EnsembleBuilder.py`](EnsembleBuilder.py) | `EnsembleBuilder` | Soft/Hard Voting and Stacking ensembles with meta-learners. |
-| [`Evaluation.py`](Evaluation.py) | `ModelEvaluator` | Confusion matrix, ROC-AUC, PR curves, and regression residuals. |
-| [`Explainability.py`](Explainability.py) | `ModelExplainer` | Native tree feature importances & permutation importance. |
-| [`ModelDeployer.py`](ModelDeployer.py) | `ModelDeployer` | Pipeline-model artifact bundling and 1-line prediction on raw data. |
-| [`DriftDetector.py`](DriftDetector.py) | `DriftDetector` | Kolmogorov-Smirnov (numbers) and Chi-Square (categories) drift tests. |
+| [`serverlex.preprocessing.clean`](serverlex/preprocessing/clean.py) | `Clean` | Headers, deduplication, IQR/Z-score outlier capping, format parsing. |
+| [`serverlex.diagnostics.dataguard`](serverlex/diagnostics/dataguard.py) | `DataGuard` | Pre-training safety audit (ID detection, target leakage, class imbalance). |
+| [`serverlex.visualization.eda`](serverlex/visualization/eda.py) | `Visualize` | EDA plots (missing, distribution, box, correlation) and real-time `plt.ion()`. |
+| [`serverlex.preprocessing.pipeline`](serverlex/preprocessing/pipeline.py) | `MLPipeline` | Leakage-free `fit`/`transform`, datetime extraction, encoding, scaling. |
+| [`serverlex.modeling.selector`](serverlex/modeling/selector.py) | `FeatureSelector` | Mutual Information ranking, collinearity pruning, variance threshold. |
+| [`serverlex.modeling.hyperparameter`](serverlex/modeling/hyperparameter.py) | `ModelHyperparameter` | Non-nested `GridSearchCV` and unbiased Nested Cross-Validation. |
+| [`serverlex.modeling.ensemble`](serverlex/modeling/ensemble.py) | `EnsembleBuilder` | Soft/Hard Voting and Stacking ensembles with meta-learners. |
+| [`serverlex.diagnostics.evaluation`](serverlex/diagnostics/evaluation.py) | `ModelEvaluator` | Confusion matrix, ROC-AUC, PR curves, and regression residuals. |
+| [`serverlex.diagnostics.explainability`](serverlex/diagnostics/explainability.py) | `ModelExplainer` | Native tree feature importances & permutation importance. |
+| [`serverlex.serving.deployer`](serverlex/serving/deployer.py) | `ModelDeployer` | Pipeline-model artifact bundling, schema validation, and raw inference. |
+| [`serverlex.diagnostics.drift`](serverlex/diagnostics/drift.py) | `DriftDetector` | KS-test, Chi-Square, PSI (Population Stability Index), and Wasserstein distance. |
+
+---
+
+## 🧪 Running Unit Tests & Benchmarks
+
+Run the complete test suite locally:
+```bash
+pytest -v tests/
+```
+
+Reproduce the exact Kaggle benchmarks:
+```bash
+python benchmarks/reproduce_benchmarks.py
+```
 
 ---
 
@@ -183,6 +196,11 @@ Serverlex was verified on real-world Kaggle datasets without custom code changes
 
 - **Customer Churn (`muhammadshahidazeem/customer-churn-dataset`)**:
   - `DataGuard` detected `CustomerID` as 100% unique ID and recommended removal.
+  - Leakage-free preprocessing reached **99.42% accuracy** using Gradient Boosting.
+
+- **Walmart Store Sales (`mikhail1681/walmart-sales`)**:
+  - Automatically extracted `year`, `month`, `day`, `dayofweek`, and `is_weekend` from dates.
+  - Achieved $R^2 = 0.9455$ and RMSE = 133,727 using Random Forest Regressor.
   - Baseline Gradient Boosting achieved **99.42% accuracy**.
   - `ModelExplainer` identified `support_calls` (0.277) and `total_spend` (0.235) as top drivers.
   

serverlex-1.2.0/Pipeline.py

@@ -0,0 +1,2 @@
+from serverlex.preprocessing.pipeline import MLPipeline
+__all__ = ["MLPipeline"]

{serverlex-1.0.0 → serverlex-1.2.0}/README.md

@@ -2,11 +2,10 @@
 **The Production-Safe Machine Learning Preprocessing, Diagnostics, & Serving Platform**
 
 [![Python Version](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11-blue.svg)](https://www.python.org/)
-[![PyPI](https://img.shields.io/badge/pypi-coming%20soon-orange.svg)](https://pypi.org/)
+[![PyPI version](https://img.shields.io/pypi/v/serverlex.svg?color=blue)](https://pypi.org/project/serverlex/)
+[![PyPI Downloads](https://img.shields.io/pypi/dm/serverlex.svg)](https://pypi.org/project/serverlex/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Code Style](https://img.shields.io/badge/code%20style-flat%20%26%20clean-green.svg)](https://github.com/)
-
-> 🚀 **Coming Soon to PyPI!** Serverlex is currently undergoing final release preparations and will soon be installable with a simple `pip install serverlex`. Star this repository to get notified when the initial PyPI package is published!
+[![Code Style](https://img.shields.io/badge/code%20style-flat%20%26%20clean-green.svg)](https://github.com/Uwais-ML/Serverlex)
 
 **Serverlex** is an end-to-end Python library that takes raw, dirty data and transforms it into model-ready features, baseline benchmarks, tuned algorithms, and live production endpoints—all without data leakage or boilerplate code.
 
@@ -14,17 +13,18 @@
 
 ## 📦 Installation
 
-### Coming Soon via PyPI:
+Install the official release directly from [PyPI](https://pypi.org/project/serverlex/):
+
 ```bash
 pip install serverlex
 ```
 
-### Current Installation (From GitHub / Source):
+### Or Install From Source / GitHub:
 ```bash
-# Direct from GitHub:
+# Latest development branch from GitHub:
 pip install git+https://github.com/Uwais-ML/Serverlex.git
 
-# Or install locally in editable mode:
+# Or clone and install in editable mode:
 git clone https://github.com/Uwais-ML/Serverlex.git
 cd Serverlex
 pip install -e .
@@ -138,17 +138,31 @@ print("Predicted Churn:", loaded_deployer.predict(raw_input)[0])
 
 | Module | Core Class | Primary Purpose |
 |---|---|---|
-| [`Clean.py`](Clean.py) | `Clean` | Headers, deduplication, IQR/Z-score outlier capping, format parsing. |
-| [`DataCheck.py`](DataCheck.py) | `DataGuard` | Pre-training safety audit (ID detection, target leakage, class imbalance). |
-| [`Visualization.py`](Visualization.py) | `Visualize` | EDA plots (missing, distribution, box, correlation) and real-time `plt.ion()`. |
-| [`Pipeline.py`](Pipeline.py) | `MLPipeline` | Leakage-free `fit`/`transform`, datetime extraction, encoding, scaling. |
-| [`FeatureSelector.py`](FeatureSelector.py) | `FeatureSelector` | Mutual Information ranking, collinearity pruning, variance threshold. |
-| [`ModelHyperparameter.py`](ModelHyperparameter.py) | `ModelHyperparameter` | Non-nested `GridSearchCV` and unbiased Nested Cross-Validation. |
-| [`EnsembleBuilder.py`](EnsembleBuilder.py) | `EnsembleBuilder` | Soft/Hard Voting and Stacking ensembles with meta-learners. |
-| [`Evaluation.py`](Evaluation.py) | `ModelEvaluator` | Confusion matrix, ROC-AUC, PR curves, and regression residuals. |
-| [`Explainability.py`](Explainability.py) | `ModelExplainer` | Native tree feature importances & permutation importance. |
-| [`ModelDeployer.py`](ModelDeployer.py) | `ModelDeployer` | Pipeline-model artifact bundling and 1-line prediction on raw data. |
-| [`DriftDetector.py`](DriftDetector.py) | `DriftDetector` | Kolmogorov-Smirnov (numbers) and Chi-Square (categories) drift tests. |
+| [`serverlex.preprocessing.clean`](serverlex/preprocessing/clean.py) | `Clean` | Headers, deduplication, IQR/Z-score outlier capping, format parsing. |
+| [`serverlex.diagnostics.dataguard`](serverlex/diagnostics/dataguard.py) | `DataGuard` | Pre-training safety audit (ID detection, target leakage, class imbalance). |
+| [`serverlex.visualization.eda`](serverlex/visualization/eda.py) | `Visualize` | EDA plots (missing, distribution, box, correlation) and real-time `plt.ion()`. |
+| [`serverlex.preprocessing.pipeline`](serverlex/preprocessing/pipeline.py) | `MLPipeline` | Leakage-free `fit`/`transform`, datetime extraction, encoding, scaling. |
+| [`serverlex.modeling.selector`](serverlex/modeling/selector.py) | `FeatureSelector` | Mutual Information ranking, collinearity pruning, variance threshold. |
+| [`serverlex.modeling.hyperparameter`](serverlex/modeling/hyperparameter.py) | `ModelHyperparameter` | Non-nested `GridSearchCV` and unbiased Nested Cross-Validation. |
+| [`serverlex.modeling.ensemble`](serverlex/modeling/ensemble.py) | `EnsembleBuilder` | Soft/Hard Voting and Stacking ensembles with meta-learners. |
+| [`serverlex.diagnostics.evaluation`](serverlex/diagnostics/evaluation.py) | `ModelEvaluator` | Confusion matrix, ROC-AUC, PR curves, and regression residuals. |
+| [`serverlex.diagnostics.explainability`](serverlex/diagnostics/explainability.py) | `ModelExplainer` | Native tree feature importances & permutation importance. |
+| [`serverlex.serving.deployer`](serverlex/serving/deployer.py) | `ModelDeployer` | Pipeline-model artifact bundling, schema validation, and raw inference. |
+| [`serverlex.diagnostics.drift`](serverlex/diagnostics/drift.py) | `DriftDetector` | KS-test, Chi-Square, PSI (Population Stability Index), and Wasserstein distance. |
+
+---
+
+## 🧪 Running Unit Tests & Benchmarks
+
+Run the complete test suite locally:
+```bash
+pytest -v tests/
+```
+
+Reproduce the exact Kaggle benchmarks:
+```bash
+python benchmarks/reproduce_benchmarks.py
+```
 
 ---
 
@@ -158,6 +172,11 @@ Serverlex was verified on real-world Kaggle datasets without custom code changes
 
 - **Customer Churn (`muhammadshahidazeem/customer-churn-dataset`)**:
   - `DataGuard` detected `CustomerID` as 100% unique ID and recommended removal.
+  - Leakage-free preprocessing reached **99.42% accuracy** using Gradient Boosting.
+
+- **Walmart Store Sales (`mikhail1681/walmart-sales`)**:
+  - Automatically extracted `year`, `month`, `day`, `dayofweek`, and `is_weekend` from dates.
+  - Achieved $R^2 = 0.9455$ and RMSE = 133,727 using Random Forest Regressor.
   - Baseline Gradient Boosting achieved **99.42% accuracy**.
   - `ModelExplainer` identified `support_calls` (0.277) and `total_spend` (0.235) as top drivers.
   

serverlex-1.2.0/Visualization.py

@@ -0,0 +1,2 @@
+from serverlex.visualization.eda import Visualize
+__all__ = ["Visualize"]

serverlex-1.2.0/pyproject.toml

@@ -0,0 +1,39 @@
+[build-system]
+requires = ["setuptools>=61.0.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "serverlex"
+version = "1.2.0"
+description = "Production-Safe ML Preprocessing, Diagnostics, Tuning, and Serving Platform"
+readme = "README.md"
+authors = [{ name = "Serverlex Team" }]
+license = { text = "MIT" }
+requires-python = ">=3.9"
+dependencies = [
+    "pandas>=2.0.0",
+    "numpy>=1.24.0",
+    "scipy>=1.10.0",
+    "matplotlib>=3.7.0",
+    "scikit-learn>=1.3.0",
+    "joblib>=1.3.0"
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence"
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-cov>=4.0.0",
+    "flake8>=6.0.0"
+]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]

serverlex-1.2.0/serverlex/__init__.py

@@ -0,0 +1,27 @@
+from serverlex.preprocessing.clean import Clean
+from serverlex.preprocessing.pipeline import MLPipeline
+from serverlex.diagnostics.dataguard import DataGuard
+from serverlex.diagnostics.evaluation import ModelEvaluator
+from serverlex.diagnostics.explainability import ModelExplainer
+from serverlex.diagnostics.drift import DriftDetector
+from serverlex.modeling.hyperparameter import ModelHyperparameter
+from serverlex.modeling.ensemble import EnsembleBuilder
+from serverlex.modeling.selector import FeatureSelector
+from serverlex.visualization.eda import Visualize
+from serverlex.serving.deployer import ModelDeployer
+
+__all__ = [
+    "Clean",
+    "MLPipeline",
+    "DataGuard",
+    "ModelEvaluator",
+    "ModelExplainer",
+    "DriftDetector",
+    "ModelHyperparameter",
+    "EnsembleBuilder",
+    "FeatureSelector",
+    "Visualize",
+    "ModelDeployer",
+]
+
+__version__ = "1.2.0"

serverlex-1.2.0/serverlex/diagnostics/__init__.py

@@ -0,0 +1,6 @@
+from .dataguard import DataGuard
+from .evaluation import ModelEvaluator
+from .explainability import ModelExplainer
+from .drift import DriftDetector
+
+__all__ = ["DataGuard", "ModelEvaluator", "ModelExplainer", "DriftDetector"]

serverlex-1.0.0/DataCheck.py → serverlex-1.2.0/serverlex/diagnostics/dataguard.py

@@ -12,8 +12,9 @@ if not logger.handlers:
 
 
 class DataGuard:
-    def __init__(self, df=None):
+    def __init__(self, df=None, target=None):
         self.data=df.copy() if df is not None else None
+        self.target=target
         self.warnings=[]
         self.id_cols=[]
         self.leakage_cols=[]
@@ -24,14 +25,14 @@ class DataGuard:
         self.warnings=[]
 
     # 1. Detect ID Columns
-    def check_id_columns(self):
+    def check_id_columns(self, threshold=0.95):
         try:
             self.id_cols=[]
             for col in self.data.columns:
                 unique_ratio=self.data[col].nunique(dropna=True) / len(self.data)
                 is_name_id=bool(re.search(r'(id|uuid|key|ssn|index|identifier)$', col.lower()))
 
-                if (unique_ratio > 0.95 and is_name_id) or (unique_ratio == 1.0 and self.data[col].dtype == 'object'):
+                if (unique_ratio >= threshold and is_name_id) or (unique_ratio == 1.0 and self.data[col].dtype == 'object'):
                     self.id_cols.append(col)
                     logger.warning("Potential unique ID column detected: '%s' (uniqueness: %.1f%%)", col, unique_ratio * 100)
 
@@ -45,114 +46,127 @@ class DataGuard:
             return self.id_cols
         except Exception as e:
             logger.error("Error in check_id_columns: %s", e)
+            return []
 
     # 2. Check Target Leakage
-    def check_target_leakage(self, target, threshold=0.95):
+    def check_target_leakage(self, target=None, threshold=0.90):
         try:
             self.leakage_cols=[]
-            if target not in self.data.columns:
-                return
-
-            num_cols=self.data.select_dtypes(include='number')
-            if target in num_cols.columns:
-                corrs=num_cols.corr().abs()[target]
+            target_to_use=target or self.target
+            if not target_to_use or target_to_use not in self.data.columns:
+                return []
+
+            num_cols=self.data.select_dtypes(include='number').copy()
+            if target_to_use not in num_cols.columns:
+                try:
+                    num_cols[target_to_use]=pd.to_numeric(self.data[target_to_use])
+                except Exception:
+                    num_cols[target_to_use]=self.data[target_to_use].astype('category').cat.codes
+
+            if target_to_use in num_cols.columns:
+                corrs=num_cols.corr().abs()[target_to_use]
                 for col, val in corrs.items():
-                    if col != target and val >= threshold:
+                    if col != target_to_use and val >= threshold:
                         self.leakage_cols.append((col, round(val, 4)))
-                        logger.error("Suspicious target leakage: feature '%s' has correlation %.4f with target '%s'", col, val, target)
+                        logger.error("Suspicious target leakage: feature '%s' has correlation %.4f with target '%s'", col, val, target_to_use)
 
             if self.leakage_cols:
                 self.warnings.append({
                     "Check": "Target Leakage",
                     "Status": "FAIL",
-                    "Details": f"Features {self.leakage_cols} have correlation >= {threshold} with target '{target}'.",
+                    "Details": f"Features {self.leakage_cols} have correlation >= {threshold} with target '{target_to_use}'.",
                     "Fix": "Verify if these columns contain future data."
                 })
             return self.leakage_cols
         except Exception as e:
             logger.error("Error in check_target_leakage: %s", e)
+            return []
 
     # 3. Check Class Imbalance
-    def check_class_imbalance(self, target):
+    def check_class_imbalance(self, target=None):
         try:
-            if target not in self.data.columns:
+            target_to_use=target or self.target
+            if not target_to_use or target_to_use not in self.data.columns:
                 return
 
-            counts=self.data[target].value_counts(normalize=True)
-            if len(counts) <= 20: # Classification
-                max_prop=counts.max()
-                min_prop=counts.min()
-                imbalance_ratio=round(max_prop / min_prop, 2)
-
-                if max_prop >= 0.70:
-                    status="WARN" if max_prop < 0.90 else "FAIL"
-                    logger.warning("Class imbalance in '%s': dominant class is %.1f%% (ratio %.2f:1)", target, max_prop * 100, imbalance_ratio)
+            counts=self.data[target_to_use].value_counts(normalize=True)
+            if len(counts) > 1 and len(counts) <= 20:
+                minority_prop=counts.min()
+                if minority_prop < 0.10:
+                    logger.warning("High class imbalance detected in '%s': minority class is %.2f%%", target_to_use, minority_prop * 100)
                     self.warnings.append({
                         "Check": "Class Imbalance",
-                        "Status": status,
-                        "Details": f"Dominant class represents {max_prop:.1%} (ratio: {imbalance_ratio}:1).",
-                        "Fix": "Use class_weight='balanced' or resampling."
+                        "Status": "WARN",
+                        "Details": f"Minority class proportion is {minority_prop:.2%}.",
+                        "Fix": "Use SMOTE, class weights, or stratified cross-validation."
                     })
         except Exception as e:
             logger.error("Error in check_class_imbalance: %s", e)
 
-    # 4. Check High-Cardinality Categoricals
-    def check_cardinality(self, threshold=30):
+    # 4. Check High Cardinality
+    def check_cardinality(self, threshold=100):
         try:
             self.high_cardinality_cols=[]
-            cat_cols=self.data.select_dtypes(include=['object', 'category']).columns
+            cat_cols=self.data.select_dtypes(include=['object', 'category', 'string']).columns
 
             for col in cat_cols:
                 n_unique=self.data[col].nunique()
-                if n_unique > threshold:
+                if n_unique > threshold and col not in self.id_cols:
                     self.high_cardinality_cols.append((col, n_unique))
-                    logger.warning("High cardinality in category '%s': %d unique values", col, n_unique)
+                    logger.warning("High cardinality column '%s': %d unique values", col, n_unique)
 
             if self.high_cardinality_cols:
                 self.warnings.append({
                     "Check": "High Cardinality",
                     "Status": "WARN",
-                    "Details": f"Columns {self.high_cardinality_cols} exceed {threshold} unique values.",
-                    "Fix": "Use label encoding or group rare categories."
+                    "Details": f"Categorical columns {self.high_cardinality_cols} have > {threshold} unique categories.",
+                    "Fix": "Use Target/Frequency Encoding or group rare categories."
                 })
+            return self.high_cardinality_cols
         except Exception as e:
             logger.error("Error in check_cardinality: %s", e)
+            return []
 
-    # 5. Check Infinite Values
+    # 5. Check Infinite or Extreme Values
     def check_infinite_values(self):
         try:
             num_cols=self.data.select_dtypes(include='number').columns
             inf_cols=[]
+
             for col in num_cols:
-                if np.isinf(self.data[col]).any():
-                    inf_cols.append(col)
-                    logger.error("Infinite values detected in column '%s'", col)
+                inf_count=np.isinf(self.data[col]).sum()
+                if inf_count > 0:
+                    inf_cols.append((col, int(inf_count)))
+                    logger.error("Infinite values detected in '%s': %d occurrences", col, inf_count)
 
             if inf_cols:
                 self.warnings.append({
                     "Check": "Infinite Values",
                     "Status": "FAIL",
-                    "Details": f"Columns {inf_cols} contain inf / -inf.",
-                    "Fix": "Replace inf values with NaN or bounds."
+                    "Details": f"Columns {inf_cols} contain infinity (+inf or -inf).",
+                    "Fix": "Replace infinite values with NaN or bounds."
                 })
+            return inf_cols
         except Exception as e:
             logger.error("Error in check_infinite_values: %s", e)
+            return []
 
     # ==========================
     # Master Health Audit Runner
     # ==========================
-    def run_audit(self, target=None):
+    def run_audit(self, target=None, leakage_threshold=0.90, id_threshold=0.95, cardinality_threshold=100):
         try:
             self.warnings=[]
             logger.info("Running data quality audit on %d rows, %d columns", len(self.data), len(self.data.columns))
 
-            self.check_id_columns()
+            self.check_id_columns(threshold=id_threshold)
             self.check_infinite_values()
-            self.check_cardinality()
+            self.check_cardinality(threshold=cardinality_threshold)
 
-            if target:
-                self.check_target_leakage(target)
-                self.check_class_imbalance(target)
+            target_to_use=target or self.target
+            if target_to_use:
+                self.check_target_leakage(target=target_to_use, threshold=leakage_threshold)
+                self.check_class_imbalance(target=target_to_use)
 
             if not self.warnings:
                 logger.info("Quality audit completed: all checks passed")
@@ -163,3 +177,4 @@ class DataGuard:
             return report_df
         except Exception as e:
             logger.error("Error in run_audit: %s", e)
+            return pd.DataFrame()