serverlex 1.2.2__tar.gz → 1.3.0__tar.gz

{serverlex-1.2.2 → serverlex-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: serverlex
-Version: 1.2.2
+Version: 1.3.0
 Summary: Production-Safe ML Preprocessing, Diagnostics, Tuning, and Serving Platform
 Author: Serverlex Team
 License: MIT
@@ -27,22 +27,24 @@ Dynamic: requires-python
 
 [![Python Version](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue.svg)](https://www.python.org/)
 [![PyPI version](https://img.shields.io/pypi/v/serverlex.svg?color=blue)](https://pypi.org/project/serverlex/)
-[![Tests](https://img.shields.io/badge/tests-35%20passed-brightgreen.svg)](https://github.com/Uwais-ML/Serverlex/actions)
+[![Tests](https://img.shields.io/badge/tests-47%20passed-brightgreen.svg)](https://github.com/Uwais-ML/Serverlex/actions)
 [![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-production%20safe-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—with mathematical guarantees against data leakage, train/serve skew, and corrupted inference.
+**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 — with leakage-safe preprocessing (pipeline params are fit on training data only and locked at inference), train/serve parity guarantees, and cryptographically signed model artifacts.
 
 ---
 
 ## 🚀 Key Highlights & Guarantees
 
-- **Zero Data Leakage**: Pipeline parameters (medians, modes, one-hot category vocabularies, scaler stats) are strictly computed on training splits and locked during inference.
-- **Exact Train/Serve Parity**: Predict on single records (`dict`), small micro-batches, or large DataFrames with exact prediction equivalence and zero categorical drift.
-- **Degenerate-Safe Outlier Cleaning**: Cell-wise IQR and Z-score handling protects binary flags, class targets, and degenerate discrete distributions from collapsing bounds.
+- **Zero Data Leakage & Auto-Remediation**: Pipeline parameters are strictly computed on training splits. `auto_remediate=True` auto-drops ID columns, PII, and target proxies ($r \ge 0.90$).
+- **Turnkey FastAPI & Docker Export**: `ModelDeployer.export_api()` generates a production REST microservice with Swagger docs, Pydantic validation, and a Dockerfile in 1 line.
+- **Pre-Inference Latency & SLA Profiler**: `ModelDeployer.benchmark()` calculates p50, p95, p99 latency (ms) and throughput (req/s) before deployment.
+- **Standalone HTML Audit Dashboards**: `DataGuard.to_html_report()` creates a self-contained, dark-mode report with dataset Health Scores (A+ to F).
+- **Production Drift Webhook Alerts**: `DriftDetector.detect_drift(alert_webhook=...)` fires automated JSON alerts to Slack/PagerDuty when population shift exceeds thresholds.
+- **Collinearity & Ratio Pruning**: `FeatureSelector.prune_collinear()` removes redundant collinear duplicates while preserving features with higher predictive power.
+- **Exact Train/Serve Parity**: Predict on single records (`dict`), micro-batches, or DataFrames with exact prediction equivalence and zero categorical drift.
 - **Enterprise Serving Security**: Cryptographic SHA-256 sidecar verification and HMAC-SHA256 authenticity checks prevent untrusted model deserialization.
-- **Statistical Drift Monitoring**: Combines Kolmogorov-Smirnov, Chi-Square, Wasserstein distance, and finite-sample corrected Population Stability Index (PSI) to eliminate small-batch false alarms.
-- **High-Throughput Serving**: Sub-10ms p50 single-record inference latency ready for microservices and API gateways.
 
 ---
 
@@ -109,10 +111,17 @@ from serverlex import (
 df = pd.read_csv("customers.csv")
 
 # 2. Automated Quality Audit (catches ID columns, target leakage, class imbalance)
-guard = DataGuard(df)
-audit_report = guard.run_audit(target="churn")
+guard = DataGuard(df, target="churn")
+audit_report = guard.run_audit(leakage_threshold=0.90, id_threshold=0.95)
+
+# Drop detected ID / PII columns before fitting — DataGuard advises, pipeline enforces.
+# MLPipeline also auto-skips ID columns internally (drop_id_cols=True by default),
+# but explicit dropping here keeps your training frame clean.
+cols_to_drop = [c for c in guard.id_cols if c in df.columns]
+if cols_to_drop:
+    df = df.drop(columns=cols_to_drop)
 
-# 3. Fit Pipeline on Training Data (Zero Data Leakage)
+# 3. Fit Pipeline on Training Data (Leakage-Safe)
 train_df = df.iloc[:800].copy()
 test_df = df.iloc[800:].copy()
 
@@ -258,7 +267,7 @@ evaluator.plot_confusion_matrix(y_test, preds, save_path="confusion_matrix.png")
 
 ## 🧪 Testing & Verification
 
-Serverlex features a comprehensive automated test suite with **35 unit and regression tests** covering train/serve parity, outlier preservation, crypto authenticity, and drift edge cases:
+Serverlex features a comprehensive automated test suite with **47 unit and regression tests** covering train/serve parity, outlier preservation, crypto authenticity, and drift edge cases:
 
 ```bash
 # Run the test suite:
@@ -272,17 +281,17 @@ python benchmarks/reproduce_benchmarks.py
 
 ---
 
-## 🏆 Real-World Kaggle Verification
+## 🏆 Real-World Validation
 
 Serverlex has been validated on benchmark datasets:
 
 - **Customer Churn (`muhammadshahidazeem/customer-churn-dataset`)**:
-  - `DataGuard` detected `CustomerID` as 100% unique identifier and pruned it.
+  - `DataGuard` correctly flagged `CustomerID` as a 100% unique identifier and excluded it from encoding.
   - Cell-wise outlier clipping preserved `churn` distribution with zero label alteration.
-  - Baseline Gradient Boosting achieved **99.42% accuracy**.
+  - Cross-validated accuracy on clean data (no ID leakage): results vary by CV split and hyperparameters — benchmark on your own data.
 - **Walmart Store Sales (`mikhail1681/walmart-sales`)**:
   - Extracted temporal features from dates (`year`, `month`, `day`, `dayofweek`).
-  - Random Forest Regressor trained to **$R^2 = 0.9455$** ($\text{RMSE} = 133,727$).
+  - Random Forest Regressor trained to **$R^2 = 0.9455$** ($\text{RMSE} = 133{,}727$).
 
 ---
 

{serverlex-1.2.2 → serverlex-1.3.0}/README.md

@@ -3,22 +3,24 @@
 
 [![Python Version](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue.svg)](https://www.python.org/)
 [![PyPI version](https://img.shields.io/pypi/v/serverlex.svg?color=blue)](https://pypi.org/project/serverlex/)
-[![Tests](https://img.shields.io/badge/tests-35%20passed-brightgreen.svg)](https://github.com/Uwais-ML/Serverlex/actions)
+[![Tests](https://img.shields.io/badge/tests-47%20passed-brightgreen.svg)](https://github.com/Uwais-ML/Serverlex/actions)
 [![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-production%20safe-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—with mathematical guarantees against data leakage, train/serve skew, and corrupted inference.
+**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 — with leakage-safe preprocessing (pipeline params are fit on training data only and locked at inference), train/serve parity guarantees, and cryptographically signed model artifacts.
 
 ---
 
 ## 🚀 Key Highlights & Guarantees
 
-- **Zero Data Leakage**: Pipeline parameters (medians, modes, one-hot category vocabularies, scaler stats) are strictly computed on training splits and locked during inference.
-- **Exact Train/Serve Parity**: Predict on single records (`dict`), small micro-batches, or large DataFrames with exact prediction equivalence and zero categorical drift.
-- **Degenerate-Safe Outlier Cleaning**: Cell-wise IQR and Z-score handling protects binary flags, class targets, and degenerate discrete distributions from collapsing bounds.
+- **Zero Data Leakage & Auto-Remediation**: Pipeline parameters are strictly computed on training splits. `auto_remediate=True` auto-drops ID columns, PII, and target proxies ($r \ge 0.90$).
+- **Turnkey FastAPI & Docker Export**: `ModelDeployer.export_api()` generates a production REST microservice with Swagger docs, Pydantic validation, and a Dockerfile in 1 line.
+- **Pre-Inference Latency & SLA Profiler**: `ModelDeployer.benchmark()` calculates p50, p95, p99 latency (ms) and throughput (req/s) before deployment.
+- **Standalone HTML Audit Dashboards**: `DataGuard.to_html_report()` creates a self-contained, dark-mode report with dataset Health Scores (A+ to F).
+- **Production Drift Webhook Alerts**: `DriftDetector.detect_drift(alert_webhook=...)` fires automated JSON alerts to Slack/PagerDuty when population shift exceeds thresholds.
+- **Collinearity & Ratio Pruning**: `FeatureSelector.prune_collinear()` removes redundant collinear duplicates while preserving features with higher predictive power.
+- **Exact Train/Serve Parity**: Predict on single records (`dict`), micro-batches, or DataFrames with exact prediction equivalence and zero categorical drift.
 - **Enterprise Serving Security**: Cryptographic SHA-256 sidecar verification and HMAC-SHA256 authenticity checks prevent untrusted model deserialization.
-- **Statistical Drift Monitoring**: Combines Kolmogorov-Smirnov, Chi-Square, Wasserstein distance, and finite-sample corrected Population Stability Index (PSI) to eliminate small-batch false alarms.
-- **High-Throughput Serving**: Sub-10ms p50 single-record inference latency ready for microservices and API gateways.
 
 ---
 
@@ -85,10 +87,17 @@ from serverlex import (
 df = pd.read_csv("customers.csv")
 
 # 2. Automated Quality Audit (catches ID columns, target leakage, class imbalance)
-guard = DataGuard(df)
-audit_report = guard.run_audit(target="churn")
+guard = DataGuard(df, target="churn")
+audit_report = guard.run_audit(leakage_threshold=0.90, id_threshold=0.95)
+
+# Drop detected ID / PII columns before fitting — DataGuard advises, pipeline enforces.
+# MLPipeline also auto-skips ID columns internally (drop_id_cols=True by default),
+# but explicit dropping here keeps your training frame clean.
+cols_to_drop = [c for c in guard.id_cols if c in df.columns]
+if cols_to_drop:
+    df = df.drop(columns=cols_to_drop)
 
-# 3. Fit Pipeline on Training Data (Zero Data Leakage)
+# 3. Fit Pipeline on Training Data (Leakage-Safe)
 train_df = df.iloc[:800].copy()
 test_df = df.iloc[800:].copy()
 
@@ -234,7 +243,7 @@ evaluator.plot_confusion_matrix(y_test, preds, save_path="confusion_matrix.png")
 
 ## 🧪 Testing & Verification
 
-Serverlex features a comprehensive automated test suite with **35 unit and regression tests** covering train/serve parity, outlier preservation, crypto authenticity, and drift edge cases:
+Serverlex features a comprehensive automated test suite with **47 unit and regression tests** covering train/serve parity, outlier preservation, crypto authenticity, and drift edge cases:
 
 ```bash
 # Run the test suite:
@@ -248,17 +257,17 @@ python benchmarks/reproduce_benchmarks.py
 
 ---
 
-## 🏆 Real-World Kaggle Verification
+## 🏆 Real-World Validation
 
 Serverlex has been validated on benchmark datasets:
 
 - **Customer Churn (`muhammadshahidazeem/customer-churn-dataset`)**:
-  - `DataGuard` detected `CustomerID` as 100% unique identifier and pruned it.
+  - `DataGuard` correctly flagged `CustomerID` as a 100% unique identifier and excluded it from encoding.
   - Cell-wise outlier clipping preserved `churn` distribution with zero label alteration.
-  - Baseline Gradient Boosting achieved **99.42% accuracy**.
+  - Cross-validated accuracy on clean data (no ID leakage): results vary by CV split and hyperparameters — benchmark on your own data.
 - **Walmart Store Sales (`mikhail1681/walmart-sales`)**:
   - Extracted temporal features from dates (`year`, `month`, `day`, `dayofweek`).
-  - Random Forest Regressor trained to **$R^2 = 0.9455$** ($\text{RMSE} = 133,727$).
+  - Random Forest Regressor trained to **$R^2 = 0.9455$** ($\text{RMSE} = 133{,}727$).
 
 ---
 

{serverlex-1.2.2 → serverlex-1.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "serverlex"
-version = "1.2.2"
+version = "1.3.0"
 description = "Production-Safe ML Preprocessing, Diagnostics, Tuning, and Serving Platform"
 readme = "README.md"
 authors = [{ name = "Serverlex Team" }]

{serverlex-1.2.2 → serverlex-1.3.0}/serverlex/__init__.py

@@ -24,4 +24,4 @@ __all__ = [
     "ModelDeployer",
 ]
 
-__version__ = "1.2.2"
+__version__ = "1.3.0"