galafis/Predictive-Analytics-Engine
Predictive analytics with scikit-learn: classification/regression pipelines, preprocessing, visualization, and model evaluation metrics
What's novel
Predictive analytics with scikit-learn: classification/regression pipelines, preprocessing, visualization, and model evaluation metrics
Code Analysis
13 files read · 4 roundsA thin scikit-learn wrapper that loads tabular data from multiple file formats, applies basic preprocessing (imputation, scaling, one-hot encoding), and trains LogisticRegression or LinearRegression models, with a standalone demo in main.py that uses RandomForest on synthetic data.
Strengths
The preprocessor module is well-structured with proper ColumnTransformer usage, and the test suite covers all major modules with reasonable edge cases. The data loader supports multiple formats with caching and validation.
Weaknesses
The core engine (PredictiveAnalyticsEngine) is fundamentally broken due to a critical import bug in visualization.py (class defined under __main__ guard), and the README significantly overstates the project's capabilities with claims of SOLID principles, factory patterns, and extensible architecture that don't match the thin sklearn wrappers in the code.
Score Breakdown
Signal breakdown
Innovation
Craft
Traction
Scope
Evidence
Commits
38
Contributors
1
Files
26
Active weeks
6
Repository
Language
Python
Stars
1
Forks
0
License
MIT