How gsaiteja25/hr_analytics works
This is an HR attrition prediction and analysis project. The main workflow loads employee records, engineers features, trains and evaluates classifiers, saves a selected model, and uses it in a Streamlit form to display an individual risk estimate. Separate scripts add SHAP explanations and group-performance audits; the pipeline also produces analytical exports, including a Power BI dataset. The source excerpts support these main relationships, but the README content was not provided, so undocumented capabilities and connections are omitted.
Main entry points: HR_Employee_Attrition.csv Employee Dataset · pipeline.py Model Training · attrition_model.joblib Saved Model · shap_analysis.py SHAP Analysis
Components 13
Employee Data
- Employee Dataset
HR_Attrition_Advanced_v2/data/HR_Employee_Attrition.csv - Data Download
HR_Attrition_Advanced_v2/src/download_data.py
Modeling Pipeline
- Data Loading
HR_Attrition_Advanced_v2/src/pipeline.py - Feature Engineering
HR_Attrition_Advanced_v2/src/pipeline.py - Model Training
HR_Attrition_Advanced_v2/src/pipeline.py - Model Evaluation
HR_Attrition_Advanced_v2/src/pipeline.py
Model Analysis
- SHAP Analysis
HR_Attrition_Advanced_v2/src/shap_analysis.py - Group Audit
HR_Attrition_Advanced_v2/src/fairness_audit.py - Audit Results
HR_Attrition_Advanced_v2/outputs/group_audit.csv
Prediction and Exports
- Saved Model
HR_Attrition_Advanced_v2/models/attrition_model.joblib - Prediction App
HR_Attrition_Advanced_v2/app/streamlit_app.py - Pipeline Reports
HR_Attrition_Advanced_v2/outputs
Other components
- HR User
Connections 15
- Data Download → Employee Dataset: downloads
HR_Attrition_Advanced_v2/src/download_data.py - Employee Dataset → Data Loading: reads
HR_Attrition_Advanced_v2/src/pipeline.py - Data Loading → Feature Engineering: passes data
HR_Attrition_Advanced_v2/src/pipeline.py - Feature Engineering → Model Training: provides features
HR_Attrition_Advanced_v2/src/pipeline.py - Model Training → Model Evaluation: evaluates models
HR_Attrition_Advanced_v2/src/pipeline.py - Model Training → Saved Model: saves selected model
HR_Attrition_Advanced_v2/src/pipeline.py - Model Evaluation → Pipeline Reports: writes reports
HR_Attrition_Advanced_v2/src/pipeline.py - HR User → Prediction App: enters profile
HR_Attrition_Advanced_v2/app/streamlit_app.py - Saved Model → Prediction App: loads model
HR_Attrition_Advanced_v2/app/streamlit_app.py - Prediction App → HR User: shows risk
HR_Attrition_Advanced_v2/app/streamlit_app.py - Employee Dataset → SHAP Analysis: reads records
HR_Attrition_Advanced_v2/src/shap_analysis.py - Saved Model → SHAP Analysis: loads model
HR_Attrition_Advanced_v2/src/shap_analysis.py - SHAP Analysis → Feature Engineering: reuses engineering
HR_Attrition_Advanced_v2/src/shap_analysis.py - Pipeline Reports → Group Audit: reads predictions
HR_Attrition_Advanced_v2/src/fairness_audit.py - Group Audit → Audit Results: writes audit
HR_Attrition_Advanced_v2/src/fairness_audit.py