# gsaiteja25/hr_analytics architecture

> Architecture diagram of the GitHub repository gsaiteja25/hr_analytics, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/gsaiteja25/hr_analytics
- Repository: https://github.com/gsaiteja25/hr_analytics

## Overview

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_Attrition_Advanced_v2/data/HR_Employee_Attrition.csv`](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/data/HR_Employee_Attrition.csv) (Employee Dataset), [`HR_Attrition_Advanced_v2/src/pipeline.py`](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/pipeline.py) (Model Training), [`HR_Attrition_Advanced_v2/models/attrition_model.joblib`](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/models/attrition_model.joblib) (Saved Model), [`HR_Attrition_Advanced_v2/src/shap_analysis.py`](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/shap_analysis.py) (SHAP Analysis)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Employee Data"]
  node_dataset[("Employee Dataset")]
  node_data_download["Data Download<br/>[download_data.py]"]
end

subgraph group_modeling["Modeling Pipeline"]
  node_loader["Data Loading<br/>[pipeline.py]"]
  node_features["Feature Engineering<br/>[pipeline.py]"]
  node_training["Model Training<br/>[pipeline.py]"]
  node_evaluation["Model Evaluation<br/>[pipeline.py]"]
end

subgraph group_analysis["Model Analysis"]
  node_shap["SHAP Analysis<br/>[shap_analysis.py]"]
  node_fairness["Group Audit<br/>[fairness_audit.py]"]
  node_audit_output["Audit Results<br/>[group_audit.csv]"]
end

subgraph group_delivery["Prediction and Exports"]
  node_model_artifact[("Saved Model")]
  node_streamlit["Prediction App<br/>[streamlit_app.py]"]
  node_pipeline_outputs["Pipeline Reports"]
end

node_user(("HR User"))

node_data_download -->|"downloads"| node_dataset
node_dataset -->|"reads"| node_loader
node_loader -->|"passes data"| node_features
node_features -->|"provides features"| node_training
node_training -->|"evaluates models"| node_evaluation
node_training -->|"saves selected model"| node_model_artifact
node_evaluation -->|"writes reports"| node_pipeline_outputs
node_user -->|"enters profile"| node_streamlit
node_model_artifact -->|"loads model"| node_streamlit
node_streamlit -->|"shows risk"| node_user
node_dataset -->|"reads records"| node_shap
node_model_artifact -->|"loads model"| node_shap
node_shap -->|"reuses engineering"| node_features
node_pipeline_outputs -->|"reads predictions"| node_fairness
node_fairness -->|"writes audit"| node_audit_output

click node_dataset "https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/data/HR_Employee_Attrition.csv"
click node_data_download "https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/download_data.py"
click node_loader "https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/pipeline.py"
click node_features "https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/pipeline.py"
click node_training "https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/pipeline.py"
click node_evaluation "https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/pipeline.py"
click node_model_artifact "https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/models/attrition_model.joblib"
click node_streamlit "https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/app/streamlit_app.py"
click node_pipeline_outputs "https://github.com/gsaiteja25/hr_analytics/tree/main/HR_Attrition_Advanced_v2/outputs"
click node_shap "https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/shap_analysis.py"
click node_fairness "https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/fairness_audit.py"
click node_audit_output "https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/outputs/group_audit.csv"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_dataset,node_data_download,node_user toneBlue
class node_loader,node_features,node_training,node_evaluation toneAmber
class node_shap,node_fairness,node_audit_output toneMint
class node_model_artifact,node_streamlit,node_pipeline_outputs toneRose
```

## Components

### Employee Data

- [Employee Dataset](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/data/HR_Employee_Attrition.csv): `HR_Attrition_Advanced_v2/data/HR_Employee_Attrition.csv`
- [Data Download](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/download_data.py): `HR_Attrition_Advanced_v2/src/download_data.py`

### Modeling Pipeline

- [Data Loading](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/pipeline.py): `HR_Attrition_Advanced_v2/src/pipeline.py`
- [Feature Engineering](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/pipeline.py): `HR_Attrition_Advanced_v2/src/pipeline.py`
- [Model Training](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/pipeline.py): `HR_Attrition_Advanced_v2/src/pipeline.py`
- [Model Evaluation](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/pipeline.py): `HR_Attrition_Advanced_v2/src/pipeline.py`

### Model Analysis

- [SHAP Analysis](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/shap_analysis.py): `HR_Attrition_Advanced_v2/src/shap_analysis.py`
- [Group Audit](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/src/fairness_audit.py): `HR_Attrition_Advanced_v2/src/fairness_audit.py`
- [Audit Results](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/outputs/group_audit.csv): `HR_Attrition_Advanced_v2/outputs/group_audit.csv`

### Prediction and Exports

- [Saved Model](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/models/attrition_model.joblib): `HR_Attrition_Advanced_v2/models/attrition_model.joblib`
- [Prediction App](https://github.com/gsaiteja25/hr_analytics/blob/main/HR_Attrition_Advanced_v2/app/streamlit_app.py): `HR_Attrition_Advanced_v2/app/streamlit_app.py`
- [Pipeline Reports](https://github.com/gsaiteja25/hr_analytics/tree/main/HR_Attrition_Advanced_v2/outputs): `HR_Attrition_Advanced_v2/outputs`

### Other components

- **HR User**

## Connections

- Data Download → Employee Dataset: downloads (evidence: `HR_Attrition_Advanced_v2/src/download_data.py`)
- Employee Dataset → Data Loading: reads (evidence: `HR_Attrition_Advanced_v2/src/pipeline.py`)
- Data Loading → Feature Engineering: passes data (evidence: `HR_Attrition_Advanced_v2/src/pipeline.py`)
- Feature Engineering → Model Training: provides features (evidence: `HR_Attrition_Advanced_v2/src/pipeline.py`)
- Model Training → Model Evaluation: evaluates models (evidence: `HR_Attrition_Advanced_v2/src/pipeline.py`)
- Model Training → Saved Model: saves selected model (evidence: `HR_Attrition_Advanced_v2/src/pipeline.py`)
- Model Evaluation → Pipeline Reports: writes reports (evidence: `HR_Attrition_Advanced_v2/src/pipeline.py`)
- HR User → Prediction App: enters profile (evidence: `HR_Attrition_Advanced_v2/app/streamlit_app.py`)
- Saved Model → Prediction App: loads model (evidence: `HR_Attrition_Advanced_v2/app/streamlit_app.py`)
- Prediction App → HR User: shows risk (evidence: `HR_Attrition_Advanced_v2/app/streamlit_app.py`)
- Employee Dataset → SHAP Analysis: reads records (evidence: `HR_Attrition_Advanced_v2/src/shap_analysis.py`)
- Saved Model → SHAP Analysis: loads model (evidence: `HR_Attrition_Advanced_v2/src/shap_analysis.py`)
- SHAP Analysis → Feature Engineering: reuses engineering (evidence: `HR_Attrition_Advanced_v2/src/shap_analysis.py`)
- Pipeline Reports → Group Audit: reads predictions (evidence: `HR_Attrition_Advanced_v2/src/fairness_audit.py`)
- Group Audit → Audit Results: writes audit (evidence: `HR_Attrition_Advanced_v2/src/fairness_audit.py`)
