KO
|
EN
gitlite — search
Search
#typescript
#ai-agents
#ai
#dsh-plugin
#deepseek-harness
#open-source
#cli
#claude-code
#codex
#developer-tools
#react
#windows
Churn-predictor
★ 53
Open GitHub ↗
No description available.
Download README (.md)
Explore Similar Repositories
verl-internvl
:
No description available.
PsyLLM
:
Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling
awesome-zk-proofs
:
Resources for learning zero knowledge proof systems
abs-agg
:
An flexible custom metadata provider
Rank-GRPO
:
(ICLR'26 + Netflix) Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
// repository documentation
Was this content helpful?
★ 0
(0 ratings)
Select Rating:
★
★
★
★
★
Submit Feedback
Recent Feedback
×
Download README
Do you want to download the
README.md
file for
Churn-predictor
?
Download (.md)
# SaaS Churn Prediction System Advanced churn prediction system using FastAPI, SHAP, and XGBoost/RandomForest. Runs purely offline on CPU. ## Project Structure ``` ├── app/ # FastAPI application ├── config/ # Configuration files ├── data/ # Dataset storage ├── models/ # Saved models and metrics ├── src/ # Source code │ ├── data/ # Data loading │ ├── evaluation/ # Metrics & Plotting │ ├── explainability/ # SHAP utilities │ ├── features/ # Feature engineering │ └── models/ # Training pipeline ├── requirements.txt ├── run_pipeline.py # Automation script └── README.md ``` ## Setup 1. Install dependencies: ```bash pip install -r requirements.txt ``` ## Training Run the full training pipeline: ```bash python run_pipeline.py ``` This will: - Load `data/churn2.csv` - Preprocess and engineer features (Ratio features, OHE) - Train Logistic Regression, Random Forest, and XGBoost (with SMOTE) - Optimize hyperparameters - Save the best model to `models/best_model.pkl` - Save metrics to `models/metrics.json` ## API Usage Start the FastAPI server: ```bash uvicorn app.main:app --host 0.0.0.0 --port 8000 ``` ### Endpoints - `GET /health`: Check system status. - `POST /predict`: Get churn probability. - `POST /explain`: Get SHAP explanation. ### Example Request ```json POST /predict { "CreditScore": 619, "Geography": "France", "Gender": "Female", "Age": 42, "Tenure": 2, "Balance": 0.0, "NumOfProducts": 1, "HasCrCard": 1, "IsActiveMember": 1, "EstimatedSalary": 101348.88 } ```
