--- title: AppUserClustering emoji: 👥✨ colorFrom: indigo colorTo: gray sdk: docker app_port: 8501 tags: - streamlit pinned: false short_description: User segmentation with KMeans clustering license: mit --- # 👥✨ KMeans User Segmentation This Streamlit app performs **user segmentation** using a trained **KMeans clustering model**. ## What it does - Loads a saved **KMeans model** (`kmeans_user_segmentation.pkl`) and **StandardScaler** (`scaler.pkl`) - Accepts input via: - **CSV upload**, or - **Manual input (demo)** - Assigns each row to a **cluster** - Shows: - cluster distribution - cluster profile (mean feature values) - optional PCA 2D visualization - Allows downloading the results as CSV ## Required CSV columns Your CSV must contain these columns exactly: - `Average Screen Time` - `Average Spent on App (INR)` - `Ratings` - `Last Visited Minutes` - `New Password Request` ## Files in this Space - `app.py` - `kmeans_user_segmentation.pkl` - `scaler.pkl` - `requirements.txt` ## Note Clustering is unsupervised: clusters represent **groups of similar behavior**, not ground-truth labels.