Upload 2 files

README.md

@@ -1,3 +1,40 @@
 ---
-license: mit
+title: Diabetes Prediction
+emoji: 📦
+colorFrom: indigo
+colorTo: blue
+sdk: gradio
+sdk_version: "6.0.2"
+app_file: app.py
+pinned: false
 ---
+
+# Diabetes Prediction App
+
+Predicts diabetes risk based on clinical parameters using machine learning.
+
+## Features
+- Real-time diabetes risk prediction
+- Probability score display
+- Clean, intuitive interface
+- Models hosted separately on [KKT-ML-Models](https://huggingface.co/spaces/kkthyagharajan/KKT-ML-Models)
+
+## How to Use
+1. Enter patient clinical parameters
+2. Click "Predict"
+3. View prediction and probability
+
+## Model Information
+- **Algorithm**: Logistic Regression
+- **Accuracy**: ~77.6%
+- **Hosted at**: [KKT-ML-Models Space](https://huggingface.co/spaces/kkthyagharajan/KKT-ML-Models)
+
+## Parameters
+- **Pregnancies**: Number of pregnancies
+- **Glucose**: Plasma glucose concentration
+- **Blood Pressure**: Diastolic blood pressure
+- **Skin Thickness**: Triceps skin fold thickness
+- **Insulin**: 2-Hour serum insulin
+- **BMI**: Body mass index
+- **Diabetes Pedigree Function**: Genetic risk score
+- **Age**: Age in years

diabetic_models/logistic_reg_diabetic.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64498d1b673606b9c27c6f8384efa8de22fdb461587d4f13988ee922a2336e2f
+size 1307