import gradio as gr
import numpy as np
import joblib

# Load trained KNN model
model, target_names = joblib.load("iris_knn.pkl")

def predict_iris(sepal_length, sepal_width, petal_length, petal_width):
    arr = np.array([[sepal_length, sepal_width, petal_length, petal_width]])
    pred = model.predict(arr)[0]
    proba = model.predict_proba(arr)[0]
    return str(target_names[pred]), {str(target_names[i]): float(proba[i]) for i in range(len(target_names))}

with gr.Blocks() as demo:
    gr.Markdown("# 🌸 Iris Detector — KNN Classifier (k=5)")
    gr.Markdown("Enter 4 iris flower measurements below to predict the species:")

    with gr.Row():
        with gr.Column():
            sepal_length = gr.Number(label="Sepal Length (cm)")
            sepal_width = gr.Number(label="Sepal Width (cm)")
            petal_length = gr.Number(label="Petal Length (cm)")
            petal_width = gr.Number(label="Petal Width (cm)")

            predict_btn = gr.Button("Predict")
            output_class = gr.Label(label="Predicted Class")
            output_proba = gr.JSON(label="Probabilities")

            predict_btn.click(
                fn=predict_iris,
                inputs=[sepal_length, sepal_width, petal_length, petal_width],
                outputs=[output_class, output_proba]
            )

        with gr.Column():
            gr.Markdown(
"""
## 📖 Iris Detector API Usage (FastAPI)

Your predictions can also be made programmatically using the FastAPI backend deployed at:

### **API Endpoint**
```
POST https://tofighi-iris-detector-api.hf.space/predict
```

---

### **📌 JSON Request Example**
```json
{
  "sepal_length": 5.1,
  "sepal_width": 3.5,
  "petal_length": 1.4,
  "petal_width": 0.2
}
```

---

### **🐍 Python Example**
```python
import requests

url = "https://tofighi-iris-detector-api.hf.space/predict"

data = {
    "sepal_length": 5.1,
    "sepal_width": 3.5,
    "petal_length": 1.4,
    "petal_width": 0.2
}

resp = requests.post(url, json=data)
print(resp.json())
```

---

### **💻 cURL Example**
```bash
curl -X POST "https://tofighi-iris-detector-api.hf.space/predict" \
     -H "Content-Type: application/json" \
     -d '{"sepal_length":5.1,"sepal_width":3.5,"petal_length":1.4,"petal_width":0.2}'
```
""")

demo.launch()