Deploy iris detector (KNN)

.gitignore

@@ -0,0 +1,3 @@
+__pycache__/
+*.pyc
+.venv/

README.md

@@ -1,14 +1,23 @@
----
-title: Iris Detector
-emoji: ⚡
-colorFrom: indigo
-colorTo: yellow
-sdk: gradio
-sdk_version: 5.49.1
-app_file: app.py
-pinned: false
-license: apache-2.0
-short_description: Iris detection
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🌸 Iris Detector (KNN, k=5)
+
+A simple Hugging Face Space that loads a pretrained KNN model (exported via Google Colab) and predicts iris species from 4 numeric inputs.
+
+## Features
+- 4 numeric inputs: sepal length, sepal width, petal length, petal width
+- Predicts one of 3 classes:
+  - setosa
+  - versicolor
+  - virginica
+- Probability distribution included
+- Works with Hugging Face API `/run/predict`
+
+## API Example
+
+POST:
+https://<user>-<space>.hf.space/run/predict
+Body:
+```json
+{
+  "data": [5.1, 3.5, 1.4, 0.2]
+}
+

app.py

@@ -0,0 +1,82 @@
+import gradio as gr
+import numpy as np
+import joblib
+
+# Load trained model and target names
+model, target_names = joblib.load("iris_knn.pkl")
+
+def predict(sepal_length, sepal_width, petal_length, petal_width):
+    """
+    Predict the iris species given 4 numeric inputs.
+
+    Returns a dictionary with 'predicted_class' and 'probabilities'.
+    """
+    data = np.array([[sepal_length, sepal_width, petal_length, petal_width]])
+    pred = model.predict(data)[0]
+    proba = model.predict_proba(data)[0]
+    return {
+        "predicted_class": str(target_names[pred]),
+        "probabilities": {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 Iris Class")
+            output = gr.JSON(label="Prediction")
+
+            predict_btn.click(
+                fn=predict,
+                inputs=[sepal_length, sepal_width, petal_length, petal_width],
+                outputs=[output]
+            )
+
+        with gr.Column():
+            gr.Markdown("## 📖 API Usage Guide")
+            gr.Markdown("""
+You can access this model programmatically using the Hugging Face Space API.
+
+**Endpoint:**
+```
+POST https://huggingface.co/spaces/tofighi/iris-detector/run/predict
+```
+
+**Request Body (JSON):**
+```json
+{
+  "data": [5.1, 3.5, 1.4, 0.2]
+}
+```
+
+**Response:**
+```json
+{
+  "predicted_class": "setosa",
+  "probabilities": {
+    "setosa": 1.0,
+    "versicolor": 0.0,
+    "virginica": 0.0
+  }
+}
+```
+
+**Python Example:**
+```python
+import requests
+
+url = "https://huggingface.co/spaces/tofighi/iris-detector/run/predict"
+payload = {"data": [5.1, 3.5, 1.4, 0.2]}
+resp = requests.post(url, json=payload)
+print(resp.json())
+```
+""")
+
+demo.launch(share=True)

iris_knn.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2f61d7c8a95f19394fb776308cd844f5ce159bff513b77e808efe98241100b
+size 14315

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+scikit-learn
+numpy
+joblib