initial iris classification space

README.md

@@ -1,14 +1,26 @@
 ---
-title: Iris Classification Using KNN
-emoji: 🏃
-colorFrom: green
-colorTo: red
+title: Iris Classification Demo
 sdk: gradio
-sdk_version: 6.15.2
-python_version: '3.13'
 app_file: app.py
-pinned: false
-short_description: A  Space that predicts Iris species using KNN classifier.
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Iris Classification Demo
+
+A simple Hugging Face Space that predicts Iris species using a KNN classifier.
+
+## What’s inside
+
+- `train.py`: trains a `StandardScaler + KNN` model with `GridSearchCV` and saves `model.joblib`.
+- `app.py`: Gradio UI for interactive predictions.
+
+## Running locally
+
+```bash
+pip install -r requirements.txt
+python train.py
+python app.py
+```
+
+## Notes
+
+- The app will auto-train the model if `model.joblib` is missing.

app.py

@@ -0,0 +1,67 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+import gradio as gr
+import joblib
+import pandas as pd
+
+
+ARTIFACT_PATH = Path(__file__).with_name("model.joblib")
+
+
+def _load_bundle() -> dict:
+    if not ARTIFACT_PATH.exists():
+        from train import train_and_save
+
+        train_and_save(ARTIFACT_PATH)
+
+    return joblib.load(ARTIFACT_PATH)
+
+
+BUNDLE = _load_bundle()
+MODEL = BUNDLE["model"]
+TARGET_NAMES = BUNDLE["target_names"]
+FEATURE_NAMES = BUNDLE["feature_names"]
+
+
+def predict(sepal_length: float, sepal_width: float, petal_length: float, petal_width: float):
+    x = pd.DataFrame(
+        [[sepal_length, sepal_width, petal_length, petal_width]],
+        columns=FEATURE_NAMES,
+    )
+
+    pred_idx = int(MODEL.predict(x)[0])
+    pred_label = TARGET_NAMES[pred_idx]
+
+    if hasattr(MODEL, "predict_proba"):
+        proba = MODEL.predict_proba(x)[0]
+        proba_dict = {str(TARGET_NAMES[i]): float(proba[i]) for i in range(len(TARGET_NAMES))}
+    else:
+        proba_dict = {TARGET_NAMES[pred_idx]: 1.0}
+
+    return pred_label, proba_dict
+
+
+demo = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Number(label=FEATURE_NAMES[0], value=5.8),
+        gr.Number(label=FEATURE_NAMES[1], value=3.0),
+        gr.Number(label=FEATURE_NAMES[2], value=4.0),
+        gr.Number(label=FEATURE_NAMES[3], value=1.2),
+    ],
+    outputs=[
+        gr.Textbox(label="Predicted class"),
+        gr.Label(label="Class probabilities"),
+    ],
+    title="Iris Classification (KNN)",
+    description=(
+        "KNN classifier trained on the classic Iris dataset. "
+        "Enter measurements and get a predicted species + probabilities."
+    ),
+)
+
+
+if __name__ == "__main__":
+    demo.launch()

metrics.json

@@ -0,0 +1,8 @@
+{
+  "cv_best_accuracy": 0.9666666666666668,
+  "best_params": {
+    "knn__n_neighbors": 6,
+    "knn__p": 2,
+    "knn__weights": "uniform"
+  }
+}

model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796d9efca47a8b3495bba825f57b2a65be7b9d9ce5abf1c81bd17e761b47dc98
+size 15144

requirements.txt

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

train.py

@@ -0,0 +1,70 @@
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+import joblib
+from sklearn.datasets import load_iris
+from sklearn.model_selection import GridSearchCV
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+
+
+ARTIFACT_PATH = Path(__file__).with_name("model.joblib")
+METRICS_PATH = Path(__file__).with_name("metrics.json")
+
+
+def train_and_save(artifact_path: Path = ARTIFACT_PATH) -> dict:
+    iris = load_iris(as_frame=True)
+    X = iris.data
+    y = iris.target
+
+    target_names = [str(name) for name in iris.target_names]
+    feature_names = [str(name) for name in iris.feature_names]
+
+    pipeline = Pipeline(
+        steps=[
+            ("scaler", StandardScaler()),
+            ("knn", KNeighborsClassifier()),
+        ]
+    )
+
+    param_grid = {
+        "knn__n_neighbors": list(range(1, 21)),
+        "knn__weights": ["uniform", "distance"],
+        "knn__p": [1, 2],
+    }
+
+    search = GridSearchCV(
+        estimator=pipeline,
+        param_grid=param_grid,
+        cv=5,
+        scoring="accuracy",
+        n_jobs=-1,
+        refit=True,
+    )
+    search.fit(X, y)
+
+    best_model = search.best_estimator_
+    joblib.dump(
+        {
+            "model": best_model,
+            "target_names": target_names,
+            "feature_names": feature_names,
+        },
+        artifact_path,
+    )
+
+    metrics = {
+        "cv_best_accuracy": float(search.best_score_),
+        "best_params": search.best_params_,
+    }
+    METRICS_PATH.write_text(json.dumps(metrics, indent=2), encoding="utf-8")
+    return metrics
+
+
+if __name__ == "__main__":
+    metrics = train_and_save()
+    print(f"Saved model to: {ARTIFACT_PATH}")
+    print(json.dumps(metrics, indent=2))