Update app.py

app.py

@@ -1,27 +1,32 @@
-from flask import Flask, render_template, request
-from sklearn.linear_model import LogisticRegression
 import pickle
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+from sklearn.datasets import load_iris
+from sklearn.ensemble import RandomForestClassifier
 
 app = Flask(__name__)
+CORS(app)  # Allow frontend calls from GitHub Pages
 
-#predicting using model saved using pickle
-model = pickle.load(open("iris_model.pkl", "rb"))
+# --- Train or load model ---
+try:
+    model = pickle.load(open("model.pkl", "rb"))
+except:
+    iris = load_iris()
+    X, y = iris.data, iris.target
+    model = RandomForestClassifier()
+    model.fit(X, y)
+    pickle.dump(model, open("model.pkl", "wb"))
 
-@app.route('/')
-def home():
-    return render_template("index.html")
-
-@app.route('/predict', methods=["POST"])
+# --- API route ---
+@app.route("/predict", methods=["POST"])
 def predict():
-    try:
-        swidth = float(request.form.get("swidth"))
-        sheight = float(request.form.get("sheight"))
-        pwidth = float(request.form.get("pwidth"))
-        pheight = float(request.form.get("pheight"))
-        prediction = model.predict([[swidth, sheight, pwidth, pheight]])
-        return render_template("index.html", data=prediction[0])
-    except Exception as e:
-        return render_template("index.html", data=f"Error: {str(e)}")
+    data = request.json
+    features = [data["sepal_length"], data["sepal_width"],
+                data["petal_length"], data["petal_width"]]
+    prediction = model.predict([features])[0]
+
+    target_names = load_iris().target_names
+    return jsonify({"prediction": target_names[prediction]})
 
 if __name__ == "__main__":
-    app.run()
+    app.run(host="0.0.0.0", port=7860)