Create app.py

app.py

@@ -0,0 +1,52 @@
+import pandas as pd
+import mlflow
+import mlflow.sklearn
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+import gradio as gr
+import os
+
+# ✅ Embedded dataset
+data = {
+    "feature1": [100, 150, 200, 250, 300],
+    "feature2": [200, 180, 160, 140, 120],
+    "price":    [300, 330, 360, 390, 420]
+}
+df = pd.DataFrame(data)
+
+# ✅ MLflow setup
+mlflow.set_tracking_uri("file://" + os.path.abspath("mlruns"))
+mlflow.set_experiment("price_prediction")
+
+# ✅ Train model
+X = df[["feature1", "feature2"]]
+y = df["price"]
+model = LinearRegression()
+model.fit(X, y)
+preds = model.predict(X)
+mse = mean_squared_error(y, preds)
+
+# ✅ Log training
+with mlflow.start_run():
+    mlflow.log_param("model_type", "LinearRegression")
+    mlflow.log_metric("mse", mse)
+    mlflow.sklearn.log_model(model, "model")
+
+# ✅ Gradio UI
+def predict_price(f1, f2):
+    input_df = pd.DataFrame([[f1, f2]], columns=["feature1", "feature2"])
+    prediction = model.predict(input_df)[0]
+    return f"Predicted Price: ₹{prediction:.2f}"
+
+demo = gr.Interface(
+    fn=predict_price,
+    inputs=[
+        gr.Number(label="Feature 1"),
+        gr.Number(label="Feature 2")
+    ],
+    outputs="text",
+    title="📈 Price Predictor",
+    description="Enter feature values to predict price"
+)
+
+demo.launch()