Added training the model and update app.py

.gitignore

@@ -0,0 +1 @@
+venv/

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+import pickle
+import numpy as np
+import pandas as pd
+
+# Load dataset
+df = pd.read_csv("bfs_municipality_and_tax_data.csv")
+
+# Load trained model
+with open("random_forest_regression_with_custom_feature.pkl", "rb") as f:
+    model = pickle.load(f)
+
+# Function for prediction
+def predict_price(municipality, tax_income):
+    # Get population density for the selected municipality
+    pop_dens = df[df["bfs_name"] == municipality]["pop_dens"].values
+    if len(pop_dens) == 0:
+        pop_dens = [1000]  # Default value if not found
+
+    # Prepare input data
+    input_data = np.array([[tax_income, pop_dens[0]]])
+    predicted_price = model.predict(input_data)[0]
+
+    return f"Estimated Property Price: CHF {predicted_price:,.2f} (Population Density: {pop_dens[0]} per km²)"
+
+# Gradio UI
+gradio_ui = gr.Interface(
+    fn=predict_price,
+    inputs=[
+        gr.Textbox(label="Municipality"),
+        gr.Number(label="Taxable Income (CHF)")
+    ],
+    outputs=gr.Text(label="Predicted Property Price"),
+    title="Apartment Price Prediction with Population Density"
+)
+
+if __name__ == "__main__":
+    gradio_ui.launch()

random_forest_regression_with_custom_feature.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf08a9b15318604c4feb3a94d3c0fb366ee52f4a0f38c72058735421056b2fe7
+size 15516395

trainModel.ipynb

@@ -0,0 +1,76 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "✅ Model trained successfully! Mean Absolute Error: 1009.95\n",
+      "✅ Model saved as random_forest_regression_with_custom_feature.pkl\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "import pandas as pd\n",
+    "import pickle\n",
+    "from sklearn.ensemble import RandomForestRegressor\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import mean_absolute_error\n",
+    "\n",
+    "df = pd.read_csv(\"bfs_municipality_and_tax_data.csv\")\n",
+    "\n",
+    "df[\"tax_income\"] = df[\"tax_income\"].astype(str).str.replace(r\"[^\\d.]\", \"\", regex=True).astype(float)\n",
+    "\n",
+    "df[\"pop_dens\"] = pd.to_numeric(df[\"pop_dens\"], errors=\"coerce\")\n",
+    "\n",
+    "df.fillna(df.select_dtypes(include=[\"number\"]).median(), inplace=True)\n",
+    "\n",
+    "X = df[[\"tax_income\", \"pop_dens\"]]\n",
+    "y = df[\"tax_income\"]  \n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "model = RandomForestRegressor(n_estimators=100, random_state=42)\n",
+    "model.fit(X_train, y_train)\n",
+    "\n",
+    "y_pred = model.predict(X_test)\n",
+    "\n",
+    "# Evaluate performance\n",
+    "mae = mean_absolute_error(y_test, y_pred)\n",
+    "print(f\"Model trained successfully! Mean Absolute Error: {mae:.2f}\")\n",
+    "\n",
+    "# Save the trained model\n",
+    "with open(\"random_forest_regression_with_custom_feature.pkl\", \"wb\") as f:\n",
+    "    pickle.dump(model, f)\n",
+    "\n",
+    "print(\"Model saved as random_forest_regression_with_custom_feature.pkl\")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}