Upload 3 files

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+import pickle
+import pandas as pd
+
+# Load the trained model
+model_path = "random_forest_regression_with_maturity.pkl"
+with open(model_path, "rb") as file:
+    model = pickle.load(file)
+
+# Load dataset to calculate average values for missing inputs
+df = pd.read_csv("apartments_data_enriched_lat_lon_combined.csv")
+
+# Compute average values for the non-input features
+avg_pop = df["pop"].mean()
+avg_pop_dens = df["pop_dens"].mean()
+avg_frg_pct = df["frg_pct"].mean()
+avg_emp = df["emp"].mean()
+avg_tax_income = df["tax_income"].astype(str).str.replace("'", "").astype(float).mean()
+
+# Define the prediction function with only three inputs
+def predict_rent(rooms, area, maturity_rate):
+    # Use average values for missing features
+    features = [[rooms, area, avg_pop, avg_pop_dens, avg_frg_pct, avg_emp, avg_tax_income, maturity_rate]]
+    
+    # Make prediction
+    predicted_price = model.predict(features)[0]
+    
+    return f"Predicted Rent Price: CHF {predicted_price:,.2f}"
+
+# Example prediction
+example_prediction = predict_rent(3.5, 75, 20.314)
+print(example_prediction)
+
+# Gradio Interface (Simplified)
+gr.Interface(
+    fn=predict_rent,
+    inputs=[
+        gr.Number(label="Rooms"),
+        gr.Number(label="Area (sqm)"),
+        gr.Number(label="Maturity Rate"),
+    ],
+    outputs="text",
+    title="Simplified Apartment Rent Price Predictor",
+    description="Enter only the number of rooms, area, and maturity rate to estimate the rent price.",
+).launch()

random_forest_regression_with_maturity.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7032ceb033efade98cd0b38108035458b3e1b500c38fc5022f0e0261687a6a
+size 13780418

requirements.txt

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