initial commit

README.md

@@ -1,14 +1,11 @@
----
-title: House Rental Predictor
-emoji: 🌍
-colorFrom: purple
-colorTo: gray
-sdk: gradio
-sdk_version: 5.25.0
-app_file: app.py
-pinned: false
-license: mit
-short_description: 'This app predicts rental prices based on given properties '
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Real Estate Rent Prediction
+
+This app predicts house rental prices based on input features like location, size, and furnishing status.
+
+- Built with: Gradio, Scikit-learn, TensorFlow
+- Model: Linear Regression
+- UI: Gradio Interface
+
+Just enter the values, and get your rent prediction instantly!
+
+**Note:** The model was trained on foreign data, so the predictions are based on foreign country cities and area types.

app.py.py

@@ -0,0 +1,82 @@
+# -*- coding: utf-8 -*-
+"""GradioUI.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/13606Sv5nfECx_rbwG8DGuXDHspZ6t4kA
+"""
+
+import gradio as gr
+import joblib
+import numpy as np
+import pandas as pd
+from sklearn.preprocessing import MinMaxScaler
+
+# Load the model and scaler
+model = joblib.load('model.joblib')
+scaler = joblib.load('scaler.joblib')
+
+# Prediction function
+def predict_rent(BHK, Size, Furnishing_Status, Bathroom, floor_number,
+                 Area_Type, City):
+
+    try:
+        # Prepare the input DataFrame with dummy variables
+        input_data = pd.DataFrame({
+            'BHK': [BHK],
+            'Size': [Size],
+            'Furnishing Status': [Furnishing_Status],
+            'Bathroom': [Bathroom],
+            'floor_number': [floor_number],
+            'Area Type_Carpet Area': [0],
+            'Area Type_Super Area': [0],
+            'City_Chennai': [0],
+            'City_Delhi': [0],
+            'City_Hyderabad': [0],
+            'City_Kolkata': [0],
+            'City_Mumbai': [0],
+        })
+
+        # Update one-hot encoded fields
+        if Area_Type == "Carpet Area":
+            input_data['Area Type_Carpet Area'] = [1]
+        elif Area_Type == "Super Area":
+            input_data['Area Type_Super Area'] = [1]
+
+        if City == "Chennai":
+            input_data['City_Chennai'] = [1]
+        elif City == "Delhi":
+            input_data['City_Delhi'] = [1]
+        elif City == "Hyderabad":
+            input_data['City_Hyderabad'] = [1]
+        elif City == "Kolkata":
+            input_data['City_Kolkata'] = [1]
+        elif City == "Mumbai":
+            input_data['City_Mumbai'] = [1]
+
+        rent = model.predict(input_data)[0]
+        return f"💰 Predicted Rent: ${rent:,.2f} per month"
+
+    except Exception as e:
+        return f"❌ Error: {e}"
+
+# Inputs
+inputs = [
+    gr.Number(label="BHK", minimum=1, maximum=6),
+    gr.Number(label="Size (in sqft)", minimum=100, maximum=80000),
+    gr.Number(label="Furnishing Status (0: Unfurnished, 1: Semi-Furnished, 2: Furnished)", minimum=0, maximum=2),
+    gr.Number(label="Bathrooms", minimum=1, maximum=3),
+    gr.Number(label="Floor Number", minimum=0, maximum=10),
+    gr.Dropdown(choices=["Carpet Area", "Super Area"], label="Area Type"),
+    gr.Dropdown(choices=["Chennai", "Delhi", "Hyderabad", "Kolkata", "Mumbai"], label="City"),
+]
+
+# Gradio UI
+gr.Interface(
+    fn=predict_rent,
+    inputs=inputs,
+    outputs=gr.Textbox(label="Prediction Result"),
+    title="🏡 Rent Prediction App",
+    description="Welcome to Leo's RealEstate! Our valued customer, please fill your preferences to get the predicted monthly rent."
+).launch()

model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5179f7144a89200e3ab67b5b114368f50f4f170db25368339c520d16af1fbc
+size 1257

requirements.txt

@@ -0,0 +1,8 @@
+gradio
+joblib
+numpy
+pandas
+seaborn
+matplotlib
+scikit-learn
+tensorflow

scaler.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe99e53249f8f5e3f7f2e6c3240443d3bc821ffc3bd4281d497318ef31f5d6f9
+size 1247