Use this script to run the model - look in Suburbs.csv and Areas.csv to find the correct format for your suburb and area
1058710
import pandas as pd | |
from joblib import load | |
# Load the trained model | |
model = load('bestmodelyet.joblib') | |
# Load the label encoders | |
le_area = load('le_area.joblib') | |
le_suburb = load('le_suburb.joblib') | |
# Get user input | |
property_type = int(input("Enter the Property type (0 for Apartment, 1 for Townhouse, 2 for House): ")) | |
area = input("Enter the Area: ") | |
suburb = input("Enter the Suburb: ") | |
bedrooms = float(input("Enter the number of Bedrooms: ")) | |
bathrooms = float(input("Enter the number of Bathrooms: ")) | |
garages = float(input("Enter the number of Garages: ")) | |
ngparking = int(input("Enter the number of dedicated non-garage parking spots (if none, enter 0): ")) | |
floor_size = int(input("Enter the floor size: ")) | |
pool = int(input("Enter 1 if there is a Pool, 0 otherwise: ")) | |
garden = int(input("Enter 1 if there is a Garden, 0 otherwise: ")) | |
study = int(input("Enter 1 if there is a Study, 0 otherwise: ")) | |
pets = int(input("Enter 1 if Pets are allowed, 0 otherwise: ")) | |
furnished = int(input("Enter 1 if the property is Furnished, 0 otherwise: ")) | |
fibre = int(input("Enter 1 if there is Fibre internet, 0 otherwise: ")) | |
# Transform the user input | |
area_encoded = le_area.transform([area]) | |
suburb_encoded = le_suburb.transform([suburb]) | |
# Create a dataframe from the user input | |
df = pd.DataFrame({ | |
'Property_type': [property_type], | |
'Area': area_encoded, | |
'Suburb': suburb_encoded, | |
'Bedrooms': [bedrooms], | |
'Bathrooms': [bathrooms], | |
'Garages': [garages], | |
'nGparking': [ngparking], | |
'floor_size': [floor_size], | |
'Pool': [pool], | |
'Garden': [garden], | |
'Study': [study], | |
'Pets': [pets], | |
'Furnished': [furnished], | |
'Fibre': [fibre] | |
}) | |
# Predict the rent | |
predicted_rent = model.predict(df) | |
# Print the predicted rent | |
print(f"The predicted rent is: {predicted_rent[0]}") | |