Building a House Price Prediction Model Using Random Forest in Python

1. Setting Up the Environment

To build a house price prediction model, we first set up the Python environment and installed necessary libraries.

# Install required libraries
!pip install numpy pandas scikit-learn matplotlib seaborn joblib

2. Loading and Exploring the Dataset

We used a housing dataset from Toronto and performed initial data exploration.

import pandas as pd

# Load the dataset
df = pd.read_csv("houses.csv")

# Display dataset structure
print(df.info())
print(df.head())

3. Data Preprocessing

We handled missing values and transformed categorical features.

# Fill missing values
df["sqft"].fillna(df["sqft"].median(), inplace=True)

# Convert categorical variables
df = pd.get_dummies(df, columns=["type", "city_district"], drop_first=True)

# Transform price into logarithmic scale
import numpy as np
df["final_price_log"] = np.log(df["final_price"])

4. Splitting the Dataset

We split the data into training and testing sets.

from sklearn.model_selection import train_test_split

X = df.drop(columns=["final_price", "final_price_log"])
y = df["final_price_log"]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

5. Training the Random Forest Model

from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error, r2_score

# Train the model
rf_model = RandomForestRegressor(n_estimators=100, random_state=42)
rf_model.fit(X_train, y_train)

# Predictions
y_pred = rf_model.predict(X_test)

# Evaluate the model
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

print(f"Mean Squared Error: {mse:.4f}")
print(f"R² Score: {r2:.4f}")

6. Model Performance

Our Random Forest model achieved:• Mean Squared Error (MSE): 0.0253• R² Score: 0.8859

7. Saving the Model

To reuse the trained model, we saved it using joblib.

import joblib

# Save the model
joblib.dump(rf_model, "random_forest_model.pkl")

print("Model saved successfully")

8. Loading the Model and Making Predictions

We reloaded the saved model and made predictions.

# Load the saved model
rf_model_loaded = joblib.load("random_forest_model.pkl")

# Sample input (example house)
sample_house = pd.DataFrame([[800, 2, 1, 2, 60000] + [0]*140], columns=X_train.columns)

# Predict the price
predicted_price_log = rf_model_loaded.predict(sample_house)
predicted_price = np.exp(predicted_price_log)[0]

print(f"Predicted House Price: ${predicted_price:,.2f}")