house_data.py

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.tree import DecisionTreeRegressor
from sklearn.tree import export_graphviz
import graphviz


# Load the dataset
data = pd.read_csv('house_data.csv')

# Drop missing values
data.dropna(inplace=True)

# One-hot encoding for categorical variables
data = pd.get_dummies(data, columns=['Location'], drop_first=True)

# Separate features and target variable
X = data.drop('Price', axis=1)
y = data['Price']

# Scale the features
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.4, random_state=42)

# Create and train the model
model = LinearRegression()
model.fit(X_train, y_train)

# Make predictions
y_pred = model.predict(X_test)

# Calculate performance metrics
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

# Create and train the Decision Tree model
tree_model = DecisionTreeRegressor(random_state=42)
tree_model.fit(X_train, y_train)

# Make predictions
y_pred_tree = tree_model.predict(X_test)

# Evaluate the model
mse_tree = mean_squared_error(y_test, y_pred_tree)
r2_tree = r2_score(y_test, y_pred_tree)

print("Decision Tree - Mean Squared Error:", mse_tree)
print("Decision Tree - R-squared:", r2_tree)