import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score

# Step 1: Load the dataset
df = pd.read_csv("house_prices.csv")
print("Original Dataset:")
print(df.head())

# Step 2: Prepare the data
X = df[['size']]
y = df['price']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Step 3: Train Linear Regression
model = LinearRegression()
model.fit(X_train, y_train)

# Step 4: Predict and evaluate
y_pred = model.predict(X_test)
r2 = r2_score(y_test, y_pred)
print("\nR-squared:", r2)