# house_price_prediction.py

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

# Generate some sample data
data = {'Size': [1400, 1600, 1700, 1875, 1100, 1550, 2350, 2450, 1425, 1700],
        'Price': [245000, 312000, 279000, 308000, 199000, 219000, 405000, 324000, 319000, 255000]}

df = pd.DataFrame(data)

# Split the data into features (X) and target variable (y)
X = df[['Size']]
y = df['Price']

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Train a linear regression model
model = LinearRegression()
model.fit(X_train, y_train)

# Make predictions on the test set
y_pred = model.predict(X_test)

# Evaluate the model
mse = mean_squared_error(y_test, y_pred)
print(f'Mean Squared Error: {mse}')

# Save the model
joblib.dump(model, 'house_price_model.joblib')