Position_salaries

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

data = pd.DataFrame({
'Level': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
'Salary': [45000, 50000, 60000, 80000, 110000, 150000, 200000, 300000, 500000, 1000000]
})

X = data[['Level']]
y = data['Salary']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

print("Training set size:", len(X_train))
print("Testing set size:", len(X_test))

model = LinearRegression()
model.fit(X_train, y_train)

y_pred = model.predict(X_test)

mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)