#define independent and dependent features
X = salary_data.drop(columns = 'salary_in_usd')
y = salary_data['salary_in_usd']

#split between training and testing sets
X_train, X_test, y_train, y_test = train_test_split(
  X, y, random_state = 104, test_size = 0.2, shuffle = True)

#fit linear regression model
regr = linear_model.LinearRegression()
regr.fit(X_train, y_train)

#make predictions
y_pred = regr.predict(X_test)

#print the coefficients
print("Coefficients: n", regr.coef_)

#print the MSE
print("Mean squared error: %.2f" % mean_squared_error(y_test, y_pred))

#print the adjusted R2 value
print("R2: %.2f" % r2_score(y_test, y_pred))