#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)

#define parameters separately to log
params = {"fit_intercept": True,
         "positive": False}

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

#make predictions
y_pred = regr.predict(X_test)