df.
loc[:,
['item', 'Flag_Occurence', 'month', 'quarter', 'half', 'year', 'woy']])
y = df.loc[:, 'Quantity']
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=42)
#['item','Flag_Occurence','month','quarter','half','year', 'woy']
# with statsmodels
X = sm.add_constant(x_train) # adding a constant
model = sm.OLS(y_train, X).fit()
print(model.summary())
#removed 'year'
X = X[:, [0, 1, 2, 3, 4, 5, 7]]
#['item','Flag_Occurence','month','quarter','half', 'woy']
model = sm.OLS(y_train, X).fit()
print(model.summary())
#removed 'quarter'
X = X[:, [0, 1, 2, 3, 5, 6]]
#['item','Flag_Occurence','month','half', 'woy']
model = sm.OLS(y_train, X).fit()
print(model.summary())
#removed 'half'
#['item','Flag_Occurence','month', 'woy']
