Data Preparation1.txt

df_timeseries = pd.DataFrame(df.groupby(['Date'])['Amount'].sum()).sort_index(axis=0)

data = pd.DataFrame(df_timeseries.Amount)
data.columns = ["y"]
data = data.loc[data.index[:-1]] # drop data after 2019-06 since we want to predict next half year in 2019 

# Adding the lag of the target variable from 7 steps back up to 48 months ago
for i in range(7, 48):
    data["lag_{}".format(i)] = data.y.shift(i)

data.tail()