Advanced Forecasting with Lags and Rolling Window Features
In this notebook, we’ll demonstrate how to use Azure Machine Learning’s automated machine learning (AutoML) for time-series forecasting, with a focus on manually configuring lag and rolling window features.
Prepare Data
We’ll start by loading the energy demand data into an MLTable, which is the required format for AutoML forecasting jobs.
import pandas as pd
from azure.ai.ml import Input
from azure.ai.ml.constants import AssetTypes
# Load the energy demand data
df = pd.read_csv('energy_demand.csv', index_col='date', parse_dates=['date'])
# Create an MLTable from the data
my_training_data_input = Input(
type=AssetTypes.MLTABLE,