October 2019
Intermediate to advanced
426 pages
10h 8m
English
In this section, we will fit DeepAR to the weekly sales. Let's start by preparing training and test datasets in JSON format.
Let's have a look at the following code, which demonstrates the creation of json lines:
import deepar as datrain_key = 'deepar_sales_training.json'test_key = 'deepar_sales_test.json'#Prediction and context length for training the DeepAR modelprediction_length = 9salesfn = 'data/store20_sales.csv'salesdf = da.retailsales.prepareSalesData(salesfn)testSet = da.retailsales.getTestSales(salesdf, test_key)trainingSet = da.retailsales.getTrainSales(salesdf, train_key, prediction_length)
In the preceding code block, we have created JSON lines for training and testing the datasets: