m5_prepare {m5}

Prepare the ready-to-use M5 data in one data.frame

Description

It's a memory-efficient function, which uses data.table under the hood. However, it still not recommended to use this function on PCs with < 16GB RAM. In such case, consider to use a custom solution based on ⁠[arrow](https://arrow.apache.org/docs/r/)⁠ or ⁠[disk.frame](https://diskframe.com/index.html)⁠

Usage

m5_prepare(sales_train, sales_test, calendar, sell_prices)

Arguments

sales_train

A data.frame with M5 train data

sales_test

A data.frame with M5 test data

calendar

A data.frame with M5 calendar

sell_prices

A data.frame with M5 sell_prices

Value

A data.table composed from input objects, which contains the following columns:

• item_id

• dept_id

• cat_id

• store_id

• state_id

• d - day ordinal number

• value - number of sold items

• wm_yr_wk - week identifier

• weekday - weekday name (character)

• wday - weekday as an integer

• month

• year

• event_name_1 - special event name, like holidays etc.

• event_type_1 - special event type

• event_name_2 - as above

• event_type_2 - as above

• snap - promotion flag

• sell_price

Examples

library(m5)
library(zeallot)


m5_download('data')
c(sales_train,
  sales_test,
  sell_prices,
  calendar,
  weights) %<-% m5_get_raw_evaluation('data')

m5_data  <-
   m5_prepare(sales_train, sales_test, calendar, sell_prices)