RemixAutoML (version 0.5.0)

TimeSeriesFill: TimeSeriesFill

Description

TimeSeriesFill For Completing Time Series Data For Single Series or Time Series by Group

Usage

TimeSeriesFill(
  data = data,
  DateColumnName = "Date",
  GroupVariables = c("Store", "Dept"),
  TimeUnit = "weeks",
  FillType = c("maxmax", "minmax", "maxmin", "minmin"),
  MaxMissingPercent = 0.05,
  SimpleImpute = FALSE
)

Arguments

data

Supply your full series data set here

DateColumnName

Supply the name of your date column

GroupVariables

Supply the column names of your group variables. E.g. "Group" or c("Group1","Group2")

TimeUnit

Choose from "second", "minute", "hour", "day", "week", "month", "quarter", "year"

FillType

Choose from maxmax - Fill from the absolute min date to the absolute max date, minmax - Fill from the max date of the min set to the absolute max date, maxmin - Fill from the absolute min date to the min of the max dates, or minmin - Fill from the max date of the min dates to the min date of the max dates

MaxMissingPercent

The maximum amount of missing values an individual series can have to remain and be imputed. Otherwise, they are discarded.

SimpleImpute

Set to TRUE or FALSE. With TRUE numeric cols will fill NAs with a -1 and non-numeric cols with a "0"

Value

Returns a data table with missing time series records filled (currently just zeros)

See Also

Other Feature Engineering: AutoDataPartition(), AutoDiffLagN(), AutoHierarchicalFourier(), AutoInteraction(), AutoLagRollStatsScoring(), AutoLagRollStats(), AutoTransformationCreate(), AutoTransformationScore(), AutoWord2VecModeler(), AutoWord2VecScoring(), ContinuousTimeDataGenerator(), CreateCalendarVariables(), CreateHolidayVariables(), DT_GDL_Feature_Engineering(), DifferenceDataReverse(), DifferenceData(), DummifyDT(), H2OAutoencoderScoring(), H2OAutoencoder(), ModelDataPrep(), Partial_DT_GDL_Feature_Engineering()

Examples

# NOT RUN {
# Pull in data
data <- data <- data.table::fread("https://www.dropbox.com/s/2str3ek4f4cheqi/walmart_train.csv?dl=1")

# Run function
data <- TimeSeriesFill(
  data,
  DateColumnName = "Date",
  GroupVariables = c("Store","Dept"),
  TimeUnit = "weeks",
  FillType = "maxmax",
  SimpleImpute = FALSE)
# }