RemixAutoML (version 0.4.2)

AutoWord2VecScoring: AutoWord2VecScoring

Description

AutoWord2VecScoring is for scoring models generated by AutoWord2VecModeler()

Usage

AutoWord2VecScoring(
  data,
  BuildType = "individual",
  ModelObject = NULL,
  ModelID = "Model_1",
  model_path = NULL,
  stringCol = NULL,
  KeepStringCol = FALSE,
  H2OStartUp = TRUE,
  H2OShutdown = TRUE,
  Threads = max(1L, parallel::detectCores() - 2L),
  MaxMemory = "28G"
)

Arguments

data

data.table

BuildType

"individual" or "combined". Used to locate model in file

ModelObject

NULL if you want it loaded in the function

ModelID

Same as in training

model_path

Location of model

stringCol

Columns to transform

KeepStringCol

FALSE to remove string col after creating vectors

H2OStartUp

= TRUE,

Threads

max(1L, parallel::detectCores() - 2L)

MaxMemory

"28G"

See Also

Other Feature Engineering: AutoDataPartition(), AutoHierarchicalFourier(), AutoInteraction(), AutoLagRollStatsScoring(), AutoLagRollStats(), AutoTransformationCreate(), AutoTransformationScore(), AutoWord2VecModeler(), ContinuousTimeDataGenerator(), CreateCalendarVariables(), CreateHolidayVariables(), DT_GDL_Feature_Engineering(), DifferenceDataReverse(), DifferenceData(), DummifyDT(), H2oAutoencoder(), ModelDataPrep(), Partial_DT_GDL_Feature_Engineering(), TimeSeriesFill()

Examples

# NOT RUN {
# Create fake data
data <- RemixAutoML::FakeDataGenerator(
  Correlation = 0.70,
  N = 1000L,
  ID = 2L,
  FactorCount = 2L,
  AddDate = TRUE,
  AddComment = TRUE,
  ZIP = 2L,
  TimeSeries = FALSE,
  ChainLadderData = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Create Model and Vectors
data <- RemixAutoML::AutoWord2VecModeler(
  data,
  BuildType = "individual",
  stringCol = c("Comment"),
  KeepStringCol = FALSE,
  ModelID = "Model_1",
  model_path = getwd(),
  vects = 10,
  MinWords = 1,
  WindowSize = 1,
  Epochs = 25,
  SaveModel = "standard",
  Threads = max(1,parallel::detectCores()-2),
  MaxMemory = "28G")

# Remove data
rm(data)

# Create fake data for mock scoring
data <- RemixAutoML::FakeDataGenerator(
  Correlation = 0.70,
  N = 1000L,
  ID = 2L,
  FactorCount = 2L,
  AddDate = TRUE,
  AddComment = TRUE,
  ZIP = 2L,
  TimeSeries = FALSE,
  ChainLadderData = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Create vectors for scoring
data <- RemixAutoML::AutoWord2VecScoring(
  data,
  BuildType = "individual",
  ModelObject = NULL,
  ModelID = "Model_1",
  model_path = getwd(),
  stringCol = "Comment",
  KeepStringCol = FALSE,
  H2OStartUp = TRUE,
  H2OShutdown = TRUE,
  Threads = max(1L, parallel::detectCores() - 2L),
  MaxMemory = "28G")
# }
# NOT RUN {
# }