RemixAutoML (version 0.5.4)

AutoH2OCARMA: AutoH2OCARMA

Description

AutoH2OCARMA Mutlivariate Forecasting with calendar variables, Holiday counts, holiday lags, holiday moving averages, differencing, transformations, interaction-based categorical encoding using target variable and features to generate various time-based aggregated lags, moving averages, moving standard deviations, moving skewness, moving kurtosis, moving quantiles, parallelized interaction-based fourier pairs by grouping variables, and Trend Variables.

Usage

AutoH2OCARMA(
  AlgoType = "drf",
  ExcludeAlgos = "XGBoost",
  data,
  TrainOnFull = FALSE,
  TargetColumnName = "Target",
  PDFOutputPath = NULL,
  SaveDataPath = NULL,
  WeightsColumn = NULL,
  NonNegativePred = FALSE,
  RoundPreds = FALSE,
  DateColumnName = "DateTime",
  GroupVariables = NULL,
  HierarchGroups = NULL,
  TimeUnit = "week",
  TimeGroups = c("weeks", "months"),
  FC_Periods = 30,
  PartitionType = "timeseries",
  MaxMem = {     gc()    
    paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo",
    intern = TRUE))/1e+06)), "G") },
  NThreads = max(1, parallel::detectCores() - 2),
  Timer = TRUE,
  DebugMode = FALSE,
  TargetTransformation = FALSE,
  Methods = c("YeoJohnson", "BoxCox", "Asinh", "Log", "LogPlus1", "Sqrt", "Asin",
    "Logit"),
  XREGS = NULL,
  Lags = c(1:5),
  MA_Periods = c(1:5),
  SD_Periods = NULL,
  Skew_Periods = NULL,
  Kurt_Periods = NULL,
  Quantile_Periods = NULL,
  Quantiles_Selected = NULL,
  AnomalyDetection = NULL,
  Difference = TRUE,
  FourierTerms = 6,
  CalendarVariables = c("second", "minute", "hour", "wday", "mday", "yday", "week",
    "wom", "isoweek", "month", "quarter", "year"),
  HolidayVariable = c("USPublicHolidays", "EasterGroup", "ChristmasGroup",
    "OtherEcclesticalFeasts"),
  HolidayLookback = NULL,
  HolidayLags = 1,
  HolidayMovingAverages = 1:2,
  TimeTrendVariable = FALSE,
  DataTruncate = FALSE,
  ZeroPadSeries = NULL,
  SplitRatios = c(0.7, 0.2, 0.1),
  EvalMetric = "rmse",
  NumOfParDepPlots = 0L,
  GridTune = FALSE,
  ModelCount = 1,
  NTrees = 1000,
  LearnRate = 0.1,
  LearnRateAnnealing = 1,
  GridStrategy = "Cartesian",
  MaxRunTimeSecs = 60 * 60 * 24,
  StoppingRounds = 10,
  MaxDepth = 20,
  SampleRate = 0.632,
  MTries = -1,
  ColSampleRate = 1,
  ColSampleRatePerTree = 1,
  ColSampleRatePerTreeLevel = 1,
  MinRows = 1,
  NBins = 20,
  NBinsCats = 1024,
  NBinsTopLevel = 1024,
  CategoricalEncoding = "AUTO",
  HistogramType = "AUTO",
  Distribution = "gaussian",
  Link = "identity",
  RandomDistribution = NULL,
  RandomLink = NULL,
  Solver = "AUTO",
  Alpha = NULL,
  Lambda = NULL,
  LambdaSearch = FALSE,
  NLambdas = -1,
  Standardize = TRUE,
  RemoveCollinearColumns = FALSE,
  InterceptInclude = TRUE,
  NonNegativeCoefficients = FALSE,
  RandomColNumbers = NULL,
  InteractionColNumbers = NULL
)

Arguments

AlgoType

Select from "dfr" for RandomForecast, "gbm" for gradient boosting, "glm" for generalized linear model, "automl" for H2O's AutoML algo, and "gam" for H2O's Generalized Additive Model.

ExcludeAlgos

For use when AlgoType = "AutoML". Selections include "DRF","GLM","XGBoost","GBM","DeepLearning" and "Stacke-dEnsemble"

data

Supply your full series data set here

TrainOnFull

Set to TRUE to train on full data

TargetColumnName

List the column name of your target variables column. E.g. "Target"

PDFOutputPath

NULL or a path file to output PDFs to a specified folder

SaveDataPath

NULL Or supply a path. Data saved will be called 'ModelID'_data.csv

WeightsColumn

NULL

NonNegativePred

TRUE or FALSE

RoundPreds

Rounding predictions to an integer value. TRUE or FALSE. Defaults to FALSE

DateColumnName

List the column name of your date column. E.g. "DateTime"

GroupVariables

Defaults to NULL. Use NULL when you have a single series. Add in GroupVariables when you have a series for every level of a group or multiple groups.

HierarchGroups

Vector of hierachy categorical columns.

TimeUnit

List the time unit your data is aggregated by. E.g. "1min", "5min", "10min", "15min", "30min", "hour", "day", "week", "month", "quarter", "year".

TimeGroups

Select time aggregations for adding various time aggregated GDL features.

FC_Periods

Set the number of periods you want to have forecasts for. E.g. 52 for weekly data to forecast a year ahead

PartitionType

Select "random" for random data partitioning "time" for partitioning by time frames

MaxMem

Set to the maximum amount of memory you want to allow for running this function. Default is "32G".

NThreads

Set to the number of threads you want to dedicate to this function.

Timer

Set to FALSE to turn off the updating print statements for progress

DebugMode

Defaults to FALSE. Set to TRUE to get a print statement of each high level comment in function

TargetTransformation

Run AutoTransformationCreate() to find best transformation for the target variable. Tests YeoJohnson, BoxCox, and Asigh (also Asin and Logit for proportion target variables).

Methods

Choose from "YeoJohnson", "BoxCox", "Asinh", "Log", "LogPlus1", "Sqrt", "Asin", or "Logit". If more than one is selected, the one with the best normalization pearson statistic will be used. Identity is automatically selected and compared.

XREGS

Additional data to use for model development and forecasting. Data needs to be a complete series which means both the historical and forward looking values over the specified forecast window needs to be supplied.

Lags

Select the periods for all lag variables you want to create. E.g. c(1:5,52) or list("day" = c(1:10), "weeks" = c(1:4))

MA_Periods

Select the periods for all moving average variables you want to create. E.g. c(1:5,52) or list("day" = c(2:10), "weeks" = c(2:4))

SD_Periods

Select the periods for all moving standard deviation variables you want to create. E.g. c(1:5,52) or list("day" = c(2:10), "weeks" = c(2:4))

Skew_Periods

Select the periods for all moving skewness variables you want to create. E.g. c(1:5,52) or list("day" = c(2:10), "weeks" = c(2:4))

Kurt_Periods

Select the periods for all moving kurtosis variables you want to create. E.g. c(1:5,52) or list("day" = c(2:10), "weeks" = c(2:4))

Quantile_Periods

Select the periods for all moving quantiles variables you want to create. E.g. c(1:5,52) or list("day" = c(2:10), "weeks" = c(2:4))

Quantiles_Selected

Select from the following c("q5","q10","q15","q20","q25","q30","q35","q40","q45","q50","q55","q60","q65","q70","q75","q80","q85","q90","q95")

AnomalyDetection

NULL for not using the service. Other, provide a list, e.g. AnomalyDetection = list("tstat_high" = 4, tstat_low = -4)

Difference

Puts the I in ARIMA for single series and grouped series.

FourierTerms

Set to the max number of pairs. E.g. 2 means to generate two pairs for by each group level and interations if hierarchy is enabled.

CalendarVariables

NULL, or select from "second", "minute", "hour", "wday", "mday", "yday", "week", "isoweek", "month", "quarter", "year"

HolidayVariable

NULL, or select from "USPublicHolidays", "EasterGroup", "ChristmasGroup", "OtherEcclesticalFeasts"

HolidayLookback

Number of days in range to compute number of holidays from a given date in the data. If NULL, the number of days are computed for you.

HolidayLags

Number of lags to build off of the holiday count variable.

HolidayMovingAverages

Number of moving averages to build off of the holiday count variable.

TimeTrendVariable

Set to TRUE to have a time trend variable added to the model. Time trend is numeric variable indicating the numeric value of each record in the time series (by group). Time trend starts at 1 for the earliest point in time and increments by one for each success time point.

DataTruncate

Set to TRUE to remove records with missing values from the lags and moving average features created

ZeroPadSeries

NULL to do nothing. Otherwise, set to "maxmax", "minmax", "maxmin", "minmin". See TimeSeriesFill for explanations of each type

SplitRatios

E.g c(0.7,0.2,0.1) for train, validation, and test sets

EvalMetric

Select from "RMSE", "MAE", "MAPE", "Poisson", "Quantile", "LogLinQuantile", "Lq", "SMAPE", "R2", "MSLE", "MedianAbsoluteError"

NumOfParDepPlots

Set to zeros if you do not want any returned. Can set to a very large value and it will adjust to the max number of features if it's too high

GridTune

Set to TRUE to run a grid tune

ModelCount

Set the number of models to try in the grid tune

NTrees

Select the number of trees you want to have built to train the model

LearnRate

Default 0.10, models available include gbm

LearnRateAnnealing

Default 1, models available include gbm

GridStrategy

Default "Cartesian", models available include

MaxRunTimeSecs

Default 60*60*24, models available include

StoppingRounds

Default 10, models available include

MaxDepth

Default 20, models available include drf, gbm

SampleRate

Default 0.632, models available include drf, gbm

MTries

Default 1, models available include drf

ColSampleRate

Default 1, model available include gbm

ColSampleRatePerTree

Default 1, models available include drf, gbm

ColSampleRatePerTreeLevel

Default 1, models available include drf, gbm

MinRows

Default 1, models available include drf, gbm

NBins

Default 20, models available include drf, gbm

NBinsCats

Default 1024, models available include drf, gbm

NBinsTopLevel

Default 1024, models available include drf, gbm

CategoricalEncoding

Default "AUTO". Choices include : "AUTO", "Enum", "OneHotInternal", "OneHotExplicit", "Binary", "Eigen", "LabelEncoder", "Sort-ByResponse", "EnumLimited"

HistogramType

Default "AUTO". Select from "AUTO", "UniformAdaptive", "Random", "QuantilesGlobal", "RoundRobin"

Distribution

Model family

Link

Link for model family

RandomDistribution

Default NULL

RandomLink

Default NULL

Solver

Model optimizer

Alpha

Default NULL

Lambda

Default NULL

LambdaSearch

Default FALSE,

NLambdas

Default -1

Standardize

Default TRUE

RemoveCollinearColumns

Default FALSE

InterceptInclude

Default TRUE

NonNegativeCoefficients

Default FALSE

RandomColNumbers

NULL

InteractionColNumbers

NULL

Value

See examples

See Also

Other Automated Panel Data Forecasting: AutoCatBoostCARMA(), AutoCatBoostHurdleCARMA(), AutoCatBoostVectorCARMA(), AutoLightGBMCARMA(), AutoXGBoostCARMA()

Examples

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

# Ensure series have no missing dates (also remove series with more than 25% missing values)
data <- RemixAutoML::TimeSeriesFill(
  data,
  DateColumnName = "Date",
  GroupVariables = c("Store","Dept"),
  TimeUnit = "weeks",
  FillType = "maxmax",
  MaxMissingPercent = 0.25,
  SimpleImpute = TRUE)

# Set negative numbers to 0
data <- data[, Weekly_Sales := data.table::fifelse(Weekly_Sales < 0, 0, Weekly_Sales)]

# Remove IsHoliday column
data[, IsHoliday := NULL]

# Create xregs (this is the include the categorical variables instead of utilizing only the interaction of them)
xregs <- data[, .SD, .SDcols = c("Date", "Store", "Dept")]

# Change data types
data[, ":=" (Store = as.character(Store), Dept = as.character(Dept))]
xregs[, ":=" (Store = as.character(Store), Dept = as.character(Dept))]

# Build forecast
Results <- RemixAutoML::AutoH2OCARMA(

  # Data Artifacts
  AlgoType = "drf",
  ExcludeAlgos = NULL,
  data = data,
  TargetColumnName = "Weekly_Sales",
  DateColumnName = "Date",
  HierarchGroups = NULL,
  GroupVariables = c("Dept"),
  TimeUnit = "week",
  TimeGroups = c("weeks","months"),

  # Data Wrangling Features
  SplitRatios = c(1 - 10 / 138, 10 / 138),
  PartitionType = "random",

  # Production args
  FC_Periods = 4L,
  TrainOnFull = FALSE,
  MaxMem = {gc();paste0(as.character(floor(max(32, as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) -32) / 1000000)),"G")},
  NThreads = parallel::detectCores(),
  PDFOutputPath = NULL,
  SaveDataPath = NULL,
  Timer = TRUE,
  DebugMode = TRUE,

  # Target Transformations
  TargetTransformation = FALSE,
  Methods = c("BoxCox", "Asinh", "Asin", "Log",
    "LogPlus1", "Sqrt", "Logit", "YeoJohnson"),
  Difference = FALSE,
  NonNegativePred = FALSE,
  RoundPreds = FALSE,

  # Calendar features
  CalendarVariables = c("week", "wom", "month", "quarter", "year"),
  HolidayVariable = c("USPublicHolidays","EasterGroup",
    "ChristmasGroup","OtherEcclesticalFeasts"),
  HolidayLookback = NULL,
  HolidayLags = 1:7,
  HolidayMovingAverages = 2:7,
  TimeTrendVariable = TRUE,

  # Time series features
  Lags = list("weeks" = c(1:4), "months" = c(1:3)),
  MA_Periods = list("weeks" = c(2:8), "months" = c(6:12)),
  SD_Periods = NULL,
  Skew_Periods = NULL,
  Kurt_Periods = NULL,
  Quantile_Periods = NULL,
  Quantiles_Selected = NULL,

  # Bonus Features
  XREGS = NULL,
  FourierTerms = 2L,
  AnomalyDetection = NULL,
  ZeroPadSeries = NULL,
  DataTruncate = FALSE,

  # ML evaluation args
  EvalMetric = "RMSE",
  NumOfParDepPlots = 0L,

  # ML grid tuning args
  GridTune = FALSE,
  GridStrategy = "Cartesian",
  ModelCount = 5,
  MaxRunTimeSecs = 60*60*24,
  StoppingRounds = 10,

  # ML Args
  NTrees = 1000L,
  MaxDepth = 20,
  SampleRate = 0.632,
  MTries = -1,
  ColSampleRatePerTree = 1,
  ColSampleRatePerTreeLevel  = 1,
  MinRows = 1,
  NBins = 20,
  NBinsCats = 1024,
  NBinsTopLevel = 1024,
  HistogramType = "AUTO",
  CategoricalEncoding = "AUTO",
  RandomColNumbers = NULL,
  InteractionColNumbers = NULL,
  WeightsColumn = NULL,

  # ML args
  Distribution = "gaussian",
  Link = "identity",
  RandomDistribution = NULL,
  RandomLink = NULL,
  Solver = "AUTO",
  Alpha = NULL,
  Lambda = NULL,
  LambdaSearch = FALSE,
  NLambdas = -1,
  Standardize = TRUE,
  RemoveCollinearColumns = FALSE,
  InterceptInclude = TRUE,
  NonNegativeCoefficients = FALSE)

UpdateMetrics <-
  Results$ModelInformation$EvaluationMetrics[
    Metric == "MSE", MetricValue := sqrt(MetricValue)]
print(UpdateMetrics)

# Get final number of trees actually used
Results$Model@model$model_summary$number_of_internal_trees

# Inspect performance
Results$ModelInformation$EvaluationMetricsByGroup[order(-R2_Metric)]
Results$ModelInformation$EvaluationMetricsByGroup[order(MAE_Metric)]
Results$ModelInformation$EvaluationMetricsByGroup[order(MSE_Metric)]
Results$ModelInformation$EvaluationMetricsByGroup[order(MAPE_Metric)]
# }