AutoCatBoostRegression: AutoCatBoostRegression is an automated catboost model grid-tuning classifier and evaluation system

Description

AutoCatBoostRegression is an automated modeling function that runs a variety of steps. First, the function will run a random grid tune over N number of models and find which model is the best (a default model is always included in that set). Once the model is identified and built, several other outputs are generated: validation data with predictions, evaluation plot, evaluation boxplot, evaluation metrics, variable importance, partial dependence calibration plots, partial dependence calibration box plots, and column names used in model fitting. You can download the catboost package using devtools, via: devtools::install_github('catboost/catboost', subdir = 'catboost/R-package')

Usage

AutoCatBoostRegression(
  data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  Weights = NULL,
  TargetColumnName = NULL,
  FeatureColNames = NULL,
  PrimaryDateColumn = NULL,
  DummifyCols = FALSE,
  IDcols = NULL,
  TransformNumericColumns = NULL,
  Methods = c("YeoJohnson", "BoxCox", "Asinh", "Log", "LogPlus1", "Sqrt", "Asin",
    "Logit"),
  task_type = "GPU",
  NumGPUs = 1,
  eval_metric = "RMSE",
  eval_metric_value = 1.5,
  loss_function = "RMSE",
  loss_function_value = 1.5,
  model_path = NULL,
  metadata_path = NULL,
  SaveInfoToPDF = FALSE,
  ModelID = "FirstModel",
  NumOfParDepPlots = 0L,
  EvalPlots = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  PassInGrid = NULL,
  GridTune = FALSE,
  MaxModelsInGrid = 30L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L * 60L,
  Shuffles = 1L,
  BaselineComparison = "default",
  MetricPeriods = 10L,
  langevin = FALSE,
  diffusion_temperature = 10000,
  Trees = 500L,
  Depth = 9,
  L2_Leaf_Reg = 3,
  RandomStrength = 1,
  BorderCount = 254,
  LearningRate = NULL,
  RSM = 1,
  BootStrapType = NULL,
  GrowPolicy = "SymmetricTree",
  model_size_reg = 0.5,
  feature_border_type = "GreedyLogSum",
  sampling_unit = "Group",
  subsample = NULL,
  score_function = "Cosine",
  min_data_in_leaf = 1
)

Arguments

data

This is your data set for training and testing your model

TrainOnFull

Set to TRUE to train on full data and skip over evaluation steps

ValidationData

This is your holdout data set used in modeling either refine your hyperparameters. Catboost using both training and validation data in the training process so you should evaluate out of sample performance with this data set.

TestData

This is your holdout data set. Catboost using both training and validation data in the training process so you should evaluate out of sample performance with this data set.

Weights

Weights vector for train.pool in catboost

TargetColumnName

Either supply the target column name OR the column number where the target is located (but not mixed types).

FeatureColNames

Either supply the feature column names OR the column number where the target is located (but not mixed types)

PrimaryDateColumn

Supply a date or datetime column for catboost to utilize time as its basis for handling categorical features, instead of random shuffling

DummifyCols

Logical. Will coerce to TRUE if loss_function or eval_metric is set to 'MultiRMSE'.

IDcols

A vector of column names or column numbers to keep in your data but not include in the modeling.

TransformNumericColumns

Set to NULL to do nothing; otherwise supply the column names of numeric variables you want transformed

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.

task_type

Set to "GPU" to utilize your GPU for training. Default is "CPU".

NumGPUs

Set to 1, 2, 3, etc.

eval_metric

Select from 'RMSE', 'MAE', 'MAPE', 'R2', 'Poisson', 'MedianAbsoluteError', 'SMAPE', 'MSLE', 'NumErrors', 'FairLoss', 'Tweedie', 'Huber', 'LogLinQuantile', 'Quantile', 'Lq', 'Expectile'

eval_metric_value

Used with the specified eval_metric. See https://catboost.ai/docs/concepts/loss-functions-regression.html

loss_function

Used in model training for model fitting. 'MAPE', 'MAE', 'RMSE', 'Poisson', 'Tweedie', 'Huber', 'LogLinQuantile', 'Quantile', 'Lq', 'Expectile'

loss_function_value

Used with the specified loss function if an associated value is required. 'Tweedie', 'Huber', 'LogLinQuantile', 'Quantile' 'Lq', 'Expectile'. See https://catboost.ai/docs/concepts/loss-functions-regression.html

model_path

A character string of your path file to where you want your output saved

metadata_path

A character string of your path file to where you want your model evaluation output saved. If left NULL, all output will be saved to model_path.

SaveInfoToPDF

Set to TRUE to save modeling information to PDF. If model_path or metadata_path aren't defined then output will be saved to the working directory

ModelID

A character string to name your model and output

NumOfParDepPlots

Tell the function the number of partial dependence calibration plots you want to create. Calibration boxplots will only be created for numerical features (not dummy variables)

EvalPlots

Defaults to TRUE. Set to FALSE to not generate and return these objects.

ReturnModelObjects

Set to TRUE to output all modeling objects (E.g. plots and evaluation metrics)

SaveModelObjects

Set to TRUE to return all modeling objects to your environment

PassInGrid

Defaults to NULL. Pass in a single row of grid from a previous output as a data.table (they are collected as data.tables)

GridTune

Set to TRUE to run a grid tuning procedure. Set a number in MaxModelsInGrid to tell the procedure how many models you want to test.

MaxModelsInGrid

Number of models to test from grid options

MaxRunsWithoutNewWinner

Number of models built before calling it quits

MaxRunMinutes

Maximum number of minutes to let this run

Shuffles

Number of times to randomize grid possibilities

BaselineComparison

Set to either "default" or "best". Default is to compare each successive model build to the baseline model using max trees (from function args). Best makes the comparison to the current best model.

MetricPeriods

Number of periods to use between Catboost evaluations

langevin

Set to TRUE to enable

diffusion_temperature

Defaults to 10000

Trees

Standard + Grid Tuning. Bandit grid partitioned. The maximum number of trees you want in your models

Depth

Standard + Grid Tuning. Bandit grid partitioned. Number, or vector for depth to test. For running grid tuning, a NULL value supplied will mean these values are tested seq(4L, 16L, 2L)

L2_Leaf_Reg

Standard + Grid Tuning. Random testing. Supply a single value for non-grid tuning cases. Otherwise, supply a vector for the L2_Leaf_Reg values to test. For running grid tuning, a NULL value supplied will mean these values are tested seq(1.0, 10.0, 1.0)

RandomStrength

Standard + Grid Tuning. A multiplier of randomness added to split evaluations. Default value is 1 which adds no randomness.

BorderCount

Standard + Grid Tuning. Number of splits for numerical features. Catboost defaults to 254 for CPU and 128 for GPU

LearningRate

Standard + Grid Tuning. Default varies if RMSE, MultiClass, or Logloss is utilized. Otherwise default is 0.03. Bandit grid partitioned. Supply a single value for non-grid tuning cases. Otherwise, supply a vector for the LearningRate values to test. For running grid tuning, a NULL value supplied will mean these values are tested c(0.01,0.02,0.03,0.04)

RSM

CPU only. Standard + Grid Tuning. If GPU is set, this is turned off. Random testing. Supply a single value for non-grid tuning cases. Otherwise, supply a vector for the RSM values to test. For running grid tuning, a NULL value supplied will mean these values are tested c(0.80, 0.85, 0.90, 0.95, 1.0)

BootStrapType

Standard + Grid Tuning. NULL value to default to catboost default (Bayesian for GPU and MVS for CPU). Random testing. Supply a single value for non-grid tuning cases. Otherwise, supply a vector for the BootStrapType values to test. For running grid tuning, a NULL value supplied will mean these values are tested c("Bayesian", "Bernoulli", "Poisson", "MVS", "No")

GrowPolicy

Standard + Grid Tuning. Catboost default of SymmetricTree. Random testing. Default "SymmetricTree", character, or vector for GrowPolicy to test. For grid tuning, supply a vector of values. For running grid tuning, a NULL value supplied will mean these values are tested c("SymmetricTree", "Depthwise", "Lossguide")

model_size_reg

Defaults to 0.5. Set to 0 to allow for bigger models. This is for models with high cardinality categorical features. Valuues greater than 0 will shrink the model and quality will decline but models won't be huge.

feature_border_type

Defaults to "GreedyLogSum". Other options include: Median, Uniform, UniformAndQuantiles, MaxLogSum, MinEntropy

sampling_unit

Default is Group. Other option is Object. if GPU is selected, this will be turned off unless the loss_function is YetiRankPairWise

subsample

Default is NULL. Catboost will turn this into 0.66 for BootStrapTypes Poisson and Bernoulli. 0.80 for MVS. Doesn't apply to others.

score_function

Default is Cosine. CPU options are Cosine and L2. GPU options are Cosine, L2, NewtonL2, and NewtomCosine (not available for Lossguide)

min_data_in_leaf

Default is 1. Cannot be used with SymmetricTree is GrowPolicy

Value

Saves to file and returned in list: VariableImportance.csv, Model, ValidationData.csv, EvalutionPlot.png, EvalutionBoxPlot.png, EvaluationMetrics.csv, ParDepPlots.R a named list of features with partial dependence calibration plots, ParDepBoxPlots.R, GridCollect, catboostgrid, and a transformation details file.

Examples

Run this code

# NOT RUN {
# Create some dummy correlated data
data <- RemixAutoML::FakeDataGenerator(
  Correlation = 0.85,
  N = 10000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Run function
TestModel <- RemixAutoML::AutoCatBoostRegression(

    # GPU or CPU and the number of available GPUs
    task_type = "GPU",
    NumGPUs = 1,

    # Metadata args
    ModelID = "Test_Model_1",
    model_path = normalizePath("./"),
    metadata_path = normalizePath("./"),
    SaveModelObjects = FALSE,
    SaveInfoToPDF = FALSE,
    ReturnModelObjects = TRUE,

    # Data args
    data = data,
    TrainOnFull = FALSE,
    ValidationData = NULL,
    TestData = NULL,
    Weights = NULL,
    TargetColumnName = "Adrian",
    FeatureColNames = names(data)[!names(data) %in%
      c("IDcol_1", "IDcol_2","Adrian")],
    PrimaryDateColumn = NULL,
    DummifyCols = FALSE,
    IDcols = c("IDcol_1","IDcol_2"),
    TransformNumericColumns = "Adrian",
    Methods = c("BoxCox", "Asinh", "Asin", "Log",
      "LogPlus1", "Sqrt", "Logit", "YeoJohnson"),

    # Model evaluation
    eval_metric = "RMSE",
    eval_metric_value = 1.5,
    loss_function = "RMSE",
    loss_function_value = 1.5,
    MetricPeriods = 10L,
    NumOfParDepPlots = ncol(data)-1L-2L,
    EvalPlots = TRUE,

    # Grid tuning args
    PassInGrid = NULL,
    GridTune = FALSE,
    MaxModelsInGrid = 30L,
    MaxRunsWithoutNewWinner = 20L,
    MaxRunMinutes = 60*60,
    Shuffles = 4L,
    BaselineComparison = "default",

    # ML args
    langevin = FALSE,
    diffusion_temperature = 10000,
    Trees = 1000,
    Depth = 6,
    L2_Leaf_Reg = 3.0,
    RandomStrength = 1,
    BorderCount = 128,
    LearningRate = NULL,
    RSM = 1,
    BootStrapType = NULL,
    GrowPolicy = "SymmetricTree",
    model_size_reg = 0.5,
    feature_border_type = "GreedyLogSum",
    sampling_unit = "Group",
    subsample = NULL,
    score_function = "Cosine",
    min_data_in_leaf = 1)

 # Output
 TestModel$Model
 TestModel$ValidationData
 TestModel$EvaluationPlot
 TestModel$EvaluationBoxPlot
 TestModel$EvaluationMetrics
 TestModel$VariableImportance
 TestModel$InteractionImportance
 TestModel$ShapValuesDT
 TestModel$VI_Plot
 TestModel$PartialDependencePlots
 TestModel$PartialDependenceBoxPlots
 TestModel$GridList
 TestModel$ColNames
 TestModel$TransformationResults
# }

Run the code above in your browser using DataLab

Description

Usage

Arguments

Value

See Also

Examples