The Auto_Regression() models handle a multitude of tasks. In order:

1. Convert your data to data.table format for faster processing
2. Transform your target variable using the best normalization method based on the AutoTransformationCreate() function
3. Create train, validation, and test data, utilizing the AutoDataPartition() function, if you didn’t supply those directly to the function
4. Consoldate columns that are used for modeling and what metadata you want returned in your test data with predictions
5. Dichotomize categorical variables (for AutoXGBoostRegression()) and save the factor levels for scoring in a way that guarentees consistency across training, validation, and test data sets, utilizing the DummifyDT() function
6. Save the final modeling column names for reference
7. Handles the data conversion to the appropriate modeling type, such as CatBoost, H2O, and XGBoost
8. Multi-armed bandit hyperparameter tuning using randomized probability matching, if you choose to grid tune
9. Loop through the grid-tuning process, building N models
10. Collect the evaluation metrics for each grid tune run
11. Identify the best model of the set of models built in the grid tuning search
12. Save the hyperparameters from the winning grid tuned model
13. Build the final model based on the best model from the grid tuning model search (I remove each model after evaluation metrics are generated in the grid tune to avoid memory overflow)
14. Back-transform your predictions based on the best transformation used earlier in the process
15. Collect evaluation metrics based on performance on test data (based on back-transformed data)
16. Store the final predictions with the associated test data and other columns you want included in that set
17. Save your transformation metadata for recreating them in a scoring process
18. Build out and save an Evaluation Calibration Line Plot and Evaluation Calibration Box-Plot, using the EvalPlot() function
19. Generate and save Variable Importance
20. Generate and save Partital Dependence Calibration Line Plots and Partital Dependence Calibration Box-Plots, using the ParDepPlots() function
21. Return all the objects generated in a named list for immediate use and evaluation

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 10000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoCatBoostRegression(

  # GPU or CPU and the number of available GPUs
  TrainOnFull = FALSE,
  task_type = 'GPU',
  NumGPUs = 1,
  DebugMode = FALSE,

  # Metadata args
  OutputSelection = c('Importances', 'EvalPlots', 'EvalMetrics', 'Score_TrainData'),
  ModelID = 'Test_Model_1',
  model_path = normalizePath('./'),
  metadata_path = normalizePath('./'),
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  ReturnModelObjects = TRUE,

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

  # 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,

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

  # ML args
  langevin = FALSE,
  diffusion_temperature = 10000,
  Trees = 1000,
  Depth = 9,
  L2_Leaf_Reg = NULL,
  RandomStrength = 1,
  BorderCount = 128,
  LearningRate = NULL,
  RSM = 1,
  BootStrapType = NULL,
  GrowPolicy = 'SymmetricTree',
  model_size_reg = 0.5,
  feature_border_type = 'GreedyLogSum',
  sampling_unit = 'Object',
  subsample = NULL,
  score_function = 'Cosine',
  min_data_in_leaf = 1)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoXGBoostRegression(
  
  # GPU or CPU
  TreeMethod = 'hist',
  NThreads = parallel::detectCores(),
  LossFunction = 'reg:squarederror',
  
  # Metadata args
  OutputSelection = c('Importances', 'EvalPlots', 'EvalMetrics', 'Score_TrainData'),
  model_path = normalizePath("./"),
  metadata_path = NULL,
  ModelID = "Test_Model_1",
  EncodingMethod = "binary",
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  DebugMode = FALSE,
  
  # Data args
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c('IDcol_1','IDcol_2','Adrian')],
  PrimaryDateColumn = NULL,
  WeightsColumnName = NULL,
  IDcols = c('IDcol_1','IDcol_2'),
  TransformNumericColumns = 'Adrian',
  Methods = c('Asinh','Asin','Log','LogPlus1','Sqrt','Logit'),
  
  # Model evaluation args
  eval_metric = 'rmse',
  NumOfParDepPlots = 3L,
  
  # Grid tuning args
  PassInGrid = NULL,
  GridTune = FALSE,
  grid_eval_metric = 'r2',
  BaselineComparison = 'default',
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  Verbose = 1L,
  
  # ML args
  Trees = 50L,
  eta = 0.05,
  max_depth = 4L,
  min_child_weight = 1.0,
  subsample = 0.55,
  colsample_bytree = 0.55)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoLightGBMRegression(

  # Metadata args
  OutputSelection = c('Importances','EvalPlots','EvalMetrics','Score_TrainData'),
  model_path = normalizePath('./'),
  metadata_path = NULL,
  ModelID = 'Test_Model_1',
  NumOfParDepPlots = 3L,
  EncodingMethod = 'credibility',
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  DebugMode = FALSE,

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

  # Grid parameters
  GridTune = FALSE,
  grid_eval_metric = 'r2',
  BaselineComparison = 'default',
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  PassInGrid = NULL,

  # Core parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#core-parameters
  input_model = NULL, # continue training a model that is stored to file
  task = 'train',
  device_type = 'CPU',
  NThreads = parallel::detectCores() / 2,
  objective = 'regression',
  metric = 'rmse',
  boosting = 'gbdt',
  LinearTree = FALSE,
  Trees = 50L,
  eta = NULL,
  num_leaves = 31,
  deterministic = TRUE,

  # Learning Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#learning-control-parameters
  force_col_wise = FALSE,
  force_row_wise = FALSE,
  max_depth = NULL,
  min_data_in_leaf = 20,
  min_sum_hessian_in_leaf = 0.001,
  bagging_freq = 0,
  bagging_fraction = 1.0,
  feature_fraction = 1.0,
  feature_fraction_bynode = 1.0,
  extra_trees = FALSE,
  early_stopping_round = 10,
  first_metric_only = TRUE,
  max_delta_step = 0.0,
  lambda_l1 = 0.0,
  lambda_l2 = 0.0,
  linear_lambda = 0.0,
  min_gain_to_split = 0,
  drop_rate_dart = 0.10,
  max_drop_dart = 50,
  skip_drop_dart = 0.50,
  uniform_drop_dart = FALSE,
  top_rate_goss = FALSE,
  other_rate_goss = FALSE,
  monotone_constraints = NULL,
  monotone_constraints_method = 'advanced',
  monotone_penalty = 0.0,
  forcedsplits_filename = NULL, # use for AutoStack option; .json file
  refit_decay_rate = 0.90,
  path_smooth = 0.0,

  # IO Dataset Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#io-parameters
  max_bin = 255,
  min_data_in_bin = 3,
  data_random_seed = 1,
  is_enable_sparse = TRUE,
  enable_bundle = TRUE,
  use_missing = TRUE,
  zero_as_missing = FALSE,
  two_round = FALSE,

  # Convert Parameters
  convert_model = NULL,
  convert_model_language = 'cpp',

  # Objective Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#objective-parameters
  boost_from_average = TRUE,
  alpha = 0.90,
  fair_c = 1.0,
  poisson_max_delta_step = 0.70,
  tweedie_variance_power = 1.5,
  lambdarank_truncation_level = 30,

  # Metric Parameters (metric is in Core)
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#metric-parameters
  is_provide_training_metric = TRUE,
  eval_at = c(1,2,3,4,5),

  # Network Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#network-parameters
  num_machines = 1,

  # GPU Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#gpu-parameters
  gpu_platform_id = -1,
  gpu_device_id = -1,
  gpu_use_dp = TRUE,
  num_gpu = 1)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoH2oGBMRegression(
  
  # Compute management
  MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
  NThreads = max(1, parallel::detectCores()-2),
  H2OShutdown = TRUE,
  H2OStartUp = TRUE,
  IfSaveModel = "mojo",
  
  # Model evaluation
  NumOfParDepPlots = 3,
  
  # Metadata arguments:
  model_path = normalizePath("./"),
  metadata_path = file.path(normalizePath("./")),
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  
  # Data arguments
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = 'Adrian',
  FeatureColNames = names(data)[!names(data) %in% c('IDcol_1','IDcol_2','Adrian')],
  WeightsColumn = NULL,
  TransformNumericColumns = NULL,
  Methods = c('Asinh','Asin','Log','LogPlus1','Sqrt','Logit'),
  
  # ML grid tuning args
  GridTune = FALSE,
  GridStrategy = "Cartesian",
  MaxRuntimeSecs = 60*60*24,
  StoppingRounds = 10,
  MaxModelsInGrid = 2,
  
  # Model args
  Trees = 50,
  LearnRate = 0.10,
  LearnRateAnnealing = 1,
  eval_metric = "RMSE",
  Alpha = NULL,
  Distribution = "poisson",
  MaxDepth = 20,
  SampleRate = 0.632,
  ColSampleRate = 1,
  ColSampleRatePerTree = 1,
  ColSampleRatePerTreeLevel  = 1,
  MinRows = 1,
  NBins = 20,
  NBinsCats = 1024,
  NBinsTopLevel = 1024,
  HistogramType = "AUTO",
  CategoricalEncoding = "AUTO")

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoH2oDRFRegression(
  
  # Compute management
  MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
  NThreads = max(1L, parallel::detectCores() - 2L),
  H2OShutdown = TRUE,
  H2OStartUp = TRUE,
  IfSaveModel = "mojo",
  
  # Model evaluation:
  eval_metric = "RMSE",
  NumOfParDepPlots = 3,
  
  # Metadata arguments:
  model_path = normalizePath("./"),
  metadata_path = NULL,
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  
  # Data Args
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
  WeightsColumn = NULL,
  TransformNumericColumns = NULL,
  Methods = c("Asinh", "Asin", "Log", "LogPlus1", "Sqrt", "Logit"),
  
  # Grid Tuning Args
  GridStrategy = "Cartesian",
  GridTune = FALSE,
  MaxModelsInGrid = 10,
  MaxRuntimeSecs = 60*60*24,
  StoppingRounds = 10,
  
  # ML Args
  Trees = 50,
  MaxDepth = 20,
  SampleRate = 0.632,
  MTries = -1,
  ColSampleRatePerTree = 1,
  ColSampleRatePerTreeLevel = 1,
  MinRows = 1,
  NBins = 20,
  NBinsCats = 1024,
  NBinsTopLevel = 1024,
  HistogramType = "AUTO",
  CategoricalEncoding = "AUTO")

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoH2oGLMRegression(
  
  # Compute management
  MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
  NThreads = max(1, parallel::detectCores()-2),
  H2OShutdown = TRUE,
  H2OStartUp = TRUE,
  IfSaveModel = "mojo",
  
  # Model evaluation:
  eval_metric = "RMSE",
  NumOfParDepPlots = 3,
  
  # Metadata arguments:
  model_path = NULL,
  metadata_path = NULL,
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  
  # Data arguments:
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
  RandomColNumbers = NULL,
  InteractionColNumbers = NULL,
  WeightsColumn = NULL,
  TransformNumericColumns = NULL,
  Methods = c("Asinh", "Asin", "Log", "LogPlus1", "Sqrt", "Logit"),
  
  # Model args
  GridTune = FALSE,
  GridStrategy = "Cartesian",
  StoppingRounds = 10,
  MaxRunTimeSecs = 3600 * 24 * 7,
  MaxModelsInGrid = 10,
  Distribution = "gaussian",
  Link = "identity",
  TweedieLinkPower = NULL,
  TweedieVariancePower = NULL,
  RandomDistribution = NULL,
  RandomLink = NULL,
  Solver = "AUTO",
  Alpha = NULL,
  Lambda = NULL,
  LambdaSearch = FALSE,
  NLambdas = -1,
  Standardize = TRUE,
  RemoveCollinearColumns = FALSE,
  InterceptInclude = TRUE,
  NonNegativeCoefficients = FALSE)

# Create some dummy correlated data with numeric and categorical features
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoH2oMLRegression(

  # Compute management
  MaxMem = "32G",
  NThreads = max(1, parallel::detectCores()-2),
  H2OShutdown = TRUE,
  IfSaveModel = "mojo",

  # Model evaluation
  eval_metric = "RMSE",
  NumOfParDepPlots = 3,

  # Metadata arguments
  model_path = NULL,
  metadata_path = NULL,
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,

  # Data arguments
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
  TransformNumericColumns = NULL,
  Methods = c("Asinh", "Asin", "Log", "LogPlus1", "Logit"),

  # Model args
  GridTune = FALSE,
  ExcludeAlgos = NULL,
  Trees = 50,
  MaxModelsInGrid = 10)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Define GAM Columns to use - up to 9 are allowed
GamCols <- names(which(unlist(lapply(data, is.numeric))))
GamCols <- GamCols[!GamCols %in% c("Adrian","IDcol_1","IDcol_2")]
GamCols <- GamCols[1L:(min(9L,length(GamCols)))]

# Run function
TestModel <- AutoQuant::AutoH2oGAMRegression(
  
  # Compute management
  MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
  NThreads = max(1, parallel::detectCores()-2),
  H2OShutdown = TRUE,
  H2OStartUp = TRUE,
  IfSaveModel = "mojo",
  
  # Model evaluation:
  eval_metric = "RMSE",
  NumOfParDepPlots = 3,
  
  # Metadata arguments:
  model_path = NULL,
  metadata_path = NULL,
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  
  # Data arguments:
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
  InteractionColNumbers = NULL,
  WeightsColumn = NULL,
  GamColNames = GamCols,
  TransformNumericColumns = NULL,
  Methods = c("Asinh", "Asin", "Log", "LogPlus1", "Sqrt", "Logit"),
  
  # Model args
  num_knots = NULL,
  keep_gam_cols = TRUE,
  GridTune = FALSE,
  GridStrategy = "Cartesian",
  StoppingRounds = 10,
  MaxRunTimeSecs = 3600 * 24 * 7,
  MaxModelsInGrid = 10,
  Distribution = "gaussian",
  Link = "Family_Default",
  TweedieLinkPower = NULL,
  TweedieVariancePower = NULL,
  Solver = "AUTO",
  Alpha = NULL,
  Lambda = NULL,
  LambdaSearch = FALSE,
  NLambdas = -1,
  Standardize = TRUE,
  RemoveCollinearColumns = FALSE,
  InterceptInclude = TRUE,
  NonNegativeCoefficients = FALSE)

The Auto_Classifier() models handle a multitude of tasks. In order:

1. Convert your data to data.table format for faster processing
2. Create train, validation, and test data if you didn’t supply those directly to the function
3. Consoldate columns that are used for modeling and what is to be kept for data returned
4. Dichotomize categorical variables (for AutoXGBoostRegression) and save the factor levels for scoring in a way that guarentees consistency across training, validation, and test data sets
5. Saves the final column names for modeling to a csv for later reference
6. Handles the data conversion to the appropriate type, based on model type (CatBoost, H2O, and XGBoost)
7. Multi-armed bandit hyperparameter tuning using randomized probability matching, if you choose to grid tune
8. Build the grid tuned models
9. Collect the evaluation metrics for each grid tune run
10. Identify the best model of the set of models built in the grid tuning setup
11. Save the hyperparameters from the winning grid tuned model
12. Build the final model based on the best model from the grid tuning model search
13. Collect evaluation metrics based on performance on test data
14. Store the final predictions with the associated test data and other columns you want included in that set
15. Build out and save an Evaluation Calibration Line Plot
16. Build out and save an ROC plot with the top 5 models used in grid-tuning (includes the winning model)
17. Generate and save Variable Importance data
18. Generate and save Partital Dependence Calibration Line Plots
19. Return all the objects generated in a named list for immediate use

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 10000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = TRUE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoCatBoostClassifier(

  # GPU or CPU and the number of available GPUs
  task_type = 'GPU',
  NumGPUs = 1,
  TrainOnFull = FALSE,
  DebugMode = FALSE,

  # Metadata args
  OutputSelection = c('Score_TrainData', 'Importance', 'EvalPlots', 'Metrics', 'PDF'),
  ModelID = 'Test_Model_1',
  model_path = normalizePath('./'),
  metadata_path = normalizePath('./'),
  SaveModelObjects = FALSE,
  ReturnModelObjects = TRUE,
  SaveInfoToPDF = FALSE,

  # Data args
  data = data,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = 'Adrian',
  FeatureColNames = names(data)[!names(data) %in%
     c('IDcol_1','IDcol_2','Adrian')],
  PrimaryDateColumn = NULL,
  WeightsColumnName = NULL,
  IDcols = c('IDcol_1','IDcol_2'),

  # Evaluation args
  ClassWeights = c(1L,1L),
  CostMatrixWeights = c(1,0,0,1),
  EvalMetric = 'AUC',
  grid_eval_metric = 'MCC',
  LossFunction = 'Logloss',
  MetricPeriods = 10L,
  NumOfParDepPlots = ncol(data)-1L-2L,

  # Grid tuning args
  PassInGrid = NULL,
  GridTune = FALSE,
  MaxModelsInGrid = 30L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  BaselineComparison = 'default',

  # ML args
  Trees = 1000,
  Depth = 9,
  LearningRate = NULL,
  L2_Leaf_Reg = NULL,
  model_size_reg = 0.5,
  langevin = FALSE,
  diffusion_temperature = 10000,
  RandomStrength = 1,
  BorderCount = 128,
  RSM = 1,
  BootStrapType = 'Bayesian',
  GrowPolicy = 'SymmetricTree',
  feature_border_type = 'GreedyLogSum',
  sampling_unit = 'Object',
  subsample = NULL,
  score_function = 'Cosine',
  min_data_in_leaf = 1)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000L,
  ID = 2L,
  ZIP = 0L,
  AddDate = FALSE,
  Classification = TRUE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoXGBoostClassifier(

  # GPU or CPU
  TreeMethod = "hist",
  NThreads = parallel::detectCores(),

  # Metadata args
  OutputSelection = c("Importances", "EvalPlots", "EvalMetrics", "PDFs", "Score_TrainData"),
  model_path = normalizePath("./"),
  metadata_path = NULL,
  ModelID = "Test_Model_1",
  EncodingMethod = "binary",
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,

  # Data args
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in%
    c("IDcol_1", "IDcol_2","Adrian")],
  WeightsColumnName = NULL,
  IDcols = c("IDcol_1","IDcol_2"),

  # Model evaluation
  LossFunction = 'reg:logistic',
  CostMatrixWeights = c(1,0,0,1),
  eval_metric = "auc",
  grid_eval_metric = "MCC",
  NumOfParDepPlots = 3L,

  # Grid tuning args
  PassInGrid = NULL,
  GridTune = FALSE,
  BaselineComparison = "default",
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  Verbose = 1L,

  # ML args
  Trees = 500L,
  eta = 0.30,
  max_depth = 9L,
  min_child_weight = 1.0,
  subsample = 1,
  colsample_bytree = 1,
  DebugMode = FALSE)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoLightGBMClassifier(

  # Metadata args
  OutputSelection = c("Importances","EvalPlots","EvalMetrics","Score_TrainData"),
  model_path = normalizePath("./"),
  metadata_path = NULL,
  ModelID = "Test_Model_1",
  NumOfParDepPlots = 3L,
  EncodingMethod = "credibility",
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  DebugMode = FALSE,

  # Data args
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
  PrimaryDateColumn = NULL,
  WeightsColumnName = NULL,
  IDcols = c("IDcol_1","IDcol_2"),

  # Grid parameters
  GridTune = FALSE,
  grid_eval_metric = 'Utility',
  BaselineComparison = 'default',
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  PassInGrid = NULL,

  # Core parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#core-parameters
  input_model = NULL, # continue training a model that is stored to file
  task = "train",
  device_type = 'CPU',
  NThreads = parallel::detectCores() / 2,
  objective = 'binary',
  metric = 'binary_logloss',
  boosting = 'gbdt',
  LinearTree = FALSE,
  Trees = 50L,
  eta = NULL,
  num_leaves = 31,
  deterministic = TRUE,

  # Learning Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#learning-control-parameters
  force_col_wise = FALSE,
  force_row_wise = FALSE,
  max_depth = NULL,
  min_data_in_leaf = 20,
  min_sum_hessian_in_leaf = 0.001,
  bagging_freq = 0,
  bagging_fraction = 1.0,
  feature_fraction = 1.0,
  feature_fraction_bynode = 1.0,
  extra_trees = FALSE,
  early_stopping_round = 10,
  first_metric_only = TRUE,
  max_delta_step = 0.0,
  lambda_l1 = 0.0,
  lambda_l2 = 0.0,
  linear_lambda = 0.0,
  min_gain_to_split = 0,
  drop_rate_dart = 0.10,
  max_drop_dart = 50,
  skip_drop_dart = 0.50,
  uniform_drop_dart = FALSE,
  top_rate_goss = FALSE,
  other_rate_goss = FALSE,
  monotone_constraints = NULL,
  monotone_constraints_method = "advanced",
  monotone_penalty = 0.0,
  forcedsplits_filename = NULL, # use for AutoStack option; .json file
  refit_decay_rate = 0.90,
  path_smooth = 0.0,

  # IO Dataset Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#io-parameters
  max_bin = 255,
  min_data_in_bin = 3,
  data_random_seed = 1,
  is_enable_sparse = TRUE,
  enable_bundle = TRUE,
  use_missing = TRUE,
  zero_as_missing = FALSE,
  two_round = FALSE,

  # Convert Parameters
  convert_model = NULL,
  convert_model_language = "cpp",

  # Objective Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#objective-parameters
  boost_from_average = TRUE,
  is_unbalance = FALSE,
  scale_pos_weight = 1.0,

  # Metric Parameters (metric is in Core)
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#metric-parameters
  is_provide_training_metric = TRUE,
  eval_at = c(1,2,3,4,5),

  # Network Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#network-parameters
  num_machines = 1,

  # GPU Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#gpu-parameters
  gpu_platform_id = -1,
  gpu_device_id = -1,
  gpu_use_dp = TRUE,
  num_gpu = 1)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000L,
  ID = 2L,
  ZIP = 0L,
  AddDate = FALSE,
  Classification = TRUE,
  MultiClass = FALSE)

TestModel <- AutoQuant::AutoH2oGBMClassifier(
  
  # Compute management
  MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
  NThreads = max(1, parallel::detectCores()-2),
  H2OShutdown = TRUE,
  H2OStartUp = TRUE,
  IfSaveModel = "mojo",
  
  # Model evaluation
  NumOfParDepPlots = 3,
  
  # Metadata arguments:
  model_path = normalizePath("./"),
  metadata_path = file.path(normalizePath("./")),
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  
  # Data arguments
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
  WeightsColumn = NULL,
  
  # ML grid tuning args
  GridTune = FALSE,
  GridStrategy = "Cartesian",
  MaxRuntimeSecs = 60*60*24,
  StoppingRounds = 10,
  MaxModelsInGrid = 2,
  
  # Model args
  Trees = 50,
  LearnRate = 0.10,
  LearnRateAnnealing = 1,
  eval_metric = "auc",
  Distribution = "bernoulli",
  MaxDepth = 20,
  SampleRate = 0.632,
  ColSampleRate = 1,
  ColSampleRatePerTree = 1,
  ColSampleRatePerTreeLevel  = 1,
  MinRows = 1,
  NBins = 20,
  NBinsCats = 1024,
  NBinsTopLevel = 1024,
  HistogramType = "AUTO",
  CategoricalEncoding = "AUTO")

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000L,
  ID = 2L,
  ZIP = 0L,
  AddDate = FALSE,
  Classification = TRUE,
  MultiClass = FALSE)

TestModel <- AutoQuant::AutoH2oDRFClassifier(
  
  # Compute management
  MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
  NThreads = max(1L, parallel::detectCores() - 2L),
  IfSaveModel = "mojo",
  H2OShutdown = FALSE,
  H2OStartUp = TRUE,
  
  # Metadata arguments:
  eval_metric = "auc",
  NumOfParDepPlots = 3L,
  
  # Data arguments:
  model_path = normalizePath("./"),
  metadata_path = NULL,
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  
  # Model evaluation:
  data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2", "Adrian")],
  WeightsColumn = NULL,
  
  # Grid Tuning Args
  GridStrategy = "Cartesian",
  GridTune = FALSE,
  MaxModelsInGrid = 10,
  MaxRuntimeSecs = 60*60*24,
  StoppingRounds = 10,
  
  # Model args
  Trees = 50L,
  MaxDepth = 20,
  SampleRate = 0.632,
  MTries = -1,
  ColSampleRatePerTree = 1,
  ColSampleRatePerTreeLevel = 1,
  MinRows = 1,
  NBins = 20,
  NBinsCats = 1024,
  NBinsTopLevel = 1024,
  HistogramType = "AUTO",
  CategoricalEncoding = "AUTO")

# Create some dummy correlated data with numeric and categorical features
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000L,
  ID = 2L,
  ZIP = 0L,
  AddDate = FALSE,
  Classification = TRUE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoH2oGLMClassifier(
  
  # Compute management
  MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
  NThreads = max(1, parallel::detectCores()-2),
  H2OShutdown = TRUE,
  H2OStartUp = TRUE,
  IfSaveModel = "mojo",
  
  # Model evaluation args
  eval_metric = "auc",
  NumOfParDepPlots = 3,
  
  # Metadata args
  model_path = NULL,
  metadata_path = NULL,
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  
  # Data args
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in%
                                  c("IDcol_1", "IDcol_2","Adrian")],
  RandomColNumbers = NULL,
  InteractionColNumbers = NULL,
  WeightsColumn = NULL,
  
  # ML args
  GridTune = FALSE,
  GridStrategy = "Cartesian",
  StoppingRounds = 10,
  MaxRunTimeSecs = 3600 * 24 * 7,
  MaxModelsInGrid = 10,
  Distribution = "binomial",
  Link = "logit",
  RandomDistribution = NULL,
  RandomLink = NULL,
  Solver = "AUTO",
  Alpha = NULL,
  Lambda = NULL,
  LambdaSearch = FALSE,
  NLambdas = -1,
  Standardize = TRUE,
  RemoveCollinearColumns = FALSE,
  InterceptInclude = TRUE,
  NonNegativeCoefficients = FALSE)

# Create some dummy correlated data with numeric and categorical features
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85, 
  N = 1000L, 
  ID = 2L, 
  ZIP = 0L, 
  AddDate = FALSE, 
  Classification = TRUE, 
  MultiClass = FALSE)

TestModel <- AutoQuant::AutoH2oMLClassifier(
   data,
   TrainOnFull = FALSE,
   ValidationData = NULL,
   TestData = NULL,
   TargetColumnName = "Adrian",
   FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
   ExcludeAlgos = NULL,
   eval_metric = "auc",
   Trees = 50,
   MaxMem = "32G",
   NThreads = max(1, parallel::detectCores()-2),
   MaxModelsInGrid = 10,
   model_path = normalizePath("./"),
   metadata_path = file.path(normalizePath("./"), "MetaData"),
   ModelID = "FirstModel",
   NumOfParDepPlots = 3,
   ReturnModelObjects = TRUE,
   SaveModelObjects = FALSE,
   IfSaveModel = "mojo",
   H2OShutdown = FALSE,
   HurdleModel = FALSE)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = TRUE,
  MultiClass = FALSE)

# Define GAM Columns to use - up to 9 are allowed
GamCols <- names(which(unlist(lapply(data, is.numeric))))
GamCols <- GamCols[!GamCols %in% c("Adrian","IDcol_1","IDcol_2")]
GamCols <- GamCols[1L:(min(9L,length(GamCols)))]

# Run function
TestModel <- AutoQuant::AutoH2oGAMClassifier(

  # Compute management
  MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
  NThreads = max(1, parallel::detectCores()-2),
  H2OShutdown = TRUE,
  H2OStartUp = TRUE,
  IfSaveModel = "mojo",

  # Model evaluation:
  eval_metric = "auc",
  NumOfParDepPlots = 3,

  # Metadata arguments:
  model_path = NULL,
  metadata_path = NULL,
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,

  # Data arguments:
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
  WeightsColumn = NULL,
  GamColNames = GamCols,

  # ML args
  num_knots = NULL,
  keep_gam_cols = TRUE,
  GridTune = FALSE,
  GridStrategy = "Cartesian",
  StoppingRounds = 10,
  MaxRunTimeSecs = 3600 * 24 * 7,
  MaxModelsInGrid = 10,
  Distribution = "binomial",
  Link = "logit",
  Solver = "AUTO",
  Alpha = NULL,
  Lambda = NULL,
  LambdaSearch = FALSE,
  NLambdas = -1,
  Standardize = TRUE,
  RemoveCollinearColumns = FALSE,
  InterceptInclude = TRUE,
  NonNegativeCoefficients = FALSE)

The Auto_MultiClass() models handle a multitude of tasks. In order:

1. Convert your data to data.table format for faster processing
2. Create train, validation, and test data if you didn’t supply those directly to the function
3. Consoldate columns that are used for modeling and what is to be kept for data returned
4. Dichotomize categorical variables (for AutoXGBoostRegression) and save the factor levels for scoring in a way that guarentees consistency across training, validation, and test data sets
5. Saves the final column names for modeling to a csv for later reference
6. Ensures the target levels are consistent across train, validate, and test sets and save the levels to file
7. Handles the data conversion to the appropriate type, based on model type (CatBoost, H2O, and XGBoost)
8. Multi-armed bandit hyperparameter tuning using randomized probability matching, if you choose to grid tune
9. Build the grid tuned models
10. Collect the evaluation metrics for each grid tune run
11. Identify the best model of the set of models built in the grid tuning setup
12. Save the hyperparameters from the winning grid tuned model
13. Build the final model based on the best model from the grid tuning model search
14. Collect evaluation metrics based on performance on test data
15. Store the final predictions with the associated test data and other columns you want included in that set
16. Generate and save Variable Importance data
17. Return all the objects generated in a named list for immediate use

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 10000L,
  ID = 2L,
  ZIP = 0L,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = TRUE)

# Run function
TestModel <- AutoQuant::AutoCatBoostMultiClass(
  
  # GPU or CPU and the number of available GPUs
  task_type = 'GPU',
  NumGPUs = 1,
  TrainOnFull = FALSE,
  DebugMode = FALSE,
  
  # Metadata args
  OutputSelection = c('Importances', 'EvalPlots', 'EvalMetrics', 'Score_TrainData'),
  ModelID = 'Test_Model_1',
  model_path = normalizePath('./'),
  metadata_path = normalizePath('./'),
  SaveModelObjects = FALSE,
  ReturnModelObjects = TRUE,
  
  # Data args
  data = data,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = 'Adrian',
  FeatureColNames = names(data)[!names(data) %in%
                                  c('IDcol_1', 'IDcol_2','Adrian')],
  PrimaryDateColumn = NULL,
  WeightsColumnName = NULL,
  ClassWeights = c(1L,1L,1L,1L,1L),
  IDcols = c('IDcol_1','IDcol_2'),
  
  # Model evaluation
  eval_metric = 'MCC',
  loss_function = 'MultiClassOneVsAll',
  grid_eval_metric = 'Accuracy',
  MetricPeriods = 10L,
  NumOfParDepPlots = 3,
  
  # Grid tuning args
  PassInGrid = NULL,
  GridTune = TRUE,
  MaxModelsInGrid = 30L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  BaselineComparison = 'default',
  
  # ML args
  langevin = FALSE,
  diffusion_temperature = 10000,
  Trees = seq(100L, 500L, 50L),
  Depth = seq(4L, 8L, 1L),
  LearningRate = seq(0.01,0.10,0.01),
  L2_Leaf_Reg = seq(1.0, 10.0, 1.0),
  RandomStrength = 1,
  BorderCount = 254,
  RSM = c(0.80, 0.85, 0.90, 0.95, 1.0),
  BootStrapType = c('Bayesian', 'Bernoulli', 'Poisson', 'MVS', 'No'),
  GrowPolicy = c('SymmetricTree', 'Depthwise', 'Lossguide'),
  model_size_reg = 0.5,
  feature_border_type = 'GreedyLogSum',
  sampling_unit = 'Object',
  subsample = NULL,
  score_function = 'Cosine',
  min_data_in_leaf = 1)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000L,
  ID = 2L,
  ZIP = 0L,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = TRUE)

# Run function
TestModel <- AutoQuant::AutoXGBoostMultiClass(
  
  # GPU or CPU
  TreeMethod = "hist",
  NThreads = parallel::detectCores(),
  
  # Metadata args
  OutputSelection = c("Importances", "EvalPlots", "EvalMetrics", "PDFs", "Score_TrainData"),
  model_path = normalizePath("./"),
  metadata_path = normalizePath("./"),
  ModelID = "Test_Model_1",
  EncodingMethod = "binary",
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  
  # Data args
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in%
                                  c("IDcol_1", "IDcol_2","Adrian")],
  WeightsColumnName = NULL,
  IDcols = c("IDcol_1","IDcol_2"),
  
  # Model evaluation args
  eval_metric = "merror",
  LossFunction = 'multi:softprob',
  grid_eval_metric = "accuracy",
  NumOfParDepPlots = 3L,
  
  # Grid tuning args
  PassInGrid = NULL,
  GridTune = FALSE,
  BaselineComparison = "default",
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  Verbose = 1L,
  DebugMode = FALSE,
  
  # ML args
  Trees = 50L,
  eta = 0.05,
  max_depth = 4L,
  min_child_weight = 1.0,
  subsample = 0.55,
  colsample_bytree = 0.55)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Run function
TestModel <- AutoQuant::AutoLightGBMMultiClass(

  # Metadata args
  OutputSelection = c("Importances","EvalPlots","EvalMetrics","Score_TrainData"),
  model_path = normalizePath("./"),
  metadata_path = NULL,
  ModelID = "Test_Model_1",
  NumOfParDepPlots = 3L,
  EncodingMethod = "credibility",
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  DebugMode = FALSE,

  # Data args
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
  PrimaryDateColumn = NULL,
  WeightsColumnName = NULL,
  IDcols = c("IDcol_1","IDcol_2"),

  # Grid parameters
  GridTune = FALSE,
  grid_eval_metric = 'microauc',
  BaselineComparison = 'default',
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  PassInGrid = NULL,

  # Core parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#core-parameters
  input_model = NULL, # continue training a model that is stored to file
  task = "train",
  device_type = 'CPU',
  NThreads = parallel::detectCores() / 2,
  objective = 'multiclass',
  multi_error_top_k = 1,
  metric = 'multi_logloss',
  boosting = 'gbdt',
  LinearTree = FALSE,
  Trees = 50L,
  eta = NULL,
  num_leaves = 31,
  deterministic = TRUE,

  # Learning Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#learning-control-parameters
  force_col_wise = FALSE,
  force_row_wise = FALSE,
  max_depth = NULL,
  min_data_in_leaf = 20,
  min_sum_hessian_in_leaf = 0.001,
  bagging_freq = 0,
  bagging_fraction = 1.0,
  feature_fraction = 1.0,
  feature_fraction_bynode = 1.0,
  extra_trees = FALSE,
  early_stopping_round = 10,
  first_metric_only = TRUE,
  max_delta_step = 0.0,
  lambda_l1 = 0.0,
  lambda_l2 = 0.0,
  linear_lambda = 0.0,
  min_gain_to_split = 0,
  drop_rate_dart = 0.10,
  max_drop_dart = 50,
  skip_drop_dart = 0.50,
  uniform_drop_dart = FALSE,
  top_rate_goss = FALSE,
  other_rate_goss = FALSE,
  monotone_constraints = NULL,
  monotone_constraints_method = "advanced",
  monotone_penalty = 0.0,
  forcedsplits_filename = NULL, # use for AutoStack option; .json file
  refit_decay_rate = 0.90,
  path_smooth = 0.0,

  # IO Dataset Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#io-parameters
  max_bin = 255,
  min_data_in_bin = 3,
  data_random_seed = 1,
  is_enable_sparse = TRUE,
  enable_bundle = TRUE,
  use_missing = TRUE,
  zero_as_missing = FALSE,
  two_round = FALSE,

  # Convert Parameters
  convert_model = NULL,
  convert_model_language = "cpp",

  # Objective Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#objective-parameters
  boost_from_average = TRUE,
  is_unbalance = FALSE,
  scale_pos_weight = 1.0,

  # Metric Parameters (metric is in Core)
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#metric-parameters
  is_provide_training_metric = TRUE,
  eval_at = c(1,2,3,4,5),

  # Network Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#network-parameters
  num_machines = 1,

  # GPU Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#gpu-parameters
  gpu_platform_id = -1,
  gpu_device_id = -1,
  gpu_use_dp = TRUE,
  num_gpu = 1)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = TRUE)

# Run function
TestModel <- AutoQuant::AutoH2oGBMMultiClass(
   data,
   TrainOnFull = FALSE,
   ValidationData = NULL,
   TestData = NULL,
   TargetColumnName = "Adrian",
   FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
   WeightsColumn = NULL,
   eval_metric = "logloss",
   MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
   NThreads = max(1, parallel::detectCores()-2),
   model_path = normalizePath("./"),
   metadata_path = file.path(normalizePath("./")),
   ModelID = "FirstModel",
   ReturnModelObjects = TRUE,
   SaveModelObjects = FALSE,
   IfSaveModel = "mojo",
   H2OShutdown = TRUE,
   H2OStartUp = TRUE,

   # Model args
   GridTune = FALSE,
   GridStrategy = "Cartesian",
   MaxRuntimeSecs = 60*60*24,
   StoppingRounds = 10,
   MaxModelsInGrid = 2,
   Trees = 50,
   LearnRate = 0.10,
   LearnRateAnnealing = 1,
   eval_metric = "RMSE",
   Distribution = "multinomial",
   MaxDepth = 20,
   SampleRate = 0.632,
   ColSampleRate = 1,
   ColSampleRatePerTree = 1,
   ColSampleRatePerTreeLevel  = 1,
   MinRows = 1,
   NBins = 20,
   NBinsCats = 1024,
   NBinsTopLevel = 1024,
   HistogramType = "AUTO",
   CategoricalEncoding = "AUTO")

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000L,
  ID = 2L,
  ZIP = 0L,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = TRUE)

# Run function
TestModel <- AutoQuant::AutoH2oDRFMultiClass(
  data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
  WeightsColumn = NULL,
  eval_metric = "logloss",
  MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
  NThreads = max(1, parallel::detectCores()-2),
  model_path = normalizePath("./"),
  metadata_path = file.path(normalizePath("./")),
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  IfSaveModel = "mojo",
  H2OShutdown = FALSE,
  H2OStartUp = TRUE,

  # Grid Tuning Args
  GridStrategy = "Cartesian",
  GridTune = FALSE,
  MaxModelsInGrid = 10,
  MaxRuntimeSecs = 60*60*24,
  StoppingRounds = 10,

  # ML args
  Trees = 50,
  MaxDepth = 20,
  SampleRate = 0.632,
  MTries = -1,
  ColSampleRatePerTree = 1,
  ColSampleRatePerTreeLevel = 1,
  MinRows = 1,
  NBins = 20,
  NBinsCats = 1024,
  NBinsTopLevel = 1024,
  HistogramType = "AUTO",
  CategoricalEncoding = "AUTO")

# Create some dummy correlated data with numeric and categorical features
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000L,
  ID = 2L,
  ZIP = 0L,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = TRUE)

# Run function
TestModel <- AutoQuant::AutoH2oGLMMultiClass(
  
  # Compute management
  MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
  NThreads = max(1, parallel::detectCores()-2),
  H2OShutdown = TRUE,
  H2OStartUp = TRUE,
  IfSaveModel = "mojo",
  
  # Model evaluation:
  eval_metric = "logloss",
  NumOfParDepPlots = 3,
  
  # Metadata arguments:
  model_path = NULL,
  metadata_path = NULL,
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  
  # Data arguments:
  data = data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
  RandomColNumbers = NULL,
  InteractionColNumbers = NULL,
  WeightsColumn = NULL,
  
  # Model args
  GridTune = FALSE,
  GridStrategy = "Cartesian",
  StoppingRounds = 10,
  MaxRunTimeSecs = 3600 * 24 * 7,
  MaxModelsInGrid = 10,
  Distribution = "multinomial",
  Link = "family_default",
  RandomDistribution = NULL,
  RandomLink = NULL,
  Solver = "AUTO",
  Alpha = NULL,
  Lambda = NULL,
  LambdaSearch = FALSE,
  NLambdas = -1,
  Standardize = TRUE,
  RemoveCollinearColumns = FALSE,
  InterceptInclude = TRUE,
  NonNegativeCoefficients = FALSE)

# Create some dummy correlated data with numeric and categorical features
data <- AutoQuant::FakeDataGenerator(Correlation = 0.85, N = 1000, ID = 2, ZIP = 0, AddDate = FALSE, Classification = FALSE, MultiClass = TRUE)

# Run function
TestModel <- AutoQuant::AutoH2oMLMultiClass(
   data,
   TrainOnFull = FALSE,
   ValidationData = NULL,
   TestData = NULL,
   TargetColumnName = "Adrian",
   FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
   ExcludeAlgos = NULL,
   eval_metric = "logloss",
   Trees = 50,
   MaxMem = "32G",
   NThreads = max(1, parallel::detectCores()-2),
   MaxModelsInGrid = 10,
   model_path = normalizePath("./"),
   metadata_path = file.path(normalizePath("./"), "MetaData"),
   ModelID = "FirstModel",
   ReturnModelObjects = TRUE,
   SaveModelObjects = FALSE,
   IfSaveModel = "mojo",
   H2OShutdown = FALSE,
   HurdleModel = FALSE)

# Create some dummy correlated data with numeric and categorical features
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 1000L,
  ID = 2L,
  ZIP = 0L,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = TRUE)

# Define GAM Columns to use - up to 9 are allowed
GamCols <- names(which(unlist(lapply(data, is.numeric))))
GamCols <- GamCols[!GamCols %in% c("Adrian","IDcol_1","IDcol_2")]
GamCols <- GamCols[1L:(min(9L,length(GamCols)))]

# Run function
TestModel <- AutoQuant::AutoH2oGAMMultiClass(
  data,
  TrainOnFull = FALSE,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = "Adrian",
  FeatureColNames = names(data)[!names(data) %in% c("IDcol_1", "IDcol_2","Adrian")],
  WeightsColumn = NULL,
  GamColNames = GamCols,
  eval_metric = "logloss",
  MaxMem = {gc();paste0(as.character(floor(as.numeric(system("awk '/MemFree/ {print $2}' /proc/meminfo", intern=TRUE)) / 1000000)),"G")},
  NThreads = max(1, parallel::detectCores()-2),
  model_path = normalizePath("./"),
  metadata_path = NULL,
  ModelID = "FirstModel",
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  IfSaveModel = "mojo",
  H2OShutdown = FALSE,
  H2OStartUp = TRUE,
  
  # ML args
  num_knots = NULL,
  keep_gam_cols = TRUE,
  GridTune = FALSE,
  GridStrategy = "Cartesian",
  StoppingRounds = 10,
  MaxRunTimeSecs = 3600 * 24 * 7,
  MaxModelsInGrid = 10,
  Distribution = "multinomial",
  Link = "Family_Default",
  Solver = "AUTO",
  Alpha = NULL,
  Lambda = NULL,
  LambdaSearch = FALSE,
  NLambdas = -1,
  Standardize = TRUE,
  RemoveCollinearColumns = FALSE,
  InterceptInclude = TRUE,
  NonNegativeCoefficients = FALSE)

# Create some dummy correlated data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 10000,
  ID = 2,
  ZIP = 0,
  AddDate = FALSE,
  Classification = FALSE,
  MultiClass = FALSE)

# Copy data
data1 <- data.table::copy(data)

# Feature Colnames
Features <- names(data1)[!names(data1) %in% c("IDcol_1", "IDcol_2","DateTime","Adrian")]

# Run function
TestModel <- AutoQuant::AutoCatBoostRegression(
  
  # GPU or CPU and the number of available GPUs
  TrainOnFull = FALSE,
  task_type = 'CPU',
  NumGPUs = 1,
  DebugMode = FALSE,
  
  # Metadata args
  OutputSelection = c('Importances','EvalPlots','EvalMetrics','Score_TrainData'),
  ModelID = 'Test_Model_1',
  model_path = getwd(),
  metadata_path = getwd(),
  SaveModelObjects = FALSE,
  SaveInfoToPDF = FALSE,
  ReturnModelObjects = TRUE,
  
  # Data args
  data = data1,
  ValidationData = NULL,
  TestData = NULL,
  TargetColumnName = 'Adrian',
  FeatureColNames = Features,
  PrimaryDateColumn = NULL,
  WeightsColumnName = NULL,
  IDcols = c('IDcol_1','IDcol_2'),
  TransformNumericColumns = 'Adrian',
  Methods = c('Asinh','Asin','Log','LogPlus1','Sqrt','Logit'),
  
  # Model evaluation
  eval_metric = 'RMSE',
  eval_metric_value = 1.5,
  loss_function = 'RMSE',
  loss_function_value = 1.5,
  MetricPeriods = 10L,
  NumOfParDepPlots = ncol(data1)-1L-2L,
  
  # Grid tuning args
  PassInGrid = NULL,
  GridTune = FALSE,
  MaxModelsInGrid = 30L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 60*60,
  BaselineComparison = 'default',
  
  # ML args
  langevin = FALSE,
  diffusion_temperature = 10000,
  Trees = 1000,
  Depth = 9,
  L2_Leaf_Reg = NULL,
  RandomStrength = 1,
  BorderCount = 128,
  LearningRate = NULL,
  RSM = 1,
  BootStrapType = NULL,
  GrowPolicy = 'SymmetricTree',
  model_size_reg = 0.5,
  feature_border_type = 'GreedyLogSum',
  sampling_unit = 'Object',
  subsample = NULL,
  score_function = 'Cosine',
  min_data_in_leaf = 1)


# Insights Report
AutoQuant::ModelInsightsReport(
  
  # Meta info
  TargetColumnName = 'Adrian',
  PredictionColumnName = 'Predict',
  FeatureColumnNames = Features,
  DateColumnName = NULL,
  
  # Control options
  TargetType = 'regression',
  ModelID = 'Test_Model_1',
  Algo = 'catboost',
  OutputPath = getwd(),
  ModelObject = TestModel)


# Score data
Preds <- AutoQuant::AutoCatBoostScoring(
  TargetType = 'regression',
  ScoringData = data,
  FeatureColumnNames = Features,
  FactorLevelsList = TestModel$FactorLevelsList,
  IDcols = c('IDcol_1','IDcol_2'),
  OneHot = FALSE,
  ReturnShapValues = TRUE,
  ModelObject = TestModel$Model,
  ModelPath = NULL,
  ModelID = 'Test_Model_1',
  ReturnFeatures = TRUE,
  MultiClassTargetLevels = NULL,
  TransformNumeric = FALSE,
  BackTransNumeric = FALSE,
  TargetColumnName = NULL,
  TransformationObject = NULL,
  TransID = NULL,
  TransPath = NULL,
  MDP_Impute = TRUE,
  MDP_CharToFactor = TRUE,
  MDP_RemoveDates = TRUE,
  MDP_MissFactor = '0',
  MDP_MissNum = -1,
  RemoveModel = FALSE)

# Refresh data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 25000L,
  ID = 2L,
  AddWeightsColumn = TRUE,
  ZIP = 0L,
  AddDate = TRUE,
  Classification = TRUE,
  MultiClass = FALSE)

# Copy data (used for scoring below``)
data1 <- data.table::copy(data)

# Partition Data
Sets <- Rodeo::AutoDataPartition(
  data = data,
  NumDataSets = 3,
  Ratios = c(0.7,0.2,0.1),
  PartitionType = "random",
  StratifyColumnNames = "Adrian",
  TimeColumnName = NULL)
TTrainData <- Sets$TrainData
VValidationData <- Sets$ValidationData
TTestData <- Sets$TestData
rm(Sets)

# Feature Colnames
Features <- names(TTrainData)[!names(TTrainData) %in% c("IDcol_1", "IDcol_2","DateTime","Adrian")]

# AutoCatBoostClassifier
TestModel <- AutoQuant::AutoCatBoostClassifier(
  
  # GPU or CPU and the number of available GPUs
  task_type = "CPU",
  NumGPUs = 1,
  
  # Metadata arguments
  OutputSelection = c("Importances", "EvalPlots", "EvalMetrics", "Score_TrainData"),
  ModelID = "Test_Model_1",
  model_path = normalizePath("./"),
  metadata_path = normalizePath("./"),
  SaveModelObjects = FALSE,
  ReturnModelObjects = TRUE,
  SaveInfoToPDF = FALSE,
  
  # Data arguments
  data = TTrainData,
  TrainOnFull = FALSE,
  ValidationData = VValidationData,
  TestData = TTestData,
  TargetColumnName = "Adrian",
  FeatureColNames = Features,
  PrimaryDateColumn = "DateTime",
  WeightsColumnName = "Weights",
  ClassWeights = c(1L,1L),
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  
  # Model evaluation
  CostMatrixWeights = c(2,0,0,1),
  EvalMetric = "MCC",
  LossFunction = "Logloss",
  grid_eval_metric = "Utility",
  MetricPeriods = 10L,
  NumOfParDepPlots = 3,
  
  # Grid tuning arguments
  PassInGrid = NULL,
  GridTune = FALSE,
  MaxModelsInGrid = 30L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  BaselineComparison = "default",
  
  # ML args
  Trees = 100L,
  Depth = 4L,
  LearningRate = NULL,
  L2_Leaf_Reg = NULL,
  RandomStrength = 1,
  BorderCount = 128,
  RSM = 0.80,
  BootStrapType = "Bayesian",
  GrowPolicy = "SymmetricTree",
  langevin = FALSE,
  diffusion_temperature = 10000,
  model_size_reg = 0.5,
  feature_border_type = "GreedyLogSum",
  sampling_unit = "Object",
  subsample = NULL,
  score_function = "Cosine",
  min_data_in_leaf = 1,
  DebugMode = TRUE)


# Insights Report
AutoQuant::ModelInsightsReport(
  
  # Meta info
  TargetColumnName = 'Adrian',
  PredictionColumnName = 'p1',
  FeatureColumnNames = Features,
  DateColumnName = NULL,
  
  # Control options
  TargetType = 'classification',
  ModelID = 'Test_Model_1',
  Algo = 'catboost',
  OutputPath = getwd(),
  ModelObject = TestModel)


# Score data
Preds <- AutoQuant::AutoCatBoostScoring(
  TargetType = 'classifier',
  ScoringData = data,
  FeatureColumnNames = Features,
  FactorLevelsList = TestModel$FactorLevelsList,
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  OneHot = FALSE,
  ReturnShapValues = TRUE,
  ModelObject = TestModel$Model,
  ModelPath = NULL,
  ModelID = 'Test_Model_1',
  ReturnFeatures = TRUE,
  MultiClassTargetLevels = NULL,
  TransformNumeric = FALSE,
  BackTransNumeric = FALSE,
  TargetColumnName = NULL,
  TransformationObject = NULL,
  TransID = NULL,
  TransPath = NULL,
  MDP_Impute = TRUE,
  MDP_CharToFactor = TRUE,
  MDP_RemoveDates = TRUE,
  MDP_MissFactor = '0',
  MDP_MissNum = -1,
  RemoveModel = FALSE)

# Refresh data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 25000L,
  ID = 2L,
  AddWeightsColumn = TRUE,
  ZIP = 0L,
  AddDate = TRUE,
  Classification = FALSE,
  MultiClass = TRUE)

# Copy data (used for scoring below``)
data1 <- data.table::copy(data)

# Partition Data
Sets <- Rodeo::AutoDataPartition(
  data = data,
  NumDataSets = 3,
  Ratios = c(0.7,0.2,0.1),
  PartitionType = "random",
  StratifyColumnNames = "Adrian",
  TimeColumnName = NULL)
TTrainData <- Sets$TrainData
VValidationData <- Sets$ValidationData
TTestData <- Sets$TestData
rm(Sets)

# Feature Colnames
Features <- names(TTrainData)[!names(TTrainData) %in% c("IDcol_1", "IDcol_2","Adrian","DateTime")]

# Run function
TestModel <- AutoQuant::AutoCatBoostMultiClass(
  
  # GPU or CPU and the number of available GPUs
  task_type = "GPU",
  NumGPUs = 1,
  
  # Metadata arguments
  OutputSelection = c("Importances", "EvalPlots", "EvalMetrics", "Score_TrainData"),
  ModelID = "Test_Model_1",
  model_path = normalizePath("./"),
  metadata_path = normalizePath("./"),
  SaveModelObjects = FALSE,
  ReturnModelObjects = TRUE,
  
  # Data arguments
  data = TTrainData,
  TrainOnFull = FALSE,
  ValidationData = VValidationData,
  TestData = TTestData,
  TargetColumnName = "Adrian",
  FeatureColNames = Features,
  PrimaryDateColumn = "DateTime",
  WeightsColumnName = "Weights",
  ClassWeights = c(1L,1L,1L,1L,1L),
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  
  # Model evaluation
  eval_metric = "MCC",
  loss_function = "MultiClassOneVsAll",
  grid_eval_metric = "Accuracy",
  MetricPeriods = 10L,
  
  # Grid tuning arguments
  PassInGrid = NULL,
  GridTune = FALSE,
  MaxModelsInGrid = 30L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  BaselineComparison = "default",
  
  # ML args
  Trees = 100L,
  Depth = 4L,
  LearningRate = 0.01,
  L2_Leaf_Reg = 1.0,
  RandomStrength = 1,
  BorderCount = 128,
  langevin = FALSE,
  diffusion_temperature = 10000,
  RSM = 0.80,
  BootStrapType = "Bayesian",
  GrowPolicy = "SymmetricTree",
  model_size_reg = 0.5,
  feature_border_type = "GreedyLogSum",
  sampling_unit = "Group",
  subsample = NULL,
  score_function = "Cosine",
  min_data_in_leaf = 1,
  DebugMode = TRUE)


# Insights Report
AutoQuant::ModelInsightsReport(
  
  # Meta info
  TargetColumnName = 'Adrian',
  PredictionColumnName = 'Predict',
  FeatureColumnNames = Features,
  DateColumnName = NULL,
  
  # Control options
  TargetType = 'multiclass',
  ModelID = 'Test_Model_1',
  Algo = 'catboost',
  OutputPath = getwd(),
  ModelObject = TestModel)


# Score data
Preds <- AutoQuant::AutoCatBoostScoring(
  TargetType = 'multiclass',
  ScoringData = data,
  FeatureColumnNames = Features,
  FactorLevelsList = TestModel$FactorLevelsList,
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  OneHot = FALSE,
  ReturnShapValues = FALSE,
  ModelObject = TestModel$Model,
  ModelPath = NULL,
  ModelID = 'Test_Model_1',
  ReturnFeatures = TRUE,
  MultiClassTargetLevels = TestModel$TargetLevels,
  TransformNumeric = FALSE,
  BackTransNumeric = FALSE,
  TargetColumnName = NULL,
  TransformationObject = NULL,
  TransID = NULL,
  TransPath = NULL,
  MDP_Impute = TRUE,
  MDP_CharToFactor = TRUE,
  MDP_RemoveDates = TRUE,
  MDP_MissFactor = '0',
  MDP_MissNum = -1,
  RemoveModel = FALSE)

# Refresh data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 25000L,
  ID = 2L,
  AddWeightsColumn = TRUE,
  ZIP = 0L,
  AddDate = TRUE,
  Classification = FALSE,
  MultiClass = FALSE)

# Partition Data
Sets <- Rodeo::AutoDataPartition(
  data = data,
  NumDataSets = 3,
  Ratios = c(0.7,0.2,0.1),
  PartitionType = "random",
  StratifyColumnNames = "Adrian",
  TimeColumnName = NULL)
TTrainData <- Sets$TrainData
VValidationData <- Sets$ValidationData
TTestData <- Sets$TestData
rm(Sets)

# Run function
TestModel <- AutoQuant::AutoLightGBMRegression(
  
  # GPU or CPU
  NThreads = parallel::detectCores(),
  
  # Metadata args
  OutputSelection = c("Importances","EvalPlots","EvalMetrics","Score_TrainData"),
  model_path = getwd(),
  metadata_path = getwd(),
  ModelID = "Test_Model_1",
  NumOfParDepPlots = 3L,
  EncodingMethod = "credibility",
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = TRUE,
  SaveInfoToPDF = FALSE,
  DebugMode = TRUE,
  
  # Data args
  data = TTrainData,
  TrainOnFull = FALSE,
  ValidationData = VValidationData,
  TestData = TTestData,
  TargetColumnName = "Adrian",
  FeatureColNames = names(TTrainData)[!names(TTrainData) %in% c("IDcol_1", "IDcol_2","DateTime","Adrian")],
  PrimaryDateColumn = "DateTime",
  WeightsColumnName = "Weights",
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  TransformNumericColumns = NULL,
  Methods = c("Asinh","Asin","Log","LogPlus1","Sqrt","Logit"),
  
  # Grid parameters
  GridTune = FALSE,
  grid_eval_metric = "r2",
  BaselineComparison = "default",
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  PassInGrid = NULL,
  
  # Core parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#core-parameters
  input_model = NULL, # continue training a model that is stored to file
  task = "train",
  device_type = "CPU",
  objective = 'regression',
  metric = "rmse",
  boosting = "gbdt",
  LinearTree = FALSE,
  Trees = 50L,
  eta = NULL,
  num_leaves = 31,
  deterministic = TRUE,
  
  # Learning Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#learning-control-parameters
  force_col_wise = FALSE,
  force_row_wise = FALSE,
  max_depth = 6,
  min_data_in_leaf = 20,
  min_sum_hessian_in_leaf = 0.001,
  bagging_freq = 1.0,
  bagging_fraction = 1.0,
  feature_fraction = 1.0,
  feature_fraction_bynode = 1.0,
  lambda_l1 = 0.0,
  lambda_l2 = 0.0,
  extra_trees = FALSE,
  early_stopping_round = 10,
  first_metric_only = TRUE,
  max_delta_step = 0.0,
  linear_lambda = 0.0,
  min_gain_to_split = 0,
  drop_rate_dart = 0.10,
  max_drop_dart = 50,
  skip_drop_dart = 0.50,
  uniform_drop_dart = FALSE,
  top_rate_goss = FALSE,
  other_rate_goss = FALSE,
  monotone_constraints = NULL,
  monotone_constraints_method = "advanced",
  monotone_penalty = 0.0,
  forcedsplits_filename = NULL, # use for AutoStack option; .json file
  refit_decay_rate = 0.90,
  path_smooth = 0.0,
  
  # IO Dataset Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#io-parameters
  max_bin = 255,
  min_data_in_bin = 3,
  data_random_seed = 1,
  is_enable_sparse = TRUE,
  enable_bundle = TRUE,
  use_missing = TRUE,
  zero_as_missing = FALSE,
  two_round = FALSE,
  
  # Convert Parameters
  convert_model = NULL,
  convert_model_language = "cpp",
  
  # Objective Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#objective-parameters
  boost_from_average = TRUE,
  alpha = 0.90,
  fair_c = 1.0,
  poisson_max_delta_step = 0.70,
  tweedie_variance_power = 1.5,
  lambdarank_truncation_level = 30,
  
  # Metric Parameters (metric is in Core)
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#metric-parameters
  is_provide_training_metric = TRUE,
  eval_at = c(1,2,3,4,5),
  
  # Network Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#network-parameters
  num_machines = 1,
  
  # GPU Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#gpu-parameters
  gpu_platform_id = -1,
  gpu_device_id = -1,
  gpu_use_dp = TRUE,
  num_gpu = 1)

# Outcome
ModelID = "Test_Model_1"
colnames <- data.table::fread(file = file.path(getwd(), paste0(ModelID, "_ColNames.csv")))
Preds <- AutoQuant::AutoLightGBMScoring(
  TargetType = "regression",
  ScoringData = TTestData,
  ReturnShapValues = FALSE,
  FeatureColumnNames = colnames[[1L]],
  IDcols = c("IDcol_1","IDcol_2"),
  EncodingMethod = "credibility",
  FactorLevelsList = NULL,
  TargetLevels = NULL,
  ModelObject = NULL,
  ModelPath = getwd(),
  ModelID = "Test_Model_1",
  ReturnFeatures = TRUE,
  TransformNumeric = FALSE,
  BackTransNumeric = FALSE,
  TargetColumnName = NULL,
  TransformationObject = NULL,
  TransID = NULL,
  TransPath = NULL,
  MDP_Impute = TRUE,
  MDP_CharToFactor = TRUE,
  MDP_RemoveDates = TRUE,
  MDP_MissFactor = "0",
  MDP_MissNum = -1)

# Refresh data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 25000L,
  ID = 2L,
  AddWeightsColumn = TRUE,
  ZIP = 0L,
  AddDate = TRUE,
  Classification = TRUE,
  MultiClass = FALSE)

# Partition Data
Sets <- Rodeo::AutoDataPartition(
  data = data,
  NumDataSets = 3,
  Ratios = c(0.7,0.2,0.1),
  PartitionType = "random",
  StratifyColumnNames = "Adrian",
  TimeColumnName = NULL)
TTrainData <- Sets$TrainData
VValidationData <- Sets$ValidationData
TTestData <- Sets$TestData
rm(Sets)

# Run function
TestModel <- AutoQuant::AutoLightGBMClassifier(
  
  # Multithreading
  NThreads = parallel::detectCores(),
  
  # Metadata args
  OutputSelection = c("Importances","EvalPlots","EvalMetrics","Score_TrainData"),
  model_path = normalizePath("./"),
  metadata_path = NULL,
  ModelID = "Test_Model_1",
  NumOfParDepPlots = 3L,
  EncodingMethod = "credibility",
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = TRUE,
  SaveInfoToPDF = FALSE,
  DebugMode = TRUE,
  
  # Data args
  data = TTrainData,
  TrainOnFull = FALSE,
  ValidationData = VValidationData,
  TestData = TTestData,
  TargetColumnName = "Adrian",
  FeatureColNames = names(TTrainData)[!names(TTrainData) %in% c("IDcol_1", "IDcol_2","DateTime","Adrian")],
  PrimaryDateColumn = NULL,
  WeightsColumnName = "Weights",
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  CostMatrixWeights = c(1,0,0,1),
  
  # Grid parameters
  GridTune = FALSE,
  grid_eval_metric = "Utility",
  BaselineComparison = "default",
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  PassInGrid = NULL,
  
  # Core parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#core-parameters
  input_model = NULL, # continue training a model that is stored to file
  task = "train",
  device_type = "CPU",
  objective = 'binary',
  metric = 'binary_logloss',
  boosting = "gbdt",
  LinearTree = FALSE,
  Trees = 50L,
  eta = NULL,
  num_leaves = 31,
  deterministic = TRUE,
  
  # Learning Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#learning-control-parameters
  force_col_wise = FALSE,
  force_row_wise = FALSE,
  max_depth = 6,
  min_data_in_leaf = 20,
  min_sum_hessian_in_leaf = 0.001,
  bagging_freq = 1.0,
  bagging_fraction = 1.0,
  feature_fraction = 1.0,
  feature_fraction_bynode = 1.0,
  lambda_l1 = 0.0,
  lambda_l2 = 0.0,
  extra_trees = FALSE,
  early_stopping_round = 10,
  first_metric_only = TRUE,
  max_delta_step = 0.0,
  linear_lambda = 0.0,
  min_gain_to_split = 0,
  drop_rate_dart = 0.10,
  max_drop_dart = 50,
  skip_drop_dart = 0.50,
  uniform_drop_dart = FALSE,
  top_rate_goss = FALSE,
  other_rate_goss = FALSE,
  monotone_constraints = NULL,
  monotone_constraints_method = 'advanced',
  monotone_penalty = 0.0,
  forcedsplits_filename = NULL, # use for AutoStack option; .json file
  refit_decay_rate = 0.90,
  path_smooth = 0.0,
  
  # IO Dataset Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#io-parameters
  max_bin = 255,
  min_data_in_bin = 3,
  data_random_seed = 1,
  is_enable_sparse = TRUE,
  enable_bundle = TRUE,
  use_missing = TRUE,
  zero_as_missing = FALSE,
  two_round = FALSE,
  
  # Convert Parameters
  convert_model = NULL,
  convert_model_language = "cpp",
  
  # Objective Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#objective-parameters
  boost_from_average = TRUE,
  is_unbalance = FALSE,
  scale_pos_weight = 1.0,
  
  # Metric Parameters (metric is in Core)
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#metric-parameters
  is_provide_training_metric = TRUE,
  eval_at = c(1,2,3,4,5),
  
  # Network Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#network-parameters
  num_machines = 1,
  
  # GPU Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#gpu-parameters
  gpu_platform_id = -1,
  gpu_device_id = -1,
  gpu_use_dp = TRUE,
  num_gpu = 1)

# Outcome
ModelID = "Test_Model_1"
colnames <- data.table::fread(file = file.path(getwd(), paste0(ModelID, "_ColNames.csv")))
Preds <- AutoQuant::AutoLightGBMScoring(
  TargetType = "classification",
  ScoringData = TTestData,
  ReturnShapValues = FALSE,
  FeatureColumnNames = colnames[[1L]],
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  EncodingMethod = "credibility",
  FactorLevelsList = NULL,
  TargetLevels = NULL,
  ModelObject = NULL,
  ModelPath = getwd(),
  ModelID = "Test_Model_1",
  ReturnFeatures = TRUE,
  TransformNumeric = FALSE,
  BackTransNumeric = FALSE,
  TargetColumnName = NULL,
  TransformationObject = NULL,
  TransID = NULL,
  TransPath = NULL,
  MDP_Impute = TRUE,
  MDP_CharToFactor = TRUE,
  MDP_RemoveDates = TRUE,
  MDP_MissFactor = "0",
  MDP_MissNum = -1)

# Refresh data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 25000L,
  ID = 2L,
  AddWeightsColumn = TRUE,
  ZIP = 0L,
  AddDate = TRUE,
  Classification = FALSE,
  MultiClass = TRUE)

# Partition Data
Sets <- Rodeo::AutoDataPartition(
  data = data,
  NumDataSets = 3,
  Ratios = c(0.7,0.2,0.1),
  PartitionType = "random",
  StratifyColumnNames = "Adrian",
  TimeColumnName = NULL)
TTrainData <- Sets$TrainData
VValidationData <- Sets$ValidationData
TTestData <- Sets$TestData
rm(Sets)

# Run function
TestModel <- AutoQuant::AutoLightGBMMultiClass(
  
  # GPU or CPU
  NThreads = parallel::detectCores(),
  
  # Metadata args
  OutputSelection = c("Importances","EvalPlots","EvalMetrics","Score_TrainData"),
  model_path = normalizePath("./"),
  metadata_path = NULL,
  ModelID = "Test_Model_1",
  NumOfParDepPlots = 3L,
  EncodingMethod = "credibility",
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = TRUE,
  SaveInfoToPDF = FALSE,
  DebugMode = TRUE,
  
  # Data args
  data = TTrainData,
  TrainOnFull = FALSE,
  ValidationData = VValidationData,
  TestData = TTestData,
  TargetColumnName = "Adrian",
  FeatureColNames = names(TTrainData)[!names(TTrainData) %in% c("IDcol_1","IDcol_2","DateTime","Adrian")],
  PrimaryDateColumn = NULL,
  WeightsColumnName = "Weights",
  IDcols = c("IDcol_1","IDcol_2",'DateTime'),
  CostMatrixWeights = c(1,0,0,1),
  
  # Grid parameters
  GridTune = FALSE,
  grid_eval_metric = "microauc",
  BaselineComparison = "default",
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  PassInGrid = NULL,
  
  # Core parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#core-parameters
  input_model = NULL, # continue training a model that is stored to file
  task = "train",
  device_type = "CPU",
  objective = 'multiclass',
  multi_error_top_k = 1,
  metric = 'multiclass_logloss',
  boosting = "gbdt",
  LinearTree = FALSE,
  Trees = 50L,
  eta = NULL,
  num_leaves = 31,
  deterministic = TRUE,
  
  # Learning Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#learning-control-parameters
  force_col_wise = FALSE,
  force_row_wise = FALSE,
  max_depth = 6,
  min_data_in_leaf = 20,
  min_sum_hessian_in_leaf = 0.001,
  bagging_freq = 1.0,
  bagging_fraction = 1.0,
  feature_fraction = 1.0,
  feature_fraction_bynode = 1.0,
  lambda_l1 = 0.0,
  lambda_l2 = 0.0,
  extra_trees = FALSE,
  early_stopping_round = 10,
  first_metric_only = TRUE,
  max_delta_step = 0.0,
  linear_lambda = 0.0,
  min_gain_to_split = 0,
  drop_rate_dart = 0.10,
  max_drop_dart = 50,
  skip_drop_dart = 0.50,
  uniform_drop_dart = FALSE,
  top_rate_goss = FALSE,
  other_rate_goss = FALSE,
  monotone_constraints = NULL,
  monotone_constraints_method = 'advanced',
  monotone_penalty = 0.0,
  forcedsplits_filename = NULL, # use for AutoStack option; .json file
  refit_decay_rate = 0.90,
  path_smooth = 0.0,
  
  # IO Dataset Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#io-parameters
  max_bin = 255,
  min_data_in_bin = 3,
  data_random_seed = 1,
  is_enable_sparse = TRUE,
  enable_bundle = TRUE,
  use_missing = TRUE,
  zero_as_missing = FALSE,
  two_round = FALSE,
  
  # Convert Parameters
  convert_model = NULL,
  convert_model_language = "cpp",
  
  # Objective Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#objective-parameters
  boost_from_average = TRUE,
  is_unbalance = FALSE,
  scale_pos_weight = 1.0,
  
  # Metric Parameters (metric is in Core)
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#metric-parameters
  is_provide_training_metric = TRUE,
  eval_at = c(1,2,3,4,5),
  
  # Network Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#network-parameters
  num_machines = 1,
  
  # GPU Parameters
  # https://lightgbm.readthedocs.io/en/latest/Parameters.html#gpu-parameters
  gpu_platform_id = -1,
  gpu_device_id = -1,
  gpu_use_dp = TRUE,
  num_gpu = 1)

# Outcome
ModelID = "Test_Model_1"
colnames <- data.table::fread(file = file.path(getwd(), paste0(ModelID, "_ColNames.csv")))
Preds <- AutoQuant::AutoLightGBMScoring(
  TargetType = "multiclass",
  ScoringData = TTestData,
  ReturnShapValues = FALSE,
  FeatureColumnNames = colnames[[1L]],
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  EncodingMethod = "credibility",
  FactorLevelsList = NULL,
  TargetLevels = NULL,
  ModelObject = NULL,
  ModelPath = getwd(),
  ModelID = "Test_Model_1",
  ReturnFeatures = TRUE,
  TransformNumeric = FALSE,
  BackTransNumeric = FALSE,
  TargetColumnName = NULL,
  TransformationObject = NULL,
  TransID = NULL,
  TransPath = NULL,
  MDP_Impute = TRUE,
  MDP_CharToFactor = TRUE,
  MDP_RemoveDates = TRUE,
  MDP_MissFactor = "0",
  MDP_MissNum = -1)

# Classify
Classify <- TRUE

# Get data
if(Classify) {
  data <- AutoQuant::FakeDataGenerator(N = 15000, ZIP = 1)
} else {
  data <- AutoQuant::FakeDataGenerator(N = 100000, ZIP = 2)
}

# Partition Data
Sets <- Rodeo::AutoDataPartition(
  data = data,
  NumDataSets = 3,
  Ratios = c(0.7,0.2,0.1),
  PartitionType = "random",
  StratifyColumnNames = "Adrian",
  TimeColumnName = NULL)
TTrainData <- Sets$TrainData
VValidationData <- Sets$ValidationData
TTestData <- Sets$TestData
rm(Sets)

# Run function
TestModel <- AutoQuant::AutoLightGBMHurdleModel(
  
  # Operationalization
  ModelID = 'ModelTest',
  SaveModelObjects = FALSE,
  ReturnModelObjects = TRUE,
  NThreads = parallel::detectCores(),
  
  # Data related args
  data = TTrainData,
  ValidationData = VValidationData,
  PrimaryDateColumn = "DateTime",
  TestData = TTestData,
  WeightsColumnName = NULL,
  TrainOnFull = FALSE,
  Buckets = if(Classify) 0L else c(0,2,3),
  TargetColumnName = "Adrian",
  FeatureColNames = names(TTrainData)[!names(data) %in% c("Adrian","IDcol_1","IDcol_2","IDcol_3","IDcol_4","IDcol_5","DateTime")],
  IDcols = c("IDcol_1","IDcol_2","IDcol_3","IDcol_4","IDcol_5","DateTime"),
  DebugMode = TRUE,
  
  # Metadata args
  EncodingMethod = "credibility",
  Paths = getwd(),
  MetaDataPaths = NULL,
  TransformNumericColumns = NULL,
  Methods = c('Asinh', 'Asin', 'Log', 'LogPlus1', 'Logit'),
  ClassWeights = c(1,1),
  SplitRatios = NULL,
  NumOfParDepPlots = 10L,
  
  # Grid tuning setup
  PassInGrid = NULL,
  GridTune = FALSE,
  BaselineComparison = 'default',
  MaxModelsInGrid = 1L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 60L*60L,
  
  # LightGBM parameters
  task = list('classifier' = 'train', 'regression' = 'train'),
  device_type = list('classifier' = 'CPU', 'regression' = 'CPU'),
  objective = if(Classify) list('classifier' = 'binary', 'regression' = 'regression') else list('classifier' = 'multiclass', 'regression' = 'regression'),
  metric = if(Classify) list('classifier' = 'binary_logloss', 'regression' = 'rmse') else list('classifier' = 'multi_logloss', 'regression' = 'rmse'),
  boosting = list('classifier' = 'gbdt', 'regression' = 'gbdt'),
  LinearTree = list('classifier' = FALSE, 'regression' = FALSE),
  Trees = list('classifier' = 50L, 'regression' = 50L),
  eta = list('classifier' = NULL, 'regression' = NULL),
  num_leaves = list('classifier' = 31, 'regression' = 31),
  deterministic = list('classifier' = TRUE, 'regression' = TRUE),
  
  # Learning Parameters
  force_col_wise = list('classifier' = FALSE, 'regression' = FALSE),
  force_row_wise = list('classifier' = FALSE, 'regression' = FALSE),
  max_depth = list('classifier' = NULL, 'regression' = NULL),
  min_data_in_leaf = list('classifier' = 20, 'regression' = 20),
  min_sum_hessian_in_leaf = list('classifier' = 0.001, 'regression' = 0.001),
  bagging_freq = list('classifier' = 0, 'regression' = 0),
  bagging_fraction = list('classifier' = 1.0, 'regression' = 1.0),
  feature_fraction = list('classifier' = 1.0, 'regression' = 1.0),
  feature_fraction_bynode = list('classifier' = 1.0, 'regression' = 1.0),
  extra_trees = list('classifier' = FALSE, 'regression' = FALSE),
  early_stopping_round = list('classifier' = 10, 'regression' = 10),
  first_metric_only = list('classifier' = TRUE, 'regression' = TRUE),
  max_delta_step = list('classifier' = 0.0, 'regression' = 0.0),
  lambda_l1 = list('classifier' = 0.0, 'regression' = 0.0),
  lambda_l2 = list('classifier' = 0.0, 'regression' = 0.0),
  linear_lambda = list('classifier' = 0.0, 'regression' = 0.0),
  min_gain_to_split = list('classifier' = 0, 'regression' = 0),
  drop_rate_dart = list('classifier' = 0.10, 'regression' = 0.10),
  max_drop_dart = list('classifier' = 50, 'regression' = 50),
  skip_drop_dart = list('classifier' = 0.50, 'regression' = 0.50),
  uniform_drop_dart = list('classifier' = FALSE, 'regression' = FALSE),
  top_rate_goss = list('classifier' = FALSE, 'regression' = FALSE),
  other_rate_goss = list('classifier' = FALSE, 'regression' = FALSE),
  monotone_constraints = list('classifier' = NULL, 'regression' = NULL),
  monotone_constraints_method = list('classifier' = 'advanced', 'regression' = 'advanced'),
  monotone_penalty = list('classifier' = 0.0, 'regression' = 0.0),
  forcedsplits_filename = list('classifier' = NULL, 'regression' = NULL),
  refit_decay_rate = list('classifier' = 0.90, 'regression' = 0.90),
  path_smooth = list('classifier' = 0.0, 'regression' = 0.0),
  
  # IO Dataset Parameters
  max_bin = list('classifier' = 255, 'regression' = 255),
  min_data_in_bin = list('classifier' = 3, 'regression' = 3),
  data_random_seed = list('classifier' = 1, 'regression' = 1),
  is_enable_sparse = list('classifier' = TRUE, 'regression' = TRUE),
  enable_bundle = list('classifier' = TRUE, 'regression' = TRUE),
  use_missing = list('classifier' = TRUE, 'regression' = TRUE),
  zero_as_missing = list('classifier' = FALSE, 'regression' = FALSE),
  two_round = list('classifier' = FALSE, 'regression' = FALSE),
  
  # Convert Parameters
  convert_model = list('classifier' = NULL, 'regression' = NULL),
  convert_model_language = list('classifier' = "cpp", 'regression' = "cpp"),
  
  # Objective Parameters
  boost_from_average = list('classifier' = TRUE, 'regression' = TRUE),
  is_unbalance = list('classifier' = FALSE, 'regression' = FALSE),
  scale_pos_weight = list('classifier' = 1.0, 'regression' = 1.0),
  
  # Metric Parameters (metric is in Core)
  is_provide_training_metric = list('classifier' = TRUE, 'regression' = TRUE),
  eval_at = list('classifier' = c(1,2,3,4,5), 'regression' = c(1,2,3,4,5)),
  
  # Network Parameters
  num_machines = list('classifier' = 1, 'regression' = 1),
  
  # GPU Parameters
  gpu_platform_id = list('classifier' = -1, 'regression' = -1),
  gpu_device_id = list('classifier' = -1, 'regression' = -1),
  gpu_use_dp = list('classifier' = TRUE, 'regression' = TRUE),
  num_gpu = list('classifier' = 1, 'regression' = 1))

# Remove Target Variable
TTrainData[, c("Target_Buckets", "Adrian") := NULL]

# Score LightGBM Hurdle Model
Output <- AutoQuant::AutoLightGBMHurdleModelScoring(
  TestData = TTrainData,
  Path = NULL,
  ModelID = "ModelTest",
  ModelList = TestModel$ModelList,
  ArgsList = TestModel$ArgsList,
  Threshold = NULL)

# Refresh data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 25000L,
  ID = 2L,
  FactorCount = 3,
  AddWeightsColumn = TRUE,
  ZIP = 0L,
  AddDate = TRUE,
  Classification = FALSE,
  MultiClass = FALSE)

# Copy data
data1 <- data.table::copy(data)

# Partition Data
Sets <- Rodeo::AutoDataPartition(
  data = data1,
  NumDataSets = 3,
  Ratios = c(0.7,0.2,0.1),
  PartitionType = "random",
  StratifyColumnNames = "Adrian",
  TimeColumnName = NULL)
TTrainData <- Sets$TrainData
VValidationData <- Sets$ValidationData
TTestData <- Sets$TestData
rm(Sets)

# Run function
TestModel <- AutoQuant::AutoXGBoostRegression(
  
  # GPU or CPU
  TreeMethod = "hist",
  NThreads = parallel::detectCores(),
  LossFunction = 'reg:squarederror',
  
  # Metadata arguments
  model_path = normalizePath("./"),
  metadata_path = NULL,
  ModelID = "Test_Model_1",
  EncodingMethod = "credibility",
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = TRUE,
  DebugMode = TRUE,
  
  # Data arguments
  data = TTrainData,
  TrainOnFull = FALSE,
  ValidationData = VValidationData,
  TestData = TTestData,
  TargetColumnName = "Adrian",
  FeatureColNames = names(TTrainData)[!names(TTrainData) %in% c("IDcol_1", "IDcol_2","DateTime","Adrian")],
  WeightsColumnName = "Weights",
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  TransformNumericColumns = NULL,
  Methods = c("Asinh", "Asin", "Log", "LogPlus1", "Sqrt", "Logit"),
  
  # Model evaluation
  eval_metric = "rmse",
  NumOfParDepPlots = 3L,
  
  # Grid tuning arguments
  PassInGrid = NULL,
  GridTune = FALSE,
  grid_eval_metric = "r2",
  BaselineComparison = "default",
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  Verbose = 1L,
  SaveInfoToPDF = TRUE,
  
  # ML args
  Trees = 50L,
  eta = 0.05,
  max_depth = 4L,
  min_child_weight = 1.0,
  subsample = 0.55,
  colsample_bytree = 0.55)

# Score model
Preds <- AutoQuant::AutoXGBoostScoring(
  TargetType = "regression",
  ScoringData = data,
  ReturnShapValues = FALSE,
  FeatureColumnNames = names(TTrainData)[!names(TTrainData) %in% c("IDcol_1", "IDcol_2","DateTime","Adrian")],
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  EncodingMethod = "credibility",
  FactorLevelsList = TestModel$FactorLevelsList,
  TargetLevels = NULL,
  ModelObject = TestModel$Model,
  ModelPath = "home",
  ModelID = "ModelTest",
  ReturnFeatures = TRUE,
  TransformNumeric = FALSE,
  BackTransNumeric = FALSE,
  TargetColumnName = NULL,
  TransformationObject = NULL,
  TransID = NULL,
  TransPath = NULL,
  MDP_Impute = TRUE,
  MDP_CharToFactor = TRUE,
  MDP_RemoveDates = TRUE,
  MDP_MissFactor = "0",
  MDP_MissNum = -1)

# Refresh data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 25000L,
  ID = 2L,
  AddWeightsColumn = TRUE,
  ZIP = 0L,
  AddDate = TRUE,
  Classification = TRUE,
  MultiClass = FALSE)

# Partition Data
Sets <- Rodeo::AutoDataPartition(
  data = data,
  NumDataSets = 3,
  Ratios = c(0.7,0.2,0.1),
  PartitionType = "random",
  StratifyColumnNames = "Adrian",
  TimeColumnName = NULL)
TTrainData <- Sets$TrainData
VValidationData <- Sets$ValidationData
TTestData <- Sets$TestData
rm(Sets)

# Run function
TestModel <- AutoQuant::AutoXGBoostClassifier(
  
  # GPU or CPU
  TreeMethod = "hist",
  NThreads = parallel::detectCores(),
  
  # Metadata arguments
  OutputSelection = c("Importances", "EvalPlots", "EvalMetrics", "Score_TrainData"),
  model_path = normalizePath("./"),
  metadata_path = NULL,
  ModelID = "Test_Model_1",
  EncodingMethod = "credibility",
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = TRUE,
  SaveInfoToPDF = TRUE,
  DebugMode = TRUE,
  
  # Data arguments
  data = TTrainData,
  TrainOnFull = FALSE,
  ValidationData = VValidationData,
  TestData = TTestData,
  TargetColumnName = "Adrian",
  FeatureColNames = names(TTrainData)[!names(TTrainData) %in% c("IDcol_1", "IDcol_2","DateTime","Adrian")],
  WeightsColumnName = "Weights",
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  
  # Model evaluation
  LossFunction = 'reg:logistic',
  eval_metric = "auc",
  grid_eval_metric = "MCC",
  CostMatrixWeights = c(1,0,0,1),
  NumOfParDepPlots = 3L,
  
  # Grid tuning arguments
  PassInGrid = NULL,
  GridTune = FALSE,
  BaselineComparison = "default",
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  Verbose = 1L,
  
  # ML Args
  Trees = 50L,
  eta = 0.05,
  max_depth = 4L,
  min_child_weight = 1.0,
  subsample = 0.55,
  colsample_bytree = 0.55)

# Score model
Preds <- AutoQuant::AutoXGBoostScoring(
  TargetType = "classifier",
  ScoringData = data,
  ReturnShapValues = FALSE,
  FeatureColumnNames = names(TTrainData)[!names(TTrainData) %in% c("IDcol_1", "IDcol_2","DateTime","Adrian")],
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  EncodingMethod = "credibility",
  FactorLevelsList = TestModel$FactorLevelsList,
  TargetLevels = NULL,
  ModelObject = TestModel$Model,
  ModelPath = "home",
  ModelID = "ModelTest",
  ReturnFeatures = TRUE,
  TransformNumeric = FALSE,
  BackTransNumeric = FALSE,
  TargetColumnName = NULL,
  TransformationObject = NULL,
  TransID = NULL,
  TransPath = NULL,
  MDP_Impute = TRUE,
  MDP_CharToFactor = TRUE,
  MDP_RemoveDates = TRUE,
  MDP_MissFactor = "0",
  MDP_MissNum = -1)

# Refresh data
data <- AutoQuant::FakeDataGenerator(
  Correlation = 0.85,
  N = 25000L,
  ID = 2L,
  AddWeightsColumn = TRUE,
  ZIP = 0L,
  AddDate = TRUE,
  Classification = FALSE,
  MultiClass = TRUE)

# Partition Data
Sets <- Rodeo::AutoDataPartition(
  data = data,
  NumDataSets = 3,
  Ratios = c(0.7,0.2,0.1),
  PartitionType = "random",
  StratifyColumnNames = "Adrian",
  TimeColumnName = NULL)
TTrainData <- Sets$TrainData
VValidationData <- Sets$ValidationData
TTestData <- Sets$TestData
rm(Sets)

# Run function
TestModel <- AutoQuant::AutoXGBoostMultiClass(
  
  # GPU or CPU
  TreeMethod = "hist",
  NThreads = parallel::detectCores(),
  
  # Metadata arguments
  OutputSelection = c("Importances", "EvalPlots", "EvalMetrics", "Score_TrainData"),
  model_path = normalizePath("./"),
  metadata_path = normalizePath("./"),
  ModelID = "Test_Model_1",
  ReturnFactorLevels = TRUE,
  ReturnModelObjects = TRUE,
  SaveModelObjects = FALSE,
  EncodingMethod = "credibility",
  DebugMode = TRUE,
  
  # Data arguments
  data = TTrainData,
  TrainOnFull = FALSE,
  ValidationData = VValidationData,
  TestData = TTestData,
  TargetColumnName = "Adrian",
  FeatureColNames = names(TTrainData)[!names(TTrainData) %in% c("IDcol_1", "IDcol_2","DateTime","Adrian")],
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  
  # Model evaluation
  eval_metric = "merror",
  LossFunction = 'multi:softprob',
  grid_eval_metric = "accuracy",
  NumOfParDepPlots = 3L,
  
  # Grid tuning arguments
  PassInGrid = NULL,
  GridTune = FALSE,
  BaselineComparison = "default",
  MaxModelsInGrid = 10L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 24L*60L,
  Verbose = 1L,
  
  # ML Args
  Trees = 50L,
  eta = 0.05,
  max_depth = 4L,
  min_child_weight = 1.0,
  subsample = 0.55,
  colsample_bytree = 0.55)

# Score model
Preds <- AutoQuant::AutoXGBoostScoring(
  TargetType = "multiclass",
  ScoringData = data,
  ReturnShapValues = FALSE,
  FeatureColumnNames = names(TTrainData)[!names(TTrainData) %in% c("IDcol_1", "IDcol_2","DateTime","Adrian")],
  IDcols = c("IDcol_1","IDcol_2","DateTime"),
  EncodingMethod = "credibility",
  FactorLevelsList = TestModel$FactorLevelsList,
  TargetLevels = TestModel$TargetLevels,
  ModelObject = TestModel$Model,
  ModelPath = NULL,
  ModelID = "ModelTest",
  ReturnFeatures = TRUE,
  TransformNumeric = FALSE,
  BackTransNumeric = FALSE,
  TargetColumnName = NULL,
  TransformationObject = NULL,
  TransID = NULL,
  TransPath = NULL,
  MDP_Impute = TRUE,
  MDP_CharToFactor = TRUE,
  MDP_RemoveDates = TRUE,
  MDP_MissFactor = "0",
  MDP_MissNum = -1)

# Classify
Classify <- TRUE

# Get data
if(Classify) {
  data <- AutoQuant::FakeDataGenerator(N = 15000, ZIP = 1)
} else {
  data <- AutoQuant::FakeDataGenerator(N = 100000, ZIP = 2)
}

# Partition Data
Sets <- Rodeo::AutoDataPartition(
  data = data,
  NumDataSets = 3,
  Ratios = c(0.7,0.2,0.1),
  PartitionType = "random",
  StratifyColumnNames = "Adrian",
  TimeColumnName = NULL)
TTrainData <- Sets$TrainData
VValidationData <- Sets$ValidationData
TTestData <- Sets$TestData
rm(Sets)

# Run function
TestModel <- AutoQuant::AutoXGBoostHurdleModel(
  
  # Operationalization
  ModelID = 'ModelTest',
  SaveModelObjects = FALSE,
  ReturnModelObjects = TRUE,
  NThreads = parallel::detectCores(),
  
  # Data related args
  data = TTrainData,
  ValidationData = VValidationData,
  PrimaryDateColumn = "DateTime",
  TestData = TTestData,
  WeightsColumnName = NULL,
  TrainOnFull = FALSE,
  Buckets = if(Classify) 0L else c(0,2,3),
  TargetColumnName = "Adrian",
  FeatureColNames = names(TTrainData)[!names(data) %in% c("Adrian","IDcol_1","IDcol_2","IDcol_3","IDcol_4","IDcol_5","DateTime")],
  IDcols = c("IDcol_1","IDcol_2","IDcol_3","IDcol_4","IDcol_5","DateTime"),
  DebugMode = FALSE,
  
  # Metadata args
  EncodingMethod = "credibility",
  Paths = normalizePath('./'),
  MetaDataPaths = NULL,
  TransformNumericColumns = NULL,
  Methods = c('Asinh', 'Asin', 'Log', 'LogPlus1', 'Logit'),
  ClassWeights = c(1,1),
  SplitRatios = NULL,
  NumOfParDepPlots = 10L,
  
  # Grid tuning setup
  PassInGrid = NULL,
  GridTune = FALSE,
  BaselineComparison = 'default',
  MaxModelsInGrid = 1L,
  MaxRunsWithoutNewWinner = 20L,
  MaxRunMinutes = 60L*60L,
  
  # XGBoost parameters
  TreeMethod = "hist",
  Trees = list("classifier" = 50, "regression" = 50),
  eta = list("classifier" = 0.05, "regression" = 0.05),
  max_depth = list("classifier" = 4L, "regression" = 4L),
  min_child_weight = list("classifier" = 1.0, "regression" = 1.0),
  subsample = list("classifier" = 0.55, "regression" = 0.55),
  colsample_bytree = list("classifier" = 0.55, "regression" = 0.55))

# Remove Target Variable
TTrainData[, c("Target_Buckets", "Adrian") := NULL]

# Score XGBoost Hurdle Model
Output <- AutoQuant::AutoXGBoostHurdleModelScoring(
  TestData = TTrainData,
  Path = NULL,
  ModelID = "ModelTest",
  ModelList = TestModel$ModelList,
  ArgsList = TestModel$ArgsList,
  Threshold = NULL)