RegressionTrainingConfig

Training config for the PREDICTIVE_MODELING problem type

KEY TYPE Description
MONOTONICALLY_INCREASING_FEATURES List[str] Constrain the model such that it behaves as if the target feature is monotonically increasing with the selected features
MAX_TOKENS_IN_SENTENCE int Specify the max tokens to be kept in a sentence based on the truncation strategy.
CUSTOM_METRICS List[str] Registered custom metrics available for selection.
BATCH_SIZE BatchSize Batch size.
PRETRAINED_LLM_NAME str Enable algorithms which process text using pretrained large language models.
NUM_CV_FOLDS int Specify the value of k in k-fold cross validation.
OBJECTIVE RegressionObjective Ranking scheme used to select final best model.
MONOTONICALLY_DECREASING_FEATURES List[str] Constrain the model such that it behaves as if the target feature is monotonically decreasing with the selected features
SORT_OBJECTIVE RegressionObjective Ranking scheme used to sort models on the metrics page.
ACTIVE_LABELS_COLUMN str Specify a column to use as the active columns in a multi label setting.
TEST_SPLITTING_TIMESTAMP str Rows with timestamp greater than this will be considered to be in the test set.
AUGMENTATION_STRATEGY RegressionAugmentationStrategy Strategy to deal with class imbalance and data augmentation.
TRAINING_ROWS_DOWNSAMPLE_RATIO float Uses this ratio to train on a sample of the dataset provided.
DISABLE_TEST_VAL_FOLD bool Do not create a TEST_VAL set. All records which would be part of the TEST_VAL fold otherwise, remain in the TEST fold.
NUMERIC_CLIPPING_PERCENTILE float Uses this option to clip the top and bottom x percentile of numeric feature columns where x is the value of this option.
TIMESTAMP_BASED_SPLITTING_METHOD RegressionTimeSplitMethod Method of selecting TEST set, top percentile wise or after a given timestamp.
TRUNCATION_STRATEGY str What strategy to use to deal with text rows with more than a given number of tokens (if num of tokens is more than "max_tokens_in_sentence").
TREE_HPO_MODE None (RegressionTreeHPOMode): Turning off Rapid Experimentation will take longer to train.
SAMPLE_WEIGHT str Specify a column to use as the weight of a sample for training and eval.
TYPE_OF_SPLIT RegressionTypeOfSplit Type of data splitting into train/test (validation also).
MIN_CATEGORICAL_COUNT int Minimum threshold to consider a value different from the unknown placeholder.
CUSTOM_LOSS_FUNCTIONS List[str] Registered custom losses available for selection.
DATA_SPLIT_FEATURE_GROUP_TABLE_NAME str Specify the table name of the feature group to export training data with the fold column.
LOSS_FUNCTION RegressionLossFunction Loss function to be used as objective for model training.
DROP_ORIGINAL_CATEGORICALS bool This option helps us choose whether to also feed the original label encoded categorical columns to the mdoels along with their target encoded versions.
DROPOUT_RATE int Dropout percentage rate.
MAX_TEXT_WORDS int Maximum number of words to use from text fields.
IGNORE_DATETIME_FEATURES bool Remove all datetime features from the model. Useful while generalizing to different time periods.
LOSS_PARAMETERS str Loss function params in format =;=;.....
PERFORM_FEATURE_SELECTION bool If enabled, additional algorithms which support feature selection as a pretraining step will be trained separately with the selected subset of features. The details about their selected features can be found in their respective logs.
TEST_SPLIT int Percent of dataset to use for test data. We support using a range between 5% to 20% of your dataset to use as test data.
DO_MASKED_LANGUAGE_MODEL_PRETRAINING bool Specify whether to run a masked language model unsupervised pretraining step before supervized training in certain supported algorithms which use BERT-like backbones.
TARGET_ENCODE_CATEGORICALS bool Use this to turn target encoding on categorical features on or off.
SAMPLING_UNIT_KEYS List[str] Constrain train/test separation to partition a column.
PRETRAINED_MODEL_NAME str Enable algorithms which process text using pretrained multilingual NLP models.
TEST_ROW_INDICATOR str Column indicating which rows to use for training (TRAIN) and testing (TEST). Validation (VAL) can also be specified.
REBALANCE_CLASSES bool Class weights are computed as the inverse of the class frequency from the training dataset when this option is selected as "Yes". It is useful when the classes in the dataset are unbalanced. Re-balancing classes generally boosts recall at the cost of precision on rare classes.
FEATURE_SELECTION_INTENSITY int This determines the strictness with which features will be filtered out. 1 being very lenient (more features kept), 100 being very strict.
K_FOLD_CROSS_VALIDATION bool Use this to force k-fold cross validation bagging on or off.
IS_MULTILINGUAL bool Enable algorithms which process text using pretrained multilingual NLP models.
PARTIAL_DEPENDENCE_ANALYSIS PartialDependenceAnalysis Specify whether to run partial dependence plots for all features or only some features.
TIMESTAMP_BASED_SPLITTING_COLUMN str Timestamp column selected for splitting into test and train.
FULL_DATA_RETRAINING bool Train models separately with all the data.
TARGET_TRANSFORM RegressionTargetTransform Specify a transform (e.g. log, quantile) to apply to the target variable.
RARE_CLASS_AUGMENTATION_THRESHOLD float Augments any rare class whose relative frequency with respect to the most frequent class is less than this threshold. Default = 0.1 for classification problems with rare classes.
© Copyright