Training config for the PREDICTIVE_MODELING problem type
KEY | TYPE | Description |
---|---|---|
FULL_DATA_RETRAINING | bool | Train models separately with all the data. |
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. |
TREE_HPO_MODE | None | (RegressionTreeHPOMode): Turning off Rapid Experimentation will take longer to train. |
DROPOUT_RATE | int | Dropout percentage rate. |
LOSS_PARAMETERS | str | Loss function params in format |
MIN_CATEGORICAL_COUNT | int | Minimum threshold to consider a value different from the unknown placeholder. |
LOSS_FUNCTION | RegressionLossFunction | Loss function to be used as objective for model training. |
MAX_TOKENS_IN_SENTENCE | int | Specify the max tokens to be kept in a sentence based on the truncation strategy. |
ACTIVE_LABELS_COLUMN | str | Specify a column to use as the active columns in a multi label setting. |
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. |
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. |
SAMPLE_WEIGHT | str | Specify a column to use as the weight of a sample for training and eval. |
TIMESTAMP_BASED_SPLITTING_COLUMN | str | Timestamp column selected for splitting into test and train. |
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. |
IS_MULTILINGUAL | bool | Enable algorithms which process text using pretrained multilingual NLP models. |
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"). |
K_FOLD_CROSS_VALIDATION | bool | Use this to force k-fold cross validation bagging on or off. |
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. |
MONOTONICALLY_DECREASING_FEATURES | List[str] | Constrain the model such that it behaves as if the target feature is monotonically decreasing with the selected features |
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. |
TARGET_TRANSFORM | RegressionTargetTransform | Specify a transform (e.g. log, quantile) to apply to the target variable. |
CUSTOM_LOSS_FUNCTIONS | List[str] | Registered custom losses available for selection. |
TEST_SPLITTING_TIMESTAMP | str | Rows with timestamp greater than this will be considered to be in the test set. |
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. |
MAX_TEXT_WORDS | int | Maximum number of words to use from text fields. |
PRETRAINED_MODEL_NAME | str | Enable algorithms which process text using pretrained multilingual NLP models. |
PRETRAINED_LLM_NAME | str | Enable algorithms which process text using pretrained large language models. |
MONOTONICALLY_INCREASING_FEATURES | List[str] | Constrain the model such that it behaves as if the target feature is monotonically increasing with the selected features |
TEST_ROW_INDICATOR | str | Column indicating which rows to use for training (TRAIN) and testing (TEST). Validation (VAL) can also be specified. |
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. |
TRAINING_ROWS_DOWNSAMPLE_RATIO | float | Uses this ratio to train on a sample of the dataset provided. |
TIMESTAMP_BASED_SPLITTING_METHOD | RegressionTimeSplitMethod | Method of selecting TEST set, top percentile wise or after a given timestamp. |
TARGET_ENCODE_CATEGORICALS | bool | Use this to turn target encoding on categorical features on or off. |
CUSTOM_METRICS | List[str] | Registered custom metrics available for selection. |
IGNORE_DATETIME_FEATURES | bool | Remove all datetime features from the model. Useful while generalizing to different time periods. |
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. |
SAMPLING_UNIT_KEYS | List[str] | Constrain train/test separation to partition a column. |
AUGMENTATION_STRATEGY | RegressionAugmentationStrategy | Strategy to deal with class imbalance and data augmentation. |
PARTIAL_DEPENDENCE_ANALYSIS | PartialDependenceAnalysis | Specify whether to run partial dependence plots for all features or only some features. |
TYPE_OF_SPLIT | RegressionTypeOfSplit | Type of data splitting into train/test (validation also). |
SORT_OBJECTIVE | RegressionObjective | Ranking scheme used to sort models on the metrics page. |
DATA_SPLIT_FEATURE_GROUP_TABLE_NAME | str | Specify the table name of the feature group to export training data with the fold column. |
OBJECTIVE | RegressionObjective | Ranking scheme used to select final best model. |
NUM_CV_FOLDS | int | Specify the value of k in k-fold cross validation. |
BATCH_SIZE | BatchSize | Batch size. |