Skip to main content

TabularClassificationTask

Task
DashAI.back.tasks.TabularClassificationTask

Task for classifying structured tabular data into discrete categories.

Tabular classification predicts categorical labels from structured feature tables (rows of observations, columns of features). It accepts numeric (Float, Integer) and categorical (Categorical) inputs, requires a single categorical output column, and is compatible with all sklearn-based and DashAI tabular classifier models.

Methods​

prepare_for_task(self, dataset: Union[ForwardRef('DatasetDict'), ForwardRef('DashAIDataset')], input_columns: List[str], output_columns: List[str]) -> 'DashAIDataset'

Defined on TabularClassificationTask

Convert the dataset to DashAIDataset and check the columns types

Parameters

dataset : Union[DatasetDict, DashAIDataset]
Dataset to be changed

Returns

DashAIDataset
Dataset with the new types

get_metadata(cls) -> Dict[str, Any]

Defined on BaseTask

Return serialisable metadata for the current task.

Parameters

cls : type
The task class (injected automatically by Python for classmethods).

Returns

Dict[str, Any]
Dictionary with keys "inputs_types", "outputs_types", "inputs_cardinality", and "outputs_cardinality".

num_labels(self, dataset: 'DashAIDataset', output_column: str) -> int | None

Defined on ClassificationTask

Get the number of unique labels in the output column.

Parameters

dataset : DashAIDataset
Dataset used for training
output_column : str
Output column

Returns

int | None
Number of unique labels or None if not applicable

process_manual_input(self, manual_input: List[dict], dataset_path: str) -> 'DashAIDataset'

Defined on BaseTask

Process manual input data into a DashAIDataset with type validation.

Parameters

manual_input : List[dict]
List of dictionaries representing manual input data.
dataset_path : str
Path to the training dataset (used to get column specs for validation)

Returns

DashAIDataset
Processed DashAIDataset from manual input.

process_predictions(self, dataset: 'DashAIDataset', predictions: 'ndarray', output_column: str) -> 'ndarray'

Defined on ClassificationTask

Process the predictions to return the class labels.

Parameters

dataset : DashAIDataset
Dataset used for training
predictions : np.ndarray
Predictions from the model (probabilities for each class)
output_column : str
Output column

Returns

np.ndarray
Processed predictions with class labels

validate_dataset_for_task(self, dataset: 'DashAIDataset', dataset_name: str, input_columns: List[str], output_columns: List[str]) -> None

Defined on BaseTask

Validate a dataset for the current task.

Parameters

dataset : DashAIDataset
Dataset to be validated
dataset_name : str
Dataset name

Compatible with​