# tfdf.keras.MultiTaskItem

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/decision-forests/blob/main/tensorflow_decision_forests/keras/core_inference.py#L197-L222) |

A single task in a multi-task configuration.

#### View aliases


**Main aliases**

[`tfdf.keras.core.MultiTaskItem`](https://www.tensorflow.org/decision_forests/api_docs/python/tfdf/keras/MultiTaskItem), [`tfdf.keras.wrappers.MultiTaskItem`](https://www.tensorflow.org/decision_forests/api_docs/python/tfdf/keras/MultiTaskItem)

<br />

    tfdf.keras.MultiTaskItem(
        label, task=1, primary=True, output=None
    )

Models trained to predict label with primary=False are used to help the
training of models with primary=True. If primary is true for all the tasks,
each task will be trained independently.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `label` | Key of the label. |
| `task` | Task for the label. |
| `primary` | The predictions of primary tasks are returned by "model.predict()", the output of non-primary tasks are not returned by "model.predict()". Non-primary tasks can be used to improve the primary task quality. |
| `output` | If None, "model.predict" returns a dictionary of prediction indexed by "label" values. If set, "model.predict" returns a dictionary of predictions indexed by "output". |

<br />

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `label` | A `namedtuple` alias for field number 0 |
| `task` | A `namedtuple` alias for field number 1 |
| `primary` | A `namedtuple` alias for field number 2 |
| `output` | A `namedtuple` alias for field number 3 |
| `prediction_key` | <br /> <br /> |

<br />