Parameters ---------- data : Data source of DMatrix. See :ref:`py-data` for a list of supported input types. Note that, if passing an iterator, it **will cache data on disk**, and note that fields like ``label`` will be concatenated in
(
self,
data: DataType,
label: Optional[ArrayLike] = None,
*,
weight: Optional[ArrayLike] = None,
base_margin: Optional[ArrayLike] = None,
missing: Optional[float] = None,
silent: bool = False,
feature_names: Optional[FeatureNames] = None,
feature_types: Optional[Union[FeatureTypes, Categories]] = None,
nthread: Optional[int] = None,
group: Optional[ArrayLike] = None,
qid: Optional[ArrayLike] = None,
label_lower_bound: Optional[ArrayLike] = None,
label_upper_bound: Optional[ArrayLike] = None,
feature_weights: Optional[ArrayLike] = None,
enable_categorical: bool = True,
data_split_mode: DataSplitMode = DataSplitMode.ROW,
)
| 658 | |
| 659 | @_deprecate_positional_args |
| 660 | def __init__( |
| 661 | self, |
| 662 | data: DataType, |
| 663 | label: Optional[ArrayLike] = None, |
| 664 | *, |
| 665 | weight: Optional[ArrayLike] = None, |
| 666 | base_margin: Optional[ArrayLike] = None, |
| 667 | missing: Optional[float] = None, |
| 668 | silent: bool = False, |
| 669 | feature_names: Optional[FeatureNames] = None, |
| 670 | feature_types: Optional[Union[FeatureTypes, Categories]] = None, |
| 671 | nthread: Optional[int] = None, |
| 672 | group: Optional[ArrayLike] = None, |
| 673 | qid: Optional[ArrayLike] = None, |
| 674 | label_lower_bound: Optional[ArrayLike] = None, |
| 675 | label_upper_bound: Optional[ArrayLike] = None, |
| 676 | feature_weights: Optional[ArrayLike] = None, |
| 677 | enable_categorical: bool = True, |
| 678 | data_split_mode: DataSplitMode = DataSplitMode.ROW, |
| 679 | ) -> None: |
| 680 | """Parameters |
| 681 | ---------- |
| 682 | data : |
| 683 | Data source of DMatrix. See :ref:`py-data` for a list of supported input |
| 684 | types. |
| 685 | |
| 686 | Note that, if passing an iterator, it **will cache data on disk**, and note |
| 687 | that fields like ``label`` will be concatenated in-memory from multiple |
| 688 | calls to the iterator. |
| 689 | label : |
| 690 | Label of the training data. |
| 691 | weight : |
| 692 | Weight for each instance. |
| 693 | |
| 694 | .. note:: |
| 695 | |
| 696 | For ranking task, weights are per-group. In ranking task, one weight |
| 697 | is assigned to each group (not each data point). This is because we |
| 698 | only care about the relative ordering of data points within each group, |
| 699 | so it doesn't make sense to assign weights to individual data points. |
| 700 | |
| 701 | base_margin : |
| 702 | Global bias for each instance. See :doc:`/tutorials/intercept` for details. |
| 703 | missing : |
| 704 | Value in the input data which needs to be present as a missing value. If |
| 705 | None, defaults to np.nan. |
| 706 | silent : |
| 707 | Whether print messages during construction |
| 708 | feature_names : |
| 709 | Set names for features. |
| 710 | feature_types : |
| 711 | |
| 712 | Set types for features. If `data` is a DataFrame type and passing |
| 713 | `enable_categorical=True`, the types will be deduced automatically from the |
| 714 | column types. |
| 715 | |
| 716 | Otherwise, one can pass a list-like input with the same length as number of |
| 717 | columns in `data`, with the following possible values: |
no test coverage detected