Inheritance diagram for xgboost.core.DataIter:

Public Member Functions
None	__init__ (self, Optional[str] cache_prefix=None, bool release_data=True)

Tuple[Callable, Callable]	get_callbacks (self, bool allow_host, bool enable_categorical)

"_ProxyDMatrix"	proxy (self)

None	reraise (self)

None	__del__ (self)

None	reset (self)

int	next (self, Callable input_data)

Data Fields
	cache_prefix

	reset

	proxy

Protected Member Functions
_T	_handle_exception (self, Callable fn, _T dft_ret)

None	_reset_wrapper (self, None this)

int	_next_wrapper (self, None this)

Protected Attributes
	_handle

	_enable_categorical

	_allow_host

	_release

	_reset_callback

	_next_callback

	_next_wrapper

	_exception

	_temporary_data

	_data_ref

Detailed Description

The interface for user defined data iterator. The iterator facilitates
distributed training, :py:class:`QuantileDMatrix`, and external memory support using
:py:class:`DMatrix`. Most of time, users don't need to interact with this class
directly.

.. note::

    The class caches some intermediate results using the `data` input (predictor
    `X`) as key. Don't repeat the `X` for multiple batches with different meta data
    (like `label`), make a copy if necessary.

Parameters
----------
cache_prefix :
    Prefix to the cache files, only used in external memory.  It can be either an
    URI or a file path.
release_data :
    Whether the iterator should release the data during reset. Set it to True if the
    data transformation (converting data to np.float32 type) is expensive.

Constructor & Destructor Documentation

◆ init()

None xgboost.core.DataIter.__init__	(		self,
		Optional[str]	cache_prefix = `None`,
		bool	release_data = `True`
	)

Reimplemented in quantile_data_iterator.IterForDMatrixDemo.

Member Function Documentation

◆ _next_wrapper()

int xgboost.core.DataIter._next_wrapper	(		self,
		None	this
	)

protected

A wrapper for user defined `next` function.

`this` is not used in Python.  ctypes can handle `self` of a Python
member function automatically when converting it to c function
pointer.

◆ _reset_wrapper()

None xgboost.core.DataIter._reset_wrapper	(		self,
		None	this
	)

protected

A wrapper for user defined `reset` function.

◆ get_callbacks()

Tuple[Callable, Callable] xgboost.core.DataIter.get_callbacks	(		self,
		bool	allow_host,
		bool	enable_categorical
	)

Get callback functions for iterating in C. This is an internal function.

◆ next()

int xgboost.core.DataIter.next	(		self,
		Callable	input_data
	)

Set the next batch of data.

Parameters
----------

input_data:
    A function with same data fields like `data`, `label` with
    `xgboost.DMatrix`.

Returns
-------
0 if there's no more batch, otherwise 1.

Reimplemented in external_memory.Iterator, xgboost.dask.DaskPartitionIter, xgboost.data.SingleBatchInternalIter, xgboost.spark.data.PartIter, and quantile_data_iterator.IterForDMatrixDemo.

◆ proxy()

"_ProxyDMatrix" xgboost.core.DataIter.proxy ( self )

Handle of DMatrix proxy.

◆ reraise()

None xgboost.core.DataIter.reraise ( self )

Reraise the exception thrown during iteration.

◆ reset()

None xgboost.core.DataIter.reset ( self )

Reset the data iterator.  Prototype for user defined function.

Reimplemented in external_memory.Iterator, quantile_data_iterator.IterForDMatrixDemo, and xgboost.dask.DaskPartitionIter.

Field Documentation

◆ reset

xgboost.core.DataIter.reset