From 5d7cdf2e36f1fc45f0cd40ab0b930f95c2c6341c Mon Sep 17 00:00:00 2001 From: Jiaming Yuan Date: Thu, 8 Jul 2021 11:34:14 +0800 Subject: [PATCH] [Breaking] Rename Quantile DMatrix C API. (#7082) The role of ProxyDMatrix is going beyond what it was designed. Now it's used by both QuantileDeviceDMatrix and inplace prediction. After the refactoring of sparse DMatrix it will also be used for external memory. Renaming the C API to extract it from QuantileDeviceDMatrix. --- include/xgboost/c_api.h | 19 ++++++++++--------- python-package/xgboost/core.py | 15 ++++++++------- python-package/xgboost/data.py | 8 +++++--- src/c_api/c_api.cc | 11 +++++------ tests/cpp/helpers.cu | 2 +- 5 files changed, 29 insertions(+), 26 deletions(-) diff --git a/include/xgboost/c_api.h b/include/xgboost/c_api.h index ac66b53d4..f367693a0 100644 --- a/include/xgboost/c_api.h +++ b/include/xgboost/c_api.h @@ -234,8 +234,8 @@ XGB_DLL int XGDMatrixCreateFromDT(void** data, * - XGProxyDMatrixCreate * - XGDMatrixCallbackNext * - DataIterResetCallback - * - XGDeviceQuantileDMatrixSetDataCudaArrayInterface - * - XGDeviceQuantileDMatrixSetDataCudaColumnar + * - XGProxyDMatrixSetDataCudaArrayInterface + * - XGProxyDMatrixSetDataCudaColumnar * - ... (data setters) */ @@ -371,9 +371,10 @@ XGB_DLL int XGDeviceQuantileDMatrixCreateFromCallback( * * \return 0 when success, -1 when failure happens */ -XGB_DLL int XGDeviceQuantileDMatrixSetDataCudaArrayInterface( - DMatrixHandle handle, - const char* c_interface_str); +XGB_DLL int +XGProxyDMatrixSetDataCudaArrayInterface(DMatrixHandle handle, + const char *c_interface_str); + /*! * \brief Set data on a DMatrix proxy. * @@ -383,9 +384,9 @@ XGB_DLL int XGDeviceQuantileDMatrixSetDataCudaArrayInterface( * * \return 0 when success, -1 when failure happens */ -XGB_DLL int XGDeviceQuantileDMatrixSetDataCudaColumnar( - DMatrixHandle handle, - const char* c_interface_str); +XGB_DLL int XGProxyDMatrixSetDataCudaColumnar(DMatrixHandle handle, + const char *c_interface_str); + /* * ==========================- End data callback APIs ========================== */ @@ -563,7 +564,7 @@ XGB_DLL int XGDMatrixGetStrFeatureInfo(DMatrixHandle handle, const char *field, * \return 0 when success, -1 when failure happens */ XGB_DLL int XGDMatrixSetDenseInfo(DMatrixHandle handle, const char *field, - void *data, bst_ulong size, int type); + void const *data, bst_ulong size, int type); /*! * \brief (deprecated) Use XGDMatrixSetUIntInfo instead. Set group of the training matrix diff --git a/python-package/xgboost/core.py b/python-package/xgboost/core.py index 61356fc52..51b87c3df 100644 --- a/python-package/xgboost/core.py +++ b/python-package/xgboost/core.py @@ -322,6 +322,7 @@ class DataIter: self._handle = _ProxyDMatrix() self.exception = None self.enable_categorical = False + self._allow_host = False @property def proxy(self): @@ -349,12 +350,12 @@ class DataIter: feature_types=None, **kwargs ): - from .data import dispatch_device_quantile_dmatrix_set_data - from .data import _device_quantile_transform - data, feature_names, feature_types = _device_quantile_transform( + from .data import dispatch_proxy_set_data + from .data import _proxy_transform + data, feature_names, feature_types = _proxy_transform( data, feature_names, feature_types, self.enable_categorical, ) - dispatch_device_quantile_dmatrix_set_data(self.proxy, data) + dispatch_proxy_set_data(self.proxy, data, self._allow_host) self.proxy.set_info( feature_names=feature_names, feature_types=feature_types, @@ -1009,18 +1010,18 @@ class _ProxyDMatrix(DMatrix): interface = data.__cuda_array_interface__ interface_str = bytes(json.dumps(interface, indent=2), 'utf-8') _check_call( - _LIB.XGDeviceQuantileDMatrixSetDataCudaArrayInterface( + _LIB.XGProxyDMatrixSetDataCudaArrayInterface( self.handle, interface_str ) ) def _set_data_from_cuda_columnar(self, data): - '''Set data from CUDA columnar format.1''' + '''Set data from CUDA columnar format.''' from .data import _cudf_array_interfaces _, interfaces_str = _cudf_array_interfaces(data) _check_call( - _LIB.XGDeviceQuantileDMatrixSetDataCudaColumnar( + _LIB.XGProxyDMatrixSetDataCudaColumnar( self.handle, interfaces_str ) diff --git a/python-package/xgboost/data.py b/python-package/xgboost/data.py index 65e5ea529..aa4764c3c 100644 --- a/python-package/xgboost/data.py +++ b/python-package/xgboost/data.py @@ -775,7 +775,7 @@ class SingleBatchInternalIter(DataIter): # pylint: disable=R0902 self.it = 0 -def _device_quantile_transform(data, feature_names, feature_types, enable_categorical): +def _proxy_transform(data, feature_names, feature_types, enable_categorical): if _is_cudf_df(data) or _is_cudf_ser(data): return _transform_cudf_df( data, feature_names, feature_types, enable_categorical @@ -788,8 +788,8 @@ def _device_quantile_transform(data, feature_names, feature_types, enable_catego raise TypeError("Value type is not supported for data iterator:" + str(type(data))) -def dispatch_device_quantile_dmatrix_set_data(proxy: _ProxyDMatrix, data: Any) -> None: - '''Dispatch for DeviceQuantileDMatrix.''' +def dispatch_proxy_set_data(proxy: _ProxyDMatrix, data: Any, allow_host: bool) -> None: + """Dispatch for DeviceQuantileDMatrix.""" if _is_cudf_df(data): proxy._set_data_from_cuda_columnar(data) # pylint: disable=W0212 return @@ -803,5 +803,7 @@ def dispatch_device_quantile_dmatrix_set_data(proxy: _ProxyDMatrix, data: Any) - data = _transform_dlpack(data) proxy._set_data_from_cuda_interface(data) # pylint: disable=W0212 return + # Part of https://github.com/dmlc/xgboost/pull/7070 + assert allow_host is False, "host data is not yet supported." raise TypeError('Value type is not supported for data iterator:' + str(type(data))) diff --git a/src/c_api/c_api.cc b/src/c_api/c_api.cc index c8be90caf..85618333c 100644 --- a/src/c_api/c_api.cc +++ b/src/c_api/c_api.cc @@ -197,8 +197,8 @@ XGB_DLL int XGProxyDMatrixCreate(DMatrixHandle* out) { } XGB_DLL int -XGDeviceQuantileDMatrixSetDataCudaArrayInterface(DMatrixHandle handle, - char const *c_interface_str) { +XGProxyDMatrixSetDataCudaArrayInterface(DMatrixHandle handle, + char const *c_interface_str) { API_BEGIN(); CHECK_HANDLE(); auto p_m = static_cast *>(handle); @@ -209,9 +209,8 @@ XGDeviceQuantileDMatrixSetDataCudaArrayInterface(DMatrixHandle handle, API_END(); } -XGB_DLL int -XGDeviceQuantileDMatrixSetDataCudaColumnar(DMatrixHandle handle, - char const *c_interface_str) { +XGB_DLL int XGProxyDMatrixSetDataCudaColumnar(DMatrixHandle handle, + char const *c_interface_str) { API_BEGIN(); CHECK_HANDLE(); auto p_m = static_cast *>(handle); @@ -433,7 +432,7 @@ XGB_DLL int XGDMatrixGetStrFeatureInfo(DMatrixHandle handle, const char *field, } XGB_DLL int XGDMatrixSetDenseInfo(DMatrixHandle handle, const char *field, - void *data, xgboost::bst_ulong size, + void const *data, xgboost::bst_ulong size, int type) { API_BEGIN(); CHECK_HANDLE(); diff --git a/tests/cpp/helpers.cu b/tests/cpp/helpers.cu index 9b70ea543..60501a67a 100644 --- a/tests/cpp/helpers.cu +++ b/tests/cpp/helpers.cu @@ -23,7 +23,7 @@ int CudaArrayIterForTest::Next() { if (iter_ == n_batches_) { return 0; } - XGDeviceQuantileDMatrixSetDataCudaArrayInterface(proxy_, batches_[iter_].c_str()); + XGProxyDMatrixSetDataCudaArrayInterface(proxy_, batches_[iter_].c_str()); iter_++; return 1; }