Expose external memory DMatrix to Python.

.github/workflows/main.yml

@@ -95,36 +95,40 @@ jobs:
         cd build
         cmake .. -DBUILD_STATIC_LIB=ON -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
         ninja -v install
+        cd -
     - name: Build and run C API demo with static
       shell: bash -l {0}
       run: |
+        pushd .
         cd demo/c-api/
         mkdir build
         cd build
         cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
         ninja -v
+        ctest
         cd ..
-        ./build/api-demo
         rm -rf ./build
-        cd ../..
+        popd
     - name: Build and install XGBoost shared library
       shell: bash -l {0}
       run: |
         cd build
         cmake .. -DBUILD_STATIC_LIB=OFF -DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX -GNinja
         ninja -v install
+        cd -
     - name: Build and run C API demo with shared
       shell: bash -l {0}
       run: |
+        pushd .
         cd demo/c-api/
         mkdir build
         cd build
         cmake .. -GNinja -DCMAKE_PREFIX_PATH=$CONDA_PREFIX
         ninja -v
-        cd ..
-        ./build/api-demo
-        cd ../../
-        ./tests/ci_build/verify_link.sh ./demo/c-api/build/api-demo
+        ctest
+        popd
+        ./tests/ci_build/verify_link.sh ./demo/c-api/build/basic/api-demo
+        ./tests/ci_build/verify_link.sh ./demo/c-api/build/external-memory/external-memory-demo
 
   lint:
     runs-on: ubuntu-latest

Makefile

@@ -92,7 +92,10 @@ endif
 mypy:
 	cd python-package; \
 	mypy ./xgboost/dask.py && \
+	mypy ../demo/guide-python/external_memory.py && \
 	mypy ../tests/python-gpu/test_gpu_with_dask.py && \
+	mypy ../tests/python/test_data_iterator.py && \
+	mypy ../tests/python-gpu/test_gpu_data_iterator.py && \
 	mypy ./xgboost/sklearn.py || exit 1; \
 	mypy . || true ;
 

demo/c-api/CMakeLists.txt

@@ -1,14 +1,17 @@
 cmake_minimum_required(VERSION 3.13)
-project(api-demo LANGUAGES C VERSION 0.0.1)
-find_package(xgboost REQUIRED)
+project(xgboost-c-examples)
 
-# xgboost is built as static libraries, all cxx dependencies need to be linked into the
-# executable.
-if (XGBOOST_BUILD_STATIC_LIB)
-  enable_language(CXX)
-  # find again for those  cxx libraries.
-  find_package(xgboost REQUIRED)
-endif(XGBOOST_BUILD_STATIC_LIB)
+add_subdirectory(basic)
+add_subdirectory(external-memory)
 
-add_executable(api-demo c-api-demo.c)
-target_link_libraries(api-demo PRIVATE xgboost::xgboost)
+enable_testing()
+add_test(
+  NAME test_xgboost_demo_c_basic
+  COMMAND api-demo
+  WORKING_DIRECTORY ${xgboost-c-examples_BINARY_DIR}
+)
+add_test(
+  NAME test_xgboost_demo_c_external_memory
+  COMMAND external-memory-demo
+  WORKING_DIRECTORY ${xgboost-c-examples_BINARY_DIR}
+)

demo/c-api/basic/CMakeLists.txt

@@ -0,0 +1,13 @@
+project(api-demo LANGUAGES C VERSION 0.0.1)
+find_package(xgboost REQUIRED)
+
+# xgboost is built as static libraries, all cxx dependencies need to be linked into the
+# executable.
+if (XGBOOST_BUILD_STATIC_LIB)
+  enable_language(CXX)
+  # find again for those  cxx libraries.
+  find_package(xgboost REQUIRED)
+endif(XGBOOST_BUILD_STATIC_LIB)
+
+add_executable(api-demo c-api-demo.c)
+target_link_libraries(api-demo PRIVATE xgboost::xgboost)

demo/c-api/c-api-demo.c → demo/c-api/basic/c-api-demo.c

@@ -24,8 +24,8 @@ int main(int argc, char** argv) {
 
   // load the data
   DMatrixHandle dtrain, dtest;
-  safe_xgboost(XGDMatrixCreateFromFile("../data/agaricus.txt.train", silent, &dtrain));
-  safe_xgboost(XGDMatrixCreateFromFile("../data/agaricus.txt.test", silent, &dtest));
+  safe_xgboost(XGDMatrixCreateFromFile("../../data/agaricus.txt.train", silent, &dtrain));
+  safe_xgboost(XGDMatrixCreateFromFile("../../data/agaricus.txt.test", silent, &dtest));
 
   // create the booster
   BoosterHandle booster;

demo/c-api/external-memory/CMakeLists.txt

@@ -0,0 +1,7 @@
+cmake_minimum_required(VERSION 3.13)
+project(external-memory-demo LANGUAGES C VERSION 0.0.1)
+
+find_package(xgboost REQUIRED)
+
+add_executable(external-memory-demo external_memory.c)
+target_link_libraries(external-memory-demo PRIVATE xgboost::xgboost)

demo/c-api/external-memory/README.md

@@ -0,0 +1,10 @@
+Data Callback
+=============
+
+A simple demo for using custom data iterator with XGBoost.  The primary function for this
+is external-memory training with user provided data loaders.  In the example, we have
+defined a custom data iterator with 2 methods: `reset` and `next`.  The `next` method
+passes data into XGBoost and tells XGBoost whether the iterator has reached its end.
+During training, XGBoost will generate some caches for internal data structures in current
+directory, which can be changed by `cache_prefix` parameter during construction of
+`DMatrix`.

demo/c-api/external-memory/external_memory.c

@@ -0,0 +1,179 @@
+/*!
+ * Copyright 2021 XGBoost contributors
+ *
+ * \brief A simple example of using xgboost data callback API.
+ */
+
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <xgboost/c_api.h>
+
+#define safe_xgboost(err)                                                      \
+  if ((err) != 0) {                                                            \
+    fprintf(stderr, "%s:%d: error in %s: %s\n", __FILE__, __LINE__, #err,      \
+            XGBGetLastError());                                                \
+    exit(1);                                                                   \
+  }
+
+#define N_BATCHS 32
+#define BATCH_LEN 512
+
+/* Shorthands. */
+typedef DMatrixHandle DMatrix;
+typedef BoosterHandle Booster;
+
+typedef struct _DataIter {
+  /* Data of each batch. */
+  float **data;
+  /* Labels of each batch */
+  float **labels;
+  /* Length of each batch. */
+  size_t *lengths;
+  /* Total number of batches. */
+  size_t n;
+  /* Current iteration. */
+  size_t cur_it;
+
+  /* Private fields */
+  DMatrix _proxy;
+  char _array[128];
+} DataIter;
+
+#define safe_malloc(ptr)                                                       \
+  if ((ptr) == NULL) {                                                         \
+    fprintf(stderr, "%s:%d: Failed to allocate memory.\n", __FILE__,           \
+            __LINE__);                                                         \
+    exit(1);                                                                   \
+  }
+
+/**
+ * Initialize with random data for demo. In practice the data should be loaded
+ * from external memory.  We jsut demonstrate how to use the iterator in
+ * XGBoost.
+ *
+ * \param batch_size  Number of elements for each batch.  The demo here is only using 1
+ *                    column.
+ * \param n_batches   Number of batches.
+ */
+void DataIterator_Init(DataIter *self, size_t batch_size, size_t n_batches) {
+  self->n = n_batches;
+
+  self->lengths = (size_t *)malloc(self->n * sizeof(size_t));
+  safe_malloc(self->lengths);
+  for (size_t i = 0; i < self->n; ++i) {
+    self->lengths[i] = batch_size;
+  }
+
+  self->data = (float **)malloc(self->n * sizeof(float *));
+  safe_malloc(self->data);
+  self->labels = (float **)malloc(self->n * sizeof(float *));
+  safe_malloc(self->labels);
+
+  /* Generate some random data. */
+  for (size_t i = 0; i < self->n; ++i) {
+    self->data[i] = (float *)malloc(self->lengths[i] * sizeof(float));
+    safe_malloc(self->data[i]);
+    for (size_t j = 0; j < self->lengths[i]; ++j) {
+      float x = (float)rand() / (float)(RAND_MAX);
+      self->data[i][j] = x;
+    }
+
+    self->labels[i] = (float *)malloc(self->lengths[i] * sizeof(float));
+    safe_malloc(self->labels[i]);
+    for (size_t j = 0; j < self->lengths[i]; ++j) {
+      float y = (float)rand() / (float)(RAND_MAX);
+      self->labels[i][j] = y;
+    }
+  }
+
+  self->cur_it = 0;
+  safe_xgboost(XGProxyDMatrixCreate(&self->_proxy));
+}
+
+void DataIterator_Free(DataIter *self) {
+  for (size_t i = 0; i < self->n; ++i) {
+    free(self->data[i]);
+    free(self->labels[i]);
+  }
+  free(self->data);
+  free(self->lengths);
+  safe_xgboost(XGDMatrixFree(self->_proxy));
+};
+
+int DataIterator_Next(DataIterHandle handle) {
+  DataIter *self = (DataIter *)(handle);
+  if (self->cur_it == self->n) {
+    self->cur_it = 0;
+    return 0;  /* At end */
+  }
+
+  /* A JSON string encoding array interface (standard from numpy). */
+  char array[] = "{\"data\": [%lu, false], \"shape\":[%lu, 1], \"typestr\": "
+                 "\"<f4\", \"version\": 3}";
+  memset(self->_array, '\0', sizeof(self->_array));
+  sprintf(self->_array, array, (size_t)self->data[self->cur_it],
+          self->lengths[self->cur_it]);
+
+  safe_xgboost(XGProxyDMatrixSetDataDense(self->_proxy, self->_array));
+  /* The data passed in the iterator must remain valid (not being freed until the next
+   * iteration or reset) */
+  safe_xgboost(XGDMatrixSetDenseInfo(self->_proxy, "label",
+                                     self->labels[self->cur_it],
+                                     self->lengths[self->cur_it], 1));
+  self->cur_it++;
+  return 1;  /* Continue. */
+}
+
+void DataIterator_Reset(DataIterHandle handle) {
+  DataIter *self = (DataIter *)(handle);
+  self->cur_it = 0;
+}
+
+/**
+ * Train a regression model and save it into JSON model file.
+ */
+void TrainModel(DMatrix Xy) {
+  /* Create booster for training. */
+  Booster booster;
+  DMatrix cache[] = {Xy};
+  safe_xgboost(XGBoosterCreate(cache, 1, &booster));
+  /* Use approx for external memory training. */
+  safe_xgboost(XGBoosterSetParam(booster, "tree_method", "approx"));
+  safe_xgboost(XGBoosterSetParam(booster, "objective", "reg:squarederror"));
+
+  /* Start training. */
+  const char *validation_names[1] = {"train"};
+  const char *validation_result = NULL;
+  size_t n_rounds = 10;
+  for (size_t i = 0; i < n_rounds; ++i) {
+    safe_xgboost(XGBoosterUpdateOneIter(booster, i, Xy));
+    safe_xgboost(XGBoosterEvalOneIter(booster, i, cache, validation_names, 1,
+                                      &validation_result));
+    printf("%s\n", validation_result);
+  }
+
+  /* Save the model to a JSON file. */
+  safe_xgboost(XGBoosterSaveModel(booster, "model.json"));
+
+  safe_xgboost(XGBoosterFree(booster));
+}
+
+int main() {
+  DataIter iter;
+  DataIterator_Init(&iter, BATCH_LEN, N_BATCHS);
+
+  /* Create DMatrix from iterator.  During training, some cache files with the
+   * prefix "cache-" will be generated in current directory */
+  char config[] = "{\"missing\": NaN, \"cache_prefix\": \"cache\"}";
+  DMatrix Xy;
+  safe_xgboost(XGDMatrixCreateFromCallback(
+      &iter, iter._proxy, DataIterator_Reset, DataIterator_Next, config, &Xy));
+
+  TrainModel(Xy);
+
+  safe_xgboost(XGDMatrixFree(Xy));
+
+  DataIterator_Free(&iter);
+  return 0;
+}