Simplify the data backends. (#5893)

src/data/proxy_dmatrix.cu

@@ -12,12 +12,16 @@ void DMatrixProxy::FromCudaColumnar(std::string interface_str) {
   auto const& value = adapter->Value();
   this->batch_ = adapter;
   device_ = adapter->DeviceIdx();
+  this->Info().num_col_ = adapter->NumColumns();
+  this->Info().num_row_ = adapter->NumRows();
 }
 
 void DMatrixProxy::FromCudaArray(std::string interface_str) {
   std::shared_ptr<CupyAdapter> adapter(new CupyAdapter(interface_str));
   this->batch_ = adapter;
   device_ = adapter->DeviceIdx();
+  this->Info().num_col_ = adapter->NumColumns();
+  this->Info().num_row_ = adapter->NumRows();
 }
 
 }  // namespace data

tests/python-gpu/test_device_quantile_dmatrix.py

@@ -12,11 +12,12 @@
 class TestDeviceQuantileDMatrix(unittest.TestCase):
     def test_dmatrix_numpy_init(self):
         data = np.random.randn(5, 5)
-        with pytest.raises(AssertionError, match='is not supported for DeviceQuantileDMatrix'):
-            dm = xgb.DeviceQuantileDMatrix(data, np.ones(5, dtype=np.float64))
+        with pytest.raises(TypeError,
+                           match='is not supported for DeviceQuantileDMatrix'):
+            xgb.DeviceQuantileDMatrix(data, np.ones(5, dtype=np.float64))
 
     @pytest.mark.skipif(**tm.no_cupy())
     def test_dmatrix_cupy_init(self):
         import cupy as cp
         data = cp.random.randn(5, 5)
-        dm = xgb.DeviceQuantileDMatrix(data, cp.ones(5, dtype=np.float64))
+        xgb.DeviceQuantileDMatrix(data, cp.ones(5, dtype=np.float64))

tests/python-gpu/test_from_cudf.py

@@ -119,10 +119,10 @@ def _test_cudf_metainfo(DMatrixT):
     dmat.set_float_info('label', floats)
     dmat.set_float_info('base_margin', floats)
     dmat.set_uint_info('group', uints)
-    dmat_cudf.set_interface_info('weight', cudf_floats)
-    dmat_cudf.set_interface_info('label', cudf_floats)
-    dmat_cudf.set_interface_info('base_margin', cudf_floats)
-    dmat_cudf.set_interface_info('group', cudf_uints)
+    dmat_cudf.set_info(weight=cudf_floats)
+    dmat_cudf.set_info(label=cudf_floats)
+    dmat_cudf.set_info(base_margin=cudf_floats)
+    dmat_cudf.set_info(group=cudf_uints)
 
     # Test setting info with cudf DataFrame
     assert np.array_equal(dmat.get_float_info('weight'), dmat_cudf.get_float_info('weight'))
@@ -132,10 +132,10 @@ def _test_cudf_metainfo(DMatrixT):
     assert np.array_equal(dmat.get_uint_info('group_ptr'), dmat_cudf.get_uint_info('group_ptr'))
 
     # Test setting info with cudf Series
-    dmat_cudf.set_interface_info('weight', cudf_floats[cudf_floats.columns[0]])
-    dmat_cudf.set_interface_info('label', cudf_floats[cudf_floats.columns[0]])
-    dmat_cudf.set_interface_info('base_margin', cudf_floats[cudf_floats.columns[0]])
-    dmat_cudf.set_interface_info('group', cudf_uints[cudf_uints.columns[0]])
+    dmat_cudf.set_info(weight=cudf_floats[cudf_floats.columns[0]])
+    dmat_cudf.set_info(label=cudf_floats[cudf_floats.columns[0]])
+    dmat_cudf.set_info(base_margin=cudf_floats[cudf_floats.columns[0]])
+    dmat_cudf.set_info(group=cudf_uints[cudf_uints.columns[0]])
     assert np.array_equal(dmat.get_float_info('weight'), dmat_cudf.get_float_info('weight'))
     assert np.array_equal(dmat.get_float_info('label'), dmat_cudf.get_float_info('label'))
     assert np.array_equal(dmat.get_float_info('base_margin'),

tests/python-gpu/test_from_cupy.py

@@ -92,10 +92,10 @@ def _test_cupy_metainfo(DMatrixT):
     dmat.set_float_info('label', floats)
     dmat.set_float_info('base_margin', floats)
     dmat.set_uint_info('group', uints)
-    dmat_cupy.set_interface_info('weight', cupy_floats)
-    dmat_cupy.set_interface_info('label', cupy_floats)
-    dmat_cupy.set_interface_info('base_margin', cupy_floats)
-    dmat_cupy.set_interface_info('group', cupy_uints)
+    dmat_cupy.set_info(weight=cupy_floats)
+    dmat_cupy.set_info(label=cupy_floats)
+    dmat_cupy.set_info(base_margin=cupy_floats)
+    dmat_cupy.set_info(group=cupy_uints)
 
     # Test setting info with cupy
     assert np.array_equal(dmat.get_float_info('weight'),

tests/python/test_basic.py

@@ -1,17 +1,14 @@
 # -*- coding: utf-8 -*-
 import sys
 from contextlib import contextmanager
-try:
-    # python 2
-    from StringIO import StringIO
-except ImportError:
-    # python 3
-    from io import StringIO
+from io import StringIO
 import numpy as np
+import os
 import xgboost as xgb
 import unittest
 import json
 from pathlib import Path
+import tempfile
 
 dpath = 'demo/data/'
 rng = np.random.RandomState(1994)
@@ -66,16 +63,19 @@ def test_basic(self):
         # error must be smaller than 10%
         assert err < 0.1
 
-        # save dmatrix into binary buffer
-        dtest.save_binary('dtest.buffer')
-        # save model
-        bst.save_model('xgb.model')
-        # load model and data in
-        bst2 = xgb.Booster(model_file='xgb.model')
-        dtest2 = xgb.DMatrix('dtest.buffer')
-        preds2 = bst2.predict(dtest2)
-        # assert they are the same
-        assert np.sum(np.abs(preds2 - preds)) == 0
+        with tempfile.TemporaryDirectory() as tmpdir:
+            dtest_path = os.path.join(tmpdir, 'dtest.dmatrix')
+            # save dmatrix into binary buffer
+            dtest.save_binary(dtest_path)
+            # save model
+            model_path = os.path.join(tmpdir, 'model.booster')
+            bst.save_model(model_path)
+            # load model and data in
+            bst2 = xgb.Booster(model_file=model_path)
+            dtest2 = xgb.DMatrix(dtest_path)
+            preds2 = bst2.predict(dtest2)
+            # assert they are the same
+            assert np.sum(np.abs(preds2 - preds)) == 0
 
     def test_record_results(self):
         dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')

tests/python/test_with_pandas.py

@@ -67,8 +67,7 @@ def test_pandas(self):
         # 0  1    1    0    0
         # 1  2    0    1    0
         # 2  3    0    0    1
-        pandas_handler = xgb.data.PandasHandler(np.nan, 0, False)
-        result, _, _ = pandas_handler._maybe_pandas_data(dummies, None, None)
+        result, _, _ = xgb.data._transform_pandas_df(dummies)
         exp = np.array([[1., 1., 0., 0.],
                         [2., 0., 1., 0.],
                         [3., 0., 0., 1.]])
@@ -129,18 +128,17 @@ def test_pandas_sparse(self):
     def test_pandas_label(self):
         # label must be a single column
         df = pd.DataFrame({'A': ['X', 'Y', 'Z'], 'B': [1, 2, 3]})
-        pandas_handler = xgb.data.PandasHandler(np.nan, 0, False)
-        self.assertRaises(ValueError, pandas_handler._maybe_pandas_data, df,
+        self.assertRaises(ValueError, xgb.data._transform_pandas_df, df,
                           None, None, 'label', 'float')
 
         # label must be supported dtype
         df = pd.DataFrame({'A': np.array(['a', 'b', 'c'], dtype=object)})
-        self.assertRaises(ValueError, pandas_handler._maybe_pandas_data, df,
+        self.assertRaises(ValueError, xgb.data._transform_pandas_df, df,
                           None, None, 'label', 'float')
 
         df = pd.DataFrame({'A': np.array([1, 2, 3], dtype=int)})
-        result, _, _ = pandas_handler._maybe_pandas_data(df, None, None,
-                                                         'label', 'float')
+        result, _, _ = xgb.data._transform_pandas_df(df, None, None,
+                                                     'label', 'float')
         np.testing.assert_array_equal(result, np.array([[1.], [2.], [3.]],
                                                        dtype=float))
         dm = xgb.DMatrix(np.random.randn(3, 2), label=df)