Merge branch 'branch-0.17' into enh-add-qn-tests

CHANGELOG.md

@@ -28,6 +28,8 @@
 - PR #3111: Adding Cython to Code Coverage
 - PR #3129:  Update notebooks README
 - PR #3135: Add QuasiNewton tests
+- PR #3040: Improved Array Conversion with CumlArrayDescriptor and Decorators
+- PR #3134: Improving the Deprecation Message Formatting in Documentation
 
 ## Bug Fixes
 - PR #3065: Refactoring prims metrics function names from camelcase to underscore format

docs/source/_static/infoboxes.css

@@ -0,0 +1,87 @@
+/* This contains code with copyright by the scikit-learn project, subject to
+the license in /thirdparty/LICENSES/LICENSE.scikit_learn */
+
+/* info boxes */
+
+div.topic {
+  padding: 0.5rem;
+  background-color: #eee;
+  margin-bottom: 1rem;
+  border-radius: 0.25rem;
+  border: 1px solid #CCC;
+}
+
+div.topic p {
+  margin-bottom: 0.25rem;
+}
+
+div.topic dd {
+  margin-bottom: 0.25rem;
+}
+
+p.topic-title {
+  font-weight: bold;
+  margin-bottom: 0.5rem;
+}
+
+div.topic > ul.simple {
+  margin-bottom: 0.25rem;
+}
+
+p.admonition-title {
+  margin-right: 0.5rem;
+  font-weight: bold;
+  display: inline;
+}
+
+p.admonition-title:after {
+  content: ":";
+}
+
+div.admonition p.admonition-title + p, div.deprecated p {
+  display: inline;
+}
+
+div.admonition, div.deprecated {
+  padding: 0.5rem;
+  border-radius: 0.5rem;
+  border: 1px solid #ddd;
+  margin-bottom: 1rem;
+}
+
+div.admonition {
+  background-color: #eee;
+}
+
+div.admonition p, div.admonition dl, div.admonition dd {
+  margin-bottom: 0
+}
+
+div.deprecated {
+  color: #b94a48;
+  background-color: #F3E5E5;
+  border: 1px solid #eed3d7;
+}
+
+div.seealso {
+  background-color: #FFFBE8;
+  border: 1px solid #fbeed5;
+  color: #AF8A4B;
+}
+
+div.versionchanged {
+  margin-top: 0.5rem;
+  padding: 0.5rem;
+  background-color: #FFFBE8;
+  border: 1px solid #fbeed5;
+  border-radius: 0.5rem;
+}
+
+div.versionchanged p {
+  margin-bottom: 0;
+}
+
+dt.label {
+  float: left;
+  padding-right: 0.5rem;
+}

docs/source/conf.py

@@ -191,6 +191,7 @@
 
 def setup(app):
     app.add_css_file('copybutton.css')
+    app.add_css_file('infoboxes.css')
     app.add_css_file('params.css')
     app.add_css_file('references.css')
 

python/cuml/__init__.py

@@ -82,7 +82,7 @@
 
 # Output type configuration
 
-global_output_type = 'input'
+global_output_type = None
 
 from cuml.common.memory_utils import set_global_output_type, using_output_type
 

python/cuml/benchmark/datagen.py

@@ -219,7 +219,8 @@ def _convert_to_gpuarray(data, order='F'):
         gs = cudf.Series.from_pandas(data)
         return cuda.as_cuda_array(gs)
     else:
-        return input_utils.input_to_dev_array(data, order=order)[0]
+        return input_utils.input_to_cuml_array(
+            data, order=order)[0].to_output("numba")
 
 
 def _convert_to_gpuarray_c(data):

python/cuml/cluster/dbscan.pyx

@@ -30,6 +30,8 @@ from cuml.common.base import Base
 from cuml.common.doc_utils import generate_docstring
 from cuml.raft.common.handle cimport handle_t
 from cuml.common import input_to_cuml_array
+from cuml.common import using_output_type
+from cuml.common.array_descriptor import CumlArrayDescriptor
 
 from collections import defaultdict
 
@@ -186,6 +188,9 @@ class DBSCAN(Base):
     <http://scikit-learn.org/stable/modules/generated/sklearn.cluster.DBSCAN.html>`_.
     """
 
+    labels_ = CumlArrayDescriptor()
+    core_sample_indices_ = CumlArrayDescriptor()
+
     def __init__(self, eps=0.5, handle=None, min_samples=5,
                  verbose=False, max_mbytes_per_batch=None,
                  output_type=None, calc_core_sample_indices=True):
@@ -196,18 +201,17 @@ class DBSCAN(Base):
         self.calc_core_sample_indices = calc_core_sample_indices
 
         # internal array attributes
-        self._labels_ = None  # accessed via estimator.labels_
+        self.labels_ = None
 
-        # accessed via estimator._core_sample_indices_ when
-        # self.calc_core_sample_indices == True
-        self._core_sample_indices_ = None
+        # One used when `self.calc_core_sample_indices == True`
+        self.core_sample_indices_ = None
 
         # C++ API expects this to be numeric.
         if self.max_mbytes_per_batch is None:
             self.max_mbytes_per_batch = 0
 
     @generate_docstring(skip_parameters_heading=True)
-    def fit(self, X, out_dtype="int32"):
+    def fit(self, X, out_dtype="int32") -> "DBSCAN":
         """
         Perform DBSCAN clustering from features.
 
@@ -218,11 +222,6 @@ class DBSCAN(Base):
             "int64", np.int64}.
 
         """
-        self._set_base_attributes(output_type=X, n_features=X)
-
-        if self._labels_ is not None:
-            del self._labels_
-
         if out_dtype not in ["int32", np.int32, "int64", np.int64]:
             raise ValueError("Invalid value for out_dtype. "
                              "Valid values are {'int32', 'int64', "
@@ -236,16 +235,16 @@ class DBSCAN(Base):
 
         cdef handle_t* handle_ = <handle_t*><size_t>self.handle.getHandle()
 
-        self._labels_ = CumlArray.empty(n_rows, dtype=out_dtype)
-        cdef uintptr_t labels_ptr = self._labels_.ptr
+        self.labels_ = CumlArray.empty(n_rows, dtype=out_dtype)
+        cdef uintptr_t labels_ptr = self.labels_.ptr
 
         cdef uintptr_t core_sample_indices_ptr = <uintptr_t> NULL
 
         # Create the output core_sample_indices only if needed
         if self.calc_core_sample_indices:
-            self._core_sample_indices_ = \
+            self.core_sample_indices_ = \
                 CumlArray.empty(n_rows, dtype=out_dtype)
-            core_sample_indices_ptr = self._core_sample_indices_.ptr
+            core_sample_indices_ptr = self.core_sample_indices_.ptr
 
         if self.dtype == np.float32:
             if out_dtype is "int32" or out_dtype is np.int32:
@@ -303,20 +302,21 @@ class DBSCAN(Base):
         # Finally, resize the core_sample_indices array if necessary
         if self.calc_core_sample_indices:
 
-            # Temp convert to cupy array only once
-            core_samples_cupy = self._core_sample_indices_.to_output("cupy")
+            # Temp convert to cupy array (better than using `cupy.asarray`)
+            with using_output_type("cupy"):
 
-            # First get the min index. These have to monotonically increasing,
-            # so the min index should be the first returned -1
-            min_index = cp.argmin(core_samples_cupy).item()
+                # First get the min index. These have to monotonically
+                # increasing, so the min index should be the first returned -1
+                min_index = cp.argmin(self.core_sample_indices_).item()
 
-            # Check for the case where there are no -1's
-            if (min_index == 0 and core_samples_cupy[min_index].item() != -1):
-                # Nothing to delete. The array has no -1's
-                pass
-            else:
-                self._core_sample_indices_ = \
-                    self._core_sample_indices_[:min_index]
+                # Check for the case where there are no -1's
+                if ((min_index == 0 and
+                     self.core_sample_indices_[min_index].item() != -1)):
+                    # Nothing to delete. The array has no -1's
+                    pass
+                else:
+                    self.core_sample_indices_ = \
+                        self.core_sample_indices_[:min_index]
 
         return self
 
@@ -325,7 +325,7 @@ class DBSCAN(Base):
                                        'type': 'dense',
                                        'description': 'Cluster labels',
                                        'shape': '(n_samples, 1)'})
-    def fit_predict(self, X, out_dtype="int32"):
+    def fit_predict(self, X, out_dtype="int32") -> CumlArray:
         """
         Performs clustering on X and returns cluster labels.