[REVIEW] Cleanup sphinx doc warnings for 0.15

CHANGELOG.md

@@ -138,6 +138,8 @@
 - PR #2634: singlegpu build option fixes
 - PR #2651: AutoARIMA Python bug fix
 - PR #2654: Fix for vectorizer concatenations
+- PR #2655: Fix C++ RF predict function access of rows/samples array
+- PR #2649: Cleanup sphinx doc warnings for 0.15
 - PR #2669: Revert PR 2655 Revert "Fixes C++ RF predict function"
 
 # cuML 0.14.0 (03 Jun 2020)

docs/source/_static/references.css

@@ -0,0 +1,23 @@
+
+/* Fix references to not look like parameters */
+dl.citation > dt.label {
+  display: unset !important;
+  float: left !important;
+  border: unset !important;
+  background: unset !important;
+  padding: unset !important;
+  margin: unset !important;
+  font-size: unset !important;
+  line-height: unset !important;
+  padding-right: 0.5rem !important;
+}
+
+/* Add opening bracket */
+dl.citation > dt.label > span::before {
+  content: "[";
+}
+
+/* Add closing bracket */
+dl.citation > dt.label > span::after {
+  content: "]";
+}

docs/source/api.rst

@@ -59,7 +59,7 @@ Model Selection and Data Splitting
 Feature and Label Encoding (Single-GPU)
 ---------------------------------------
 
- .. autoclass:: cuml.preprocessing.LabelEncoder
+ .. autoclass:: cuml.preprocessing.LabelEncoder.LabelEncoder
     :members:
 
  .. autoclass:: cuml.preprocessing.LabelBinarizer
@@ -248,12 +248,14 @@ Nearest Neighbors Classification
 
 .. autoclass:: cuml.neighbors.KNeighborsClassifier
     :members:
+    :noindex:
 
 Nearest Neighbors Regression
 ----------------------------
 
 .. autoclass:: cuml.neighbors.KNeighborsRegressor
     :members:
+    :noindex:
 
 Clustering
 ==========

docs/source/conf.py

@@ -187,4 +187,6 @@
 
 
 def setup(app):
+    app.add_css_file('copybutton.css')
     app.add_css_file('params.css')
+    app.add_css_file('references.css')

python/cuml/cluster/dbscan.pyx

@@ -93,7 +93,7 @@ class DBSCAN(Base):
     neighbours.
 
     Examples
-    ---------
+    --------
 
     .. code-block:: python
 

python/cuml/common/array.py

@@ -31,16 +31,16 @@ class CumlArray(Buffer):
     """
     Array represents an abstracted array allocation. It can be instantiated by
     itself, creating an rmm.DeviceBuffer underneath, or can be instantiated by
-    __cuda_array_interface__ or __array_interface__ compliant arrays, in which
-    case it'll keep a reference to that data underneath. Also can be created
-    from a pointer, specifying the characteristics of the array, in that case
-    the owner of the data referred to by the pointer should be specified
-    explicitly.
+    ``__cuda_array_interface__`` or ``__array_interface__`` compliant arrays,
+    in which case it'll keep a reference to that data underneath. Also can be
+    created from a pointer, specifying the characteristics of the array, in
+    that case the owner of the data referred to by the pointer should be
+    specified explicitly.
 
     Parameters
     ----------
 
-    data : rmm.DeviceBuffer, cudf.Buffer, array_like, int, bytes, bytearray or
+    data : rmm.DeviceBuffer, cudf.Buffer, array_like, int, bytes, bytearray or\
            memoryview
         An array-like object or integer representing a
         device or host pointer to pre-allocated memory.
@@ -71,23 +71,7 @@ class CumlArray(Buffer):
     strides : tuple of ints
         Strides of the data
     __cuda_array_interface__ : dictionary
-        __cuda_array_interface__ to interop with other libraries.
-
-    Object Methods
-    --------------
-
-    to_output : Convert the array to the appropriate output format.
-
-    Class Methods
-    -------------
-
-    Array.empty : Create an empty array, allocating a DeviceBuffer.
-    Array.full : Create an Array with allocated DeviceBuffer initialized with
-        a particular value.
-    Array.ones : Create an Array with allocated DeviceBuffer initialized with
-        ones.
-    Array.zeros : Create an Array with allocated DeviceBuffer initialized with
-        zeros.
+        ``__cuda_array_interface__`` to interop with other libraries.
 
     Notes
     -----
@@ -204,16 +188,19 @@ def to_output(self, output_type='cupy', output_dtype=None):
         ----------
         output_type : string
             Format to convert the array to. Acceptable formats are:
-            'cupy' - to cupy array
-            'numpy' - to numpy (host) array
-            'numba' - to numba device array
-            'dataframe' - to cuDF DataFrame
-            'series' - to cuDF Series
-            'cudf' - to cuDF Series if array is single dimensional, to
-                DataFrame otherwise
+
+            - 'cupy' - to cupy array
+            - 'numpy' - to numpy (host) array
+            - 'numba' - to numba device array
+            - 'dataframe' - to cuDF DataFrame
+            - 'series' - to cuDF Series
+            - 'cudf' - to cuDF Series if array is single dimensional, to
+               DataFrame otherwise
+
         output_dtype : string, optional
             Optionally cast the array to a specified dtype, creating
             a copy if necessary.
+
         """
         if output_dtype is None:
             output_dtype = self.dtype

python/cuml/common/kernel_utils.py

@@ -66,8 +66,8 @@ def cuda_kernel_factory(nvrtc_kernel_str, dtypes, kernel_name=None):
     included in the kernel string. These will be added by this function and
     the function name will be made unique, based on the given dtypes.
 
-    Example
-    -------
+    Examples
+    --------
 
         The following kernel string with dtypes = [float, double, int]
 

python/cuml/common/logger.pyx

@@ -97,7 +97,6 @@ def set_level(level):
 
     .. code-block:: python
 
-
         # regular usage of setting a logging level for all subsequent logs
         # in this case, it will enable all logs upto and including `info()`
         logger.set_level(logger.level_info)
@@ -147,7 +146,6 @@ def set_pattern(pattern):
 
     .. code-block:: python
 
-
         # regular usage of setting a logging pattern for all subsequent logs
         logger.set_pattern("--> [%H-%M-%S] %v")
 

python/cuml/common/memory_utils.py

@@ -63,7 +63,6 @@ def rmm_cupy_ary(cupy_fn, *args, **kwargs):
 
     Function to call CuPy functions with RMM memory management
 
-
     Parameters
     ----------
     cupy_fn : cupy function,
@@ -76,13 +75,13 @@ def rmm_cupy_ary(cupy_fn, *args, **kwargs):
         Keyword named arguments to pass to the CuPy function
 
 
-    Note: this function should be used if the result of cupy_fn creates
+    .. note:: this function should be used if the result of cupy_fn creates
     a new array. Functions to create a new CuPy array by reference to
     existing device array (through __cuda_array_interface__) can be used
     directly.
 
     Examples
-    ---------
+    --------
 
     .. code-block:: python
 
@@ -242,30 +241,32 @@ def set_global_output_type(output_type):
     output_type : {'input', 'cudf', 'cupy', 'numpy'} (default = 'input')
         Desired output type of results and attributes of the estimators.
 
-        'input' will mean that the parameters and methods will mirror the
-        format of the data sent to the estimators/methods as much as
-        possible. Specifically:
-
-            Input type -> Output type
-
-            cuDF DataFrame or Series -> cuDF DataFrame or Series
-
-            NumPy arrays -> NumPy arrays
-
-            Pandas DataFrame or Series -> NumPy arrays
-
-            Numba device arrays -> Numba device arrays
-
-            CuPy arrays -> CuPy arrays
-
-            Other __cuda_array_interface__ objects -> CuPy arrays
-
-        'cudf' will return cuDF Series for single dimensional results and
-        DataFrames for the rest.
-
-        'cupy' will return CuPy arrays.
-
-        'numpy' will return NumPy arrays.
+        * ``'input'`` will mean that the parameters and methods will mirror the
+          format of the data sent to the estimators/methods as much as
+          possible. Specifically:
+
+          +---------------------------------------+--------------------------+
+          | Input type                            | Output type              |
+          +=======================================+==========================+
+          | cuDF DataFrame or Series              | cuDF DataFrame or Series |
+          +---------------------------------------+--------------------------+
+          | NumPy arrays                          | NumPy arrays             |
+          +---------------------------------------+--------------------------+
+          | Pandas DataFrame or Series            | NumPy arrays             |
+          +---------------------------------------+--------------------------+
+          | Numba device arrays                   | Numba device arrays      |
+          +---------------------------------------+--------------------------+
+          | CuPy arrays                           | CuPy arrays              |
+          +---------------------------------------+--------------------------+
+          | Other `__cuda_array_interface__` objs | CuPy arrays              |
+          +---------------------------------------+--------------------------+
+
+        * ``'cudf'`` will return cuDF Series for single dimensional results and
+          DataFrames for the rest.
+
+        * ``'cupy'`` will return CuPy arrays.
+
+        * ``'numpy'`` will return NumPy arrays.
 
     Examples
     --------
@@ -288,7 +289,7 @@ def set_global_output_type(output_type):
 
     Output:
 
-    .. code-block:: python
+    .. code-block::
 
         cuML output type
         0    0
@@ -299,10 +300,11 @@ def set_global_output_type(output_type):
 
     Notes
     -----
-    'cupy' and 'numba' options (as well as 'input' when using Numba and CuPy
-    ndarrays for input) have the least overhead. cuDF add memory consumption
-    and processing time needed to build the Series and DataFrames. 'numpy' has
-    the biggest overhead due to the need to transfer data to CPU memory.
+    ``'cupy'`` and ``'numba'`` options (as well as ``'input'`` when using Numba
+    and CuPy ndarrays for input) have the least overhead. cuDF add memory
+    consumption and processing time needed to build the Series and DataFrames.
+    ``'numpy'`` has the biggest overhead due to the need to transfer data to
+    CPU memory.
 
     """
     if isinstance(output_type, str):
@@ -330,30 +332,32 @@ def using_output_type(output_type):
     output_type : {'input', 'cudf', 'cupy', 'numpy'} (default = 'input')
         Desired output type of results and attributes of the estimators.
 
-        'input' will mean that the parameters and methods will mirror the
-        format of the data sent to the estimators/methods as much as
-        possible. Specifically:
-
-            Input type -> Output type
-
-            cuDF DataFrame or Series -> cuDF DataFrame or Series
-
-            NumPy arrays -> NumPy arrays
-
-            Pandas DataFrame or Series -> NumPy arrays
-
-            Numba device arrays -> Numba device arrays
-
-            CuPy arrays -> CuPy arrays
-
-            Other __cuda_array_interface__ objects -> CuPy arrays
-
-        'cudf' will return cuDF Series for single dimensional results and
-        DataFrames for the rest.
-
-        'cupy' will return CuPy arrays.
-
-        'numpy' will return NumPy arrays.
+        * ``'input'`` will mean that the parameters and methods will mirror the
+          format of the data sent to the estimators/methods as much as
+          possible. Specifically:
+
+          +---------------------------------------+--------------------------+
+          | Input type                            | Output type              |
+          +=======================================+==========================+
+          | cuDF DataFrame or Series              | cuDF DataFrame or Series |
+          +---------------------------------------+--------------------------+
+          | NumPy arrays                          | NumPy arrays             |
+          +---------------------------------------+--------------------------+
+          | Pandas DataFrame or Series            | NumPy arrays             |
+          +---------------------------------------+--------------------------+
+          | Numba device arrays                   | Numba device arrays      |
+          +---------------------------------------+--------------------------+
+          | CuPy arrays                           | CuPy arrays              |
+          +---------------------------------------+--------------------------+
+          | Other `__cuda_array_interface__` objs | CuPy arrays              |
+          +---------------------------------------+--------------------------+
+
+        * ``'cudf'`` will return cuDF Series for single dimensional results and
+          DataFrames for the rest.
+
+        * ``'cupy'`` will return CuPy arrays.
+
+        * ``'numpy'`` will return NumPy arrays.
 
     Examples
     --------
@@ -370,7 +374,7 @@ def using_output_type(output_type):
             dbscan_float = cuml.DBSCAN(eps=1.0, min_samples=1)
             dbscan_float.fit(ary)
 
-            print("cuML output inside `with` context")
+            print("cuML output inside 'with' context")
             print(dbscan_float.labels_)
             print(type(dbscan_float.labels_))
 
@@ -384,16 +388,15 @@ def using_output_type(output_type):
 
     Output:
 
-    .. code-block:: python
+    .. code-block::
 
-        cuML output inside `with` context
+        cuML output inside 'with' context
         0    0
         1    1
         2    2
         dtype: int32
         <class 'cudf.core.series.Series'>
 
-
         cuML default output
         [0 1 2]
         <class 'cupy.core.core.ndarray'>

python/cuml/common/opg_data_utils_mg.pyx

@@ -114,7 +114,7 @@ def build_rank_size_pair(parts_to_sizes, rank):
     parts_to_sizes: array of tuples in the format: [(rank,size)]
     rank: rank to be mapped
 
-    Returns:
+    Returns
     --------
     ptr: vector pointer of the RankSizePair*
     """
@@ -162,7 +162,7 @@ def build_part_descriptor(m, n, rank_size_t, rank):
         building the part descriptor
     rank: rank to be mapped
 
-    Returns:
+    Returns
     --------
     ptr: PartDescriptor object
     """

python/cuml/common/sparsefuncs.py

@@ -150,7 +150,8 @@ def _insert_zeros(ary, zero_indices):
     Create a new array of len(ary + zero_indices) where zero_indices
     indicates indexes of 0s in the new array. Ary is used to fill the rest.
 
-    Example:
+    Examples
+    --------
         _insert_zeros([1, 2, 3], [1, 3]) => [1, 0, 2, 0, 3]
     """
     if len(zero_indices) == 0: