[REVIEW] Change docs theme to pydata-sphinx theme

.gitignore

@@ -35,6 +35,8 @@ _skbuild/
 
 ## files pickled in notebook when ran during python docstring generation
 docs/source/*.model
+docs/source/*.pkl
+docs/source/*.tl
 
 ## eclipse
 .project

conda/environments/builddocs_py37.yml

@@ -19,7 +19,7 @@ dependencies:
 - pytest
 # required for building rapids project docs
 - sphinx
-- sphinx_rtd_theme
+- pydata-sphinx-theme
 - sphinx-markdown-tables
 - sphinxcontrib-websupport
 - nbsphinx

cpp/include/cuml/manifold/tsne.h

@@ -85,7 +85,7 @@ struct TSNEParams {
   // The momentum used after the exaggeration phase.
   float post_momentum = 0.8;
 
-  // Set this to -1 for pure random intializations or >= 0 for
+  // Set this to -1 for pure random initializations or >= 0 for
   // reproducible outputs. This sets random seed correctly, but there
   // may still be some variance due to the parallel nature of this algorithm.
   long long random_state = -1;

docs/source/conf.py

@@ -50,6 +50,7 @@
     "nbsphinx",
     "recommonmark",
     "sphinx_markdown_tables",
+    "sphinx_copybutton"
 ]
 
 ipython_mplbackend = "str"
@@ -107,31 +108,26 @@
 # a list of builtin themes.
 #
 
-html_theme = 'sphinx_rtd_theme'
-
-# on_rtd is whether we are on readthedocs.org
-on_rtd = os.environ.get('READTHEDOCS', None) == 'True'
-
-if not on_rtd:
-    # only import and set the theme if we're building docs locally
-    # otherwise, readthedocs.org uses their theme by default,
-    # so no need to specify it
-    import sphinx_rtd_theme
-    html_theme = 'sphinx_rtd_theme'
-    html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
+html_theme = 'pydata_sphinx_theme'
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
 # documentation.
 #
-# html_theme_options = {}
+html_theme_options = {
+    "external_links": [],
+    "github_url": "https://github.com/rapidsai/cuml",
+    "twitter_url": "https://twitter.com/rapidsai",
+    "show_toc_level": 1,
+    "navbar_align": "right",
+}
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
 html_static_path = ['_static']
 
-html_js_files = ["example_mod.js"]
+html_js_files = []
 
 # -- Options for HTMLHelp output ------------------------------------------
 
@@ -193,8 +189,6 @@
 
 
 def setup(app):
-    app.add_css_file("copybutton.css")
-    app.add_css_file("infoboxes.css")
     app.add_css_file("references.css")
     app.add_css_file("https://docs.rapids.ai/assets/css/custom.css")
     app.add_js_file("https://docs.rapids.ai/assets/js/custom.js", loading_method="defer")

notebooks/kmeans_demo.ipynb

@@ -8,7 +8,7 @@
     "\n",
     "KMeans is a basic but powerful clustering method which is optimized via Expectation Maximization. It randomly selects K data points in X, and computes which samples are close to these points. For every cluster of points, a mean is computed, and this becomes the new centroid.\n",
     "\n",
-    "cuML’s KMeans supports the scalable KMeans++ intialization method. This method is more stable than randomnly selecting K points.\n",
+    "cuML’s KMeans supports the scalable KMeans++ initialization method. This method is more stable than randomnly selecting K points.\n",
     "    \n",
     "The model can take array-like objects, either in host as NumPy arrays or in device (as Numba or cuda_array_interface-compliant), as well as cuDF DataFrames as the input.\n",
     "\n",

python/cuml/_thirdparty/sklearn/preprocessing/_column_transformer.py

@@ -432,18 +432,18 @@ class ColumnTransformer(TransformerMixin, BaseComposition, BaseEstimator):
     ----------
     transformers : list of tuples
         List of (name, transformer, columns) tuples specifying the
-        transformer objects to be applied to subsets of the data.
+        transformer objects to be applied to subsets of the data:
 
-        name : str
+        * name : str
             Like in Pipeline and FeatureUnion, this allows the transformer and
             its parameters to be set using ``set_params`` and searched in grid
             search.
-        transformer : {'drop', 'passthrough'} or estimator
+        * transformer : {'drop', 'passthrough'} or estimator
             Estimator must support `fit` and `transform`.
             Special-cased strings 'drop' and 'passthrough' are accepted as
             well, to indicate to drop the columns or to pass them through
             untransformed, respectively.
-        columns :  str, array-like of str, int, array-like of int, \
+        * columns :  str, array-like of str, int, array-like of int, \
                 array-like of bool, slice or callable
             Indexes the data on its second axis. Integers are interpreted as
             positional columns, while strings can reference DataFrame columns
@@ -1028,14 +1028,14 @@ def make_column_transformer(*transformers,
     ----------
     *transformers : tuples
         Tuples of the form (transformer, columns) specifying the
-        transformer objects to be applied to subsets of the data.
+        transformer objects to be applied to subsets of the data:
 
-        transformer : {'drop', 'passthrough'} or estimator
+        * transformer : {'drop', 'passthrough'} or estimator
             Estimator must support `fit` and `transform`.
             Special-cased strings 'drop' and 'passthrough' are accepted as
             well, to indicate to drop the columns or to pass them through
             untransformed, respectively.
-        columns : str,  array-like of str, int, array-like of int, slice, \
+        * columns : str,  array-like of str, int, array-like of int, slice, \
                 array-like of bool or callable
             Indexes the data on its second axis. Integers are interpreted as
             positional columns, while strings can reference DataFrame columns
@@ -1097,7 +1097,6 @@ def make_column_transformer(*transformers,
                                      ['numerical_column']),
                                     ('onehotencoder', OneHotEncoder(...),
                                      ['categorical_column'])])
-
     """
     # transformer_weights keyword is not passed through because the user
     # would need to know the automatically generated names of the transformers

python/cuml/benchmark/datagen.py

@@ -352,26 +352,24 @@ def gen_data(
 ):
     """Returns a tuple of data from the specified generator.
 
-    Output
-    -------
-        (train_features, train_labels, test_features, test_labels) tuple
-        containing matrices or dataframes of the requested format.
-        test_features and test_labels may be None if no splitting was done.
-
     Parameters
     ----------
     dataset_name : str
         Dataset to use. Can be a synthetic generator (blobs or regression)
         or a specified dataset (higgs currently, others coming soon)
-
     dataset_format : str
         Type of data to return. (One of cudf, numpy, pandas, gpuarray)
-
     n_samples : int
         Number of samples to include in training set (regardless of test split)
     test_fraction : float
         Fraction of the dataset to partition randomly into the test set.
         If this is 0.0, no test set will be created.
+
+    Returns
+    -------
+        (train_features, train_labels, test_features, test_labels) tuple
+        containing matrices or dataframes of the requested format.
+        test_features and test_labels may be None if no splitting was done.
     """
     data = _data_generators[dataset_name](
         int(n_samples / (1 - test_fraction)),

python/cuml/cluster/dbscan.pyx

@@ -132,7 +132,7 @@ class DBSCAN(Base,
         dtype: int32
 
     Parameters
-    -----------
+    ----------
     eps : float (default = 0.5)
         The maximum distance between 2 points such they reside in the same
         neighborhood.
@@ -187,7 +187,7 @@ class DBSCAN(Base,
         calc_core_sample_indices==True
 
     Notes
-    ------
+    -----
     DBSCAN is very sensitive to the distance metric it is used with, and a
     large assumption is that datapoints need to be concentrated in groups for
     clusters to be constructed.

python/cuml/cluster/kmeans.pyx

@@ -220,7 +220,7 @@ class KMeans(Base,
         Which cluster each datapoint belongs to.
 
     Notes
-    ------
+    -----
     KMeans requires `n_clusters` to be specified. This means one needs to
     approximately guess or know how many clusters a dataset has. If one is not
     sure, one can start with a small number of clusters, and visualize the