Create forked branch-0.20

CHANGELOG.md

@@ -1,3 +1,7 @@
+# cuGraph 0.20.0 (Date TBD)
+
+Please see https://github.com/rapidsai/cugraph/releases/tag/v0.20.0a for the latest changes to this development branch.
+
 # cuGraph 0.19.0 (Date TBD)
 
 Please see https://github.com/rapidsai/cugraph/releases/tag/v0.19.0a for the latest changes to this development branch.

README.md

@@ -82,6 +82,7 @@ As of Release 0.18 - including 0.18 nightly
 |              | Breadth First Search (BFS)             | Multi-GPU    | with cutoff support <br/> [C++ README](cpp/src/traversal/README.md#BFS) |
 |              | Single Source Shortest Path (SSSP)     | Multi-GPU    | [C++ README](cpp/src/traversal/README.md#SSSP) |
 |              | Traveling Salesperson Problem (TSP)    | Single-GPU   |                     |
+| Sampling     | Random Walks (RW)                      | Single-GPU   |                     |
 | Structure    |                                        |              |                     |
 |              | Renumbering                            | Single-GPU   | multiple columns, any data type  |
 |              | Symmetrize                             | Multi-GPU    |                     |

conda/environments/cugraph_dev_cuda10.1.yml

@@ -5,17 +5,17 @@ channels:
 - rapidsai-nightly
 - conda-forge
 dependencies:
-- cudf=0.19.*
-- libcudf=0.19.*
-- rmm=0.19.*
-- cuxfilter=0.19.*
-- librmm=0.19.*
+- cudf=0.20.*
+- libcudf=0.20.*
+- rmm=0.20.*
+- cuxfilter=0.20.*
+- librmm=0.20.*
 - dask>=2.12.0
 - distributed>=2.12.0
-- dask-cuda=0.19*
-- dask-cudf=0.19*
+- dask-cuda=0.20*
+- dask-cudf=0.20*
 - nccl>=2.8.4
-- ucx-py=0.19*
+- ucx-py=0.20*
 - ucx-proc=*=gpu
 - scipy
 - networkx>=2.5.1

conda/environments/cugraph_dev_cuda10.2.yml

@@ -5,17 +5,17 @@ channels:
 - rapidsai-nightly
 - conda-forge
 dependencies:
-- cudf=0.19.*
-- libcudf=0.19.*
-- rmm=0.19.*
-- cuxfilter=0.19.*
-- librmm=0.19.*
+- cudf=0.20.*
+- libcudf=0.20.*
+- rmm=0.20.*
+- cuxfilter=0.20.*
+- librmm=0.20.*
 - dask>=2.12.0
 - distributed>=2.12.0
-- dask-cuda=0.19*
-- dask-cudf=0.19*
+- dask-cuda=0.20*
+- dask-cudf=0.20*
 - nccl>=2.8.4
-- ucx-py=0.19*
+- ucx-py=0.20*
 - ucx-proc=*=gpu
 - scipy
 - networkx>=2.5.1

conda/environments/cugraph_dev_cuda11.0.yml

@@ -5,17 +5,17 @@ channels:
 - rapidsai-nightly
 - conda-forge
 dependencies:
-- cudf=0.19.*
-- libcudf=0.19.*
-- rmm=0.19.*
-- cuxfilter=0.19.*
-- librmm=0.19.*
+- cudf=0.20.*
+- libcudf=0.20.*
+- rmm=0.20.*
+- cuxfilter=0.20.*
+- librmm=0.20.*
 - dask>=2.12.0
 - distributed>=2.12.0
-- dask-cuda=0.19*
-- dask-cudf=0.19*
+- dask-cuda=0.20*
+- dask-cudf=0.20*
 - nccl>=2.8.4
-- ucx-py=0.19*
+- ucx-py=0.20*
 - ucx-proc=*=gpu
 - scipy
 - networkx>=2.5.1

cpp/CMakeLists.txt

@@ -16,7 +16,7 @@
 
 cmake_minimum_required(VERSION 3.18...3.18 FATAL_ERROR)
 
-project(CUGRAPH VERSION 0.19.0 LANGUAGES C CXX CUDA)
+project(CUGRAPH VERSION 0.20.0 LANGUAGES C CXX CUDA)
 
 # Write the version header
 include(cmake/Modules/Version.cmake)

docs/source/api.rst

@@ -192,7 +192,7 @@ Pagerank
     :undoc-members:
 
 Pagerank (MG)
----------
+-------------
 
 .. automodule:: cugraph.dask.link_analysis.pagerank
     :members: pagerank
@@ -225,6 +225,17 @@ Overlap Coefficient
     :undoc-members:
 
 
+Sampling
+========
+
+Random Walks
+------------
+
+.. automodule:: cugraph.sampling.random_walks
+    :members:
+    :undoc-members:
+
+
 Traversal
 =========
 
@@ -236,7 +247,7 @@ Breadth-first-search
     :undoc-members:
 
 Breadth-first-search (MG)
---------------------
+-------------------------
 
 .. automodule:: cugraph.dask.traversal.bfs
     :members:
@@ -250,12 +261,19 @@ Single-source-shortest-path
     :undoc-members:
 
 Single-source-shortest-path (MG)
----------------------------
+--------------------------------
 
 .. automodule:: cugraph.dask.traversal.sssp
     :members:
     :undoc-members:
 
+Traveling-salesperson-problem
+-----------------------------
+
+.. automodule:: cugraph.traversal.traveling_salesperson
+    :members:
+    :undoc-members:
+
 
 Tree
 =========
@@ -264,27 +282,25 @@ Minimum Spanning Tree
 ---------------------
 
 .. automodule:: cugraph.tree.minimum_spanning_tree
-    :members:
+    :members: minimum_spanning_tree
     :undoc-members:
 
 Maximum Spanning Tree
 ---------------------
 
-.. automodule:: cugraph.tree.maximum_spanning_tree
-    :members:
+.. automodule:: cugraph.tree.minimum_spanning_tree
+    :members: maximum_spanning_tree
     :undoc-members:
+    :noindex:
 
 
-DASK MG Helper functions 
+DASK MG Helper functions
 ===========================
 
 .. automodule:: cugraph.comms.comms
-    :members: initialize
-    :undoc-members:
-
-.. automodule:: cugraph.comms.comms
-    :members: destroy
+    :members: initialize, destroy
     :undoc-members:
+    :member-order: bysource
 
 .. automodule:: cugraph.dask.common.read_utils
     :members: get_chunksize

docs/source/conf.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 #
-# Copyright (c) 2018-2020 NVIDIA CORPORATION.
+# Copyright (c) 2018-2021, NVIDIA CORPORATION.
 #
 # pygdf documentation build configuration file, created by
 # sphinx-quickstart on Wed May  3 10:59:22 2017.
@@ -80,9 +80,9 @@
 # built documents.
 #
 # The short X.Y version.
-version = '0.19'
+version = '0.20'
 # The full version, including alpha/beta/rc tags.
-release = '0.19.0'
+release = '0.20.0'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

python/cugraph/__init__.py

@@ -101,6 +101,8 @@
 from cugraph.raft import raft_include_test
 from cugraph.comms import comms
 
+from cugraph.sampling import random_walks
+
 # Versioneer
 from ._version import get_versions
 

python/cugraph/centrality/katz_centrality.py

@@ -39,14 +39,16 @@ def katz_centrality(
         Attenuation factor defaulted to None. If alpha is not specified then
         it is internally calculated as 1/(degree_max) where degree_max is the
         maximum out degree.
-        NOTE : The maximum acceptable value of alpha for convergence
-        alpha_max = 1/(lambda_max) where lambda_max is the largest eigenvalue
-        of the graph.
-        Since lambda_max is always lesser than or equal to degree_max for a
-        graph, alpha_max will always be greater than or equal to
-        (1/degree_max). Therefore, setting alpha to (1/degree_max) will
-        guarantee that it will never exceed alpha_max thus in turn fulfilling
-        the requirement for convergence.
+
+        NOTE
+            The maximum acceptable value of alpha for convergence
+            alpha_max = 1/(lambda_max) where lambda_max is the largest eigenvalue
+            of the graph.
+            Since lambda_max is always lesser than or equal to degree_max for a
+            graph, alpha_max will always be greater than or equal to
+            (1/degree_max). Therefore, setting alpha to (1/degree_max) will
+            guarantee that it will never exceed alpha_max thus in turn fulfilling
+            the requirement for convergence.
     beta : None
         A weight scalar - currently Not Supported
     max_iter : int

python/cugraph/components/connectivity.py

@@ -138,8 +138,10 @@ def weakly_connected_components(G,
 
     directed : bool, optional
 
-        NOTE: For non-Graph-type (eg. sparse matrix) values of G only. Raises
-              TypeError if used with a Graph object.
+        NOTE
+            For non-Graph-type (eg. sparse matrix) values of G only. 
+            Raises TypeError if used with a Graph object.
+
         If True (default), then convert the input matrix to a cugraph.DiGraph
         and only move from point i to point j along paths csgraph[i, j]. If
         False, then find the shortest path on an undirected graph: the
@@ -154,8 +156,10 @@ def weakly_connected_components(G,
 
     return_labels : bool, optional
 
-        NOTE: For non-Graph-type (eg. sparse matrix) values of G only. Raises
-              TypeError if used with a Graph object.
+        NOTE
+            For non-Graph-type (eg. sparse matrix) values of G only. Raises
+            TypeError if used with a Graph object.
+
         If True (default), then return the labels for each of the connected
         components.
 
@@ -231,8 +235,10 @@ def strongly_connected_components(G,
 
     directed : bool, optional
 
-        NOTE: For non-Graph-type (eg. sparse matrix) values of G only. Raises
-              TypeError if used with a Graph object.
+        NOTE
+            For non-Graph-type (eg. sparse matrix) values of G only.
+            Raises TypeError if used with a Graph object.
+
         If True (default), then convert the input matrix to a cugraph.DiGraph
         and only move from point i to point j along paths csgraph[i, j]. If
         False, then find the shortest path on an undirected graph: the
@@ -247,8 +253,10 @@ def strongly_connected_components(G,
 
     return_labels : bool, optional
 
-        NOTE: For non-Graph-type (eg. sparse matrix) values of G only. Raises
-              TypeError if used with a Graph object.
+        NOTE
+            For non-Graph-type (eg. sparse matrix) values of G only. Raises
+            TypeError if used with a Graph object.
+
         If True (default), then return the labels for each of the connected
         components.
 
@@ -325,8 +333,10 @@ def connected_components(G,
 
     directed : bool, optional
 
-        NOTE: For non-Graph-type (eg. sparse matrix) values of G only. Raises
-              TypeError if used with a Graph object.
+        NOTE
+            For non-Graph-type (eg. sparse matrix) values of G only. Raises
+            TypeError if used with a Graph object.
+
         If True (default), then convert the input matrix to a cugraph.DiGraph
         and only move from point i to point j along paths csgraph[i, j]. If
         False, then find the shortest path on an undirected graph: the
@@ -340,8 +350,10 @@ def connected_components(G,
 
     return_labels : bool, optional
 
-        NOTE: For non-Graph-type (eg. sparse matrix) values of G only. Raises
-              TypeError if used with a Graph object.
+        NOTE
+            For non-Graph-type (eg. sparse matrix) values of G only. Raises
+            TypeError if used with a Graph object.
+
         If True (default), then return the labels for each of the connected
         components.
 

python/cugraph/dask/centrality/katz_centrality.py

@@ -68,14 +68,16 @@ def katz_centrality(input_graph,
         Attenuation factor defaulted to None. If alpha is not specified then
         it is internally calculated as 1/(degree_max) where degree_max is the
         maximum out degree.
-        NOTE : The maximum acceptable value of alpha for convergence
-        alpha_max = 1/(lambda_max) where lambda_max is the largest eigenvalue
-        of the graph.
-        Since lambda_max is always lesser than or equal to degree_max for a
-        graph, alpha_max will always be greater than or equal to
-        (1/degree_max). Therefore, setting alpha to (1/degree_max) will
-        guarantee that it will never exceed alpha_max thus in turn fulfilling
-        the requirement for convergence.
+
+        NOTE
+            The maximum acceptable value of alpha for convergence
+            alpha_max = 1/(lambda_max) where lambda_max is the largest eigenvalue
+            of the graph.
+            Since lambda_max is always lesser than or equal to degree_max for a
+            graph, alpha_max will always be greater than or equal to
+            (1/degree_max). Therefore, setting alpha to (1/degree_max) will
+            guarantee that it will never exceed alpha_max thus in turn fulfilling
+            the requirement for convergence.
     beta : None
         A weight scalar - currently Not Supported
     max_iter : int
@@ -94,6 +96,7 @@ def katz_centrality(input_graph,
         acceptable.
     nstart : dask_cudf.Dataframe
         GPU Dataframe containing the initial guess for katz centrality
+
         nstart['vertex'] : dask_cudf.Series
             Contains the vertex identifiers
         nstart['values'] : dask_cudf.Series

python/cugraph/dask/link_analysis/pagerank.py

@@ -73,6 +73,7 @@ def pagerank(input_graph,
     personalization : cudf.Dataframe
         GPU Dataframe containing the personalization information.
         Currently not supported.
+
         personalization['vertex'] : cudf.Series
             Subset of vertices of graph for personalization
         personalization['values'] : cudf.Series
@@ -91,6 +92,7 @@ def pagerank(input_graph,
         acceptable.
     nstart : not supported
         initial guess for pagerank
+
     Returns
     -------
     PageRank : dask_cudf.DataFrame

python/cugraph/link_analysis/pagerank.py

@@ -46,7 +46,6 @@ def pagerank(
             Subset of vertices of graph for personalization
         personalization['values'] : cudf.Series
             Personalization values for vertices
-
     max_iter : int
         The maximum number of iterations before an answer is returned. This can
         be used to limit the execution time and do an early exit before the

python/cugraph/sampling/__init__.py

@@ -0,0 +1,14 @@
+# Copyright (c) 2021, NVIDIA CORPORATION.
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from cugraph.sampling.random_walks import random_walks