diff --git a/python/cugraph/cugraph/dask/centrality/katz_centrality.py b/python/cugraph/cugraph/dask/centrality/katz_centrality.py index 61c1869f974..6b9fd6492f8 100644 --- a/python/cugraph/cugraph/dask/centrality/katz_centrality.py +++ b/python/cugraph/cugraph/dask/centrality/katz_centrality.py @@ -125,6 +125,7 @@ def katz_centrality(input_graph, >>> import cugraph.dask as dcg >>> ... Init a DASK Cluster >> see https://docs.rapids.ai/api/cugraph/stable/dask-cugraph.html + >> Download dataset from https://github.com/rapidsai/cugraph/datasets/... >>> chunksize = dcg.get_chunksize(input_data_path) >>> ddf = dask_cudf.read_csv(input_data_path, chunksize=chunksize, delimiter=' ', diff --git a/python/cugraph/cugraph/dask/community/louvain.py b/python/cugraph/cugraph/dask/community/louvain.py index c4db00ab27a..a75a44a663f 100644 --- a/python/cugraph/cugraph/dask/community/louvain.py +++ b/python/cugraph/cugraph/dask/community/louvain.py @@ -58,6 +58,7 @@ def louvain(input_graph, max_iter=100, resolution=1.0): >>> import cugraph.dask as dcg >>> ... Init a DASK Cluster >> see https://docs.rapids.ai/api/cugraph/stable/dask-cugraph.html + >> Download dataset from https://github.com/rapidsai/cugraph/datasets/... >>> chunksize = dcg.get_chunksize(input_data_path) >>> ddf = dask_cudf.read_csv('datasets/karate.csv', chunksize=chunksize, delimiter=' ', diff --git a/python/cugraph/cugraph/dask/link_analysis/pagerank.py b/python/cugraph/cugraph/dask/link_analysis/pagerank.py index 85d61233179..68f0ccfe907 100644 --- a/python/cugraph/cugraph/dask/link_analysis/pagerank.py +++ b/python/cugraph/cugraph/dask/link_analysis/pagerank.py @@ -115,6 +115,7 @@ def pagerank(input_graph, >>> import cugraph.dask as dcg >>> ... Init a DASK Cluster >> see https://docs.rapids.ai/api/cugraph/stable/dask-cugraph.html + >> Download dataset from https://github.com/rapidsai/cugraph/datasets/... >>> chunksize = dcg.get_chunksize(input_data_path) >>> ddf = dask_cudf.read_csv(input_data_path, chunksize=chunksize, delimiter=' ', diff --git a/python/cugraph/cugraph/dask/traversal/bfs.py b/python/cugraph/cugraph/dask/traversal/bfs.py index f65ae4bf9a2..7e3ae1b0162 100644 --- a/python/cugraph/cugraph/dask/traversal/bfs.py +++ b/python/cugraph/cugraph/dask/traversal/bfs.py @@ -88,6 +88,7 @@ def bfs(graph, >>> import cugraph.dask as dcg >>> ... Init a DASK Cluster >> see https://docs.rapids.ai/api/cugraph/stable/dask-cugraph.html + >> Download dataset from https://github.com/rapidsai/cugraph/datasets/... >>> chunksize = dcg.get_chunksize(input_data_path) >>> ddf = dask_cudf.read_csv(input_data_path, chunksize=chunksize, delimiter=' ', diff --git a/python/cugraph/cugraph/linear_assignment/lap.py b/python/cugraph/cugraph/linear_assignment/lap.py index ed40e96fb47..a8846e6e177 100644 --- a/python/cugraph/cugraph/linear_assignment/lap.py +++ b/python/cugraph/cugraph/linear_assignment/lap.py @@ -65,6 +65,7 @@ def hungarian(G, workers, epsilon=None): Examples -------- + >> Download dataset from https://github.com/rapidsai/cugraph/datasets/... >>> M = cudf.read_csv('datasets/bipartite.csv', delimiter=' ', >>> dtype=['int32', 'int32', 'float32'], header=None) >>> G = cugraph.Graph() diff --git a/python/cugraph/cugraph/link_prediction/jaccard.py b/python/cugraph/cugraph/link_prediction/jaccard.py index e1e4b9c875e..fafad9b014c 100644 --- a/python/cugraph/cugraph/link_prediction/jaccard.py +++ b/python/cugraph/cugraph/link_prediction/jaccard.py @@ -58,7 +58,7 @@ def jaccard(input_graph, vertex_pair=None): >>> dtype=['int32', 'int32', 'float32'], header=None) >>> G = cugraph.Graph() >>> G.from_cudf_edgelist(gdf, source='0', destination='1') - >>> pairs = cugraph.get_two_hop_neighbors(G) + >>> pairs = G.get_two_hop_neighbors() >>> df = cugraph.jaccard(G, pairs) But please remember that cugraph will fill the dataframe with the entire diff --git a/python/cugraph/cugraph/link_prediction/woverlap.py b/python/cugraph/cugraph/link_prediction/woverlap.py index 41dcd2c504f..40f54f6867c 100644 --- a/python/cugraph/cugraph/link_prediction/woverlap.py +++ b/python/cugraph/cugraph/link_prediction/woverlap.py @@ -35,8 +35,15 @@ def overlap_w(input_graph, weights, vertex_pair=None): as an edge list (edge weights are not used for this algorithm). The adjacency list will be computed if not already present. - weights : cudf.Series + weights : cudf.DataFrame Specifies the weights to be used for each vertex. + Vertex should be represented by multiple columns for multi-column + vertices. + + weights['vertex'] : cudf.Series + Contains the vertex identifiers + weights['weight'] : cudf.Series + Contains the weights of vertices vertex_pair : cudf.DataFrame A GPU dataframe consisting of two columns representing pairs of diff --git a/python/cugraph/cugraph/structure/convert_matrix.py b/python/cugraph/cugraph/structure/convert_matrix.py index 5b3c375ea9d..4b5b7129d52 100644 --- a/python/cugraph/cugraph/structure/convert_matrix.py +++ b/python/cugraph/cugraph/structure/convert_matrix.py @@ -233,11 +233,14 @@ def from_pandas_edgelist(df, Examples -------- + >> Download dataset from + >> https://github.com/rapidsai/cugraph/datasets/... >>> df = pandas.read_csv('datasets/karate.csv', delimiter=' ', - >>> dtype=['int32', 'int32', 'float32'], header=None) + >>> header=None, names=["0", "1", "2"], + >>> dtype={"0": "int32", "1": "int32", "2": "float32"}) >>> G = cugraph.Graph() >>> G.from_pandas_edgelist(df, source='0', destination='1', - edge_attr='2', renumber=False) + edge_attr='2', renumber=False) """ if create_using is Graph: G = Graph() diff --git a/python/cugraph/cugraph/structure/graph_classes.py b/python/cugraph/cugraph/structure/graph_classes.py index 744e19966ab..8be1bc50a62 100644 --- a/python/cugraph/cugraph/structure/graph_classes.py +++ b/python/cugraph/cugraph/structure/graph_classes.py @@ -292,8 +292,11 @@ def from_pandas_edgelist( Examples -------- + >> Download dataset from + >> https://github.com/rapidsai/cugraph/datasets/... >>> df = pandas.read_csv('datasets/karate.csv', delimiter=' ', - >>> dtype=['int32', 'int32', 'float32'], header=None) + >>> header=None, names=["0", "1", "2"], + >>> dtype={"0": "int32", "1": "int32", "2": "float32"}) >>> G = cugraph.Graph() >>> G.from_pandas_edgelist(df, source='0', destination='1', edge_attr='2', renumber=False) diff --git a/python/cugraph/cugraph/structure/symmetrize.py b/python/cugraph/cugraph/structure/symmetrize.py index 13116eabb07..d98c6d57c9b 100644 --- a/python/cugraph/cugraph/structure/symmetrize.py +++ b/python/cugraph/cugraph/structure/symmetrize.py @@ -53,15 +53,11 @@ def symmetrize_df(df, src_name, dst_name, multi=False, symmetrize=True): Examples -------- - >>> import cugraph.dask as dcg - >>> Comms.initialize() - >>> chunksize = dcg.get_chunksize(input_data_path) - >>> ddf = dask_cudf.read_csv(input_data_path, chunksize=chunksize, - delimiter=' ', - names=['src', 'dst', 'weight'], - dtype=['int32', 'int32', 'float32']) - >>> sym_ddf = cugraph.symmetrize_ddf(ddf, "src", "dst", "weight") - >>> Comms.destroy() + >>> from cugraph.structure.symmetrize import symmetrize_df + >> Download dataset from https://github.com/rapidsai/cugraph/datasets/... + >>> M = cudf.read_csv('datasets/karate.csv', delimiter=' ', + >>> dtype=['int32', 'int32', 'float32'], header=None) + >>> sym_df = symmetrize(M, '0', '1') """ # # Now append the columns. We add sources to the end of destinations, @@ -127,9 +123,17 @@ def symmetrize_ddf(df, src_name, dst_name, weight_name=None): Examples -------- - >>> M = cudf.read_csv('datasets/karate.csv', delimiter=' ', - >>> dtype=['int32', 'int32', 'float32'], header=None) - >>> sym_df = cugraph.symmetrize(M, '0', '1') + >>> import cugraph.dask as dcg + >>> from cugraph.structure.symmetrize import symmetrize_ddf + >>> ... Init a DASK Cluster + >> Download dataset from https://github.com/rapidsai/cugraph/datasets/... + >>> chunksize = dcg.get_chunksize(input_data_path) + >>> ddf = dask_cudf.read_csv(input_data_path, chunksize=chunksize, + delimiter=' ', + names=['src', 'dst', 'weight'], + dtype=['int32', 'int32', 'float32']) + >>> sym_ddf = symmetrize_ddf(ddf, "src", "dst", "weight") + >>> Comms.destroy() """ if weight_name: ddf2 = df[[dst_name, src_name, weight_name]] @@ -180,12 +184,14 @@ def symmetrize(source_col, dest_col, value_col=None, multi=False, Examples -------- + >>> from cugraph.structure.symmetrize import symmetrize + >> Download dataset from https://github.com/rapidsai/cugraph/datasets/... >>> M = cudf.read_csv('datasets/karate.csv', delimiter=' ', >>> dtype=['int32', 'int32', 'float32'], header=None) >>> sources = cudf.Series(M['0']) >>> destinations = cudf.Series(M['1']) >>> values = cudf.Series(M['2']) - >>> src, dst, val = cugraph.symmetrize(sources, destinations, values) + >>> src, dst, val = symmetrize(sources, destinations, values) """ input_df = None