-
Notifications
You must be signed in to change notification settings - Fork 299
/
pagerank.py
184 lines (166 loc) · 7.25 KB
/
pagerank.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
# Copyright (c) 2019-2021, 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 dask.distributed import wait, default_client
from cugraph.dask.common.input_utils import (get_distributed_data,
get_vertex_partition_offsets)
from cugraph.dask.link_analysis import mg_pagerank_wrapper as mg_pagerank
import cugraph.comms.comms as Comms
import dask_cudf
def call_pagerank(sID,
data,
num_verts,
num_edges,
vertex_partition_offsets,
aggregate_segment_offsets,
alpha,
max_iter,
tol,
personalization,
nstart):
wid = Comms.get_worker_id(sID)
handle = Comms.get_handle(sID)
local_size = len(aggregate_segment_offsets) // Comms.get_n_workers(sID)
segment_offsets = \
aggregate_segment_offsets[local_size * wid: local_size * (wid + 1)]
return mg_pagerank.mg_pagerank(data[0],
num_verts,
num_edges,
vertex_partition_offsets,
wid,
handle,
segment_offsets,
alpha,
max_iter,
tol,
personalization,
nstart)
def pagerank(input_graph,
alpha=0.85,
personalization=None,
max_iter=100,
tol=1.0e-5,
nstart=None):
"""
Find the PageRank values for each vertex in a graph using multiple GPUs.
cuGraph computes an approximation of the Pagerank using the power method.
The input graph must contain edge list as dask-cudf dataframe with
one partition per GPU.
Parameters
----------
graph : cugraph.DiGraph
cuGraph graph descriptor, should contain the connectivity information
as dask cudf edge list dataframe(edge weights are not used for this
algorithm). Undirected Graph not currently supported.
alpha : float
The damping factor alpha represents the probability to follow an
outgoing edge, standard value is 0.85.
Thus, 1.0-alpha is the probability to “teleport” to a random vertex.
Alpha should be greater than 0.0 and strictly lower than 1.0.
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
Personalization values for vertices
max_iter : int
The maximum number of iterations before an answer is returned.
If this value is lower or equal to 0 cuGraph will use the default
value, which is 30.
tolerance : float
Set the tolerance the approximation, this parameter should be a small
magnitude value.
The lower the tolerance the better the approximation. If this value is
0.0f, cuGraph will use the default value which is 1.0E-5.
Setting too small a tolerance can lead to non-convergence due to
numerical roundoff. Usually values between 0.01 and 0.00001 are
acceptable.
nstart : not supported
initial guess for pagerank
Returns
-------
PageRank : dask_cudf.DataFrame
GPU data frame containing two dask_cudf.Series of size V: the
vertex identifiers and the corresponding PageRank values.
ddf['vertex'] : dask_cudf.Series
Contains the vertex identifiers
ddf['pagerank'] : dask_cudf.Series
Contains the PageRank score
Examples
--------
>>> import cugraph.dask as dcg
>>> ... Init a DASK Cluster
>> see https://docs.rapids.ai/api/cugraph/stable/dask-cugraph.html
>>> chunksize = dcg.get_chunksize(input_data_path)
>>> ddf = dask_cudf.read_csv(input_data_path, chunksize=chunksize,
delimiter=' ',
names=['src', 'dst', 'value'],
dtype=['int32', 'int32', 'float32'])
>>> dg = cugraph.DiGraph()
>>> dg.from_dask_cudf_edgelist(ddf, source='src', destination='dst',
edge_attr='value')
>>> pr = dcg.pagerank(dg)
"""
from cugraph.structure.graph_classes import null_check
nstart = None
client = default_client()
input_graph.compute_renumber_edge_list(transposed=True)
ddf = input_graph.edgelist.edgelist_df
vertex_partition_offsets = get_vertex_partition_offsets(input_graph)
num_verts = vertex_partition_offsets.iloc[-1]
num_edges = len(ddf)
data = get_distributed_data(ddf)
if personalization is not None:
null_check(personalization["vertex"])
null_check(personalization["values"])
if input_graph.renumbered is True:
personalization = input_graph.add_internal_vertex_id(
personalization, "vertex", "vertex"
)
p_data = get_distributed_data(personalization)
result = [client.submit(call_pagerank,
Comms.get_session_id(),
wf[1],
num_verts,
num_edges,
vertex_partition_offsets,
input_graph.aggregate_segment_offsets,
alpha,
max_iter,
tol,
p_data.worker_to_parts[wf[0]][0],
nstart,
workers=[wf[0]])
for idx, wf in enumerate(data.worker_to_parts.items())]
else:
result = [client.submit(call_pagerank,
Comms.get_session_id(),
wf[1],
num_verts,
num_edges,
vertex_partition_offsets,
input_graph.aggregate_segment_offsets,
alpha,
max_iter,
tol,
personalization,
nstart,
workers=[wf[0]])
for idx, wf in enumerate(data.worker_to_parts.items())]
wait(result)
ddf = dask_cudf.from_delayed(result)
if input_graph.renumbered:
return input_graph.unrenumber(ddf, 'vertex')
return ddf