History of aminer_cross_domain
The changes to the source code of this entry in the repository, newest first, each with the differences it made to the entry's files. They are also listed on GitLab.
[entries] Add the date when each entry was added, and remove icon_hash beff7c9
The dates are those of the commits that first added the entries' files (2020-08-11 for the entries of the initial commit); renamed entries keep the date of their first name. Changed: none
diff --git a/entries/aminer_cross_domain/__init__.py b/entries/aminer_cross_domain/__init__.py
index d4f65e8..a9444f6 100644
--- a/entries/aminer_cross_domain/__init__.py
+++ b/entries/aminer_cross_domain/__init__.py
@@ -42,7 +42,7 @@ tags = ['Social', 'Collaboration', 'Affiliation', 'Unweighted', 'Metadata']
url = ['https://web.archive.org/web/20141102002646/http://arnetminer.org/collaboration',
'https://lfs.aminer.cn/lab-datasets/crossdomain/']
citation = [('J. Tang, S. Wu, J. Sun, H. Su, "Cross-domain collaboration recommendation." Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1285-1293 (2012)', 'https://doi.org/10.1145/2339530.2339730')]
-icon_hash = '595b1f44549f067e0263b53b'
+date_added = '2026-10-25'
upstream_license = None
upstream_prefix = 'https://lfs.aminer.cn/lab-datasets/crossdomain'
domains = {'data_mining': 'Data Mining', 'medical_informatics': 'Medical Informatics',
[entries] Prefix the properties in the descriptions with (Node), (Edge) or (Graph) bc3dbbd
The lists of properties at the end of the descriptions marked edge properties with "Edge" but left node properties unmarked, or grouped them in "Nodes: `a`, ...; `b`, ..." items, so the kind of a property was often unclear. Every item now starts with (Node), (Edge) or (Graph), followed by the property names, a colon and the explanation, one item per property or group of properties; qualifications (kinds of nodes, networks) follow the names in parentheses. Properties that were only named got a short explanation, and a few items that named the wrong kind of property were corrected.
diff --git a/entries/aminer_cross_domain/__init__.py b/entries/aminer_cross_domain/__init__.py
index 72ebe41..d4f65e8 100644
--- a/entries/aminer_cross_domain/__init__.py
+++ b/entries/aminer_cross_domain/__init__.py
@@ -32,10 +32,10 @@ Nodes are papers and authors (identified by their names), and an undirected edge
The networks have the following properties:
-- `is_paper`: whether the node is a paper (otherwise it is an author).
-- `name`: the title of the paper or the name of the author.
-- `venue` (papers): the publication venue (empty for authors).
-- `year` (papers): the year of publication (-1 for authors).
+- (Node) `is_paper`: whether the node is a paper (otherwise it is an author).
+- (Node) `name`: the title of the paper or the name of the author.
+- (Node) `venue` (papers): the publication venue (empty for authors).
+- (Node) `year` (papers): the year of publication (-1 for authors).
The abstracts of the papers (replaced by the titles when missing) are not included."""
tags = ['Social', 'Collaboration', 'Affiliation', 'Unweighted', 'Metadata']
[entries] Remove unneeded code from the entries 2c69f19
Unneeded "global files" statements, unused imports and variables, f-strings without placeholders, duplicate keys in foodweb_little_rock (keeping the order and the values used), and the second definition of get_lines() in twitter_higgs. Nothing changes in the networks or descriptions. Changed: none
diff --git a/entries/aminer_cross_domain/__init__.py b/entries/aminer_cross_domain/__init__.py
index 5964dfa..72ebe41 100644
--- a/entries/aminer_cross_domain/__init__.py
+++ b/entries/aminer_cross_domain/__init__.py
@@ -58,7 +58,6 @@ def fetch_upstream(force=False):
@coerce_props(vforce={'name': 'string'})
@annotate()
def parse(alts=None):
- global files
name = __name__.split(".")[-1]
for fname, alt, fmt in files:
if alts is not None and alt not in alts:
[entries] New entry: aminer_cross_domain ab5b603
diff --git a/entries/aminer_cross_domain/__init__.py b/entries/aminer_cross_domain/__init__.py
new file mode 100644
index 0000000..5964dfa
--- /dev/null
+++ b/entries/aminer_cross_domain/__init__.py
@@ -0,0 +1,89 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2020-2026 Tiago de Paula Peixoto <tiago@skewed.de>
+#
+# This program is free software: you can redistribute it and/or modify it under
+# the terms of the GNU Affero General Public License as published by the Free
+# Software Foundation, either version 3 of the License, or (at your option) any
+# later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more
+# details.
+#
+# You should have received a copy of the GNU Affero General Public License along
+# with this program. If not, see <http://www.gnu.org/licenses/>.
+
+from .. import *
+import io
+
+title = "AMiner computer science subfields, papers and authors (1990-2005)"
+description = """Bipartite networks of papers and their authors in five subfields of computer science, extracted from AMiner (ArnetMiner) by J. Tang, S. Wu, J. Sun and H. Su to study cross-domain collaboration recommendation. The data cover papers published from 1990 to 2005 in the main venues of each subfield:
+
+- `data_mining`: KDD, SDM, ICDM, WSDM and PKDD.
+- `medical_informatics`: Journal of the American Medical Informatics Association, Journal of Biomedical Informatics, Artificial Intelligence in Medicine, IEEE Transactions on Medical Imaging and IEEE Transactions on Information Technology in Biomedicine.
+- `theory`: STOC, FOCS and SODA.
+- `visualization`: CVPR, ICCV, VAST, TVCG, IEEE Visualization and Information Visualization.
+- `database`: SIGMOD, VLDB and ICDE.
+
+Nodes are papers and authors (identified by their names), and an undirected edge connects a paper to each of its authors.
+
+The networks have the following properties:
+
+- `is_paper`: whether the node is a paper (otherwise it is an author).
+- `name`: the title of the paper or the name of the author.
+- `venue` (papers): the publication venue (empty for authors).
+- `year` (papers): the year of publication (-1 for authors).
+
+The abstracts of the papers (replaced by the titles when missing) are not included."""
+tags = ['Social', 'Collaboration', 'Affiliation', 'Unweighted', 'Metadata']
+url = ['https://web.archive.org/web/20141102002646/http://arnetminer.org/collaboration',
+ 'https://lfs.aminer.cn/lab-datasets/crossdomain/']
+citation = [('J. Tang, S. Wu, J. Sun, H. Su, "Cross-domain collaboration recommendation." Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1285-1293 (2012)', 'https://doi.org/10.1145/2339530.2339730')]
+icon_hash = '595b1f44549f067e0263b53b'
+upstream_license = None
+upstream_prefix = 'https://lfs.aminer.cn/lab-datasets/crossdomain'
+domains = {'data_mining': 'Data Mining', 'medical_informatics': 'Medical Informatics',
+ 'theory': 'Theory', 'visualization': 'Visualization', 'database': 'Database'}
+files = [(f'Cross-Domain_data.zip:Cross-Domain_data/{d}.txt', alt, None)
+ for alt, d in domains.items()]
+
+def fetch_upstream(force=False):
+ return fetch_upstream_files(__name__.split(".")[-1], upstream_prefix, files,
+ force)
+
+@cache_network()
+@coerce_props(vforce={'name': 'string'})
+@annotate()
+def parse(alts=None):
+ global files
+ name = __name__.split(".")[-1]
+ for fname, alt, fmt in files:
+ if alts is not None and alt not in alts:
+ continue
+ # Tab-separated: venue, title, authors (separated by commas), year,
+ # abstract
+ with open_upstream_file(name, fname, "rb") as f:
+ text = f.read().decode("utf-8", "replace")
+ rows = [r for r in csv.reader(io.StringIO(text), delimiter="\t")
+ if len(r) >= 4]
+ authors = {}
+ edges = []
+ for i, r in enumerate(rows):
+ for a in r[2].split(","):
+ a = a.strip()
+ if a:
+ edges.append((i, authors.setdefault(a, len(authors))))
+ P = len(rows)
+ g = Graph(directed=False)
+ g.add_vertex(P + len(authors))
+ g.add_edge_list([(i, P + j) for i, j in edges])
+ g.vp.is_paper = g.new_vp("bool")
+ g.vp.is_paper.a[:P] = 1
+ g.vp.name = g.new_vp("string", vals=[r[1].strip() for r in rows] + list(authors))
+ g.vp.venue = g.new_vp("string", vals=[r[0].strip() for r in rows] + [""] * len(authors))
+ g.vp.year = g.new_vp("int", vals=[int(r[3]) if r[3].strip().isdigit() else -1
+ for r in rows] + [-1] * len(authors))
+ yield alt, g