logo Netzschleuder network catalog, repository, and centrifuge

History of tkgl_icews

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 by Tiago de Paula Peixoto 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/tkgl_icews/__init__.py b/entries/tkgl_icews/__init__.py
index 75dee62..1f21136 100644
--- a/entries/tkgl_icews/__init__.py
+++ b/entries/tkgl_icews/__init__.py
@@ -36,7 +36,7 @@ url = ['https://tgb.complexdatalab.com/docs/tkg/',
        'https://dataverse.harvard.edu/dataverse/icews']
 citation = [('J. Gastinger, S. Huang, M. Galkin, E. Loghmani, A. Parviz, F. Poursafaei, J. Danovitch, E. Rossi, I. Koutis, H. Stuckenschmidt, R. Rabbany, G. Rabusseau, "TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs." Advances in Neural Information Processing Systems 37 (Datasets and Benchmarks Track) (2024)', 'https://doi.org/10.48550/arXiv.2406.09639'),
             ('E. Boschee, J. Lautenschlager, S. O\'Brien, S. Shellman, J. Starz, M. Ward, "ICEWS Coded Event Data." Harvard Dataverse (2015)', 'https://doi.org/10.7910/DVN/28075')]
-icon_hash = None
+date_added = '2026-10-27'
 upstream_license = ('ICEWS custom license: research and educational use only, no commercial use', 'https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/28075')
 upstream_prefix = 'https://object-arbutus.alliancecan.ca/swift/v1/14c95234f6cd4a21a47deafe20cce2a7/tgb'
 files = [(('tkgl-icews.zip:tkgl-icews_edgelist.csv',
[entries] Prefix the properties in the descriptions with (Node), (Edge) or (Graph) by Tiago de Paula Peixoto 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/tkgl_icews/__init__.py b/entries/tkgl_icews/__init__.py
index 0cf9628..75dee62 100644
--- a/entries/tkgl_icews/__init__.py
+++ b/entries/tkgl_icews/__init__.py
@@ -28,8 +28,8 @@ description = """A temporal network of political events between socio-political
 
 The network has the following properties:
 
-- Edge `relation`: the CAMEO code of the type of the event (e.g. `051`, "praise or endorse", or `173`, "arrest, detain, or charge with legal action"), see the CAMEO codebook.
-- Edge `time`: the date of the event, in Unix time (of midnight in the US Eastern time zone, as given)."""
+- (Edge) `relation`: the CAMEO code of the type of the event (e.g. `051`, "praise or endorse", or `173`, "arrest, detain, or charge with legal action"), see the CAMEO codebook.
+- (Edge) `time`: the date of the event, in Unix time (of midnight in the US Eastern time zone, as given)."""
 tags = ['Social', 'Political', 'Conflict', 'Unweighted', 'Multigraph', 'Timestamps', 'Metadata']
 url = ['https://tgb.complexdatalab.com/docs/tkg/',
        'https://github.com/shenyangHuang/TGB',
[entries] Remove unneeded code from the entries by Tiago de Paula Peixoto 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/tkgl_icews/__init__.py b/entries/tkgl_icews/__init__.py
index c7f6003..0cf9628 100644
--- a/entries/tkgl_icews/__init__.py
+++ b/entries/tkgl_icews/__init__.py
@@ -50,7 +50,6 @@ def fetch_upstream(force=False):
 @coerce_props(eforce={"relation": "string"})
 @annotate()
 def parse(alts=None):
-    global files
     name = __name__.split(".")[-1]
     for fnames, alt, fmt in files:
         if alts is not None and alt not in alts:
[entries] New entry: tkgl_icews by Tiago de Paula Peixoto f880c18
diff --git a/entries/tkgl_icews/__init__.py b/entries/tkgl_icews/__init__.py
new file mode 100644
index 0000000..c7f6003
--- /dev/null
+++ b/entries/tkgl_icews/__init__.py
@@ -0,0 +1,70 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 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/>.
+
+
+
+import pandas
+
+from .. import *
+
+
+title = "Political events between actors (ICEWS, tkgl-icews, TGB 2.0, 1995-2022)"
+description = """A temporal network of political events between socio-political actors (e.g. governments, politicians, organizations, or citizens of a country) worldwide, from January 1995 to December 2022, from the `tkgl-icews` dataset of the Temporal Graph Benchmark (TGB 2.0), based on the Integrated Crisis Early Warning System (ICEWS) coded event data. ICEWS codes events automatically from news stories with the CAMEO taxonomy of event types. Each node is an actor, and each directed edge from actor A to actor B is an event of one of the CAMEO types (e.g. A makes a statement to, consults, accuses, or attacks B), with its date. The events whose source or target is missing were removed by TGB. The actors are anonymized in the data (they are identified only by indices).
+
+The network has the following properties:
+
+- Edge `relation`: the CAMEO code of the type of the event (e.g. `051`, "praise or endorse", or `173`, "arrest, detain, or charge with legal action"), see the CAMEO codebook.
+- Edge `time`: the date of the event, in Unix time (of midnight in the US Eastern time zone, as given)."""
+tags = ['Social', 'Political', 'Conflict', 'Unweighted', 'Multigraph', 'Timestamps', 'Metadata']
+url = ['https://tgb.complexdatalab.com/docs/tkg/',
+       'https://github.com/shenyangHuang/TGB',
+       'https://dataverse.harvard.edu/dataverse/icews']
+citation = [('J. Gastinger, S. Huang, M. Galkin, E. Loghmani, A. Parviz, F. Poursafaei, J. Danovitch, E. Rossi, I. Koutis, H. Stuckenschmidt, R. Rabbany, G. Rabusseau, "TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs." Advances in Neural Information Processing Systems 37 (Datasets and Benchmarks Track) (2024)', 'https://doi.org/10.48550/arXiv.2406.09639'),
+            ('E. Boschee, J. Lautenschlager, S. O\'Brien, S. Shellman, J. Starz, M. Ward, "ICEWS Coded Event Data." Harvard Dataverse (2015)', 'https://doi.org/10.7910/DVN/28075')]
+icon_hash = None
+upstream_license = ('ICEWS custom license: research and educational use only, no commercial use', 'https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/28075')
+upstream_prefix = 'https://object-arbutus.alliancecan.ca/swift/v1/14c95234f6cd4a21a47deafe20cce2a7/tgb'
+files = [(('tkgl-icews.zip:tkgl-icews_edgelist.csv',
+           'tkgl-icews.zip:tkgl-icews_edgemapping.csv'), None, None)]
+
+def fetch_upstream(force=False):
+    return fetch_upstream_files(__name__.split(".")[-1], upstream_prefix, files,
+                                force)
+
+@cache_network()
+@coerce_props(eforce={"relation": "string"})
+@annotate()
+def parse(alts=None):
+    global files
+    name = __name__.split(".")[-1]
+    for fnames, alt, fmt in files:
+        if alts is not None and alt not in alts:
+            continue
+        with open_upstream_file(name, fnames[1], "r") as f:
+            # "edge_id,type": the relation and its index
+            rels = {int(r["type"]): r["edge_id"] for r in csv.DictReader(f)}
+        with open_upstream_file(name, fnames[0], "rb") as f:
+            # "date,head,tail,relation_type"
+            edges = pandas.read_csv(f, dtype="int64").values
+        g = Graph(directed=True)
+        g.add_vertex(max(edges[:, 1].max(), edges[:, 2].max()) + 1)
+        g.add_edge_list(edges[:, [1, 2]])
+        g.ep.relation = g.new_ep("string", vals=[rels[r] for r in edges[:, 3]])
+        g.ep.time = g.new_ep("int64_t", vals=edges[:, 0])
+        yield alt, g
+