History of email_eu_core
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/email_eu_core/__init__.py b/entries/email_eu_core/__init__.py
index 3b40d45..dabf2f4 100644
--- a/entries/email_eu_core/__init__.py
+++ b/entries/email_eu_core/__init__.py
@@ -33,7 +33,7 @@ url = ['https://www.cs.cornell.edu/~arb/data/email-Eu/',
citation = [('A. R. Benson, R. Abebe, M. T. Schaub, A. Jadbabaie, J. Kleinberg, "Simplicial closure and higher-order link prediction." Proceedings of the National Academy of Sciences 115(48), E11221-E11230 (2018)', 'https://doi.org/10.1073/pnas.1800683115'),
('H. Yin, A. R. Benson, J. Leskovec, D. F. Gleich, "Local Higher-Order Graph Clustering." Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 555-564 (2017)', 'https://doi.org/10.1145/3097983.3098069'),
('J. Leskovec, J. Kleinberg, C. Faloutsos, "Graph evolution: Densification and shrinking diameters." ACM Transactions on Knowledge Discovery from Data 1(1), 2 (2007)', 'https://doi.org/10.1145/1217299.1217301')]
-icon_hash = None
+date_added = '2026-10-25'
upstream_license = None
upstream_prefix = 'gdrive://'
files = [(('1oFnrRaLPlYCNgABInjjW8fUgui49eOZN:tar.gz:email-Eu-full/email-Eu-full-nverts.txt',
[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/email_eu_core/__init__.py b/entries/email_eu_core/__init__.py
index 34c7837..3b40d45 100644
--- a/entries/email_eu_core/__init__.py
+++ b/entries/email_eu_core/__init__.py
@@ -23,9 +23,10 @@ description = """A bipartite network of the members of a large European research
The network has the following properties:
-- `is_email`, whether the node is an email (otherwise a member of the institution).
-- Member nodes: `department`, the department of the member (anonymized index, from 0 to 41); `snap_id`, the node identifier in the SNAP `email-Eu-core` network (0-based; equal to the source's 1-based identifier minus one).
-- Email nodes: `time`, the time the email was sent, in Unix time (seconds since 1970-01-01 UTC)."""
+- (Node) `is_email`: whether the node is an email (otherwise a member of the institution).
+- (Node) `department` (members): the department of the member (anonymized index, from 0 to 41).
+- (Node) `snap_id` (members): the node identifier in the SNAP `email-Eu-core` network (0-based; equal to the source's 1-based identifier minus one).
+- (Node) `time` (emails): the time the email was sent, in Unix time (seconds since 1970-01-01 UTC)."""
tags = ['Social', 'Communication', 'Unweighted', 'Timestamps', 'Metadata']
url = ['https://www.cs.cornell.edu/~arb/data/email-Eu/',
'https://snap.stanford.edu/data/email-Eu-core.html']
[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/email_eu_core/__init__.py b/entries/email_eu_core/__init__.py
index 0424b7d..34c7837 100644
--- a/entries/email_eu_core/__init__.py
+++ b/entries/email_eu_core/__init__.py
@@ -54,7 +54,6 @@ def fetch_upstream(force=False):
@coerce_props()
@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: email_eu_core 165bc45
diff --git a/entries/email_eu_core/__init__.py b/entries/email_eu_core/__init__.py
new file mode 100644
index 0000000..0424b7d
--- /dev/null
+++ b/entries/email_eu_core/__init__.py
@@ -0,0 +1,76 @@
+#! /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 *
+
+title = "Email recipients at a European research institution (2003-2005)"
+description = """A bipartite network of the members of a large European research institution and the emails they exchanged, constructed by Benson et al. from the timestamped email records underlying the SNAP `email-Eu-core` network (Leskovec, Kleinberg and Faloutsos; Yin et al.). The records are anonymized (sender, recipient, time) entries, at 1-second resolution, of the emails sent between members of the institution from September 2003 to December 2005 (803 days); messages to or from people outside the institution are not included. Benson et al. reconstructed each email as a group made of a sender and all the recipients that the sender emailed at exactly the same time. In this network each email is a node connected to its sender and recipients (the source data do not distinguish the sender from the recipients). This is the version of the data without restriction on the number of participants (at most 40 per email). 25,755 emails have a single participant, i.e. a member who emailed themselves. Each member belongs to one of 42 departments of the institution, as given by the SNAP department labels.
+
+The network has the following properties:
+
+- `is_email`, whether the node is an email (otherwise a member of the institution).
+- Member nodes: `department`, the department of the member (anonymized index, from 0 to 41); `snap_id`, the node identifier in the SNAP `email-Eu-core` network (0-based; equal to the source's 1-based identifier minus one).
+- Email nodes: `time`, the time the email was sent, in Unix time (seconds since 1970-01-01 UTC)."""
+tags = ['Social', 'Communication', 'Unweighted', 'Timestamps', 'Metadata']
+url = ['https://www.cs.cornell.edu/~arb/data/email-Eu/',
+ 'https://snap.stanford.edu/data/email-Eu-core.html']
+citation = [('A. R. Benson, R. Abebe, M. T. Schaub, A. Jadbabaie, J. Kleinberg, "Simplicial closure and higher-order link prediction." Proceedings of the National Academy of Sciences 115(48), E11221-E11230 (2018)', 'https://doi.org/10.1073/pnas.1800683115'),
+ ('H. Yin, A. R. Benson, J. Leskovec, D. F. Gleich, "Local Higher-Order Graph Clustering." Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 555-564 (2017)', 'https://doi.org/10.1145/3097983.3098069'),
+ ('J. Leskovec, J. Kleinberg, C. Faloutsos, "Graph evolution: Densification and shrinking diameters." ACM Transactions on Knowledge Discovery from Data 1(1), 2 (2007)', 'https://doi.org/10.1145/1217299.1217301')]
+icon_hash = None
+upstream_license = None
+upstream_prefix = 'gdrive://'
+files = [(('1oFnrRaLPlYCNgABInjjW8fUgui49eOZN:tar.gz:email-Eu-full/email-Eu-full-nverts.txt',
+ '1oFnrRaLPlYCNgABInjjW8fUgui49eOZN:tar.gz:email-Eu-full/email-Eu-full-simplices.txt',
+ '1oFnrRaLPlYCNgABInjjW8fUgui49eOZN:tar.gz:email-Eu-full/email-Eu-full-times.txt'),
+ None, None)]
+
+# Department labels, from SNAP (the node ids are the same as Benson's, minus
+# one)
+labels_prefix = 'https://snap.stanford.edu/data'
+labels_files = [('email-Eu-core-department-labels.txt.gz', None, None)]
+
+def fetch_upstream(force=False):
+ name = __name__.split(".")[-1]
+ fetch_upstream_files(name, upstream_prefix, files, force)
+ return fetch_upstream_files(name, labels_prefix, labels_files, force)
+
+@cache_network()
+@coerce_props()
+@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 ExitStack() as stack:
+ fs = [stack.enter_context(open_upstream_file(name, fn, "r")) for fn in fnames]
+ groups, members = read_simplices(fs[0], fs[1])
+ times = read_ints(fs[2])
+ with open_upstream_file(name, labels_files[0][0], "r") as f:
+ labels = read_ints(f).reshape(-1, 2)
+ N = max(members.max() + 1, labels[:, 0].max() + 1)
+ g = bipartite_graph(groups, members, len(times), N, "is_email")
+ g.vp.department = g.new_vp("int", val=-1)
+ g.vp.department.a[labels[:, 0]] = labels[:, 1]
+ g.vp.snap_id = g.new_vp("int", val=-1)
+ g.vp.snap_id.a[:N] = numpy.arange(N)
+ g.vp.time = g.new_vp("int64_t")
+ g.vp.time.a[N:] = times
+ yield alt, g