logo Netzschleuder network catalog, repository, and centrifuge

History of hollywood_golden_age

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/hollywood_golden_age/__init__.py b/entries/hollywood_golden_age/__init__.py
index 8981fb5..c8a6afc 100644
--- a/entries/hollywood_golden_age/__init__.py
+++ b/entries/hollywood_golden_age/__init__.py
@@ -37,7 +37,7 @@ The networks have the following properties:
 tags = ['Social', 'Collaboration', 'Weighted', 'Projection', 'Timestamps', 'Multigraph']
 url = 'https://aaronclauset.github.io/datacode.htm'
 citation = [('D. Taylor, S. A. Myers, A. Clauset, M. A. Porter, P. J. Mucha, "Eigenvector-based centrality measures for temporal networks." Multiscale Modeling & Simulation 15(1), 537-574 (2017)', 'https://doi.org/10.1137/16M1066142')]
-icon_hash = '56a85c8e26855e083a2f7923'
+date_added = '2026-10-25'
 upstream_license = None
 upstream_prefix = 'https://aaronclauset.github.io/data'
 
[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/hollywood_golden_age/__init__.py b/entries/hollywood_golden_age/__init__.py
index b365c2b..8981fb5 100644
--- a/entries/hollywood_golden_age/__init__.py
+++ b/entries/hollywood_golden_age/__init__.py
@@ -31,8 +31,9 @@ Two versions are provided:
 
 The networks have the following properties:
 
-- Nodes: `name`, the actor name, as in IMDb.
-- Edges: `decade`, the first year of the decade (1909, 1920, ..., 2000); `count`, the number of movies in that decade giving rise to the edge. Pairs of actors can be connected by several edges, one for each decade."""
+- (Node) `name`: the actor name, as in IMDb.
+- (Edge) `decade`: the first year of the decade (1909, 1920, ..., 2000).
+- (Edge) `count`: the number of movies in that decade giving rise to the edge. Pairs of actors can be connected by several edges, one for each decade."""
 tags = ['Social', 'Collaboration', 'Weighted', 'Projection', 'Timestamps', 'Multigraph']
 url = 'https://aaronclauset.github.io/datacode.htm'
 citation = [('D. Taylor, S. A. Myers, A. Clauset, M. A. Porter, P. J. Mucha, "Eigenvector-based centrality measures for temporal networks." Multiscale Modeling & Simulation 15(1), 537-574 (2017)', 'https://doi.org/10.1137/16M1066142')]
[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/hollywood_golden_age/__init__.py b/entries/hollywood_golden_age/__init__.py
index 5981c24..b365c2b 100644
--- a/entries/hollywood_golden_age/__init__.py
+++ b/entries/hollywood_golden_age/__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: hollywood_golden_age by Tiago de Paula Peixoto d174047
diff --git a/entries/hollywood_golden_age/__init__.py b/entries/hollywood_golden_age/__init__.py
new file mode 100644
index 0000000..5981c24
--- /dev/null
+++ b/entries/hollywood_golden_age/__init__.py
@@ -0,0 +1,77 @@
+#! /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 = "Golden Age of Hollywood actor collaborations (1909-2009)"
+description = """Collaborations among 55 actors representative of the Golden Age of Hollywood (1930-1959), compiled by A. Clauset from the full text of the Internet Movie Database (IMDb), downloaded in September 2011. The actors are those listed on the Wikipedia page "Classical Hollywood cinema" at that time (not a scientific selection). Each network is the directed actor-actor projection of the underlying actor-movie network, aggregated over decades from 1909 to 2009.
+
+A directed edge from actor A to actor B exists if both appear in the billing of the same movie, and B has an equal or better (smaller) billing position than A; actors without a listed billing position are assumed to have the lowest rank. If only one of the 55 actors appears in a movie, a self-loop is added if the actor had the first billing position. Archive footage, unconfirmed and suspended entries, TV and video movies, and television series were excluded. Only movies released strictly within each decade are counted (the first period, 1909-1919, is eleven years long).
+
+Two versions are provided:
+
+- `s0`: edges follow the rule above exactly.
+- `s2`: billing positions i and j are considered equal if |i-j| <= 2, as a heuristic to account for the fact that the billing order of women and men was not informative of their status during this period, and that small differences in billing may not be meaningful.
+
+The networks have the following properties:
+
+- Nodes: `name`, the actor name, as in IMDb.
+- Edges: `decade`, the first year of the decade (1909, 1920, ..., 2000); `count`, the number of movies in that decade giving rise to the edge. Pairs of actors can be connected by several edges, one for each decade."""
+tags = ['Social', 'Collaboration', 'Weighted', 'Projection', 'Timestamps', 'Multigraph']
+url = 'https://aaronclauset.github.io/datacode.htm'
+citation = [('D. Taylor, S. A. Myers, A. Clauset, M. A. Porter, P. J. Mucha, "Eigenvector-based centrality measures for temporal networks." Multiscale Modeling & Simulation 15(1), 537-574 (2017)', 'https://doi.org/10.1137/16M1066142')]
+icon_hash = '56a85c8e26855e083a2f7923'
+upstream_license = None
+upstream_prefix = 'https://aaronclauset.github.io/data'
+
+decades = ["1909-1919"] + [f"{y}-{y + 9}" for y in range(1920, 2001, 10)]
+prefix = "GoldenAgeOfHollywood_networkdata.zip:GoldenAgeOfHollywood_networkdata/HollywoodGoldenAge_"
+files = [(tuple([prefix + "names.txt"] +
+                [prefix + f"matrix_{d}_{s}.txt" for d in decades]), s, None)
+         for s in ["s0", "s2"]]
+
+def fetch_upstream(force=False):
+    return fetch_upstream_files(__name__.split(".")[-1], upstream_prefix, 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]
+            names = [line.strip().replace("_", " ") for line in fs[0] if line.strip()]
+            g = Graph(directed=True)
+            g.add_vertex(len(names))
+            g.vp.name = g.new_vp("string", vals=names)
+            g.ep.decade = g.new_ep("int")
+            g.ep.count = g.new_ep("int")
+            for d, f in zip(decades, fs[1:]):
+                A = numpy.loadtxt(f, dtype="int")
+                i, j = A.nonzero()
+                year = int(d.split("-")[0])
+                g.add_edge_list(numpy.array([i, j, [year] * len(i), A[i, j]]).T,
+                                eprops=[g.ep.decade, g.ep.count])
+        yield alt, g