Add scotus_majority

entries/scotus_majority/__init__.py

+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2020 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 pandas
+
+title = "SCOTUS majority opinions"
+description = """Network of legal citations among majority opinions written by the Supreme Court of the United States (SCOTUS), from 1754-2002 (2008 version) and 1792-2006 (2007 version). In addition to the citation network, node metadata is included giving some description of each opinion.[^icon]
+[^icon]: Description obtained from the [ICON](https://icon.colorado.edu) project."""
+tags = ['Informational', 'Legal', 'Unweighted', 'Metadata', 'Temporal']
+url = 'http://fowler.ucsd.edu/judicial.htm'
+citation = [('J. H. Fowler and S. Jeon, "The Authority of Supreme Court Precedent." Social Networks 30(1), 16-30 (2008)', 'http://jhfowler.ucsd.edu/authority_of_supreme_court_precedent.pdf'),
+            ('J. H. Fowler et al., "Network Analysis and the Law: Measuring the Legal Importance of Supreme Court Precedents." Political Analysis 15(3), 324-346 (2007)', 'http://jhfowler.ucsd.edu/network_analysis_and_the_law.pdf')]
+icon_hash = '57114fb76afce8e9253875c7'
+ustream_license = None
+upstream_prefix = 'http://jhfowler.ucsd.edu/data'
+files = [(('judicial.zip:allcites.txt', 'judicial.zip:judicial.csv'), "2008", 'loadtxt'),
+         (('Pol_Analysis_ussc_cites.csv.zip:Pol_Analysis_ussc_cites.csv',
+           'Pol_Analysis_replication.zip:Pol_Analysis_replication.dta'), "2007", 'csv')]
+
+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
+        if isinstance(fnames, str):
+            fnames = [fnames]
+        with ExitStack() as stack:
+            fs = [stack.enter_context(open_upstream_file(name, fn, "rb")) for fn in fnames]
+            g = parse_graph([fs[0]], fmt, directed=True)
+
+            vs = {g.vp.name[v] : v for v in g.vertices()}
+
+            if alt == "2008":
+                vps = ["usid", "parties", "overruled", "overruling", "oxford"]
+
+                for p in vps:
+                    g.vp[p] = g.new_vp("string")
+
+                reader = csv.reader(io.TextIOWrapper(fs[1]))
+                next(reader)
+                for row in reader:
+                    id = row[0]
+                    try:
+                        v = vs[id]
+                    except KeyError:
+                        continue
+                    for p, val in zip(vps, row[1:len(vps)+1]):
+                        g.vp[p][v] = val
+            else:
+                g.vp.lexid = g.vp.name
+                del g.vp["name"]
+
+                vps = ["usid", "name", "amiciz_num", "auth_num", "oxford_num",
+                       "cq_num", "nyt_num", "insc_num", "apin_num", "stin_num",
+                       "citedyr_num", "citingyr_num", "size_num", "age",
+                       "insc_num_lag", "apin_num_lag", "stin_num_lag",
+                       "outsc_num_lag", "sc_cumul_cites_lag"]
+
+                for p in vps:
+                    g.vp[p] = g.new_vp("string")
+
+                df = pandas.read_stata(fs[1])
+                for index, row in df.iterrows():
+                    try:
+                        v = vs[row["lexid"]]
+                    except KeyError:
+                        continue
+                    for p in vps:
+                        g.vp[p][v] = row[p]
+
+            for p in g.vp.keys():
+                try:
+                    g.vp[p] = g.vp[p].copy("int")
+                except ValueError:
+                    continue
+
+        yield alt, g