__init__.py 2.19 KB
Newer Older
Tiago Peixoto's avatar
Tiago Peixoto committed
1 2 3 4 5
#! /usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (C) 2020 Tiago de Paula Peixoto <tiago@skewed.de>
#
6 7 8 9
# 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.
Tiago Peixoto's avatar
Tiago Peixoto committed
10
#
11 12 13 14
# 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.
Tiago Peixoto's avatar
Tiago Peixoto committed
15
#
16 17
# 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/>.
Tiago Peixoto's avatar
Tiago Peixoto committed
18 19 20 21

from .. import *

title = "Yahoo song ratings (2011)"
22 23
description = """A bipartite network of users and songs they rated, as used in the 2011 KDD Cup and extracted from Yahoo! Music. Edge weights denote a rating scaled from 0 to 100. More information about this data set is available at http://konect.cc/networks/yahoo-song[^icon]
[^icon]: Description obtained from the [ICON](https://icon.colorado.edu) project."""
Tiago Peixoto's avatar
Tiago Peixoto committed
24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
tags = ['Economic', 'Preferences', 'Timestamps', 'Weighted']
url = 'http://konect.cc/networks/yahoo-song'
citation = [('G. Dror et al. "The Yahoo! Music Dataset and KDD-Cup\'11." KDD Cup (2012).', 'http://www.jmlr.org/proceedings/papers/v18/dror12a/dror12a.pdf')]
icon_hash = '58879753a411221d0e7c6789'
upstream_prefix = 'http://konect.cc/files'
files = [('download.tsv.yahoo-song.tar.bz2', None, 'konect')]

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, fmt, directed=True)
        yield alt, g