logo Netzschleuder network catalog, repository, and centrifuge

History of walmart_trips

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/walmart_trips/__init__.py b/entries/walmart_trips/__init__.py
index 22d099c..02a147e 100644
--- a/entries/walmart_trips/__init__.py
+++ b/entries/walmart_trips/__init__.py
@@ -29,7 +29,7 @@ tags = ['Commerce', 'Offline', 'Unweighted', 'Metadata']
 url = 'https://www.cs.cornell.edu/~arb/data/walmart-trips/'
 citation = [('I. Amburg, N. Veldt, A. R. Benson, "Clustering in graphs and hypergraphs with categorical edge labels." Proceedings of The Web Conference 2020, 706-717 (2020)', 'https://doi.org/10.1145/3366423.3380152'),
             ('Kaggle, "Walmart Recruiting: Trip Type Classification." (2015)', 'https://www.kaggle.com/c/walmart-recruiting-trip-type-classification')]
-icon_hash = None
+date_added = '2026-10-25'
 upstream_license = None
 upstream_prefix = 'gdrive://'
 files = [(('1kl6wuvopJ5_wvEIy6YnwoXh1SjlIpRhu:zip:walmart-trips/hyperedges-walmart-trips.txt',
[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/walmart_trips/__init__.py b/entries/walmart_trips/__init__.py
index 4c8360d..22d099c 100644
--- a/entries/walmart_trips/__init__.py
+++ b/entries/walmart_trips/__init__.py
@@ -23,8 +23,8 @@ description = """A bipartite network of shopping trips at Walmart stores and the
 
 The network has the following properties:
 
-- `is_trip`: whether the node is a shopping trip (otherwise it is a product).
-- Product nodes: `department`, the walmart.com department of the product: "Clothing, Shoes & Accessories", "Electronics and Office", "Home, Furniture & Appliances", "Home Improvement & Patio", "Baby", "Toys, Games, and Video Games", "Food, Household & Pets", "Pharmacy, Health & Beauty", "Sports, Fitness & Outdoors", "Auto, Tires & Industrial", or "Other"."""
+- (Node) `is_trip`: whether the node is a shopping trip (otherwise it is a product).
+- (Node) `department` (products): the walmart.com department of the product: "Clothing, Shoes & Accessories", "Electronics and Office", "Home, Furniture & Appliances", "Home Improvement & Patio", "Baby", "Toys, Games, and Video Games", "Food, Household & Pets", "Pharmacy, Health & Beauty", "Sports, Fitness & Outdoors", "Auto, Tires & Industrial", or "Other"."""
 tags = ['Commerce', 'Offline', 'Unweighted', 'Metadata']
 url = 'https://www.cs.cornell.edu/~arb/data/walmart-trips/'
 citation = [('I. Amburg, N. Veldt, A. R. Benson, "Clustering in graphs and hypergraphs with categorical edge labels." Proceedings of The Web Conference 2020, 706-717 (2020)', 'https://doi.org/10.1145/3366423.3380152'),
[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/walmart_trips/__init__.py b/entries/walmart_trips/__init__.py
index e3990df..4c8360d 100644
--- a/entries/walmart_trips/__init__.py
+++ b/entries/walmart_trips/__init__.py
@@ -45,7 +45,6 @@ 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: walmart_trips by Tiago de Paula Peixoto dcfcccc
diff --git a/entries/walmart_trips/__init__.py b/entries/walmart_trips/__init__.py
new file mode 100644
index 0000000..e3990df
--- /dev/null
+++ b/entries/walmart_trips/__init__.py
@@ -0,0 +1,72 @@
+#! /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 = "Walmart shopping trips (2015)"
+description = """A bipartite network of shopping trips at Walmart stores and the products bought in each trip. The purchase data were released by Walmart for the 2015 Kaggle competition "Walmart Recruiting: Trip Type Classification", in which each record is an item scanned during a customer visit (identified by a visit number, with the product's UPC code, its store department and the number of items scanned), and visits were to be classified into trip types defined by Walmart. Amburg, Veldt and Benson formed the trips from these records and assigned each product to one of ten broad departments under which it appears on walmart.com, or to an "Other" class. Each trip in the network contains at least two distinct products; not all visits of the competition data are included, and the selection criteria are not documented. Product identities, item counts and the trip types are not included in this version of the data.
+
+The network has the following properties:
+
+- `is_trip`: whether the node is a shopping trip (otherwise it is a product).
+- Product nodes: `department`, the walmart.com department of the product: "Clothing, Shoes & Accessories", "Electronics and Office", "Home, Furniture & Appliances", "Home Improvement & Patio", "Baby", "Toys, Games, and Video Games", "Food, Household & Pets", "Pharmacy, Health & Beauty", "Sports, Fitness & Outdoors", "Auto, Tires & Industrial", or "Other"."""
+tags = ['Commerce', 'Offline', 'Unweighted', 'Metadata']
+url = 'https://www.cs.cornell.edu/~arb/data/walmart-trips/'
+citation = [('I. Amburg, N. Veldt, A. R. Benson, "Clustering in graphs and hypergraphs with categorical edge labels." Proceedings of The Web Conference 2020, 706-717 (2020)', 'https://doi.org/10.1145/3366423.3380152'),
+            ('Kaggle, "Walmart Recruiting: Trip Type Classification." (2015)', 'https://www.kaggle.com/c/walmart-recruiting-trip-type-classification')]
+icon_hash = None
+upstream_license = None
+upstream_prefix = 'gdrive://'
+files = [(('1kl6wuvopJ5_wvEIy6YnwoXh1SjlIpRhu:zip:walmart-trips/hyperedges-walmart-trips.txt',
+           '1kl6wuvopJ5_wvEIy6YnwoXh1SjlIpRhu:zip:walmart-trips/node-labels-walmart-trips.txt',
+           '1kl6wuvopJ5_wvEIy6YnwoXh1SjlIpRhu:zip:walmart-trips/label-names-walmart-trips.txt'),
+          None, None)]
+
+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, "r")) for fn in fnames]
+
+            # One trip per line, comma-separated 1-based product ids
+            groups, members, n = read_hyperedges(fs[0], sep=",")
+            # Line i: the (1-based) department index of product i (the
+            # format allows a comma-separated list, but there is a single
+            # department per product)
+            labels = read_ints(fs[1])
+            # Department names contain commas: one name per line
+            depts = [l.rstrip("\r\n") for l in fs[2]]
+            N = len(labels)
+            assert members.max() < N
+            g = bipartite_graph(groups, members, n, N, "is_trip")
+            g.vp.department = g.new_vp("string")
+            for v, c in enumerate(labels):
+                g.vp.department[v] = depts[c - 1]
+        yield alt, g