From 3525a69869cbf2c4ce75a9a2054a0b33bd914dda Mon Sep 17 00:00:00 2001
From: Martin Czygan <martin.czygan@gmail.com>
Date: Thu, 8 Jul 2021 18:36:00 +0200
Subject: note on timings

---
 python/notes/version_4.md | 8 ++++++++
 python/refcat/tasks.py    | 2 +-
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'python')

diff --git a/python/notes/version_4.md b/python/notes/version_4.md
index 4d8e9e3..e7be1e6 100644
--- a/python/notes/version_4.md
+++ b/python/notes/version_4.md
@@ -883,3 +883,11 @@ igyewr6er5epfozhk7dyfqa5tu      igyewr6er5epfozhk7dyfqa5tu      exact   doi
 * linked open library titles: 12394810
 * URLs extracted from corpus: 25405592
 * sample ratio IA/URL from corpus (N=100000):
+
+----
+
+# Timing
+
+Completed 24/25 jobs in 42h with a few failures from disk space issues.
+
+* 2562m34.844s
diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py
index 0db6f86..58e0e38 100644
--- a/python/refcat/tasks.py
+++ b/python/refcat/tasks.py
@@ -1411,7 +1411,7 @@ class UnmatchedResolveJournalNamesMapped(Refcat):
 
 class WikipediaDOI(Refcat):
     """
-    Sorted DOI keys from wikipedia.
+    Sorted DOI keys from wikipedia. Takes about a minute.
     """
     def requires(self):
         return WikipediaCitationsMinimalDataset()
-- 
cgit v1.2.3