From 85986ba965387021dea0473ae691a73541fb68a6 Mon Sep 17 00:00:00 2001
From: Alice BRENON <alice.brenon@ens-lyon.fr>
Date: Tue, 19 Apr 2022 19:10:24 +0200
Subject: [PATCH] Add function to EDdA.data module to keep only the first word
of multi-word domain labels longer than 20
---
EDdA/classification/classSimilarities.py | 7 ++++---
EDdA/data.py | 7 +++++++
2 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/EDdA/classification/classSimilarities.py b/EDdA/classification/classSimilarities.py
index bcc7c05..e36e390 100644
--- a/EDdA/classification/classSimilarities.py
+++ b/EDdA/classification/classSimilarities.py
@@ -33,10 +33,11 @@ def confusionMatrix(vectorizer, metric, domains=data.domains):
m[a][b] = metric(vectorizer(domains[a]), vectorizer(domains[b]))
return m
-def toPNG(matrix, filePath, domains=data.domains):
+def toPNG(matrix, filePath, domains=list(map(data.shortDomain, data.domains)), **kwargs):
plot.figure(figsize=(16,13))
+ if 'cmap' not in kwargs:
+ kwargs['cmap'] = 'Blues'
ax = seaborn.heatmap(
- matrix, xticklabels=domains, yticklabels=domains, cmap='Blues'
+ matrix, xticklabels=domains, yticklabels=domains, **kwargs
)
plot.savefig(filePath, dpi=300, bbox_inches='tight')
-
diff --git a/EDdA/data.py b/EDdA/data.py
index 2243c1c..49ae599 100644
--- a/EDdA/data.py
+++ b/EDdA/data.py
@@ -32,5 +32,12 @@ domains = [
domainId = dict([(domains[k], k) for k in range(0, len(domains))])
+def shortDomain(name, maxSize=20):
+ if len(name) > maxSize:
+ components = name.split(' ')
+ return components[0] + ' […]'
+ else:
+ return name
+
def domain(articles, name):
return articles[articles.ensemble_domaine_enccre == name]
--
GitLab