From 6812b51648b3a1d7d1bd69f1fe9fef489d5e0900 Mon Sep 17 00:00:00 2001
From: Maximilian Blunck <blunck@cl.uni-heidelberg.de>
Date: Wed, 17 Jan 2018 17:19:32 +0100
Subject: [PATCH] Bug fix
---
contrast_feature.py | 7 +++----
ngram_feature.py | 4 ++--
2 files changed, 5 insertions(+), 6 deletions(-)
diff --git a/contrast_feature.py b/contrast_feature.py
index e2ef84a..224a77c 100644
--- a/contrast_feature.py
+++ b/contrast_feature.py
@@ -49,10 +49,9 @@ def extract(corpus_instance):
sent_verb = analyser.polarity_scores(verb)['compound']
sent_situation = analyser.polarity_scores(situation)['compound']
- if (sent_verb > 0.0 and sent_situation < 0.0) or (sent_verb < 0.0 and sent_situation > 0.0):
- print("phrase: {} {} sent verb: {} sent situation: {}".format(verb, situation, sent_verb, sent_situation))
-
-
+ #if (sent_verb > 0.0 and sent_situation < 0.0) or (sent_verb < 0.0 and sent_situation > 0.0):
+ print("phrase: {} {} sent verb: {} sent situation: {}".format(verb, situation, sent_verb, sent_situation))
+
if __name__ == '__main__':
corpus = corpus.read_corpus("corpus_shuffled.csv")[:1000]
diff --git a/ngram_feature.py b/ngram_feature.py
index 2a5354d..7a940d9 100644
--- a/ngram_feature.py
+++ b/ngram_feature.py
@@ -15,7 +15,7 @@ def extract(corpus_instance, corpus_dict_key, vocabulary):
return vector.toarray()[0]
-def get_vocabulary(corpus, corpus_dict_key, n):
+def get_vocabulary(corpus, corpus_dict_key, n_range):
"""
Creates vocabulary based on given corpus.
"""
@@ -23,7 +23,7 @@ def get_vocabulary(corpus, corpus_dict_key, n):
for line in corpus:
all_reviews.append(line[corpus_dict_key])
- vectorizer = CountVectorizer(ngram_range=(n, n))
+ vectorizer = CountVectorizer(ngram_range=n_range)
vectorizer.fit(all_reviews)
return vectorizer.vocabulary_
--
GitLab