From 164ce55bbe6549d1cc2618dca2f53eeac04de349 Mon Sep 17 00:00:00 2001 From: Tiravy Amaury <amaury.tiravy@ecl20.ec-lyon.fr> Date: Thu, 7 Mar 2024 10:54:14 +0100 Subject: [PATCH] enlever_accents --- requirements.txt | 3 ++- test_combine.py | 4 +++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/requirements.txt b/requirements.txt index fcec211..bcfb64b 100644 --- a/requirements.txt +++ b/requirements.txt @@ -11,4 +11,5 @@ spacy PyQt5 sklearn nltk -sys \ No newline at end of file +sys +unidecode \ No newline at end of file diff --git a/test_combine.py b/test_combine.py index 233702c..a3b610b 100644 --- a/test_combine.py +++ b/test_combine.py @@ -7,6 +7,7 @@ from sklearn.metrics.pairwise import cosine_similarity import numpy as np from nltk.corpus import stopwords from nltk.tokenize import word_tokenize +from unidecode import unidecode def read_text_file(file_path): """ @@ -18,7 +19,7 @@ def read_text_file(file_path): """ with open(file_path, 'r', encoding='utf-8') as file: content = file.read().split('\n\n') - content1 = [item for item in content if item != ""] + content1 = [unidecode(item) for item in content if item != ""] return content1 def extract_keywords_french(sentence): @@ -251,6 +252,7 @@ class ChatbotInterface(QWidget): Handles the user's input, processes it, and displays the chatbot's response. """ user_command = self.user_input_entry.text() + user_command=unidecode(user_command) if len(user_command)>0: self.conversation_text.clear() self.conversation_text.append(f"demande élève: {user_command}") -- GitLab