From 98a6d660d88ae4c1b9c863404a9a0e2d2d9c97f7 Mon Sep 17 00:00:00 2001
From: amau345 <amaury.tiravy@ecl20.ec-lyon.fr>
Date: Wed, 31 Jan 2024 17:23:25 +0100
Subject: [PATCH] add_score
---
test_combine.py | 33 ++++-----------------------------
1 file changed, 4 insertions(+), 29 deletions(-)
diff --git a/test_combine.py b/test_combine.py
index 1a829df..8aea1c2 100644
--- a/test_combine.py
+++ b/test_combine.py
@@ -1,31 +1,3 @@
-def calculate_combined_score(tfidf_score, jaccard_score):
- # You can adjust the weights based on the importance of each score
- return 0.7 * tfidf_score + 0.3 * jaccard_score
-
-def get_best_answers(question, text_lines, vectorizer, vectorial_base):
-
- question_vector = vectorizer.transform([question]).toarray()
-
- # Calculate cosine similarity between the question and each text line
- similarities = cosine_similarity(question_vector, vectorial_base).flatten()
-
- jaccard_similarities = [jaccard_similarity(question, text) for text in text_lines]
-
- # Calculate TF-IDF score for each text line
- tfidf_scores = [vectorizer.transform([text]).toarray() for text in text_lines]
-
- # Calculate combined scores using both TF-IDF and cosine similarity
- combined_scores = [calculate_combined_score(tfidf_score, jaccard_score)
- for tfidf_score, jaccard_score in zip(tfidf_scores, jaccard_similarities)]
-
- # Get the indices of the top 3 most similar text lines based on the combined scores
- top_indices = np.argsort(combined_scores)[-3:][::-1]
-
- # Retrieve the corresponding text lines along with their combined scores
- best_answers = [text_lines[i]+"\n" for i in top_indices]
-
- return best_answers
-
import sys
from PyQt5.QtWidgets import QApplication, QWidget, QHBoxLayout, QVBoxLayout, QTextEdit, QLineEdit, QPushButton, QSizePolicy, QListWidget, QListWidgetItem, QLabel
from PyQt5.QtCore import Qt
@@ -64,6 +36,9 @@ def extract_keywords_french(sentence):
keywords = [word for word in words if word.lower() not in stop_words]
return ' '.join(keywords)
+def calculate_combined_score(tfidf_score, jaccard_score):
+ # You can adjust the weights based on the importance of each score
+ return 0.6 * tfidf_score + 0.4 * jaccard_score
def create_vectorial_base(text_lines, min_chars=10):
"""
@@ -124,7 +99,7 @@ def get_best_answers(question, text_lines, vectorizer, vectorial_base):
# Get the indices of the top 3 most similar text lines
top_indices = np.argsort(combined_scores)[-3:][::-1]
# Retrieve the corresponding text lines
- best_answers = [text_lines[i]+"\n" for i in top_indices]
+ best_answers = [text_lines[i]+"\n"+"score TFIDF : "+str(similarities[i])+" score jacard : "+str(jaccard_similarities[i])+"\n" for i in top_indices]
return best_answers
--
GitLab