From 3665a50a48c3601395437f63cd2e40206ed4b9fe Mon Sep 17 00:00:00 2001
From: Bouchafaa <mohamed.bouchafaa@ec-lyon.fr>
Date: Thu, 28 Mar 2024 08:21:40 +0100
Subject: [PATCH] fixed
---
chatbot_complet.py | 2 +-
chatbot_with_summarizer.py | 159 +++++++++++++++++++++++++++++--------
2 files changed, 128 insertions(+), 33 deletions(-)
diff --git a/chatbot_complet.py b/chatbot_complet.py
index fd3d200..7a6bceb 100644
--- a/chatbot_complet.py
+++ b/chatbot_complet.py
@@ -159,7 +159,7 @@ class ChatbotInterface(QWidget):
"""
def __init__(self):
super().__init__()
- file_path = '../reglementdescolarite-ingegeneraliste2324-1.docx.txt'
+ file_path = 'reglementdescolarite-ingegeneraliste2324-1.docx.txt'
self.text_lines = read_text_file(file_path)
if not self.text_lines:
diff --git a/chatbot_with_summarizer.py b/chatbot_with_summarizer.py
index 11adeb6..e3a28a2 100644
--- a/chatbot_with_summarizer.py
+++ b/chatbot_with_summarizer.py
@@ -1,26 +1,40 @@
import sys
-
-import numpy as np
-from PyQt5.QtCore import Qt
-from PyQt5.QtGui import QPalette, QColor, QPixmap
from PyQt5.QtWidgets import QApplication, QWidget, QHBoxLayout, QVBoxLayout, QTextEdit, QLineEdit, QPushButton, \
QSizePolicy, QListWidget, QListWidgetItem, QLabel
-from nltk.corpus import stopwords
-from nltk.tokenize import word_tokenize
+from PyQt5.QtCore import Qt
+from PyQt5.QtGui import QPalette, QColor, QFont, QIcon
from sklearn.feature_extraction.text import TfidfVectorizer
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
from language_models import flant5_summarizer
def read_text_file(file_path):
+ """
+ Reads the content of a text file specified by `file_path` and splits it into paragraphs based on double line breaks (`'\n\n'`).
+ Parameters:
+ - file_path (str): The path to the text file.
+ Returns:
+ - list: A list of non-empty paragraphs from the file.
+ """
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_textblob_french(sentence):
+def extract_keywords_french(sentence):
+ """
+ Tokenizes and filters a given sentence to extract keywords in French. Removes stop words and focuses on meaningful terms.
+ Parameters:
+ - sentence (str): The input sentence.
+ Returns:
+ - str: A string containing the extracted keywords.
+ """
stop_words = set(stopwords.words('french'))
mots_questions = ['qui', 'quoi', 'où', 'quand', 'pourquoi', 'comment', 'quel', 'quelle', 'quels', 'quelles',
'est-ce que', 'y a-t-il', 'peut-on', 'sont-ils', 'sont-elles', 'combien', 'lequel', 'laquelle',
@@ -32,41 +46,93 @@ def extract_keywords_textblob_french(sentence):
return ' '.join(keywords)
-def create_vectorial_base(text_lines, min_chars=50):
+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 create_vectorial_base(text_lines, min_chars=10):
+ """
+ Creates a TF-IDF vectorial base from a list of text lines.
+ Parameters:
+ - text_lines (list): List of text lines.
+ - min_chars (int): Minimum number of characters required for a line to be included (default is 10).
+ Returns:
+ - tuple: A tuple containing the TF-IDF vectorizer, the TF-IDF matrix (vectorial base), and the feature names.
+ """
filtered_lines = [line for line in text_lines if len(line) >= min_chars]
if not filtered_lines:
- print("No lines with at least 50 characters found.")
+ print("No lines with at least 10 characters found.")
return None, None, None
- vectorizer = TfidfVectorizer()
+ vectorizer = TfidfVectorizer() # a tester en option : stop_words=list(stopwords.words('french'))
vectorial_base = vectorizer.fit_transform(filtered_lines).toarray()
feature_names = vectorizer.get_feature_names_out()
return vectorizer, vectorial_base, feature_names
+def jaccard_similarity(str1, str2):
+ tokens_str1 = set(word_tokenize(str1.lower()))
+ tokens_str2 = set(word_tokenize(str2.lower()))
+
+ stop_words = set(stopwords.words('french'))
+ tokens_str1 = tokens_str1 - stop_words
+ tokens_str2 = tokens_str2 - stop_words
+
+ intersection = len(tokens_str1.intersection(tokens_str2))
+ union = len(tokens_str1) + len(tokens_str2) - intersection
+
+ similarity = intersection / union if union != 0 else 0.0
+ return similarity
+
+
def get_best_answers(question, text_lines, vectorizer, vectorial_base):
+ """
+ Retrieves the top 3 most similar text lines to a given question based on cosine similarity.
+ Parameters:
+ - question (str): The user's question.
+ - text_lines (list): List of text lines.
+ - vectorizer: The TF-IDF vectorizer.
+ - vectorial_base: The TF-IDF matrix (vectorial base).
+ Returns:
+ - list: A list of the top 3 most similar text lines as answers.
+ """
question_vector = vectorizer.transform([question]).toarray()
# Calculate cosine similarity between the question and each text line
similarities = cosine_similarity(question_vector, vectorial_base).flatten()
- # Get the indices of the top 5 most similar text lines
- top_indices = np.argsort(similarities)[-3:][::-1]
+ jaccard_similarities = [jaccard_similarity(question, text) for text in text_lines]
+
+ combined_scores = [calculate_combined_score(similarities, jaccard_score)
+ for similarities, jaccard_score in zip(similarities, jaccard_similarities)]
+
+ # 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
class WrappingLabel(QLabel):
+ """
+ Subclass of QLabel with word wrapping enabled. Used for displaying text in the GUI.
+ """
+
def __init__(self, text='', parent=None):
super(WrappingLabel, self).__init__(text, parent)
self.setWordWrap(True)
class StyledListWidgetItem(QListWidgetItem):
+ """
+ Subclass of QListWidgetItem with custom styling for the chat history list.
+ """
+
def __init__(self, text='', parent=None):
super(StyledListWidgetItem, self).__init__(parent)
self.setText(text)
@@ -81,6 +147,10 @@ class StyledListWidgetItem(QListWidgetItem):
class StyledListWidget(QListWidget):
+ """
+ Subclass of QListWidget with custom styling for the chat history list.
+ """
+
def __init__(self, parent=None):
super(StyledListWidget, self).__init__(parent)
self.setAlternatingRowColors(False)
@@ -93,12 +163,21 @@ class StyledListWidget(QListWidget):
""")
def addStyledItem(self, text):
+ """
+ Adds a styled item to the list widget.
+ Parameters:
+ - text (str): The text to be added to the list.
+ """
item = StyledListWidgetItem(text)
item.initStyle()
self.addItem(item)
class ChatbotInterface(QWidget):
+ """
+ Main class representing the chatbot interface. Initializes the UI and handles user interactions.
+ """
+
def __init__(self):
super().__init__()
file_path = 'reglementdescolarite-ingegeneraliste2324-1.docx.txt'
@@ -111,10 +190,15 @@ class ChatbotInterface(QWidget):
self.init_ui()
self.command_history = [] # Pour stocker l'historique des commandes
self.dico = {}
+ self.dico2 = {}
def init_ui(self):
+ """
+ Initializes the user interface.
+ """
# Créer des widgets
self.conversation_text = QTextEdit(self)
+ self.conversation_text.setFont(QFont("consolas", 9))
self.conversation_text.setReadOnly(True)
self.user_input_entry = QLineEdit(self)
@@ -139,6 +223,7 @@ class ChatbotInterface(QWidget):
left_layout = QVBoxLayout()
left_layout.addWidget(self.conversation_text)
left_layout.addWidget(self.user_input_entry)
+
# Ajouter le bouton "Envoyer" avec une taille réduite
self.send_button.setMaximumWidth(self.send_button.width() // 3)
left_layout.addWidget(self.send_button, alignment=Qt.AlignRight)
@@ -153,7 +238,9 @@ class ChatbotInterface(QWidget):
self.conversation_text.setSizePolicy(size_policy)
# Définir la fenêtre principale
- self.setWindowTitle('Chatbot Interface')
+ icon = QIcon("../public/chatbot.png")
+ self.setWindowIcon(icon)
+ self.setWindowTitle('chatbot')
self.setGeometry(100, 100, 800, 600)
# Appliquer les styles
@@ -177,18 +264,22 @@ class ChatbotInterface(QWidget):
""")
+
self.user_input_entry.returnPressed.connect(self.send_message)
self.history_list_widget.itemClicked.connect(self.history_item_clicked)
def send_message(self):
-
+ """
+ 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"Commande utilisateur: {user_command}")
+ self.conversation_text.append(f"demande élève: {user_command}")
+ self.conversation_text.append("Réponse du chatbot pour la demande: ")
best_answers = get_best_answers(user_command, self.text_lines, self.vectorizer, self.vectorial_base)
-
flant5_summarized_text = "La réponse formulée par flan-T5 (1024) : \n" + flant5_summarizer(
" ".join(best_answers))
@@ -199,8 +290,9 @@ class ChatbotInterface(QWidget):
self.conversation_text.append(chatbot_response)
# Ajouter la commande à l'historique
- user_command1 = extract_keywords_textblob_french(user_command)
+ user_command1 = extract_keywords_french(user_command)
self.command_history.append(user_command1)
+ self.dico2[user_command1] = user_command
self.dico[user_command1] = chatbot_response
# Mettre à jour la liste d'historique
@@ -210,40 +302,43 @@ class ChatbotInterface(QWidget):
else:
pass
- def set_logo(self, image_path):
- pixmap = QPixmap(image_path)
- self.logo_label.setPixmap(pixmap)
- self.logo_label.setScaledContents(True)
-
def update_history_list(self):
+ """
+ Updates the chat history list in the UI.
+ """
self.history_list_widget.clear()
for command in self.command_history:
self.history_list_widget.addStyledItem(command)
def history_item_clicked(self, item):
+ """
+ Displays the chat history when an item is clicked.
+ Parameters:
+ - item: The clicked item.
+ """
self.conversation_text.clear()
# Réafficher le contenu dans la conversation_text lorsque l'élément de l'historique est cliqué
selected_index = self.history_list_widget.row(item)
if selected_index < len(self.command_history):
selected_command = self.command_history[selected_index]
- self.conversation_text.append(f"Commande utilisateur: {selected_command}")
+ self.conversation_text.append(f"demande élève: {self.dico2[selected_command]}")
# Traiter la commande et obtenir la réponse du chatbot (vous devrez ajuster cela en fonction de votre application)
- chatbot_response = f"Réponse du chatbot pour la commande: {self.dico[selected_command]}"
+ chatbot_response = f"Réponse du chatbot pour la demande: \n{self.dico[selected_command]}"
self.conversation_text.append(chatbot_response)
if __name__ == '__main__':
app = QApplication(sys.argv)
chatbot_app = ChatbotInterface()
-
- # Centrer la fenêtre
screen = app.primaryScreen()
- center_point = screen.availableGeometry().center()
- chatbot_app.move(center_point - chatbot_app.rect().center())
# Ajuster la taille de la fenêtre
- new_width = screen.availableGeometry().width() // 2
- chatbot_app.resize(new_width, screen.availableGeometry().height() * round(7 / 8))
+ new_width = screen.availableGeometry().width() * 3 // 5
+ chatbot_app.resize(new_width, int(screen.availableGeometry().height() - 48))
+
+ # Centrer la fenêtre
+ center_point = screen.availableGeometry().center().x() - chatbot_app.rect().center().x()
+ chatbot_app.move(center_point, 0)
chatbot_app.show()
sys.exit(app.exec_())
--
GitLab