From fbfe219039eef930a00aeccfe71d3c983815adac Mon Sep 17 00:00:00 2001
From: amau345 <amaury.tiravy@ecl20.ec-lyon.fr>
Date: Tue, 30 Jan 2024 20:49:54 +0100
Subject: [PATCH] function_documentation
---
chatbot_complet.py | 70 +++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 66 insertions(+), 4 deletions(-)
diff --git a/chatbot_complet.py b/chatbot_complet.py
index 489221f..04ba8a3 100644
--- a/chatbot_complet.py
+++ b/chatbot_complet.py
@@ -1,5 +1,5 @@
import sys
-from PyQt5.QtWidgets import QApplication, QWidget, QHBoxLayout, QVBoxLayout, QTextEdit, QLineEdit, QPushButton, QSizePolicy, QListWidget, QListWidgetItem,QLabel
+from PyQt5.QtWidgets import QApplication, QWidget, QHBoxLayout, QVBoxLayout, QTextEdit, QLineEdit, QPushButton, QSizePolicy, QListWidget, QListWidgetItem, QLabel
from PyQt5.QtCore import Qt
from PyQt5.QtGui import QPalette, QColor, QFont, QIcon
from sklearn.feature_extraction.text import TfidfVectorizer
@@ -9,12 +9,26 @@ from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
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 != ""]
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', 'lesquels', 'lesquelles', 'est-ce', 'n\'est-ce pas', 'savoir', 'pouvez-vous', 'êtes-vous', 'avez-vous', 'dois-je', 'quelqu\'un', 'quelque chose']
stop_words=stop_words.union(mots_questions)
@@ -24,6 +38,14 @@ def extract_keywords_textblob_french(sentence):
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:
@@ -37,6 +59,16 @@ def create_vectorial_base(text_lines, min_chars=10):
return vectorizer, vectorial_base, feature_names
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
@@ -50,12 +82,18 @@ def get_best_answers(question, text_lines, vectorizer, vectorial_base):
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)
@@ -67,6 +105,9 @@ class StyledListWidgetItem(QListWidgetItem):
self.setData(Qt.UserRole, palette)
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)
@@ -79,12 +120,20 @@ 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'
@@ -100,6 +149,9 @@ class ChatbotInterface(QWidget):
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))
@@ -173,7 +225,9 @@ class ChatbotInterface(QWidget):
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()
if len(user_command)>0:
self.conversation_text.clear()
@@ -187,7 +241,7 @@ 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
@@ -200,12 +254,20 @@ class ChatbotInterface(QWidget):
pass
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)
--
GitLab