# Importing necessary libraries to read and analyze the PDF file import fitz # PyMuPDF import pandas as pd import matplotlib.pyplot as plt import seaborn as sns # Reading the PDF file pdf_path = 'synthese_satisfaction_reclamations_formations_en_cours.pdf' doc = fitz.open(pdf_path) # Extracting text from the first few pages to understand the structure of the data text = "" for page_num in range(min(3, len(doc))): # Limiting to the first 3 pages page = doc[page_num] text += page.get_text() # Printing the extracted text to understand its structure print(text[:2000]) # Displaying the first 2000 characters of the text for inspection