last update

Dramas.csv

-show_id,type,title,director,cast,country,date_added,release_year,rating,duration,listed_in,description
-s1237,Movie,Sentinelle,Julien Leclercq,"Olga Kurylenko, Marilyn Lima, Michel Nabokoff, Martin Swabey, Carole Weyers, Andrey Gorlenko, Antonia Malinova, Gabriel Almaer, Blaise Afonso, Guillaume Duhesme, Michel Biel",France,"March 5, 2021",2021,TV-MA,81 min,"Action & Adventure, Dramas, International Movies","Transferred home after a traumatizing combat mission, a highly trained French soldier uses her lethal skills to hunt down the man who hurt her sister."
-s2669,Movie,Earth and Blood,Julien Leclercq,"Sami Bouajila, Eriq Ebouaney, Samy Seghir, Sofia Lesaffre","France, Belgium","April 17, 2020",2020,TV-MA,81 min,"Dramas, International Movies, Thrillers",A sawmill owner and his teenage daughter become tangled in a deadly feud when a drug dealer stashes stolen cocaine on their remote property.

projet_en_groupe/algorithme_netflix.py

-# afficher le premier document
-
+# ALL the imports
 import pandas as pd
 import tabulate
 import os
@@ -27,7 +26,7 @@ def catalog(data_1):
     # Be careful, you need to ask each time if they want to save the list to a .csv
 
 
-def movies(data_1): # enregistrement 
+def movies(data_1): # register
 
     films = data_1[data_1['type'] == 'Movie']  # Filter the data to include only movies
     movie_titles = films['title'].tolist()  # Extract movie titles
@@ -129,8 +128,6 @@ def by_country(data_1):
 
  # Be careful, you need to ask each time if they want to save the list to a .csv
 
-
-
 def genre(data_1):
     filtered_data = filter_media_type(data_1)
 
@@ -174,8 +171,6 @@ def genre(data_1):
     return
 
 
-from fuzzywuzzy import process
-
 def duration(data_1):
     filtered_data = filter_media_type(data_1)
 
@@ -254,7 +249,9 @@ def director(data_1):
             if director_name not in director_list and director_name != '':
                 director_list.append(director_name)
 
+    # Sort the director_list in alphabetical order
     print("List of all possible directors: ")
+    director_list = sorted(director_list)
     print(director_list)
 
     while True:
@@ -298,6 +295,7 @@ def actor(data_1):
             if actor_name not in actor_list and actor_name != '':
                 actor_list.append(actor_name)
 
+    actor_list = sorted(actor_list)
     print("List of all possible actors: ")
     print(actor_list)
 
@@ -340,7 +338,10 @@ def specific_genre_director(data_1):
     unique_directors = filtered_data['director'].unique()
     # Convert elements to strings to handle potential float values
     unique_directors = [str(director) for director in unique_directors]
-    
+
+    # Sort the unique_directors in alphabetical order
+    unique_directors = sorted(unique_directors)
+
     print("List of all available directors:")
     print(', '.join(unique_directors))
 
@@ -366,6 +367,9 @@ def specific_genre_director(data_1):
     # Get a list of all available types without duplicates
     unique_types = filtered_data['listed_in'].str.split(', ').explode().unique()
 
+    # Sort the unique_types in alphabetical order
+    unique_types = sorted(unique_types)
+
     print("\nList of all available types:")
     print(', '.join(unique_types))
 
@@ -412,7 +416,10 @@ def specific_genre_actor(data_1):
     # Get a list of unique actors
     unique_actors = filtered_data['cast'].str.split(', ').explode().unique()
     unique_actors = [str(actor) for actor in unique_actors]
-    
+
+    # Sort the unique_actors in alphabetical order
+    unique_actors = sorted(unique_actors)
+
     print("List of all available actors:")
     print(', '.join(unique_actors))
 
@@ -436,6 +443,9 @@ def specific_genre_actor(data_1):
     # Get a list of all available types without duplicates
     unique_types = filtered_data['listed_in'].str.split(', ').explode().unique()
 
+    # Sort the unique_types in alphabetical order
+    unique_types = sorted(unique_types)
+
     print("\nList of all available types:")
     print(', '.join(unique_types))
 
@@ -674,39 +684,50 @@ def basic_statistics(data_1):
  # attention il faut demander à chaque fois, s'il désire enregistrer la liste sur un .csv
 
 def save_to_csv(data, default_filename='output.csv'):
-    # Ask if the user wants to save to a CSV file
-    save_choice = input("Do you want to save the data to a CSV file? (YES/NO): ").upper()
-
-    if save_choice == 'YES':
-        # Prompt for a file name
-        file_name = input("Enter the file name (DO NOT include .csv extension, or press Enter for the default): ")
-        file_name = file_name + ".csv"
-        if not file_name:
-            file_name = default_filename
-
-        # Check if the file already exists
-        if os.path.exists(file_name):
-            # Ask if the user wants to overwrite or create a new file
-            overwrite_choice = input(f"The file '{file_name}' already exists. Do you want to overwrite it? (YES/NO): ").upper()
-
-            if overwrite_choice == 'YES':
-                # Overwrite the existing file
+    while True:
+        # Ask if the user wants to save to a CSV file
+        save_choice = input("Do you want to save the data to a CSV file? (YES/NO): ").upper()
+
+        if save_choice == 'YES':
+            # Prompt for a file name
+            file_name = input("Enter the file name (DO NOT include .csv extension, or press Enter for the default): ")
+            file_name = file_name + ".csv"
+            if not file_name:
+                file_name = default_filename
+
+            # Check if the file already exists
+            if os.path.exists(file_name):
+                while True:
+                    # Ask if the user wants to overwrite or create a new file
+                    overwrite_choice = input(f"The file '{file_name}' already exists. Do you want to overwrite it? (YES/NO): ").upper()
+
+                    if overwrite_choice == 'YES':
+                        # Overwrite the existing file
+                        data.to_csv(file_name, index=False)
+                        print(f"Data saved to {file_name}")
+                        break
+                    elif overwrite_choice == 'NO':
+                        # Prompt for a new file name
+                        new_filename = input("Enter a new file name (DO NOT include .csv extension): ")
+                        new_filename = new_filename + ".csv"
+                        data.to_csv(new_filename, index=False)
+                        print(f"Data saved to {new_filename}")
+                        break
+                    else:
+                        print("Invalid choice. Please enter either 'YES' or 'NO'.")
+
+            else:
+                # Save to a new file
                 data.to_csv(file_name, index=False)
                 print(f"Data saved to {file_name}")
+                break
 
-            else:
-                # Prompt for a new file name
-                new_filename = input("Enter a new file name (DO NOT include .csv extension): ")
-                new_filename = new_filename + ".csv"
-                data.to_csv(new_filename, index=False)
-                print(f"Data saved to {new_filename}")
-        else:
-            # Save to a new file
-            data.to_csv(file_name, index=False)
-            print(f"Data saved to {file_name}")
+        elif save_choice == 'NO':
+            print("Data not saved.")
+            break
 
-    else:
-        print("Data not saved.")
+        else:
+            print("Invalid choice. Please enter either 'YES' or 'NO.'")
 
 
 
@@ -802,11 +823,6 @@ def recommend_movies(user_id, catalog, user_ratings, category_matrix, threshold=
 
     return sorted_suggestions[:5]
 
-
-
-# Ajout d'impression pour déboguer
-print("User categories:", categories)
-
 def recommandation_algorithm() :
 
     # Replace file_path_1 and file_path_2 with the actual file paths