diff --git a/.DS_Store b/.DS_Store
index 476cff3271cdbbab862a81ad2a8e56af759ca6b7..a05bdbf17207db37fd9f7d4ef9dab08547ed1654 100644
Binary files a/.DS_Store and b/.DS_Store differ
diff --git a/Data_Base.xlsx b/Data_Base.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..467cf6659b1278f0a87da721fbdd0895369da3f1
Binary files /dev/null and b/Data_Base.xlsx differ
diff --git a/projet_en_groupe/.DS_Store b/projet_en_groupe/.DS_Store
index cee0b65dddcd5835972253a55dd2037bd4548c61..002561828bb5df759e0eb963818a54096c654419 100644
Binary files a/projet_en_groupe/.DS_Store and b/projet_en_groupe/.DS_Store differ
diff --git a/projet_en_groupe/algorithme_netflix.py b/projet_en_groupe/algorithme_netflix.py
index a1dfdc15e5d426f822eac5a4cc104d8cce503bcd..911459a9517246c68a6a59a26f7a54a49017658f 100644
--- a/projet_en_groupe/algorithme_netflix.py
+++ b/projet_en_groupe/algorithme_netflix.py
@@ -474,32 +474,12 @@ def save_to_csv(data, default_filename='output.csv'):
# début de l'algorithme de recommandation
# Load the CSV file
-"""
-def print_matrix(data_1):
- # Initialize the category matrix with zeros
- unique_categories = set(category for categories in data_1['listed_in'].str.split(', ') for category in categories)
- category_matrix = {category: {other_category: 0 for other_category in unique_categories} for category in unique_categories}
+categories = []
- # Fill the matrix with the number of movies/series for each category pair
- for categories in data_1['listed_in'].str.split(', '):
- for category1 in categories:
- for category2 in categories:
- category_matrix[category1][category2] += 1
- category_df = pd.DataFrame(category_matrix)
-
- # Save the DataFrame to an Excel file
- output_file = 'category_matrix.xlsx'
- category_df.to_excel(output_file, index_label='Categories')
-
- print(f"Category matrix saved to {output_file}")
- return category_matrix"""
-
-
-
-def read_movie_series_info(file_path_1):
+def read_movie_series_info(file_path):
catalog = {}
- with open(file_path_1, 'r') as info_file:
+ with open(file_path, 'r', encoding='utf-8') as info_file:
info_reader = csv.reader(info_file)
next(info_reader) # Skip header row
for row in info_reader:
@@ -507,57 +487,106 @@ def read_movie_series_info(file_path_1):
catalog[show_id] = [title, listed_in.split(', ')]
return catalog
-def read_user_ratings(file_path_2):
+def read_user_ratings(file_path):
ratings = {}
- user_ids = [] # Assurez-vous d'initialiser la liste user_ids
- with open(file_path_2, 'r') as ratings_file:
+ with open(file_path, 'r', encoding='utf-8') as ratings_file:
ratings_reader = csv.reader(ratings_file)
- header = next(ratings_reader) # Lire la première ligne pour obtenir les ID des utilisateurs
- user_ids = header[1:] # Les ID des utilisateurs sont dans la première ligne, sauf la première colonne (show_id)
+ header = next(ratings_reader) # Skip header row
+ user_ids = list(map(int, header[1:]))
+
for row in ratings_reader:
show_id = row[0]
user_ratings = list(map(int, row[1:]))
- ratings[show_id] = user_ratings
- return ratings, user_ids
+ ratings[show_id] = dict(zip(user_ids, user_ratings))
+
+ return ratings
-def create_category_matrix(catalog, ratings, categories):
- category_matrix = [[0 for _ in range(len(categories))] for _ in range(len(categories))]
+def create_category_matrix(catalog, categories):
+ # Créez la matrice avec une rangée et une colonne supplémentaires pour les noms de catégories
+ category_matrix = [[0 for _ in range(len(categories) + 1)] for _ in range(len(categories) + 1)]
+ # Ajoutez les noms de catégories à la première ligne et à la première colonne
+ for i in range(len(categories)):
+ category_matrix[0][i + 1] = categories[i] # Ajoutez les noms de catégories à la première ligne
+ category_matrix[i + 1][0] = categories[i] # Ajoutez les noms de catégories à la première colonne
+
+ # Remplissez la matrice avec les données
for show_id, movie_categories in catalog.items():
for i in range(len(categories)):
if categories[i] in movie_categories[1]:
for j in range(len(categories)):
if categories[j] in movie_categories[1]:
- category_matrix[i][j] += ratings[show_id][j]
-
+ category_matrix[i + 1][j + 1] += 1 # Commencez à remplir à partir de la deuxième ligne et de la deuxième colonne
+ # Ajoutez les noms de catégories à la première colonne et les données de la matrice
return category_matrix
-def calculate_user_preferences(category_matrix, user_preferences, categories):
- user_vector = []
- print("Length of user_preferences:", len(user_preferences))
- print("Length of categories:", len(categories))
+def recommend_movies(user_id, catalog, user_ratings, category_matrix, threshold=0.5):
+ global categories # Déclarer categories en tant que variable globale
+ categories = list(set(category for _, movie_info in catalog.items() for category in movie_info[1])) # permet d'actualiser la variable catégories global au niveau local
- # Check if user_preferences is not empty and has the same length as categories
- if len(user_preferences) != len(categories) or not user_preferences:
- print("Error: Invalid user preferences")
- return []
+ user_id = int(user_id) # Convertir user_id en entier
- for i in range(len(categories)):
- user_vector.append(sum(category_matrix[i][j] * user_preferences[j] for j in range(len(categories))))
+ suggestions = {}
+ category_index = {}
+
+ # Créer le dictionnaire pour stocker les indices des catégories
+ category_index = {category: i + 1 for i, category in enumerate(categories)}
+ for show_id, categories in catalog.items():
+ # Check if the user has rated the show
+ if show_id in user_ratings and user_id in user_ratings[show_id] and user_ratings[show_id][user_id] == 0:
+ # Liste des catégories communes entre le film/série et les films/séries notés par l'utilisateur
+ common_categories = [category for category in categories[1] if category in catalog[show_id][1]]
+ if common_categories:
+ # Calculez la similarité entre le film/série et les films/séries notés par l'utilisateur
+ similarity = sum(
+ min(category_matrix[category_index[category]][category_index[user_category]] for user_category in common_categories)
+ for category in categories[1]
+ )
+
+ # Ne recommandez que des films/séries dont la similarité dépasse le seuil spécifié
+ if similarity > threshold:
+ suggestions[show_id] = {'title': catalog[show_id][0], 'similarity': similarity}
+
+ # Triez les suggestions par similarité décroissante
+ sorted_suggestions = sorted(suggestions.items(), key=lambda x: x[1]['similarity'], reverse=True)
+
+ return sorted_suggestions[:5]
+
+def recommandation_algorithm() :
+
+ # Replace file_path_1 and file_path_2 with the actual file paths
+ file_path_1 = "/Users/adrien/vscodeworkspace/coding-project/projet_en_groupe/data_cp_2023/netflix_titles-2.csv"
+ file_path_2 = "/Users/adrien/vscodeworkspace/coding-project/projet_en_groupe/data_cp_2023/ratings.csv"
+
+ user_id = input("quel est ton user ? ")
+
+ try:
+ user_id = int(user_id)
+ except ValueError:
+ print("Veuillez entrer un identifiant d'utilisateur valide.")
+ exit()
- return user_vector
+ # Read data from CSV files
+ catalog = read_movie_series_info(file_path_1)
+ ratings = read_user_ratings(file_path_2)
+ # Create category matrix
+ categories = list(set(category for _, movie_info in catalog.items() for category in movie_info[1]))
+ category_matrix = create_category_matrix(catalog, categories)
-def recommend_movies(catalog, ratings, category_matrix, user_preferences, categories):
- recommended_movies = []
+ # Display movies already viewed by the user
+ print("Films déjà vus par l'utilisateur:")
+ for show_id, user_rating in ratings.items():
+ if user_id in user_rating and user_rating[user_id] > 0:
+ print(f"- {catalog[show_id][0]}")
- for show_id, (title, movie_categories) in catalog.items():
- if show_id not in ratings:
- movie_score = sum(category_matrix[i][j] * user_preferences[j] for i, j in enumerate(categories) if categories[i] in movie_categories[1])
- recommended_movies.append((title, movie_score))
+ # Recommend movies
+ recommended_movies = recommend_movies(user_id, catalog, ratings, category_matrix, threshold=0.5)
- recommended_movies.sort(key=lambda x: x[1], reverse=True)
- return recommended_movies[:5]
+ # Display top 5 recommendations
+ print("\nTop 5 recommandations:")
+ for show_id, info in recommended_movies:
+ print(f"Title: {info['title']}, Similarity: {info['similarity']}")
# Création du menu
@@ -618,55 +647,8 @@ def action() :
directors_nationality(data_1)
elif command == "17" :
basic_statistics(data_1)
- elif command == "test" :
- # Read data from CSV files
- catalog = read_movie_series_info(file_path_1)
- ratings, user_ids = read_user_ratings(file_path_2)
-
- transposed_ratings = {user_id: {} for user_id in user_ids}
- for show_id, user_ratings in ratings.items():
- for i, user_id in enumerate(user_ids):
- transposed_ratings[user_id][show_id] = user_ratings[i]
-
- print("User IDs in ratings:", transposed_ratings.keys())
- # Check if the user ID exists in the ratings dictionary
- user_id_to_recommend = input("Enter your user ID: ")
- user_id_to_recommend = str(user_id_to_recommend)
-
- # Check if the user ID exists in the ratings dictionary
- if user_id_to_recommend not in transposed_ratings:
- print(f"User with ID '{user_id_to_recommend}' not found in ratings.")
- else:
- # Get categories that exist in both catalog and user ratings
- unique_types = file_path_1['listed_in'].unique()
-
- print("Common Categories:", unique_types)
-
- # Create category matrix
- categories = list(common_categories)
- print("Categories:", categories)
-
- category_matrix = create_category_matrix(catalog, transposed_ratings, categories)
-
-
- # Use user ratings as preferences
- user_preferences = [transposed_ratings[user_id_to_recommend][category] for category in categories]
- print("User Preferences:", user_preferences)
-
- # Calculate user preferences
- user_vector = calculate_user_preferences(category_matrix, user_preferences, categories)
-
- # Recommend movies
- recommended_movies = recommend_movies(catalog, transposed_ratings, category_matrix, user_vector, categories)
-
- # Display top 5 recommendations
- print(recommended_movies)
-
elif command == "18" :
- user_id_to_recommend = input("Enter your user ID: ")
- # Assuming 'catalog', 'ratings', 'category_matrix', 'categories' are available from your data loading
- recommended_movies = recommend_movies(catalog, ratings, category_matrix, user_preferences, categories)
- print(recommended_movies)
+ recommandation_algorithm()
elif command == "..." :
return False
diff --git a/projet_en_groupe/recom_sys.py b/projet_en_groupe/recom_sys.py
index f61d2a2d742f4a0f599285328ba22d2b3bb9edf4..28a982b399fcdad34ea2a053e59b729c669b1c82 100644
--- a/projet_en_groupe/recom_sys.py
+++ b/projet_en_groupe/recom_sys.py
@@ -56,6 +56,7 @@ def recommend_movies(user_id, catalog, user_ratings, category_matrix, threshold=
# Créer le dictionnaire pour stocker les indices des catégories
category_index = {category: i + 1 for i, category in enumerate(categories)}
+ print(category_index)
for show_id, categories in catalog.items():
# Check if the user has rated the show
@@ -100,10 +101,10 @@ if __name__ == "__main__":
category_matrix = create_category_matrix(catalog, categories)
# Display movies already viewed by the user
- print("Films déjà vus par l'utilisateur:")
+ """print("Films déjà vus par l'utilisateur:")
for show_id, user_rating in ratings.items():
if user_id in user_rating and user_rating[user_id] > 0:
- print(f"- {catalog[show_id][0]}")
+ print(f"- {catalog[show_id][0]}")"""
# Recommend movies
recommended_movies = recommend_movies(user_id, catalog, ratings, category_matrix, threshold=0.5)