diff --git a/.DS_Store b/.DS_Store
index 61d4d58717b48b98fb5d3fe59cafce93e0a06cb7..450fa5260957417979a4fceeb7accfaa24bedc19 100644
Binary files a/.DS_Store and b/.DS_Store differ
diff --git a/projet_en_groupe/.DS_Store b/projet_en_groupe/.DS_Store
index 48795fe3866d137a4ccd4936b41dfc63713555ee..72b0ce1e438fdd2638258e185d10e0b3b8b707a5 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 051bb9a30c73ed94cd7160fad72a13385e36fb56..e395b93b34a3066ab724df54c00782b586eefb09 100644
--- a/projet_en_groupe/algorithme_netflix.py
+++ b/projet_en_groupe/algorithme_netflix.py
@@ -4,28 +4,6 @@ import pandas as pd
import tabulate
import os
-# allow us to display maximum things
-#pd.set_option('display.max_rows', None)
-
-"""file_path_1 = "/content/drive/MyDrive/Coding_project_2023/netflix_titles-2.csv
-
-
-data_1 = pd.read_csv(file_path_1)"""
-
-#display(data_1)
-
-"""from google.colab import drive
-drive.mount('/content/drive')"""
-
-
-
-# afficher le second document
-
-
-"""file_path_2 = "/content/drive/MyDrive/Coding_project_2023/ratings.csv
-
-data_2 = pd.read_csv(file_path_2)"""
-
#display(data_2)
@@ -354,6 +332,7 @@ def parental_code(data_1):
print("Here are the parental codes: ")
print(code_list)
save_to_csv(code_list)
+ return
@@ -386,6 +365,7 @@ def directors_nationality(data_1):
for director, info in sorted_directors:
print(f"{director}: {', '.join(info['nationalities'])} - {info['count']} movies/series")
save_to_csv(sorted_directors)
+ return
@@ -490,6 +470,93 @@ 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}
+
+ # 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 recommend_movies(user_ratings, category_matrix, unique_categories, num_recommendations=5):
+ # Calculate the weighted sum of category matrix based on user ratings
+ weighted_sum = {category: 0 for category in unique_categories}
+ for category, rating in user_ratings.items():
+ if category != 'title':
+ for other_category in unique_categories:
+ weighted_sum[other_category] += rating * category_matrix[category][other_category]
+
+ # Find top N categories
+ top_categories = sorted(weighted_sum, key=weighted_sum.get, reverse=True)[:num_recommendations]
+
+ # Find movies in top categories not rated by the user
+ recommended_movies = []
+ for category in top_categories:
+ for i, row in user_ratings.iterrows():
+ if row['title'] not in user_ratings['title'] and category in row.values:
+ recommended_movies.append(row['title'])
+
+ return recommended_movies[:num_recommendations]
+
+
+def print_user_matrix(data_1, data_2, user_id_to_recommend, category_matrix=None, num_recommendations=5):
+ # Load the category matrix if not provided
+ if category_matrix is None:
+ category_matrix = print_matrix(data_1)
+
+ linked_base = pd.merge(data_1, data_2, on='show_id')
+
+ data_of_users = data_2.drop(['show_id', 'appreciation (%)'], axis=1)
+ titles = linked_base['title']
+ data_of_users.insert(0, 'title', titles)
+
+ # Pivot the DataFrame
+ user_item_matrix = data_of_users.set_index('title').transpose()
+
+ unique_categories = set(category for categories in data_1['listed_in'].str.split(', ') for category in categories)
+
+ # Get user ID from the user_id_to_recommend variable
+ user_id = linked_base.loc[linked_base['user_id'] == user_id_to_recommend, 'show_id'].values[0]
+
+ # Get user ratings
+ user_ratings = data_of_users.loc[user_id]
+
+ # Recommend movies for the specified user
+ recommendations = recommend_movies(user_ratings, category_matrix, unique_categories, num_recommendations)
+
+ print(f"Top {num_recommendations} recommendations for user {user_id_to_recommend}:")
+ for movie_title in recommendations:
+ print(movie_title)
+
+ # Save the transposed user-item matrix to an Excel file
+ user_item_matrix.to_excel("user_item_matrix.xlsx", index_label='user_id')
+
+ print("Transposed User-item matrix saved to user_item_matrix.xlsx")
+ return
+
+
+
+
+
+
+
# Création du menu
def action() :
@@ -548,6 +615,11 @@ def action() :
directors_nationality(data_1)
elif command == "17" :
basic_statistics(data_1)
+ elif command == "A" :
+ print_matrix(data_1)
+ elif command == "B" :
+ user_id_to_recommend = str(input("Quel utilisateur es-tu ? "))
+ print_user_matrix(data_1,data_2, user_id_to_recommend)
elif command == "..." :
return False
diff --git a/projet_en_groupe/category_matrix.xlsx b/projet_en_groupe/category_matrix.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..0e3828c53cc2b42adbbe085683e1bfd2a8a16f4c
Binary files /dev/null and b/projet_en_groupe/category_matrix.xlsx differ
diff --git a/projet_en_groupe/excel_filename.xlsx b/projet_en_groupe/excel_filename.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..56a3d8fa3d278a792946f2b9932f6fc7e9b9a832
Binary files /dev/null and b/projet_en_groupe/excel_filename.xlsx differ
diff --git a/projet_en_groupe/~$excel_filename.xlsx b/projet_en_groupe/~$excel_filename.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..d10daf560a7f8247050905285b3e618c244966d6
Binary files /dev/null and b/projet_en_groupe/~$excel_filename.xlsx differ