diff --git a/.DS_Store b/.DS_Store
index 8cdf8e4b7ca3b1bf1dcfe086c4c07c192600439a..156ca34711eaf46fe3192a05010af95e03ebcf38 100644
Binary files a/.DS_Store and b/.DS_Store differ
diff --git a/Data_Base.xlsx b/Data_Base.xlsx
index 73faea6556dd7a214ee3b831aca8b026044880f3..03aeda0b44da3c8f933e563c8d2f81b30e256c49 100644
Binary files a/Data_Base.xlsx and b/Data_Base.xlsx differ
diff --git a/projet_en_groupe/.DS_Store b/projet_en_groupe/.DS_Store
index 7497e4708f6e1681ff033c1a5e38ccb73901f431..d61b1e5fc16293879ed2e29cb960a6608b268bef 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 9947d8006408bf87ba09dd14c9a6bf606ad66a01..5e801f301cdac3b039799693cd0cdc7a3de9f84c 100644
--- a/projet_en_groupe/algorithme_netflix.py
+++ b/projet_en_groupe/algorithme_netflix.py
@@ -23,20 +23,15 @@ def catalog(data_1):
print(data_1.head(100))
save_to_csv(data_1)
+ return
# Be careful, you need to ask each time if they want to save the list to a .csv
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
-
- movie_df = pd.DataFrame({'Movie Titles': movie_titles})
-
- # afficher que les 100 premiers
-
- print(movie_df) # Display movie titles
- save_to_csv(movie_df)
+ print(films) # Display movie titles
+ save_to_csv(films)
return # Be careful, you need to ask each time if they want to save the list to a .csv
@@ -44,13 +39,10 @@ def movies(data_1): # register
def series(data_1):
series = data_1[data_1['type'] == 'TV Show'] # Filter the data to include only series
- series_titles = series['title'].tolist() # Extract series titles
-
- series_df = pd.DataFrame({'Movie Titles': series_titles})
- print(series_df) # Display series titles
+ print(series) # Display series titles
- save_to_csv(series_df)
+ save_to_csv(series)
return # Be careful, you need to ask each time if they want to save the list to a .csv
@@ -172,37 +164,42 @@ def genre(data_1):
def duration(data_1):
+ # Filtrer par type de média
filtered_data = filter_media_type(data_1)
+ # Obtenir la liste de tous les genres possibles
genre_list = []
for genres in data_1['listed_in'].dropna().str.split(', '):
for genre in genres:
if genre not in genre_list and genre != '':
genre_list.append(genre)
+ # Afficher la liste des genres possibles
print("List of all possible genres:")
genre_list.sort()
print(genre_list)
+ # Demander à l'utilisateur de saisir le genre
while True:
type_input = input("Enter the type (romantic, action, drama, etc.) to display movies and/or series: ")
- # Use FuzzyWuzzy to find the closest match
+ # Utiliser FuzzyWuzzy pour trouver la correspondance la plus proche
matches = process.extractOne(type_input, genre_list)
- if matches[1] >= 80: # Adjust the similarity threshold as needed
+ if matches[1] >= 80: # Ajuster le seuil de similarité si nécessaire
type_input = matches[0]
break
else:
closest_match = matches[0]
print(f"Invalid genre. The closest match is: {closest_match}")
- # Check if the entered genre is correct
+ # Vérifier si le genre saisi est correct
if type_input in genre_list:
print(f"You selected: {type_input}")
else:
print(f"You entered: {type_input}, which is not in the list.")
+ # Demander le type de tri
print("What type of sorting do you want? ")
print("1. Ascending")
print("2. Descending")
@@ -215,20 +212,22 @@ def duration(data_1):
else:
print("Invalid sort order. Please enter 1 for ascending or 2 for descending.")
- type_data = filtered_data[filtered_data['listed_in'].str.lower().str.contains(type_input.lower(), case=False, na=False)]
+ # Filtrer les données en fonction du genre saisi
+ type_data = filtered_data[filtered_data['listed_in'].str.lower().str.contains(type_input.lower(), case=False, na=False)].copy()
if not type_data.empty:
print(f"\nDisplaying data for {type_input} sorted in {'ascending' if sort_order == '1' else 'descending'} order:")
-
- type_data.loc[:, 'duration'] = type_data['duration'].str.extract('(\\d+)').astype(int)
- if sort_order == '1':
- type_data_sorted = type_data.sort_values(by=['type', 'duration'], ascending=[True, True])
- elif sort_order == '2':
- type_data_sorted = type_data.sort_values(by=['type', 'duration'], ascending=[True, False])
-
+ # Extraire les valeurs numériques de la colonne 'duration'
+ type_data['duration'] = type_data['duration'].str.extract('(\\d+)').astype(float)
+
+ # Trier les données en fonction du type et de la durée
+ type_data_sorted = type_data.sort_values(by=['type', 'duration'], ascending=[True, sort_order == '1'])
+
+ # Convertir les valeurs de durée en texte formaté
type_data_sorted['duration'] = type_data_sorted.apply(
- lambda row: f"{row['duration']} min" if row['type'].lower() == 'movie' else f"{row['duration']} Season", axis=1
+ lambda row: f"{int(row['duration'])} min" if row['type'].lower() == 'movie' else f"{int(row['duration'])} Season",
+ axis=1
)
print(type_data_sorted)
@@ -273,14 +272,32 @@ def director(data_1):
else:
print(f"You entered: {director_input}, which is not in the list.")
+ # Menu for sorting order
+ while True:
+ print("Select sorting order:")
+ print("1. Ascending")
+ print("2. Descending")
+ sort_order_input = input("Enter the number of your choice: ")
+
+ if sort_order_input == '1':
+ sort_order_bool = True
+ break
+ elif sort_order_input == '2':
+ sort_order_bool = False
+ break
+ else:
+ print("Invalid input. Please enter '1' for Ascending or '2' for Descending.")
+
+ order_text = 'ascending' if sort_order_bool else 'descending'
+
director_data = filtered_data[filtered_data['director'].str.lower().str.contains(director_input.lower(), case=False, na=False)]
if not director_data.empty:
- print(f"\nDisplaying data for movies and/or series directed by {director_input} sorted by release year in ascending order:")
+ print(f"\nDisplaying data for movies and/or series directed by {director_input} sorted by release year in {order_text} order:")
- director_data_sorted = director_data.sort_values(by='release_year', ascending=True)
+ director_data_sorted = director_data.sort_values(by='release_year', ascending=sort_order_bool)
print(director_data_sorted)
- save_to_csv(director_data_sorted)
+ save_to_csv(director_data_sorted) # Uncomment this line if you want to save to CSV
else:
print(f"No person found with the name {director_input}.")
@@ -560,6 +577,7 @@ def most_rated_recent(data_1, data_2):
def parental_code(data_1):
valid_codes = set(['PG-13', 'TV-MA', 'PG', 'TV-14', 'TV-PG', 'TV-Y', 'TV-Y7', 'R', 'TV-G', 'G', 'NC-17', 'NR', 'TV-Y7-FV', 'UR'])
+ # there is a problem in the csv (values ​​which should not be there). So we sorted
# Filter out entries that are not valid parental codes
filtered_data = data_1[data_1['rating'].isin(valid_codes)]
@@ -650,8 +668,6 @@ def filter_media_type(data):
print("Invalid choice. Please enter a valid number.")
-
-
# Example usage
def basic_statistics(data_1):
# Check if the 'type' and 'country' columns exist in the dataset
@@ -872,7 +888,7 @@ def action() :
print("Here are the different options available:")
print("1. View the entire catalog")
print("2. View all movies in the catalog")
- print("3. View all series")
+ print("3. View all series in the catalog")
print("4. View all series, movies or both by year")
print("5. View all series, movies or both by country")
print("6. View all series, movies or both by type")
@@ -927,7 +943,7 @@ def action() :
basic_statistics(data_1)
elif command == "18" :
recommandation_algorithm()
- elif command == "STOP" :
+ elif command.upper() == "STOP" :
return False
diff --git a/projet_personnel/algorithme_gestion_etudiants.py b/projet_personnel/algorithme_gestion_etudiants.py
index 03b03100f5ba0a0d8367f733fa3a60acd12de098..208ace9e1804a8fd1c0a0b0c3c13620083429790 100644
--- a/projet_personnel/algorithme_gestion_etudiants.py
+++ b/projet_personnel/algorithme_gestion_etudiants.py
@@ -19,7 +19,7 @@ all_course_MA2 = ("Advanced English 2", "Español avanzado 1", "Responsabilité
-file_path = '/coding-project/Data_Base.xlsx'
+file_path = '/Users/adrien/vscodeworkspace/coding-project/Data_Base.xlsx'
data = pd.read_excel(file_path)
excel_file_path = 'export_names.xlsx'