You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
115 lines
4.0 KiB
115 lines
4.0 KiB
import csv
|
|
import os
|
|
from typing import List
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
def levenshtein_distance(s1, s2):
|
|
if len(s1) < len(s2):
|
|
return levenshtein_distance(s2, s1)
|
|
|
|
if len(s2) == 0:
|
|
return len(s1)
|
|
|
|
previous_row = range(len(s2) + 1)
|
|
for i, c1 in enumerate(s1):
|
|
current_row = [i + 1]
|
|
for j, c2 in enumerate(s2):
|
|
insertions = previous_row[j + 1] + 1
|
|
deletions = current_row[j] + 1
|
|
substitutions = previous_row[j] + (c1 != c2)
|
|
current_row.append(min(insertions, deletions, substitutions))
|
|
previous_row = current_row
|
|
|
|
return previous_row[-1]
|
|
|
|
def find_closest_actor_name(input_name, actor_names):
|
|
closest_name = None
|
|
min_distance = float('inf')
|
|
for i in range(len(actor_names)):
|
|
actor_name = actor_names[i]
|
|
distance = levenshtein_distance(input_name, actor_name)
|
|
if distance < min_distance:
|
|
min_distance = distance
|
|
closest_name = actor_name
|
|
return (closest_name)
|
|
|
|
def getUniqueActorNames(filePath):
|
|
# Lire le fichier TSV
|
|
df = pd.read_csv(filePath, sep='\t')
|
|
actor_names = df['primaryName'].tolist()
|
|
return (actor_names)
|
|
|
|
def saveUniqueActorsSorted(inputFilePath, outputFilePath):
|
|
# Lire le fichier TSV
|
|
df = pd.read_csv(inputFilePath, sep='\t')
|
|
|
|
# Trier le DataFrame par 'primaryName' en ordre alphabétique
|
|
df_sorted = df.sort_values(by='primaryName')
|
|
|
|
# Écrire les données triées dans le fichier CSV
|
|
with open(outputFilePath, mode='w', newline='', encoding='utf-8') as file:
|
|
writer = csv.writer(file, delimiter='\t')
|
|
|
|
# Écrire l'en-tête
|
|
writer.writerow(['primaryName', 'nconst'])
|
|
|
|
# Écrire chaque ligne du DataFrame trié dans le fichier CSV
|
|
for index, row in df_sorted.iterrows():
|
|
writer.writerow([row['primaryName'], row['nconst']])
|
|
|
|
|
|
def ask_user_verification(actor_name):
|
|
response = input(f"Est-ce que vous vouliez dire {actor_name}? (Oui/Non) ")
|
|
return response.lower() in ['oui', 'o', 'yes', 'y']
|
|
|
|
def add_actor(actor_names):
|
|
user_input = input("Entrez le nom de l'acteur à ajouter : ")
|
|
closest_name = find_closest_actor_name(user_input, actor_names)
|
|
if ask_user_verification(closest_name):
|
|
return closest_name
|
|
else:
|
|
user_choice = input("Voulez-vous réessayer avec un autre nom? (Oui/Non) ")
|
|
if user_choice.lower() in ['oui', 'o', 'yes', 'y']:
|
|
return add_actor(actor_names)
|
|
else:
|
|
return None
|
|
|
|
if __name__ == "__main__":
|
|
mustContinue = True
|
|
if not os.path.exists("processedData/uniqueActorNames.tsv"):
|
|
saveUniqueActorsSorted("processedData/actorsRatingsGroupedWithName.tsv", "processedData/uniqueActorNames.tsv")
|
|
actor_names = getUniqueActorNames("processedData/uniqueActorNames.tsv")
|
|
selectedActorNames = []
|
|
|
|
print("Bienvenue dans MoviePrecog!")
|
|
while mustContinue:
|
|
print("1: Ajouter un acteur à la liste (4 acteurs / actrices requis)")
|
|
print("2: Afficher la liste")
|
|
print("3: Vider la liste")
|
|
print("4: Lancer la prévision")
|
|
print("5: Quitter")
|
|
|
|
choice = input("Faites votre choix : ")
|
|
|
|
if choice == '1':
|
|
result = add_actor(actor_names)
|
|
if result:
|
|
selectedActorNames.append(result[0])
|
|
print(f"{result[0]} a été ajouté à la liste.")
|
|
elif choice == '2':
|
|
print("Liste des acteurs sélectionnés :")
|
|
for actor in selectedActorNames:
|
|
print(actor)
|
|
elif choice == '3':
|
|
selectedActorNames.clear()
|
|
print("La liste a été vidée.")
|
|
elif choice == '4':
|
|
# TODO: Implémenter la comparaison
|
|
print("Lancement de la prévision... (TODO)")
|
|
elif choice == '5':
|
|
print("Au revoir !")
|
|
mustContinue = False
|
|
else:
|
|
print("Choix non valide, veuillez réessayer.")
|