dernier tp

interface.py

@@ -0,0 +1,105 @@
+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, actor_ids):
+    closest_name = None
+    closest_id = None
+    min_distance = float('inf')
+    for i in range(len(actor_names)):
+        actor_name = actor_names[i]
+        actor_id = actor_ids[i]
+        distance = levenshtein_distance(input_name, actor_name)
+        if distance < min_distance:
+            min_distance = distance
+            closest_name = actor_name
+            closest_id = actor_id
+    return (closest_name,closest_id)
+
+def getUniqueActorNames(filePath):
+    # Lire le fichier TSV
+    df = pd.read_csv(filePath, sep='\t')
+    actor_names = df['primaryName'].tolist()
+    actor_ids = df['nconst'].tolist()  # Supposer que la colonne s'appelle 'ActorName'
+  # Supposer que la colonne s'appelle 'ActorName'
+    return (actor_names,actor_ids)
+
+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']])
+
+
+if __name__ == "__main__":
+    mustContinue = True
+    if not os.path.exists("processedData/uniqueActorNames.tsv"):
+        saveUniqueActorsSorted("processedData/actorsRatingsGroupedWithName.tsv", "processedData/uniqueActorNames.tsv")
+    tupleActors = 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")
+        userChoice = input("Votre choix: ")
+        if(userChoice == "1"):
+            actorName = input("Quel acteur voulez-vous chercher ? ")
+            actorFound = find_closest_actor_name(actorName, tupleActors[0], tupleActors[1])
+            print("L'acteur/actrice trouvé est: " + actorFound)
+            sublevelMustContinue = True
+            leave = False
+            correctActorChoice = input("Est-ce le bon acteur/actrice ? (o = oui, n = non)")
+            if(correctActorChoice == "n"):
+                while(sublevelMustContinue):
+                    leave = input("Sortir ou relancer ? (sortir = s, relancer = r)")
+                    if(leave == "r"):
+                        actorName = input("Quel acteur voulez-vous chercher ? ")
+                        actorFound = find_closest_actor_name(actorName, tupleActors[0], tupleActors[1])
+                        print("L'acteur/actrice trouvé est: " + actorFound)
+                        sublevelMustContinue = True
+                        correctActorChoice = input("Est-ce le bon acteur/actrice ? (o = oui, n = non)")
+                        if(correctActorChoice == o):
+                            sublevelMustContinue = False
+                    else if(leave != "r" or (leave != "s" and leave ))
+
+
+            
+print(find_closest_actor_name("Robert downey jr",tupleActors[0],tupleActors[1]))