🔨 modif path des fichiers dans le script

getRatingsActeur.py

@@ -26,26 +26,26 @@ def data_manipulation(DataIsLoaded = None):
     # Démarre le thread de suivi du temps
     timer_thread.start()
 
-    names = pd.read_csv("name.basics.tsv", sep="\t")
+    names = pd.read_csv("baseData/name.basics.tsv", sep="\t")
 
     # filter by actor / actress 
     # ------------------------------------------------------------------ #
     if DataIsLoaded is not None:
-        df = pd.read_csv("title.principals.tsv", sep="\t")
+        df = pd.read_csv("baseData/title.principals.tsv", sep="\t")
         actors = df.loc[(df.category == 'actor') | (df.category =='actress')]
-        actors.to_csv("actors.tsv", sep="\t", index=False)  # outputs actors.tsv
+        actors.to_csv("processedData/actors.tsv", sep="\t", index=False)  # outputs actors.tsv
         # ------------------------------------------------------------------ #
 
         # merges actors and movies to have each actor that played in a movie
         # ------------------------------------------------------------------ #
-        actors = pd.read_csv("actors.tsv", sep="\t")
-        ratings = pd.read_csv("title.ratings.tsv", sep="\t")
+        actors = pd.read_csv("processedData/actors.tsv", sep="\t")
+        ratings = pd.read_csv("baseData/title.ratings.tsv", sep="\t")
     
         actorsRatings = actors.merge(ratings, left_on="tconst", right_on="tconst", how="inner")
-        actorsRatings.to_csv("actorsRatings.tsv", sep="\t", index=False) # outputs actorsRatings.tsv
+        actorsRatings.to_csv("processedData/actorsRatings.tsv", sep="\t", index=False) # outputs actorsRatings.tsv
 
     else:
-        actorsRatings = pd.read_csv("actorsRatings.tsv", sep="\t")
+        actorsRatings = pd.read_csv("processedData/actorsRatings.tsv", sep="\t")
 
     # ------------------------------------------------------------------ #
 
@@ -64,16 +64,16 @@ def data_manipulation(DataIsLoaded = None):
 
     if DataIsLoaded is not None:
         # Enregistrer dans un fichier CSV avec les noms de colonnes personnalisés
-        grouped.to_csv("actorsRatingsGrouped.tsv", index=False, sep="\t") # outputs actorsRatingsGrouped.tsv
+        grouped.to_csv("processedData/actorsRatingsGrouped.tsv", index=False, sep="\t") # outputs actorsRatingsGrouped.tsv
     # ------------------------------------------------------------------ #
 
-    # merges the last file with the names of the actors
+    # merges the last file with the names of the actors getRatingsActeur.py
     # ------------------------------------------------------------------ #
     actorNames = names[['nconst','primaryName']]
     groupedWithActorNames = grouped.merge(actorNames, left_on="nconst", right_on="nconst", how="inner")
 
     if DataIsLoaded is not None:
-        groupedWithActorNames.to_csv("actorsRatingsGroupedWithName.tsv", index=True, sep="\t") # outputs actorsRatingsGroupedWithName.tsv
+        groupedWithActorNames.to_csv("processedData/actorsRatingsGroupedWithName.tsv", index=True, sep="\t") # outputs actorsRatingsGroupedWithName.tsv
     # ------------------------------------------------------------------ #
 
     # Joindre les deux DataFrames sur 'nconst' pour associer chaque 'tconst' avec les 'averageRating'
@@ -94,7 +94,7 @@ def data_manipulation(DataIsLoaded = None):
         'averageRatingMovie': grouped['averageRating']  # Ajoute 'averageRating' comme 'averageRatingMovie'
     })
 
-    actorsRatingsPerMovie.to_csv("actorsRatingsPerMovie.tsv", index=False, sep="\t")
+    actorsRatingsPerMovie.to_csv("processedData/actorsRatingsPerMovie.tsv", index=False, sep="\t")
 
     
 
@@ -102,7 +102,8 @@ def data_manipulation(DataIsLoaded = None):
     # actorsRatingsPerMovie.to_csv("actorsRatingsPerMovie.tsv", index=False, sep="\t")
 
 # Fonction principale pour exécuter à la fois le timer et la manipulation de données
-if __name__ == "__main__":     # Crée un thread pour suivre le temps
+if __name__ == "__main__":     
+    # Crée un thread pour suivre le temps
     timer_thread = threading.Thread(target=time_tracker)
 
     # Démarre le thread de suivi du temps