From 0373460105a6ec18047c4cb2a326549c14d1bf8b Mon Sep 17 00:00:00 2001
From: GassiGiuseppe <g.gassi@studenti.poliba.it>
Date: Mon, 6 Oct 2025 10:57:50 +0200
Subject: [PATCH] Movie filters updated

---
 Scripts/DataCleaning/pipeline/movie_filter.py | 39 +++++++++++++++++++
 Scripts/DataCleaning/pipeline/pipeline.py     |  7 ++--
 2 files changed, 43 insertions(+), 3 deletions(-)

diff --git a/Scripts/DataCleaning/pipeline/movie_filter.py b/Scripts/DataCleaning/pipeline/movie_filter.py
index a65b360..14e679c 100644
--- a/Scripts/DataCleaning/pipeline/movie_filter.py
+++ b/Scripts/DataCleaning/pipeline/movie_filter.py
@@ -45,5 +45,44 @@ class MovieFilter:
         self.MOVIE_FILTER = self.sql_endpoint.get_dataframe_from_query(filter_query, params)
 
 
+    def filter_by_director(self):
+        director_list = ['dbp-dbo:director','dbp-dbp:director']
+
+        movie_ids = self.MOVIE_FILTER["MovieID"].to_list()
+        movie_list_placeholder = ",".join(["?"] * len(movie_ids))
+
+        filter_query = f"""
+            SELECT DISTINCT RDFs.MovieID
+            FROM RDFs
+            JOIN ParsedRelationships USING (RelationshipID)
+            WHERE RDFs.MovieID IN ({movie_list_placeholder})
+            AND ParsedRelationships.RelationshipURI IN {tuple(director_list)};
+        """
+
+        params = tuple(movie_ids)
+        self.MOVIE_FILTER = self.sql_endpoint.get_dataframe_from_query(filter_query, params)
+
+
+    def filter_by_english_movies(self):
+        movie_ids = self.MOVIE_FILTER["MovieID"].to_list()
+        movie_list_placeholder = ",".join(["?"] * len(movie_ids))
+
+        relationship = ["<PRED>dbp-dbp:language"]
+        objects_list = ["<OBJ>English", "<OBJ>dbp-dbr:English_language"]
+
+        filter_query = f"""
+            SELECT DISTINCT RDFs.MovieID
+            FROM RDFs
+            INNER JOIN ParsedRelationships USING (RelationshipID)
+            INNER JOIN ParsedObjects USING (ObjectID)
+            WHERE RDFs.MovieID IN ({movie_list_placeholder})
+            AND ParsedRelationships.RelationshipURI IN {tuple(relationship)}
+            AND ParsedObjects.ObjectURI in {tuple(objects_list)};
+        """
+        params = tuple(movie_ids)
+        self.MOVIE_FILTER = self.sql_endpoint.get_dataframe_from_query(filter_query, params)
+
+        
+
 # movie_filter = MovieFilter()
 # movie_filter.frequency_filter(5,10)
\ No newline at end of file
diff --git a/Scripts/DataCleaning/pipeline/pipeline.py b/Scripts/DataCleaning/pipeline/pipeline.py
index 42c3aad..44c9a94 100644
--- a/Scripts/DataCleaning/pipeline/pipeline.py
+++ b/Scripts/DataCleaning/pipeline/pipeline.py
@@ -40,7 +40,8 @@ class Pipeline():
 
     def other_filter(self):
         self._movie_filter.relation_filter("purl:dc/terms/subject",5,100)
-        self._movie_filter.relation_filter("dbp-dbo:director",1,100)
+        self._movie_filter.filter_by_director()
+        # self._movie_filter.relation_filter("dbp-dbo:director",1,100)
 
     def _get_cleaned_movie_rows(self):
         movie_ids = self._movie_filter.get_movie_id()
@@ -110,7 +111,7 @@ class Pipeline():
         # Django Unchained  : 138952
         # Spirited Away     : 144137
         # Knives Out        : 148025
-        movie_list = [117248, 147074, 113621, 1123, 117586, 90177, 71587, 138952, 144137, 148025]
+        movie_list = [106465,106466,106467,106468,106469,106470,106471,106472,106473]#[117248, 147074, 113621, 1123, 117586, 90177, 71587, 138952, 144137, 148025]
         self._movie_filter.MOVIE_FILTER = pd.DataFrame({"MovieID": movie_list})
 
     def generate_csv_debug_file(self, debug_path:str):
@@ -123,7 +124,7 @@ class Pipeline():
 
 
 pipe = Pipeline()
-pipe.use_toy_dataset()
+# pipe.use_toy_dataset()
 pipe.other_filter()
 # pipe.execute_all_task()
 pipe.generate_csv_debug_file("Assets/Dataset/Tmp/debug.csv")
\ No newline at end of file