WIP abbrevietion_datawarehouse to creat an abbreviation system

Scripts/DataCleaning/abbrevietion_datawarehouse.py

@@ -0,0 +1,105 @@
+import sqlite3
+import csv
+import pandas as pd
+
+DB_NAME = "./Assets/Dataset/DatawareHouse/dataset.db"
+CSV_MAPPER = "./Assets/Dataset/1-hop/uri-abbreviations.csv"
+# MAPPER_HANDLER = open(CSV_MAPPER,"r",newline='', encoding="utf-8")
+mapper = pd.read_csv(CSV_MAPPER)
+mapper_key_list = mapper["uri"].to_list()
+mapper_value_list = mapper["abbreviation"].to_list()
+
+CONN = sqlite3.connect(DB_NAME)
+CURS = CONN.cursor()
+
+def insert_abbreviation(uri, abbreviation) -> bool:
+    QUERY = "INSERT INTO Abbreviations(URI, Abbreviation) VALUES (?,?);"
+    try:
+        CURS.execute(QUERY,[uri, abbreviation])
+        return True
+    except sqlite3.IntegrityError:
+        return False
+    
+def inserto_object_abbreviation(object_id, abbreviation_id) -> bool:
+    QUERY = "INSERT INTO Objects_Abbreviations(ObjectID, AbrreviationID) VALUES (?,?);"
+    try:
+        CURS.execute(QUERY,[object_id, abbreviation_id])
+        return True
+    except sqlite3.IntegrityError:
+        return False
+    
+def insert_relationship_abbreviation(relationship_id, abbreviation_id) -> bool:
+    QUERY = "INSERT INTO Relationships_Abbreviations(RelationshipID, AbbreviationID) VALUES (?,?);"
+    try:
+        CURS.execute(QUERY,[relationship_id, abbreviation_id])
+        return True
+    except sqlite3.IntegrityError:
+        return False
+    
+def insert_subject_abbreviation(subject_id, abbreviation_id) -> bool:
+    QUERY = "INSERT INTO Subjects_Abbreviations(SubjectID, AbbreviationID) VALUES (?,?);"
+    try:
+        CURS.execute(QUERY,[subject_id, abbreviation_id])
+        return True
+    except sqlite3.IntegrityError:
+        return False
+    
+def select_abbreviation_id(uri) -> int | None:
+    QUERY = "SELECT AbbreviationID FROM Abbreviations WHERE URI LIKE ?;"
+    CURS.execute(QUERY, [uri])
+    abbreviation_id = CURS.fetchone()
+    if not abbreviation_id:
+        return None
+    
+    # in this case the real id is the first element of the tuple
+    return abbreviation_id[0]
+
+def parser(element: pd.DataFrame):
+    # df.replace(['Boston Celtics', 'Amir Johnson', 'R.J. Hunter'],
+    #            ['Omega Warriors', 'Mitcell Johnson', 'Shivang Thomas'])
+    return element.replace(mapper_key_list, mapper_value_list)
+# # map by csv
+
+
+
+def populate():
+    # get subject, relationships, objects
+    # for index, row in df.iterrows():
+    Subjects = pd.read_sql_query('SELECT * FROM Subjects;', CONN)
+    Objects = pd.read_sql_query('SELECT * FROM Objects;', CONN)
+    Relationships = pd.read_sql_query('SELECT * FROM Relationships;', CONN)
+    # add at each df their abbreviation
+    Subjects["Abbreviation"] = Subjects["SubjectURI"]
+    Objects["Abbreviation"] = Objects["ObjectURI"]
+    Relationships["Abbreviation"] = Relationships["RelationshipURI"]
+
+
+    for index, row in Subjects.iterrows():
+        subject_uri = row["SubjectURI"]
+        subject_id = row["SubjectID"]
+        abbreviation = parser(subject_uri)
+        insert_abbreviation(subject_uri,abbreviation)
+        abbreviation_id = select_abbreviation_id(subject_uri)
+        insert_subject_abbreviation(subject_id,abbreviation_id)
+
+    for index, row in Objects.iterrows():
+        object_uri = row["ObjectURI"]
+        object_id = row["ObjectID"]
+        abbreviation = parser(object_uri)
+        insert_abbreviation(object_uri,abbreviation)
+        abbreviation_id = select_abbreviation_id(object_uri)
+        insert_subject_abbreviation(object_id,abbreviation_id)
+
+    for index, row in Relationships.iterrows():
+        relationship_uri = row["RelationshipURI"]
+        relationship_id = row["RelationshipID"]
+        abbreviation = parser(relationship_uri)
+        insert_abbreviation(relationship_uri,abbreviation)
+        abbreviation_id = select_abbreviation_id(relationship_uri)
+        insert_subject_abbreviation(relationship_id,abbreviation_id)
+
+
+CONN.commit()
+CONN.close()
+
+# MAPPER_HANDLER.close()