CSV support added to path_splitter_tree

Also resolved a minor bug to print also leaf nodes

Scripts/DataCleaning/path_splitter_tree.py

@@ -6,8 +6,16 @@ from typing import Self
 
 class ProgramArgs:
 
-    def __init__(self, file: str, output: str, treshold: int):
+    def __init__(self, file: str, csv_uri_header: str, output: str, treshold: int):
+        """
+        Args:
+            file (str): 
+            csv_header (str): The name of the column of the csv file from which the program will get the URIs
+            output (str): 
+            treshold (int): 
+        """        
         self.file = file
+        self.csv_uri_header = csv_uri_header
         self.output = output
         self.treshold = treshold
 
@@ -33,11 +41,15 @@ class Node:
         KEY = child[0]
 
         if not self.children.get(KEY):
+            # if the key has no value, it means we are traversing this branch for the first time
+            # create another node for the key
             self.children[KEY] = Node(KEY, 0)
 
+        # take the node for the key
         CHILD = self.children[KEY]
         self.quantity += 1
 
+        # if the child list to enter has only one element, which is KEY, no more node will be created
         if len(child) == 1:
             return
 
@@ -53,27 +65,32 @@ def get_args(args: list[str]) -> ProgramArgs:
 
     PARSER = argparse.ArgumentParser()
     PARSER.add_argument("--input-file", "-i", required=True, type=str)
+    PARSER.add_argument("--header-name", "-c", required=True, type=str)                       # c stands for column
     PARSER.add_argument("--output-file", "-o", required=True, type=str)
     PARSER.add_argument("--treshold", "-t", type=int, default=1)
     parsed_args, _ = PARSER.parse_known_args(args)
 
     # print(parsed_args.input_file)
 
-    return ProgramArgs(parsed_args.input_file,parsed_args.output_file, parsed_args.treshold)  # type ignore
+    return ProgramArgs(parsed_args.input_file, parsed_args.header_name ,parsed_args.output_file, parsed_args.treshold)  # type ignore
 
 
 def get_debug_args() -> ProgramArgs:
-
-    FILE = "./Assets/Dataset/Tmp/reverse-rel.txt"
+    # -i ./Assets/Dataset/1-hop/movies.csv  -c subject -o Assets/Dataset/Tmp/prova.csv -t 1
+    FILE = "./Assets/Dataset/1-hop/movies.csv"
+    CSV_HEADER = "subject"
+    OUTPUT = "./Assets/Dataset/Tmp/prova.csv"
     TRESHOLD = 1
 
     return ProgramArgs(
         FILE,
+        CSV_HEADER,
+        OUTPUT,
         TRESHOLD
     )
 
 
-def tree_like(file: str, out: str):
+def tree_like(file: str, csv_uri_header:str, out: str):
 
     INDENTATION = "    "
 
@@ -85,9 +102,11 @@ def tree_like(file: str, out: str):
     FILE = open(file, "r", encoding="utf-8")
 
     # TODO: Change here so it takes single URI from a CSV file
-    for row in FILE:
+    # It is needed the header-name
+    for row in csv.DictReader(FILE):
 
-        sections = row.split("/")
+        uri_element = row[csv_uri_header]
+        sections = uri_element.split("/")
         sections = list(filter(lambda item: item != "", sections))
 
         # print(sections)
@@ -116,7 +135,9 @@ def tree_like(file: str, out: str):
 
         INDENT: str = INDENTATION * DEPTH
 
-        if NODE.quantity < ARGS.treshold:
+        # Leaf node have quantity 0, so if i want them to appear the threshold have to be 0
+        # if NODE.quantity < ARGS.treshold:
+        if ARGS.treshold > NODE.quantity:
             continue
 
         OUT.write(f"{INDENT}- {NODE}\n")
@@ -134,7 +155,8 @@ def tree_like(file: str, out: str):
     OUT.close()
 
 
+
 if __name__ == "__main__":
     ARGS = get_args(sys.argv)
     # ARGS = get_debug_args()
-    tree_like(ARGS.file, ARGS.output)
+    tree_like(ARGS.file,ARGS.csv_uri_header, ARGS.output)