Refactor code for improved clarity and consistency.

Remove unnecessary parentheses in conditional expressions and list comprehensions. Add docstrings to test functions in `test_utils.py` for better documentation. Simplify error handling messages in `cli.py` to reduce redundancy and enhance readability.

Author: jacksonpradolima

gsppy/cli.py

@@ -56,8 +56,9 @@ def read_transactions_from_json(file_path: str) -> List[List]:
                 raise ValueError("File should contain a JSON array of transaction lists.")
         return transactions
     except Exception as e:
-        logging.error(f"Error reading transaction data from JSON file '{file_path}': {e}")
-        raise ValueError(f"Error reading transaction data from JSON file: {e}")
+        msg = f"Error reading transaction data from JSON file '{file_path}': {e}"
+        logging.error(msg)
+        raise ValueError(msg)
 
 
 def read_transactions_from_csv(file_path: str) -> List[List]:
@@ -85,8 +86,9 @@ def read_transactions_from_csv(file_path: str) -> List[List]:
                 transactions.append([item.strip() for item in row if item.strip()])
         return transactions
     except Exception as e:
-        logging.error(f"Error reading transaction data from CSV file '{file_path}': {e}")
-        raise ValueError(f"Error reading transaction data from CSV file: {e}")
+        msg = f"Error reading transaction data from CSV file '{file_path}': {e}"
+        logging.error(msg)
+        raise ValueError(msg)
 
 
 def detect_and_read_file(file_path: str) -> List[List]:
@@ -110,10 +112,11 @@ def detect_and_read_file(file_path: str) -> List[List]:
 
     if file_extension == ".json":
         return read_transactions_from_json(file_path)
-    elif file_extension == ".csv":
+
+    if file_extension == ".csv":
         return read_transactions_from_csv(file_path)
-    else:
-        raise ValueError("Unsupported file format. Please provide a JSON or CSV file.")
+
+    raise ValueError("Unsupported file format. Please provide a JSON or CSV file.")
 
 
 def main():

gsppy/gsp.py

@@ -173,7 +173,7 @@ def _pre_processing(self, raw_transactions: List[List]):
             raise ValueError(msg)
 
         logger.info("Pre-processing transactions...")
-        self.max_size = max([len(item) for item in raw_transactions])
+        self.max_size = max(len(item) for item in raw_transactions)
         self.transactions = [tuple(transaction) for transaction in raw_transactions]
         counts = Counter(chain.from_iterable(raw_transactions))
         self.unique_candidates = [(item,) for item in counts.keys()]
@@ -273,7 +273,7 @@ def search(self, min_support: float = 0.2) -> List[Dict[Tuple, int]]:
               and completion.
             - Status updates for each iteration until the algorithm terminates.
         """
-        if not (0.0 < min_support <= 1.0):
+        if not 0.0 < min_support <= 1.0:
             raise ValueError("Minimum support must be in the range (0.0, 1.0]")
 
         min_support = len(self.transactions) * min_support

gsppy/tests/test_gsp.py

@@ -83,7 +83,7 @@ def test_no_frequent_items(supermarket_transactions):
     """
     gsp = GSP(supermarket_transactions)
     result = gsp.search(min_support=0.9)  # High minimum support
-    assert result == [], "High minimum support should filter out all items."
+    assert not result, "High minimum support should filter out all items."
 
 
 def test_frequent_patterns(supermarket_transactions):

gsppy/tests/test_utils.py

@@ -12,6 +12,9 @@
 
 
 def test_split_into_batches():
+    """
+    Test the `split_into_batches` utility function.
+    """
     # Test with exact batches
     items = [(1,), (2,), (3,), (4,), (5,)]
     batch_size = 2
@@ -32,10 +35,13 @@ def test_split_into_batches():
     items = []
     batch_size = 3
     result = list(split_into_batches(items, batch_size))
-    assert result == [], "Failed empty input"
+    assert not result, "Failed empty input"
 
 
 def test_is_subsequence_in_list():
+    """
+    Test the `is_subsequence_in_list` utility function.
+    """
     # Test when the subsequence is present
     assert is_subsequence_in_list((1, 2), (0, 1, 2, 3)), "Failed to find subsequence"
     assert is_subsequence_in_list((3,), (0, 1, 2, 3)), "Failed single-element subsequence"
@@ -53,6 +59,9 @@ def test_is_subsequence_in_list():
 
 
 def test_generate_candidates_from_previous():
+    """
+    Test the `generate_candidates_from_previous` utility function.
+    """
     # Test if candidates are generated correctly
     prev_patterns = {
         (1, 2): 3,

gsppy/utils.py

@@ -83,4 +83,3 @@ def generate_candidates_from_previous(prev_patterns: Dict[Tuple, int]) -> List[T
         for pattern1, pattern2 in product(keys, repeat=2)
         if pattern1[1:] == pattern2[:-1] and not (len(pattern1) == 1 and pattern1 == pattern2)
     ]
-