Switched to Black linter

.github/workflows/linter.yaml

@@ -1,21 +1,21 @@
-name: Lint Code Base
+name: Python Code Formatting with Black
 
 on: [push, pull_request]
 
 jobs:
-  build:
-    name: Lint Code Base
+  black:
     runs-on: ubuntu-latest
-
     steps:
+    - name: Check out repository
+      uses: actions/checkout@v2
+
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.11'
 
-      - name: Checkout Code
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
+    - name: Install Black
+      run: pip install black
 
-      - name: Lint Code Base
-        uses: github/super-linter@v4
-        env:
-          VALIDATE_ALL_CODEBASE: true
-          VALIDATE_PYTHON_BLACK: true
+    - name: Run Black Check
+      run: black --check .

dictionaries.py

@@ -20,18 +20,17 @@ def generate_sample_data(size, max_list_length):
     :return: List of tuples (key, value) where key is a string and value is an integer.
     """
     if size <= 0 or max_list_length <= 0:
-        logger.error(
-            "Size and max list length must be non-negative, and non-zero.")
-        raise ValueError(
-            "Size and max list length must be non-negative, and non-zero.")
+        logger.error("Size and max list length must be non-negative, and non-zero.")
+        raise ValueError("Size and max list length must be non-negative, and non-zero.")
 
     try:
         logger.info("Generating sample data.")
         sample_data = []
 
         for _ in range(size):
-            key = ''.join(random.choice(string.ascii_lowercase)
-                          for _ in range(3))  # Generate a random 3-letter string
+            key = "".join(
+                random.choice(string.ascii_lowercase) for _ in range(3)
+            )  # Generate a random 3-letter string
             if max_list_length > 0:
                 for _ in range(random.randint(1, max_list_length)):
                     # Generate a random integer between 1 and 100
@@ -73,9 +72,11 @@ def convert_to_dictionary(sample_data):
                 raise TypeError("Each item in sample_data must be a tuple.")
             if len(item) != 2:
                 logger.error(
-                    "Each tuple in sample data must contain exactly 2 elements.")
+                    "Each tuple in sample data must contain exactly 2 elements."
+                )
                 raise ValueError(
-                    "Each tuple in sample_data must contain exactly 2 elements.")
+                    "Each tuple in sample_data must contain exactly 2 elements."
+                )
 
             key, value = item
             if key in dictionary:
@@ -84,8 +85,10 @@ def convert_to_dictionary(sample_data):
                 dictionary[key] = [value]
 
     except Exception as convert_to_dictionary_error:
-        logger.error("Error converting sample data to a Python dictionary: " +
-                     str(convert_to_dictionary_error))
+        logger.error(
+            "Error converting sample data to a Python dictionary: "
+            + str(convert_to_dictionary_error)
+        )
         raise convert_to_dictionary_error
 
     logger.info("Successfully converted sample data to a Python dictionary.")
@@ -113,17 +116,17 @@ def convert_to_numpy_array(sample_data):
 
         # Verify that all tuples have the same length
         if len(set(len(item) for item in sample_data if isinstance(item, tuple))) != 1:
-            logger.error(
-                "All tuples in sample data must have the same length.")
-            raise ValueError(
-                "All tuples in sample_data must have the same length.")
+            logger.error("All tuples in sample data must have the same length.")
+            raise ValueError("All tuples in sample_data must have the same length.")
 
         # Convert to NumPy array
         np_array = np.array(sample_data)
 
     except Exception as convert_to_numpy_array_error:
-        logger.error("Error converting sample data to a NumPy array: " +
-                     str(convert_to_numpy_array_error))
+        logger.error(
+            "Error converting sample data to a NumPy array: "
+            + str(convert_to_numpy_array_error)
+        )
         raise convert_to_numpy_array_error
 
     logger.info("Successfully converted sample data to a NumPy array.")
@@ -146,17 +149,17 @@ def convert_to_pandas_df(sample_data):
         logger.info("Converting sample data to a Pandas DataFrame.")
 
         if not all(isinstance(item, tuple) and len(item) == 2 for item in sample_data):
-            logger.error(
-                "Each item in sample data must be a 2-element tuple.")
-            raise ValueError(
-                "Each item in sample_data must be a 2-element tuple")
+            logger.error("Each item in sample data must be a 2-element tuple.")
+            raise ValueError("Each item in sample_data must be a 2-element tuple")
 
         # Creating DataFrame from sample_data
-        df = pd.DataFrame(sample_data, columns=['Key', 'Value'])
+        df = pd.DataFrame(sample_data, columns=["Key", "Value"])
 
     except Exception as convert_to_pandas_df_error:
-        logger.error("Error converting sample data to a Pandas DataFrame: " +
-                     str(convert_to_pandas_df_error))
+        logger.error(
+            "Error converting sample data to a Pandas DataFrame: "
+            + str(convert_to_pandas_df_error)
+        )
         raise convert_to_pandas_df_error
 
     logger.info("Successfully converted sample data to a Pandas DataFrame.")
@@ -184,17 +187,17 @@ def convert_to_polars_df(sample_data):
 
         # Verify that all tuples have the same length
         if len(set(len(item) for item in sample_data if isinstance(item, tuple))) != 1:
-            logger.error(
-                "All tuples in sample data must have the same length.")
-            raise ValueError(
-                "All tuples in sample_data must have the same length.")
+            logger.error("All tuples in sample data must have the same length.")
+            raise ValueError("All tuples in sample_data must have the same length.")
 
         # Convert to Polars DataFrame
         df = pl.DataFrame(sample_data)
 
     except Exception as convert_to_polars_df_error:
-        logger.error("Error converting sample data to a Polars DataFrame: " +
-                     str(convert_to_polars_df_error))
+        logger.error(
+            "Error converting sample data to a Polars DataFrame: "
+            + str(convert_to_polars_df_error)
+        )
         raise convert_to_polars_df_error
 
     logger.info("Successfully converted sample data to a Polars DataFrame.")

logger.py

@@ -17,7 +17,8 @@ def __init__(self, name, log_file=None, level=logging.INFO):
         self.logger.setLevel(level)
 
         formatter = logging.Formatter(
-            '%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+            "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+        )
 
         # File handler to log messages in a file
         if log_file is None:

main.py

@@ -4,7 +4,13 @@
 import string
 from logger import log_this
 import logging
-from dictionaries import generate_sample_data, convert_to_dictionary, convert_to_numpy_array, convert_to_pandas_df, convert_to_polars_df
+from dictionaries import (
+    generate_sample_data,
+    convert_to_dictionary,
+    convert_to_numpy_array,
+    convert_to_pandas_df,
+    convert_to_polars_df,
+)
 from speed_tests import measure_execution_time
 
 CONST_SIZE = 10000
@@ -25,7 +31,6 @@
     pandas_df = convert_to_pandas_df(sample_data)
     polars_df = convert_to_polars_df(sample_data)
 
-
     # Speed tests
     measure_execution_time(convert_to_dictionary, 10, sample_data)
     measure_execution_time(convert_to_numpy_array, 10, sample_data)

speed_tests.py

@@ -16,6 +16,8 @@ def measure_execution_time(func, repetitions=10, *args, **kwargs):
 
     average_elapsed_time = total_elapsed_time / repetitions
     average_elapsed_time_ms = int(
-        average_elapsed_time.microseconds)  # Convert to milliseconds
+        average_elapsed_time.microseconds
+    )  # Convert to milliseconds
     logger.info(
-        f"Function {func} Average execution time (microseconds): {average_elapsed_time_ms}")
+        f"Function {func} Average execution time (microseconds): {average_elapsed_time_ms}"
+    )

test_convert_to_dictionary.py

@@ -3,8 +3,8 @@
 
 
 def test_normal_input():
-    sample_data = [('a', 1), ('b', 2), ('a', 3)]
-    expected_output = {'a': [1, 3], 'b': [2]}
+    sample_data = [("a", 1), ("b", 2), ("a", 3)]
+    expected_output = {"a": [1, 3], "b": [2]}
     assert convert_to_dictionary(sample_data) == expected_output
 
 
@@ -15,8 +15,8 @@ def test_empty_input():
 
 
 def test_multiple_entries_same_key():
-    sample_data = [('a', 1), ('a', 2), ('a', 3)]
-    expected_output = {'a': [1, 2, 3]}
+    sample_data = [("a", 1), ("a", 2), ("a", 3)]
+    expected_output = {"a": [1, 2, 3]}
     assert convert_to_dictionary(sample_data) == expected_output
 
 
@@ -26,6 +26,6 @@ def test_invalid_input_data():
 
 
 def test_incorrect_tuple_length():
-    sample_data = [('a', 1, 'extra'), ('b', 2)]
+    sample_data = [("a", 1, "extra"), ("b", 2)]
     with pytest.raises(ValueError):
         convert_to_dictionary(sample_data)

test_convert_to_numpy_array.py

@@ -6,22 +6,19 @@
 def test_normal_input():
     sample_data = [(1, 2), (3, 4)]
     expected_output = np.array([[1, 2], [3, 4]])
-    np.testing.assert_array_equal(
-        convert_to_numpy_array(sample_data), expected_output)
+    np.testing.assert_array_equal(convert_to_numpy_array(sample_data), expected_output)
 
 
 def test_empty_input():
     sample_data = []
     expected_output = np.array([])
-    np.testing.assert_array_equal(
-        convert_to_numpy_array(sample_data), expected_output)
+    np.testing.assert_array_equal(convert_to_numpy_array(sample_data), expected_output)
 
 
 def test_multiple_entries():
-    sample_data = [('a', 1), ('a', 2), ('a', 3)]
-    expected_output = np.array([('a', 1), ('a', 2), ('a', 3)])
-    np.testing.assert_array_equal(
-        convert_to_numpy_array(sample_data), expected_output)
+    sample_data = [("a", 1), ("a", 2), ("a", 3)]
+    expected_output = np.array([("a", 1), ("a", 2), ("a", 3)])
+    np.testing.assert_array_equal(convert_to_numpy_array(sample_data), expected_output)
 
 
 def test_invalid_input_data():
@@ -30,6 +27,6 @@ def test_invalid_input_data():
 
 
 def test_incorrect_tuple_length():
-    sample_data = [('a', 1, 'extra'), ('b', 2)]
+    sample_data = [("a", 1, "extra"), ("b", 2)]
     with pytest.raises(ValueError):
         convert_to_numpy_array(sample_data)