⚡️ Speed up function coco_categories_to_classes by 22%

[codeflash-ai]

📄 22% (0.22x) speedup for coco_categories_to_classes in supervision/dataset/formats/coco.py

⏱️ Runtime : 259 microseconds → 212 microseconds (best of 559 runs)

📝 Explanation and details

To optimize the runtime of this function, we can avoid the overhead of the lambda function by using the itemgetter from the operator module, which is generally faster for this kind of key extraction. Let's rewrite the function accordingly.

This minor change leverages the itemgetter for sorting, which should improve performance. The rest of the logic remains the same, providing the same return values for the given input.

✅ Correctness verification report:

Test	Status
⚙️ Existing Unit Tests	✅ 12 Passed
🌀 Generated Regression Tests	✅ 33 Passed
⏪ Replay Tests	🔘 None Found
🔎 Concolic Coverage Tests	🔘 None Found
📊 Tests Coverage	100.0%

⚙️ Existing Unit Tests Details

- dataset/formats/test_coco.py

🌀 Generated Regression Tests Details

from typing import List

# imports
import pytest  # used for our unit tests
from supervision.dataset.formats.coco import coco_categories_to_classes

# unit tests

def test_basic_functionality():
    # Standard Input
    codeflash_output = coco_categories_to_classes([{"id": 1, "name": "cat"}, {"id": 2, "name": "dog"}])
    # Unsorted Input
    codeflash_output = coco_categories_to_classes([{"id": 2, "name": "dog"}, {"id": 1, "name": "cat"}])

def test_edge_cases():
    # Empty List
    codeflash_output = coco_categories_to_classes([])
    # Single Element
    codeflash_output = coco_categories_to_classes([{"id": 1, "name": "cat"}])
    # Duplicate IDs
    codeflash_output = coco_categories_to_classes([{"id": 1, "name": "cat"}, {"id": 1, "name": "dog"}])

def test_missing_keys():
    # Missing 'id' Key
    with pytest.raises(KeyError):
        coco_categories_to_classes([{"name": "cat"}])
    # Missing 'name' Key
    with pytest.raises(KeyError):
        coco_categories_to_classes([{"id": 1}])


def test_large_scale():
    # Large Input List
    large_input = [{"id": i, "name": f"name_{i}"} for i in range(10000, 9000, -1)]
    expected_output = [f"name_{i}" for i in range(1, 1001)]
    codeflash_output = coco_categories_to_classes(large_input)
    # Performance with Random IDs
    import random
    random_ids = random.sample(range(1, 1001), 1000)
    random_input = [{"id": i, "name": f"name_{i}"} for i in random_ids]
    codeflash_output = coco_categories_to_classes(random_input)

def test_special_characters_in_names():
    # Names with Special Characters
    codeflash_output = coco_categories_to_classes([{"id": 1, "name": "c@t"}, {"id": 2, "name": "d#g"}])
    # Names with Spaces
    codeflash_output = coco_categories_to_classes([{"id": 1, "name": "cat "}, {"id": 2, "name": " dog"}])

def test_non_sequential_ids():
    # Non-Sequential IDs
    codeflash_output = coco_categories_to_classes([{"id": 10, "name": "cat"}, {"id": 5, "name": "dog"}])
    # Negative IDs
    codeflash_output = coco_categories_to_classes([{"id": -1, "name": "cat"}, {"id": -2, "name": "dog"}])

def test_mixed_valid_and_invalid_entries():
    # Mixed Valid and Invalid Entries
    with pytest.raises(KeyError):
        coco_categories_to_classes([{"id": 1, "name": "cat"}, {"name": "dog"}, {"id": 2, "name": "bird"}])

def test_duplicate_names():
    # Duplicate Names
    codeflash_output = coco_categories_to_classes([{"id": 1, "name": "cat"}, {"id": 2, "name": "cat"}])

def test_ids_with_different_data_types():
    # Mixed Type IDs
    with pytest.raises(TypeError):
        coco_categories_to_classes([{"id": 1, "name": "cat"}, {"id": "2", "name": "dog"}])
# codeflash_output is used to check that the output of the original code is the same as that of the optimized code.

from typing import List

# imports
import pytest  # used for our unit tests
from supervision.dataset.formats.coco import coco_categories_to_classes

# unit tests

def test_basic_valid_input():
    # Test with multiple categories with unique IDs
    coco_categories = [{"id": 2, "name": "cat"}, {"id": 1, "name": "dog"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

    coco_categories = [{"id": 3, "name": "bird"}, {"id": 2, "name": "fish"}, {"id": 1, "name": "hamster"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_empty_input():
    # Test with an empty list
    coco_categories = []
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_single_element_input():
    # Test with a single category
    coco_categories = [{"id": 1, "name": "dog"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_already_sorted_input():
    # Test with categories already sorted by ID
    coco_categories = [{"id": 1, "name": "dog"}, {"id": 2, "name": "cat"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_reverse_sorted_input():
    # Test with categories sorted in reverse order by ID
    coco_categories = [{"id": 2, "name": "cat"}, {"id": 1, "name": "dog"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_duplicate_ids():
    # Test with categories having duplicate IDs
    coco_categories = [{"id": 1, "name": "dog"}, {"id": 1, "name": "cat"}]
    codeflash_output = coco_categories_to_classes(coco_categories)  # Order is not guaranteed for duplicates


def test_missing_keys():
    # Test with categories missing the "id" or "name" key
    coco_categories = [{"id": 1, "name": "dog"}, {"id": 2}]
    with pytest.raises(KeyError):
        coco_categories_to_classes(coco_categories)

    coco_categories = [{"id": 1}, {"id": 2, "name": "cat"}]
    with pytest.raises(KeyError):
        coco_categories_to_classes(coco_categories)

def test_large_input():
    # Test with a large number of categories
    coco_categories = [{"id": i, "name": f"category_{i}"} for i in range(1000)]
    expected_output = [f"category_{i}" for i in range(1000)]
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_non_unique_names():
    # Test with categories having non-unique names but different IDs
    coco_categories = [{"id": 1, "name": "animal"}, {"id": 2, "name": "animal"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_unsorted_input_with_mixed_order():
    # Test with categories in a random order
    coco_categories = [{"id": 3, "name": "bird"}, {"id": 1, "name": "dog"}, {"id": 2, "name": "cat"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_negative_ids():
    # Test with categories having negative IDs
    coco_categories = [{"id": -1, "name": "dog"}, {"id": -2, "name": "cat"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_zero_id():
    # Test with categories having an ID of zero
    coco_categories = [{"id": 0, "name": "dog"}, {"id": 1, "name": "cat"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_large_ids():
    # Test with categories having very large ID values
    coco_categories = [{"id": 999999999, "name": "dog"}, {"id": 1000000000, "name": "cat"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_special_characters_in_names():
    # Test with categories having special characters in their names
    coco_categories = [{"id": 1, "name": "d@g"}, {"id": 2, "name": "c@t"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

def test_empty_strings_in_names():
    # Test with categories having empty strings as names
    coco_categories = [{"id": 1, "name": ""}, {"id": 2, "name": "cat"}]
    codeflash_output = coco_categories_to_classes(coco_categories)

# Run the tests
if __name__ == "__main__":
    pytest.main()
# codeflash_output is used to check that the output of the original code is the same as that of the optimized code.