{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"bigcodebench","formal_name":"BigCodeBench","introduction":"BigCodeBench poses 1,140 function-level tasks drawn across 139 libraries. It tests whether a model can compose several real APIs correctly rather than write one self-contained function.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://bigcode-bench.github.io/","indexing_mode":"index","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[],"history":"","construction":"","limitations":"","saturation":"","scores":[]}},"task_id":"9766dd7c-4bde-54e1-b707-23c612535ccf","task_key":"default--v0~2e1~2e0~5fhf--9766dd7c-4bde-54e1-b707-23c612535ccf","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 9766dd7c-4bde-54e1-b707-23c612535ccf","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import numpy as np\\nimport cv2\\nimport os\\ndef task_func(image_path='image.jpg', threshold=128):\\n\",\"complete_prompt\":\"import numpy as np\\nimport cv2\\nimport os\\n\\ndef task_func(image_path='image.jpg', threshold=128):\\n    \\\"\\\"\\\"\\n    Read an image, convert it to grayscale, binarize it using a given threshold, and save it as 'binary_image.jpg'.\\n    The function returns numpy arrays of the original and binarized images, and ensures that the threshold value is valid.\\n\\n    Parameters:\\n    - image_path (str): The path to the image file. Default is 'image.jpg'.\\n    - threshold (int): The threshold value for binarization, must be between 0 and 255. Default is 128.\\n\\n    Returns:\\n    - tuple: A tuple containing two numpy arrays; the first is the original grayscale image, the second is the binarized image.\\n\\n    Raises:\\n    - FileNotFoundError: If the image file does not exist at the specified path.\\n    - ValueError: If the threshold is not an integer or not in the range 0-255.\\n\\n    Requirements:\\n    - opencv\\n    - numpy\\n    - os\\n    - pillow\\n\\n    Example:\\n    >>> create_dummy_image('image.jpg')\\n    >>> original_img_array, binary_img_array = task_func('image.jpg', 128)\\n    >>> os.remove('image.jpg')\\n    >>> original_img_array.shape, binary_img_array.shape # ((image_height, image_width), (image_height, image_width))\\n    ((20, 20), (20, 20))\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Read an image, convert it to grayscale, binarize it using a given threshold, and save it as 'binary_image.jpg'. The function returns numpy arrays of the original and binarized images, and ensures that the threshold value is valid.\\nThe function should raise the exception for: FileNotFoundError: If the image file does not exist at the specified path. ValueError: If the threshold is not an integer or not in the range 0-255.\\nThe function should output with:\\n    tuple: A tuple containing two numpy arrays; the first is the original grayscale image, the second is the binarized image.\\nYou should write self-contained code starting with:\\n```\\nimport numpy as np\\nimport cv2\\nimport os\\ndef task_func(image_path='image.jpg', threshold=128):\\n```\",\"libs\":\"['numpy', 'cv2', 'os']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}