{"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":"24e95fa8-e21c-51fd-b613-4896c82ccb9e","task_key":"default--v0~2e1~2e0~5fhf--24e95fa8-e21c-51fd-b613-4896c82ccb9e","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 24e95fa8-e21c-51fd-b613-4896c82ccb9e","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import pickle\\nimport os\\nfrom sklearn.datasets import make_classification\\n# Constants\\nFILE_NAME = 'save.pkl'\\nDATA, TARGET = make_classification(n_samples=100, n_features=20, n_informative=2, n_redundant=10, n_classes=2, random_state=1)\\ndef task_func(data, target):\\n\",\"complete_prompt\":\"import pickle\\nimport os\\nfrom sklearn.datasets import make_classification\\n\\n# Constants\\nFILE_NAME = 'save.pkl'\\nDATA, TARGET = make_classification(n_samples=100, n_features=20, n_informative=2, n_redundant=10, n_classes=2, random_state=1)\\n\\ndef task_func(data, target):\\n    \\\"\\\"\\\"\\n    Save the Sklearn dataset (\\\"Data\\\" and \\\"Destination\\\") in the pickle file \\\"save.pkl\\\" and then read it back for validation.\\n\\n    Parameters:\\n    - data (numpy array): The data part of the sklearn dataset.\\n    - target (numpy array): The target part of the sklearn dataset.\\n\\n    Returns:\\n    tuple: The loaded tuple (data, target) from 'save.pkl'.\\n\\n    Requirements:\\n    - pickle\\n    - os\\n    - sklearn.datasets\\n\\n    Example:\\n    >>> data, target = make_classification(n_samples=100, n_features=20, n_informative=2, n_redundant=10, n_classes=2, random_state=1)\\n    >>> loaded_data, loaded_target = task_func(data, target)\\n    >>> assert np.array_equal(data, loaded_data) and np.array_equal(target, loaded_target)\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Save the Sklearn dataset (\\\"Data\\\" and \\\"Destination\\\") in the pickle file \\\"save.pkl\\\" and then read it back for validation.\\nThe function should output with:\\n    tuple: The loaded tuple (data, target) from 'save.pkl'.\\nYou should write self-contained code starting with:\\n```\\nimport pickle\\nimport os\\nfrom sklearn.datasets import make_classification\\n# Constants\\nFILE_NAME = 'save.pkl'\\nDATA, TARGET = make_classification(n_samples=100, n_features=20, n_informative=2, n_redundant=10, n_classes=2, random_state=1)\\ndef task_func(data, target):\\n```\",\"libs\":\"['pickle', 'os', 'sklearn']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}