{"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":"0d99a3b5-0103-5bd1-babf-1018da2b2299","task_key":"default--v0~2e1~2e0~5fhf--0d99a3b5-0103-5bd1-babf-1018da2b2299","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 0d99a3b5-0103-5bd1-babf-1018da2b2299","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import numpy as np\\nfrom scipy import stats\\ndef task_func(df):\\n\",\"complete_prompt\":\"import numpy as np\\nfrom scipy import stats\\n\\ndef task_func(df):\\n    \\\"\\\"\\\"\\n    Given a Pandas DataFrame with random numeric values test if the data in each column is normally distributed using the Shapiro-Wilk test.\\n\\n    Parameters:\\n    - df (DataFrame): A Pandas DataFrame with random numeric values.\\n    \\n    Returns:\\n    - dict: A dictionary with p-values from the Shapiro-Wilk test for each column.\\n\\n    Requirements:\\n    - numpy\\n    - scipy\\n\\n    Example:\\n    >>> np.random.seed(42)\\n    >>> df = pd.DataFrame(np.random.normal(size=(100, 5)))\\n    >>> p_values = task_func(df)\\n    >>> print(p_values)\\n    {0: 0.3595593273639679, 1: 0.23594242334365845, 2: 0.7625704407691956, 3: 0.481273353099823, 4: 0.13771861791610718}\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Given a Pandas DataFrame with random numeric values test if the data in each column is normally distributed using the Shapiro-Wilk test.\\nThe function should output with:\\n    dict: A dictionary with p-values from the Shapiro-Wilk test for each column.\\nYou should write self-contained code starting with:\\n```\\nimport numpy as np\\nfrom scipy import stats\\ndef task_func(df):\\n```\",\"libs\":\"['numpy', 'scipy']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}