{"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":"25d0a8ef-2ee4-52d6-a9c5-490b26bb2da6","task_key":"default--v0~2e1~2e0~5fhf--25d0a8ef-2ee4-52d6-a9c5-490b26bb2da6","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 25d0a8ef-2ee4-52d6-a9c5-490b26bb2da6","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import numpy as np\\nimport pandas as pd\\ndef task_func(rows, columns=[\\\"A\\\", \\\"B\\\", \\\"C\\\", \\\"D\\\", \\\"E\\\"], seed=0) -> pd.DataFrame:\\n\",\"complete_prompt\":\"import numpy as np\\nimport pandas as pd\\n\\ndef task_func(rows, columns=[\\\"A\\\", \\\"B\\\", \\\"C\\\", \\\"D\\\", \\\"E\\\"], seed=0) -> pd.DataFrame:\\n    \\\"\\\"\\\"\\n    Create a Pandas DataFrame with a specified number of rows filled with random\\n    values in [0, 1) and shuffled columns.\\n    \\n    Note:\\n    - The columns should be unique and sorted in the ascending order.\\n\\n    Parameters:\\n    rows (int): The number of rows for the DataFrame. Must not be negative.\\n    columns (list of str): Column names for the DataFrame.\\n                           Defaults to ['A', 'B', 'C', 'D', 'E'].\\n                           If it contains repeated columns, the function deduplicates\\n                           it in a case and spacing sensitive way. If it is empty,\\n                           the function returns an empty DataFrame.\\n    seed (int): The random seed for reproducibility.\\n    \\n    Returns:\\n    pd.DataFrame: A pandas DataFrame with shuffled columns.\\n\\n    Requirements:\\n    - numpy\\n    - pandas\\n\\n    Example:\\n    >>> df = task_func(10)\\n    >>> df.head(2)\\n              D         E         A         C         B\\n    0  0.548814  0.715189  0.602763  0.544883  0.423655\\n    1  0.645894  0.437587  0.891773  0.963663  0.383442\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Create a Pandas DataFrame with a specified number of rows filled with random values in [0, 1) and shuffled columns.\\nNote that: The columns should be unique and sorted in the ascending order.\\nThe function should output with:\\n    pd.DataFrame: A pandas DataFrame with shuffled columns.\\nYou should write self-contained code starting with:\\n```\\nimport numpy as np\\nimport pandas as pd\\ndef task_func(rows, columns=[\\\"A\\\", \\\"B\\\", \\\"C\\\", \\\"D\\\", \\\"E\\\"], seed=0) -> pd.DataFrame:\\n```\",\"libs\":\"['pandas', 'numpy']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}