{"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":"noindex","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[]}},"task_id":"c39432e7-f946-5e1a-8510-e8aad8838e71","task_key":"default--v0~2e1~2e0~5fhf--c39432e7-f946-5e1a-8510-e8aad8838e71","task_revision_id":"2","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf c39432e7-f946-5e1a-8510-e8aad8838e71","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import numpy as np\\nimport pandas as pd\\nimport statistics\\ndef task_func(rows, columns=['A', 'B', 'C', 'D', 'E', 'F'], seed=42):\\n\",\"complete_prompt\":\"import numpy as np\\nimport pandas as pd\\nimport statistics\\n\\ndef task_func(rows, columns=['A', 'B', 'C', 'D', 'E', 'F'], seed=42):\\n    \\\"\\\"\\\"\\n    Create a Pandas DataFrame with a specified number of rows and six columns (default A-F), \\n    each filled with random numbers between 1 and 100, using a specified seed for reproducibility. \\n    Additionally, calculate the mean and median for each column.\\n\\n    Parameters:\\n        - rows (int): The number of rows in the DataFrame. Must be a positive integer greater than 0.\\n        - columns (list, optional): Column names for the DataFrame. Defaults to ['A', 'B', 'C', 'D', 'E', 'F'].\\n        - seed (int, optional): Seed for the random number generator. Defaults to 42.\\n\\n    Returns:\\n        - DataFrame: A pandas DataFrame with the generated data.\\n        - dict: A dictionary containing the calculated mean and median for each column. \\n                The dictionary format is:\\n                {\\n                    'ColumnName': {\\n                        'mean': MeanValue,\\n                        'median': MedianValue\\n                    }, ...\\n                }\\n                where 'ColumnName' is each of the specified column names, 'MeanValue' is the calculated mean, \\n                and 'MedianValue' is the calculated median for that column.\\n\\n    Raises:\\n        - ValueError: If 'rows' is not a positive integer greater than 0.\\n\\n    Requirements:\\n        - numpy\\n        - pandas\\n        - statistics\\n\\n    Example:\\n        >>> df, stats = task_func(10)\\n        >>> print(df)\\n            A   B   C   D   E    F\\n        0  52  93  15  72  61   21\\n        1  83  87  75  75  88  100\\n        2  24   3  22  53   2   88\\n        3  30  38   2  64  60   21\\n        4  33  76  58  22  89   49\\n        5  91  59  42  92  60   80\\n        6  15  62  62  47  62   51\\n        7  55  64   3  51   7   21\\n        8  73  39  18   4  89   60\\n        9  14   9  90  53   2   84\\n        >>> print(stats)\\n        {'A': {'mean': 47, 'median': 42.5}, 'B': {'mean': 53, 'median': 60.5}, 'C': {'mean': 38.7, 'median': 32.0}, 'D': {'mean': 53.3, 'median': 53.0}, 'E': {'mean': 52, 'median': 60.5}, 'F': {'mean': 57.5, 'median': 55.5}}\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Create a Pandas DataFrame with a specified number of rows and six columns (default A-F), each filled with random numbers between 1 and 100, using a specified seed for reproducibility. Additionally, calculate the mean and median for each column.\\nThe function should raise the exception for: ValueError: If 'rows' is not a positive integer greater than 0.\\nThe function should output with:\\n    DataFrame: A pandas DataFrame with the generated data.\\n    dict: A dictionary containing the calculated mean and median for each column.\\n    The dictionary format is:\\n    {\\n    'ColumnName': {\\n    'mean': MeanValue,\\n    'median': MedianValue\\n    }, ...\\n    }\\n    where 'ColumnName' is each of the specified column names, 'MeanValue' is the calculated mean,\\n    and 'MedianValue' is the calculated median for that column.\\nYou should write self-contained code starting with:\\n```\\nimport numpy as np\\nimport pandas as pd\\nimport statistics\\ndef task_func(rows, columns=['A', 'B', 'C', 'D', 'E', 'F'], seed=42):\\n```\",\"libs\":\"['statistics', 'pandas', 'numpy']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"noindex","subproblems":[],"grids":[]}