{"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":"db0f2433-b7b1-51de-8dcb-f028c8ec3419","task_key":"default--v0~2e1~2e0~5fhf--db0f2433-b7b1-51de-8dcb-f028c8ec3419","task_revision_id":"2","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf db0f2433-b7b1-51de-8dcb-f028c8ec3419","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import numpy as np\\nimport seaborn as sns\\ndef task_func(df):\\n\",\"complete_prompt\":\"import numpy as np\\nimport seaborn as sns\\n\\ndef task_func(df):\\n    \\\"\\\"\\\"\\n    Describe a dataframe and draw a distribution chart for each numeric column after replacing the NaN values with the average of the column.\\n\\n    Parameters:\\n    df (DataFrame): The pandas DataFrame.\\n\\n    Returns:\\n    tuple: A tuple containing:\\n        - DataFrame: A pandas DataFrame with statistics. This includes count, mean, standard deviation (std), min, 25%, 50%, 75%, and max values for each numeric column.\\n        - List[Axes]: A list of matplotlib Axes objects representing the distribution plots for each numeric column.\\n                    Each plot visualizes the distribution of data in the respective column with 10 bins.\\n\\n    Requirements:\\n    - numpy\\n    - seaborn\\n\\n    Example:\\n    >>> import pandas as pd\\n    >>> import numpy as np\\n    >>> df = pd.DataFrame([[1,2,3],[4,5,6],[7.0,np.nan,9.0]], columns=[\\\"c1\\\",\\\"c2\\\",\\\"c3\\\"])\\n    >>> description, plots = task_func(df)\\n    >>> print(description)\\n            c1    c2   c3\\n    count  3.0  3.00  3.0\\n    mean   4.0  3.50  6.0\\n    std    3.0  1.50  3.0\\n    min    1.0  2.00  3.0\\n    25%    2.5  2.75  4.5\\n    50%    4.0  3.50  6.0\\n    75%    5.5  4.25  7.5\\n    max    7.0  5.00  9.0\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Describe a dataframe and draw a distribution chart for each numeric column after replacing the NaN values with the average of the column.\\nThe function should output with:\\n    tuple: A tuple containing:\\n    DataFrame: A pandas DataFrame with statistics. This includes count, mean, standard deviation (std), min, 25%, 50%, 75%, and max values for each numeric column.\\n    List[Axes]: A list of matplotlib Axes objects representing the distribution plots for each numeric column.\\n    Each plot visualizes the distribution of data in the respective column with 10 bins.\\nYou should write self-contained code starting with:\\n```\\nimport numpy as np\\nimport seaborn as sns\\ndef task_func(df):\\n```\",\"libs\":\"['numpy', 'seaborn']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"noindex","subproblems":[],"grids":[]}