{"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":"91cd72b2-b479-5a45-8711-eb5b15175f84","task_key":"default--v0~2e1~2e0~5fhf--91cd72b2-b479-5a45-8711-eb5b15175f84","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 91cd72b2-b479-5a45-8711-eb5b15175f84","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import json\\nimport numpy as np\\nfrom collections import defaultdict\\nimport matplotlib.pyplot as plt\\ndef task_func(input_file):\\n\",\"complete_prompt\":\"import json\\nimport numpy as np\\nfrom collections import defaultdict\\nimport matplotlib.pyplot as plt\\n\\n\\ndef task_func(input_file):\\n    \\\"\\\"\\\"\\n    Reads a JSON file containing a list of dictionaries. For each key across all dictionaries,\\n    calculates the mean and median of its values using numpy. Visualizes the mean and median\\n    using bar charts. Returns the results and plots.\\n\\n    Parameters:\\n        - input_file (str): Path to the input JSON file containing a list of dictionaries.\\n\\n    Returns:\\n        - result (dict): each key corresponds to those in the input dictionaries, and the corresponding\\n          value is another dict with keys 'mean' and 'median', representing the calculated statistics.\\n        - plots  (list[matplotlib.axes._axes.Axes]): A list of bar charts, one for\\n          each key in the dictionaries, visualizing the mean and median values.\\n\\n    Requirements:\\n        - json\\n        - numpy\\n        - collections.defaultdict\\n        - matplotlib.pyplot\\n\\n    Example:\\n    >>> results, plots = task_func(\\\"sample_data.json\\\")\\n    >>> type(plots[0])\\n    <class 'matplotlib.axes._axes.Axes'>\\n    >>> results\\n    {'a': {'mean': 3.0, 'median': 3.0}, 'b': {'mean': 6.0, 'median': 6.0}}\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Reads a JSON file containing a list of dictionaries. For each key across all dictionaries, calculates the mean and median of its values using numpy. Visualizes the mean and median using bar charts. Returns the results and plots.\\nThe function should output with:\\n    result (dict): each key corresponds to those in the input dictionaries, and the corresponding\\n    value is another dict with keys 'mean' and 'median', representing the calculated statistics.\\n    plots  (list[matplotlib.axes._axes.Axes]): A list of bar charts, one for\\n    each key in the dictionaries, visualizing the mean and median values.\\nYou should write self-contained code starting with:\\n```\\nimport json\\nimport numpy as np\\nfrom collections import defaultdict\\nimport matplotlib.pyplot as plt\\ndef task_func(input_file):\\n```\",\"libs\":\"['collections', 'numpy', 'matplotlib', 'json']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}