{"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":"42748ac8-0870-5b0e-ae55-6782acacf9ec","task_key":"default--v0~2e1~2e0~5fhf--42748ac8-0870-5b0e-ae55-6782acacf9ec","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 42748ac8-0870-5b0e-ae55-6782acacf9ec","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"from random import choice\\nimport numpy as np\\nimport pandas as pd\\n# Constants\\nTEAMS = ['Team A', 'Team B', 'Team C', 'Team D', 'Team E']\\nPENALTIES_COSTS = [100, 200, 300, 400, 500]\\ndef task_func(goals, penalties, teams=TEAMS, penalties_costs=PENALTIES_COSTS):\\n\",\"complete_prompt\":\"from random import choice\\nimport numpy as np\\nimport pandas as pd\\n\\n\\n# Constants\\nTEAMS = ['Team A', 'Team B', 'Team C', 'Team D', 'Team E']\\nPENALTIES_COSTS = [100, 200, 300, 400, 500]\\n\\n\\ndef task_func(goals, penalties, teams=TEAMS, penalties_costs=PENALTIES_COSTS):\\n    \\\"\\\"\\\"\\n    Generates a performance report DataFrame for teams, detailing goals and penalties. For each team, the function fetches\\n    goal and penalty counts, calculates 'Penalties Cost' using a random multiplier from a predefined list, and computes\\n    a 'Performance Score' as the non-negative difference between goals and penalties. Return a Dataframe with colomns 'Team',\\n    'Goals', 'Penalties', 'Penalties Cost' and 'Performance Score'.\\n\\n    Parameters:\\n    - goals (dict): Team names as keys, numbers of goals scored as values.\\n    - penalties (dict): Team names as keys, numbers of penalties incurred as values.\\n    - teams (list, optioanl): input teams. Default value is ['Team A', 'Team B', 'Team C', 'Team D', 'Team E']\\n    - penalties_costs (list, optional): input penalties_costs. Default value is [100, 200, 300, 400, 500].\\n\\n    Returns:\\n    - pd.DataFrame: DataFrame with Team, Goals, Penalties, Penalties Cost, Performance Score.\\n\\n    Requirements:\\n    - pandas\\n    - numpy\\n    - random.choice\\n\\n    Example:\\n    >>> goals = {'Team A': 3, 'Team B': 2}\\n    >>> penalties = {'Team A': 1, 'Team B': 0}\\n    >>> report = task_func(goals, penalties)\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Generates a performance report DataFrame for teams, detailing goals and penalties. For each team, the function fetches goal and penalty counts, calculates 'Penalties Cost' using a random multiplier from a predefined list, and computes a 'Performance Score' as the non-negative difference between goals and penalties. Return a Dataframe with colomns 'Team', 'Goals', 'Penalties', 'Penalties Cost' and 'Performance Score'.\\nThe function should output with:\\n    pd.DataFrame: DataFrame with Team, Goals, Penalties, Penalties Cost, Performance Score.\\nYou should write self-contained code starting with:\\n```\\nfrom random import choice\\nimport numpy as np\\nimport pandas as pd\\n# Constants\\nTEAMS = ['Team A', 'Team B', 'Team C', 'Team D', 'Team E']\\nPENALTIES_COSTS = [100, 200, 300, 400, 500]\\ndef task_func(goals, penalties, teams=TEAMS, penalties_costs=PENALTIES_COSTS):\\n```\",\"libs\":\"['pandas', 'numpy', 'random']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}