{"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":"0bb7871f-0c44-570b-85ce-f0ab6ddd9fb2","task_key":"default--v0~2e1~2e0~5fhf--0bb7871f-0c44-570b-85ce-f0ab6ddd9fb2","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 0bb7871f-0c44-570b-85ce-f0ab6ddd9fb2","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import pandas as pd\\nimport random\\nimport csv\\ndef task_func(n, \\n           categories=['Sports', 'Technology', 'Business', 'Politics', 'Entertainment'],\\n           news_sites=['New York Times', 'USA Today', 'Apple News', 'CNN', 'BBC'],\\n           likert_scale=['Strongly Disagree', 'Disagree', 'Neither Agree nor Disagree', 'Agree', 'Strongly Agree'],\\n           file_path='news_survey_data.csv',\\n           random_seed=None):\\n\",\"complete_prompt\":\"import pandas as pd\\nimport random\\nimport csv\\n\\ndef task_func(n, \\n           categories=['Sports', 'Technology', 'Business', 'Politics', 'Entertainment'],\\n           news_sites=['New York Times', 'USA Today', 'Apple News', 'CNN', 'BBC'],\\n           likert_scale=['Strongly Disagree', 'Disagree', 'Neither Agree nor Disagree', 'Agree', 'Strongly Agree'],\\n           file_path='news_survey_data.csv',\\n           random_seed=None):\\n    \\\"\\\"\\\"\\n    Generate a DataFrame with random survey data based on given categories, \\n    news sites, and Likert scale responses. The function writes the generated\\n    data to a CSV file and then reads it into a Pandas DataFrame.\\n    \\n    Parameters:\\n    n (int): The number of survey responses to generate.\\n    categories (list, optional): Categories of news to choose from. Defaults to ['Sports', 'Technology', 'Business', 'Politics', 'Entertainment'].\\n    news_sites (list, optional): News sites to choose from. Defaults to ['New York Times', 'USA Today', 'Apple News', 'CNN', 'BBC'].\\n    likert_scale (list, optional): Likert scale responses to choose from. Defaults to ['Strongly Disagree', 'Disagree', 'Neither Agree nor Disagree', 'Agree', 'Strongly Agree'].\\n    file_path (str, optional): Path to save the generated CSV file. Defaults to 'news_survey_data.csv'.\\n    random_seed (int): Seed for rng. Used for generating datapoints. Defaults to None.\\n\\n    Returns:\\n    DataFrame: A pandas DataFrame with columns ['Site', 'Category', 'Response', 'Value']. \\n               The 'Value' column assigns a numerical value to the Likert scale response (starting from 1).\\n    \\n    Requirements:\\n    - pandas\\n    - random\\n    - csv\\n    \\n    Example:\\n    >>> df = task_func(5, random_seed=1)\\n    >>> print(df)\\n                 Site       Category           Response  Value\\n    0       USA Today  Entertainment  Strongly Disagree      1\\n    1      Apple News         Sports              Agree      4\\n    2             CNN       Politics              Agree      4\\n    3       USA Today         Sports              Agree      4\\n    4  New York Times       Politics              Agree      4\\n    \\n    >>> df = task_func(8, ['test', 'fun'], likert_scale=['true', 'false'], news_sites=['cat', 'dog'], random_seed=12)\\n    >>> print(df)\\n      Site Category  Response  Value\\n    0  dog      fun     False      2\\n    1  cat      fun      True      1\\n    2  dog      fun     False      2\\n    3  dog     test      True      1\\n    4  cat      fun     False      2\\n    5  cat      fun      True      1\\n    6  cat     test      True      1\\n    7  dog      fun      True      1\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Generate a DataFrame with random survey data based on given categories, news sites, and Likert scale responses. The function writes the generated data to a CSV file and then reads it into a Pandas DataFrame. >>> df = task_func(8, ['test', 'fun'], likert_scale=['true', 'false'], news_sites=['cat', 'dog'], random_seed=12) >>> print(df) Site Category  Response  Value 0  dog      fun     False      2 1  cat      fun      True      1 2  dog      fun     False      2 3  dog     test      True      1 4  cat      fun     False      2 5  cat      fun      True      1 6  cat     test      True      1 7  dog      fun      True      1\\nThe function should output with:\\n    DataFrame: A pandas DataFrame with columns ['Site', 'Category', 'Response', 'Value'].\\n    The 'Value' column assigns a numerical value to the Likert scale response (starting from 1).\\nYou should write self-contained code starting with:\\n```\\nimport pandas as pd\\nimport random\\nimport csv\\ndef task_func(n, \\n           categories=['Sports', 'Technology', 'Business', 'Politics', 'Entertainment'],\\n           news_sites=['New York Times', 'USA Today', 'Apple News', 'CNN', 'BBC'],\\n           likert_scale=['Strongly Disagree', 'Disagree', 'Neither Agree nor Disagree', 'Agree', 'Strongly Agree'],\\n           file_path='news_survey_data.csv',\\n           random_seed=None):\\n```\",\"libs\":\"['pandas', 'csv', 'random']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}