{"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":"45c32335-b891-5f00-aab1-ebdb5f305d61","task_key":"default--v0~2e1~2e0~5fhf--45c32335-b891-5f00-aab1-ebdb5f305d61","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 45c32335-b891-5f00-aab1-ebdb5f305d61","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import pandas as pd\\nimport requests\\nfrom io import StringIO\\ndef task_func(csv_url_dict, sort_by_column=\\\"title\\\"):\\n\",\"complete_prompt\":\"import pandas as pd\\nimport requests\\nfrom io import StringIO\\n\\ndef task_func(csv_url_dict, sort_by_column=\\\"title\\\"):\\n    \\\"\\\"\\\"\\n    Fetches data from a given dictionary that includes a CSV URL and returns a pandas DataFrame sorted based on two specified columns.\\n    \\n    Parameters:\\n    - csv_url_dict (dict): The dictionary with the key \\\"URL\\\" to fetch the CSV data from.\\n    - sort_by_column (str): The column name based on which the data needs to be sorted. Default is \\\"title\\\".\\n    \\n    Returns:\\n    DataFrame: The pandas DataFrame sorted based on the specified column.\\n    \\n    Raises:\\n    - This function will raise a ValueError if the dictionary is empty or the key \\\"URL\\\" does not exist in the dictionary.\\n\\n    Requirements:\\n    - pandas\\n    - requests\\n    - io.StringIO\\n    \\n    Example:\\n    >>> task_func({\\\"URL\\\": \\\"http://example.com/data.csv\\\"}, \\\"title\\\")\\n       id   title  price\\n    0   1   Apple    0.3\\n    1   2  Banana    0.5\\n    2   3  Cherry    0.2\\n\\n    >>> task_func({\\\"URL\\\": \\\"http://example.com/test.csv\\\"}, \\\"price\\\")\\n       id   title  price\\n    2   3  Cherry    0.2\\n    0   1   Apple    0.3\\n    1   2  Banana    0.5\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Fetches data from a given dictionary that includes a CSV URL and returns a pandas DataFrame sorted based on two specified columns. >>> task_func({\\\"URL\\\": \\\"http://example.com/test.csv\\\"}, \\\"price\\\") id   title  price 2   3  Cherry    0.2 0   1   Apple    0.3 1   2  Banana    0.5\\nThe function should raise the exception for: This function will raise a ValueError if the dictionary is empty or the key \\\"URL\\\" does not exist in the dictionary.\\nThe function should output with:\\n    DataFrame: The pandas DataFrame sorted based on the specified column.\\nYou should write self-contained code starting with:\\n```\\nimport pandas as pd\\nimport requests\\nfrom io import StringIO\\ndef task_func(csv_url_dict, sort_by_column=\\\"title\\\"):\\n```\",\"libs\":\"['pandas', 'io', 'requests']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}