{"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":"4b0a2bec-c8a4-5abc-952d-21979e564eca","task_key":"default--v0~2e1~2e0~5fhf--4b0a2bec-c8a4-5abc-952d-21979e564eca","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 4b0a2bec-c8a4-5abc-952d-21979e564eca","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import pandas as pd\\nfrom texttable import Texttable\\nimport os\\nimport glob\\ndef task_func(data_dir='./data/'):\\n\",\"complete_prompt\":\"import pandas as pd\\nfrom texttable import Texttable\\nimport os\\nimport glob\\n\\ndef task_func(data_dir='./data/'):\\n    \\\"\\\"\\\"\\n    Generates a summary table of all ascendingly sorted CSV files in a specified directory using Texttable. \\n    If an empty CSV file is encountered, a pandas.errors.EmptyDataError is raised.\\n\\n    Parameters:\\n    - data_dir (str): The directory to search for CSV files. Default is './data/'.\\n\\n    Returns:\\n    - str: A string representation of the table summarizing the CSV files. Each row contains the file name, number of rows, and number of columns.\\n\\n    Raises:\\n    - FileNotFoundError: If the specified directory does not exist.\\n    - ValueError: If there are no CSV files in the specified directory.\\n    - pandas.errors.EmptyDataError: If an empty CSV file is encountered.\\n\\n    Requirements:\\n    - pandas\\n    - texttable\\n    - os\\n    - glob\\n\\n    Example:\\n    >>> data_dir = './test_data/'\\n    >>> dummy_files = create_dummy_files(data_dir)\\n    >>> print(task_func(data_dir))\\n    +-----------+------+---------+\\n    |   File    | Rows | Columns |\\n    +===========+======+=========+\\n    | test2.csv | 10   | 4       |\\n    +-----------+------+---------+\\n    | test2.csv | 10   | 4       |\\n    +-----------+------+---------+\\n    | test1.csv | 5    | 2       |\\n    +-----------+------+---------+\\n    | test1.csv | 5    | 2       |\\n    +-----------+------+---------+\\n    >>> tear_down_dummy_files(data_dir, dummy_files)\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Generates a summary table of all ascendingly sorted CSV files in a specified directory using Texttable. If an empty CSV file is encountered, a pandas.errors.EmptyDataError is raised.\\nThe function should raise the exception for: FileNotFoundError: If the specified directory does not exist. ValueError: If there are no CSV files in the specified directory. pandas.errors.EmptyDataError: If an empty CSV file is encountered.\\nThe function should output with:\\n    str: A string representation of the table summarizing the CSV files. Each row contains the file name, number of rows, and number of columns.\\nYou should write self-contained code starting with:\\n```\\nimport pandas as pd\\nfrom texttable import Texttable\\nimport os\\nimport glob\\ndef task_func(data_dir='./data/'):\\n```\",\"libs\":\"['glob', 'pandas', 'texttable', 'os']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}