{"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":"noindex","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[]}},"task_id":"47631d8a-1940-5dc9-9023-5a8e511a496f","task_key":"default--v0~2e1~2e0~5fhf--47631d8a-1940-5dc9-9023-5a8e511a496f","task_revision_id":"2","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 47631d8a-1940-5dc9-9023-5a8e511a496f","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import pandas as pd\\nfrom sklearn.preprocessing import LabelEncoder\\ndef task_func(data):\\n\",\"complete_prompt\":\"import pandas as pd\\nfrom sklearn.preprocessing import LabelEncoder\\n\\n\\ndef task_func(data):\\n    \\\"\\\"\\\"\\n    Transforms categorical data into a numerical format suitable for machine learning algorithms using sklearn's\\n    LabelEncoder. This function generates a DataFrame that pairs original categorical values with their numerical\\n    encodings.\\n\\n    Parameters:\\n    data (list): List of categorical data to be encoded.\\n\\n    Returns:\\n    DataFrame: A DataFrame with columns 'Category' and 'Encoded', where 'Category' is the original data and 'Encoded'\\n    is the numerical representation.\\n\\n    Requirements:\\n    - pandas\\n    - sklearn\\n\\n    Example:\\n    >>> df = task_func(['A', 'B', 'C', 'A', 'D', 'E', 'B', 'C'])\\n    >>> print(df.to_string(index=False))\\n    Category  Encoded\\n           A        0\\n           B        1\\n           C        2\\n           A        0\\n           D        3\\n           E        4\\n           B        1\\n           C        2\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Transforms categorical data into a numerical format suitable for machine learning algorithms using sklearn's LabelEncoder. This function generates a DataFrame that pairs original categorical values with their numerical encodings.\\nThe function should output with:\\n    DataFrame: A DataFrame with columns 'Category' and 'Encoded', where 'Category' is the original data and 'Encoded'\\n    is the numerical representation.\\nYou should write self-contained code starting with:\\n```\\nimport pandas as pd\\nfrom sklearn.preprocessing import LabelEncoder\\ndef task_func(data):\\n```\",\"libs\":\"['pandas', 'sklearn']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"noindex","subproblems":[],"grids":[]}