{"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":"c10ec801-5d7e-5bf5-a05e-cea3a87cbe61","task_key":"default--v0~2e1~2e0~5fhf--c10ec801-5d7e-5bf5-a05e-cea3a87cbe61","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf c10ec801-5d7e-5bf5-a05e-cea3a87cbe61","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import nltk\\nfrom string import punctuation\\nimport pandas as pd\\ndef task_func(text):\\n\",\"complete_prompt\":\"import nltk\\nfrom string import punctuation\\nimport pandas as pd\\n\\n\\ndef task_func(text):\\n    \\\"\\\"\\\"\\n    Finds all words in a text, that are seperated by whitespace, \\n    beginning with the \\\"$\\\" character and computes their number of occurences.\\n\\n    Parameters:\\n    text (str): The input text.\\n\\n    Returns:\\n    DataFrame: A pandas DataFrame with two columns: \\\"Word\\\" and \\\"Frequency\\\". \\n               \\\"Word\\\" contains the '$' prefixed words, and \\\"Frequency\\\" contains their occurrences.\\n\\n               \\n    Raises:\\n    ValueError: if text is not a string\\n    \\n    Requirements:\\n    - nltk\\n    - string\\n    - pandas\\n\\n    Note:\\n    The function ignores words that are entirely made up of punctuation, even if they start with a '$'.\\n\\n    Example:\\n    >>> text = \\\"$abc def $efg $hij klm $ $abc $abc $hij $hij\\\"\\n    >>> task_func(text)\\n       Word  Frequency\\n    0  $abc          3\\n    1  $efg          1\\n    2  $hij          3\\n\\n    >>> text = \\\"$hello this i$s a $test $test $test\\\"\\n    >>> task_func(text)\\n         Word  Frequency\\n    0  $hello          1\\n    1   $test          3\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Finds all words in a text, that are seperated by whitespace, beginning with the \\\"$\\\" character and computes their number of occurences. >>> text = \\\"$hello this i$s a $test $test $test\\\" >>> task_func(text) Word  Frequency 0  $hello          1 1   $test          3\\nNote that: The function ignores words that are entirely made up of punctuation, even if they start with a '$'.\\nThe function should raise the exception for: ValueError: if text is not a string\\nThe function should output with:\\n    DataFrame: A pandas DataFrame with two columns: \\\"Word\\\" and \\\"Frequency\\\".\\n    \\\"Word\\\" contains the '$' prefixed words, and \\\"Frequency\\\" contains their occurrences.\\nYou should write self-contained code starting with:\\n```\\nimport nltk\\nfrom string import punctuation\\nimport pandas as pd\\ndef task_func(text):\\n```\",\"libs\":\"['nltk', 'pandas', 'string']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}