{"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":"4fedc293-c4c6-5bda-bd9a-77751f43b38e","task_key":"default--v0~2e1~2e0~5fhf--4fedc293-c4c6-5bda-bd9a-77751f43b38e","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 4fedc293-c4c6-5bda-bd9a-77751f43b38e","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import re\\nfrom sklearn.feature_extraction.text import TfidfVectorizer\\ndef task_func(texts):\\n\",\"complete_prompt\":\"import re\\nfrom sklearn.feature_extraction.text import TfidfVectorizer\\n\\n\\ndef task_func(texts):\\n    \\\"\\\"\\\"\\n    Processes a collection of text documents to compute the TF-IDF (Term Frequency-Inverse Document Frequency) scores\\n    for each word, excluding any URLs present in the texts. The TF-IDF scores help to identify the importance of a word\\n    within a document relative to a collection of documents.\\n\\n    Parameters:\\n    texts (list of str): A list containing the text documents to be analyzed.\\n\\n    Returns:\\n    tuple of (list of tuples, list of str):\\n        - The first element is a list of tuples, each tuple representing a document with its words' TF-IDF scores in a\\n          dense matrix format. Each score in the tuple corresponds to a word's TF-IDF score in the document.\\n        - The second element is a list of strings, representing the unique words (features) across all documents for\\n          which TF-IDF scores have been calculated. The order of words in this list matches the order of scores in the\\n          tuples of the first element.\\n\\n    Requirements:\\n    - re\\n    - sklearn.feature_extraction.text.TfidfVectorizer\\n\\n    Example:\\n    >>> task_func(['Visit https://www.python.org for more info.', 'Python is great.', 'I love Python.'])\\n    ([(0.5, 0.0, 0.5, 0.0, 0.0, 0.5, 0.0, 0.5), (0.0, 0.62276601, 0.0, 0.62276601, 0.0, 0.0, 0.4736296, 0.0), (0.0, 0.0, 0.0, 0.0, 0.79596054, 0.0, 0.60534851, 0.0)], ['for', 'great', 'info', 'is', 'love', 'more', 'python', 'visit'])\\n\\n    Notes:\\n    - URLs in the text documents are removed before calculating TF-IDF scores to ensure they do not affect the analysis.\\n    - The TF-IDF scores are rounded to 8 decimal places for precision.\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Processes a collection of text documents to compute the TF-IDF (Term Frequency-Inverse Document Frequency) scores for each word, excluding any URLs present in the texts. The TF-IDF scores help to identify the importance of a word within a document relative to a collection of documents.\\nNote that: Notes: URLs in the text documents are removed before calculating TF-IDF scores to ensure they do not affect the analysis. The TF-IDF scores are rounded to 8 decimal places for precision.\\nThe function should output with:\\n    tuple of (list of tuples, list of str):\\n    The first element is a list of tuples, each tuple representing a document with its words' TF-IDF scores in a\\n    dense matrix format. Each score in the tuple corresponds to a word's TF-IDF score in the document.\\n    The second element is a list of strings, representing the unique words (features) across all documents for\\n    which TF-IDF scores have been calculated. The order of words in this list matches the order of scores in the\\n    tuples of the first element.\\nYou should write self-contained code starting with:\\n```\\nimport re\\nfrom sklearn.feature_extraction.text import TfidfVectorizer\\ndef task_func(texts):\\n```\",\"libs\":\"['re', 'sklearn']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}