{"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":"cb49af52-b7a0-582d-a162-012bf37e443e","task_key":"default--v0~2e1~2e0~5fhf--cb49af52-b7a0-582d-a162-012bf37e443e","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf cb49af52-b7a0-582d-a162-012bf37e443e","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"from nltk.tokenize import word_tokenize\\nfrom sklearn.feature_extraction.text import TfidfVectorizer\\nimport pandas as pd\\ndef task_func(documents):\\n\",\"complete_prompt\":\"from nltk.tokenize import word_tokenize\\nfrom sklearn.feature_extraction.text import TfidfVectorizer\\nimport pandas as pd\\n\\n\\ndef task_func(documents):\\n    \\\"\\\"\\\"\\n    Calculate the TF-IDF score of the words in a list of documents.\\n    \\n    Parameters:\\n    - documents (list of str): A list of text documents.\\n    \\n    Returns:\\n    pandas.DataFrame: A DataFrame with words as columns and documents as rows, containing the TF-IDF scores.\\n    \\n    Requirements:\\n    - nltk.tokenize.word_tokenize\\n    - sklearn.feature_extraction.text.TfidfVectorizer\\n    - pandas\\n    \\n    Example:\\n    >>> docs = ['This is the first document.', 'This document is the second document.', 'And this is the third one.', 'Is this the first document?']\\n    >>> tfidf = task_func(docs)\\n    >>> print(tfidf.shape)\\n    (4, 11)\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Calculate the TF-IDF score of the words in a list of documents.\\nThe function should output with:\\n    pandas.DataFrame: A DataFrame with words as columns and documents as rows, containing the TF-IDF scores.\\nYou should write self-contained code starting with:\\n```\\nfrom nltk.tokenize import word_tokenize\\nfrom sklearn.feature_extraction.text import TfidfVectorizer\\nimport pandas as pd\\ndef task_func(documents):\\n```\",\"libs\":\"['nltk', 'pandas', 'sklearn']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}