{"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":"aa402664-1daf-581e-a0e4-ee5459a6008a","task_key":"default--v0~2e1~2e0~5fhf--aa402664-1daf-581e-a0e4-ee5459a6008a","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf aa402664-1daf-581e-a0e4-ee5459a6008a","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import re\\nimport nltk\\nfrom gensim.models import Word2Vec\\n# Constants\\nALPHANUMERIC = re.compile('[\\\\W_]+')\\ndef task_func(texts, stopwords=None):\\n\",\"complete_prompt\":\"import re\\nimport nltk\\nfrom gensim.models import Word2Vec\\n# Constants\\nALPHANUMERIC = re.compile('[\\\\W_]+')\\n\\n\\ndef task_func(texts, stopwords=None):\\n    \\\"\\\"\\\"\\n    Generate word vectors from a list of texts using the gensim Word2Vec model and nltk.corpus.stopwords.\\n    The texts are first cleaned by removing all non-alphanumeric characters except space,\\n    lowercased, and stop words are removed.\\n\\n    Parameters:\\n    texts (list): A list of strings.\\n    stopwords (list, optional): A list of stopwords to be removed. If not provided, nltk's stopwords will be used.\\n\\n    Returns:\\n    Word2Vec: A trained Word2Vec model.\\n\\n    Requirements:\\n    - re\\n    - nltk\\n    - gensim\\n\\n    Example:\\n    >>> texts = [\\\"Hello, World!\\\", \\\"Machine Learning is great\\\", \\\"Python is my favorite programming language\\\"]\\n    >>> model = task_func(texts)\\n    >>> vector = model.wv['python']\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Generate word vectors from a list of texts using the gensim Word2Vec model and nltk.corpus.stopwords. The texts are first cleaned by removing all non-alphanumeric characters except space, lowercased, and stop words are removed.\\nThe function should output with:\\n    Word2Vec: A trained Word2Vec model.\\nYou should write self-contained code starting with:\\n```\\nimport re\\nimport nltk\\nfrom gensim.models import Word2Vec\\n# Constants\\nALPHANUMERIC = re.compile('[\\\\W_]+')\\ndef task_func(texts, stopwords=None):\\n```\",\"libs\":\"['nltk', 'gensim', 're']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}