{"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":"27d6125f-c01a-5424-adb7-300202be76fb","task_key":"default--v0~2e1~2e0~5fhf--27d6125f-c01a-5424-adb7-300202be76fb","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 27d6125f-c01a-5424-adb7-300202be76fb","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import re\\nimport nltk\\nimport pandas as pd\\nfrom sklearn.feature_extraction.text import CountVectorizer\\n# Make sure to download NLTK stopwords\\nnltk.download('stopwords')\\n# Define a regex pattern for matching all non-alphanumeric characters\\nALPHANUMERIC = re.compile('[\\\\W_]+')\\n# Load NLTK's list of English stop words\\nSTOPWORDS = nltk.corpus.stopwords.words('english')\\ndef task_func(texts):\\n\",\"complete_prompt\":\"import re\\nimport nltk\\nimport pandas as pd\\nfrom sklearn.feature_extraction.text import CountVectorizer\\n\\n# Make sure to download NLTK stopwords\\nnltk.download('stopwords')\\n\\n# Define a regex pattern for matching all non-alphanumeric characters\\nALPHANUMERIC = re.compile('[\\\\W_]+')\\n\\n# Load NLTK's list of English stop words\\nSTOPWORDS = nltk.corpus.stopwords.words('english')\\n\\n\\ndef task_func(texts):\\n    \\\"\\\"\\\"\\n    Creates a document-term matrix (DTM) from a list of text documents using CountVectorizer from Scikit-learn.\\n    Texts are preprocessed by removing non-alphanumeric characters (excluding spaces),\\n    converting to lowercase, and excluding English stop words defined in NLTK.\\n\\n    Parameters:\\n    - texts (list of str): The list of text documents to convert into a DTM.\\n\\n    Returns:\\n    - pd.DataFrame: A DataFrame where rows represent documents and columns represent unique terms;\\n                    cell values indicate the frequency of a term in a document.\\n\\n    Requirements:\\n    - re\\n    - nltk\\n    - pandas\\n    - sklearn.feature_extraction.text\\n\\n    Example:\\n    >>> texts = [\\\"Hello, world!\\\", \\\"Machine learning is great.\\\", \\\"Python is my favorite programming language.\\\"]\\n    >>> dtm = task_func(texts)\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Creates a document-term matrix (DTM) from a list of text documents using CountVectorizer from Scikit-learn. Texts are preprocessed by removing non-alphanumeric characters (excluding spaces), converting to lowercase, and excluding English stop words defined in NLTK.\\nThe function should output with:\\n    pd.DataFrame: A DataFrame where rows represent documents and columns represent unique terms;\\n    cell values indicate the frequency of a term in a document.\\nYou should write self-contained code starting with:\\n```\\nimport re\\nimport nltk\\nimport pandas as pd\\nfrom sklearn.feature_extraction.text import CountVectorizer\\n# Make sure to download NLTK stopwords\\nnltk.download('stopwords')\\n# Define a regex pattern for matching all non-alphanumeric characters\\nALPHANUMERIC = re.compile('[\\\\W_]+')\\n# Load NLTK's list of English stop words\\nSTOPWORDS = nltk.corpus.stopwords.words('english')\\ndef task_func(texts):\\n```\",\"libs\":\"['nltk', 'pandas', '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":[]}