{"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":"a24735db-c917-5418-b479-f3f69301165e","task_key":"default--v0~2e1~2e0~5fhf--a24735db-c917-5418-b479-f3f69301165e","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf a24735db-c917-5418-b479-f3f69301165e","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"# Importing the required libraries\\nimport re\\nimport matplotlib.pyplot as plt\\nimport numpy as np\\nimport pandas as pd\\nfrom sklearn.feature_extraction.text import CountVectorizer\\nfrom nltk.corpus import stopwords\\ndef task_func(text, n=2):\\n\",\"complete_prompt\":\"# Importing the required libraries\\nimport re\\nimport matplotlib.pyplot as plt\\nimport numpy as np\\nimport pandas as pd\\nfrom sklearn.feature_extraction.text import CountVectorizer\\nfrom nltk.corpus import stopwords\\n\\n\\ndef task_func(text, n=2):\\n    \\\"\\\"\\\"\\n    Analyzes a text string, removing duplicate consecutive words and stopwords defined by nltk.corpus,\\n    generates a square co-occurrence matrix of words, and plots this matrix.\\n\\n    Parameters:\\n    - text (str): Input text to be analyzed.\\n    - n (int, optional): Size of n-grams for the co-occurrence matrix. Defaults to 2.\\n\\n    Returns:\\n    - tuple:\\n        - pd.DataFrame: Square co-occurrence matrix of words.\\n        - matplotlib.axes.Axes: Plot object of the co-occurrence matrix.\\n\\n    Requirements:\\n        - re\\n        - pandas\\n        - matplotlib.pyplot\\n        - numpy\\n        - sklearn.feature_extraction.text\\n        - nltk.corpus\\n\\n    Example:\\n    >>> import matplotlib\\n    >>> text = \\\"hello hello world world\\\"\\n    >>> df, ax = task_func(text, n=2)\\n    >>> df.columns.tolist()\\n    ['hello world']\\n    >>> df.index.tolist()\\n    ['hello world']\\n    >>> df.iloc[0, 0]\\n    0\\n    >>> isinstance(ax, matplotlib.axes.Axes)\\n    True\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Analyzes a text string, removing duplicate consecutive words and stopwords defined by nltk.corpus, generates a square co-occurrence matrix of words, and plots this matrix.\\nThe function should output with:\\n    tuple:\\n    pd.DataFrame: Square co-occurrence matrix of words.\\n    matplotlib.axes.Axes: Plot object of the co-occurrence matrix.\\nYou should write self-contained code starting with:\\n```\\n# Importing the required libraries\\nimport re\\nimport matplotlib.pyplot as plt\\nimport numpy as np\\nimport pandas as pd\\nfrom sklearn.feature_extraction.text import CountVectorizer\\nfrom nltk.corpus import stopwords\\ndef task_func(text, n=2):\\n```\",\"libs\":\"['nltk', 'pandas', 'matplotlib', 'numpy', 'sklearn', 're']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}