{"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":"noindex","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[]}},"task_id":"2040273f-6ace-5d73-93e2-c1418268a9ea","task_key":"default--v0~2e1~2e0~5fhf--2040273f-6ace-5d73-93e2-c1418268a9ea","task_revision_id":"2","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 2040273f-6ace-5d73-93e2-c1418268a9ea","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import numpy as np\\nimport matplotlib.pyplot as plt\\ndef task_func(mu, sigma, sample_size):\\n\",\"complete_prompt\":\"import numpy as np\\nimport matplotlib.pyplot as plt\\n\\ndef task_func(mu, sigma, sample_size):\\n    \\\"\\\"\\\"\\n    Generates a numpy array of random samples drawn from a normal distribution\\n    and plots the histogram of these samples. This function specifies the mean (mu), \\n    standard deviation (sigma), and sample size (sample_size), making it useful \\n    for simulating data, conducting statistical experiments, or initializing \\n    algorithms that require normally distributed data with visualization.\\n\\n    Parameters:\\n        mu (float): The mean of the normal distribution.\\n        sigma (float): The standard deviation of the normal distribution.\\n        sample_size (int): The number of samples to draw from the distribution.\\n\\n    Returns:\\n        ndarray: A numpy array of shape (sample_size,) containing samples drawn from the\\n                 specified normal distribution.\\n\\n    Notes:\\n        Plots a histogram of the generated samples to show the distribution. The histogram\\n        features:\\n        - X-axis labeled \\\"Sample values\\\", representing the value of the samples.\\n        - Y-axis labeled \\\"Frequency\\\", showing how often each value occurs.\\n        - Title \\\"Histogram of Generated Samples\\\", describing the content of the graph.\\n        - Number of bins set to 30, to discretize the sample data into 30 intervals.\\n        - Alpha value of 0.75 for bin transparency, making the histogram semi-transparent.\\n        - Color 'blue', giving the histogram a blue color.\\n\\n    Requirements:\\n    - numpy\\n    - matplotlib.pyplot\\n\\n    Examples:\\n    >>> data = task_func(0, 1, 1000)\\n    >>> len(data)\\n    1000\\n    >>> isinstance(data, np.ndarray)\\n    True\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Generates a numpy array of random samples drawn from a normal distribution and plots the histogram of these samples. This function specifies the mean (mu), standard deviation (sigma), and sample size (sample_size), making it useful for simulating data, conducting statistical experiments, or initializing algorithms that require normally distributed data with visualization.\\nNote that: Notes: Plots a histogram of the generated samples to show the distribution. The histogram features: X-axis labeled \\\"Sample values\\\", representing the value of the samples. Y-axis labeled \\\"Frequency\\\", showing how often each value occurs. Title \\\"Histogram of Generated Samples\\\", describing the content of the graph. Number of bins set to 30, to discretize the sample data into 30 intervals. Alpha value of 0.75 for bin transparency, making the histogram semi-transparent. Color 'blue', giving the histogram a blue color.\\nThe function should output with:\\n    ndarray: A numpy array of shape (sample_size,) containing samples drawn from the\\n    specified normal distribution.\\nYou should write self-contained code starting with:\\n```\\nimport numpy as np\\nimport matplotlib.pyplot as plt\\ndef task_func(mu, sigma, sample_size):\\n```\",\"libs\":\"['numpy', 'matplotlib']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"noindex","subproblems":[],"grids":[]}