{"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":"0f5bd7f8-0058-55cb-89c7-bcb664f362de","task_key":"default--v0~2e1~2e0~5fhf--0f5bd7f8-0058-55cb-89c7-bcb664f362de","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 0f5bd7f8-0058-55cb-89c7-bcb664f362de","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import numpy as np\\nfrom sklearn.preprocessing import StandardScaler\\nfrom sklearn.metrics import mean_squared_error\\ndef task_func(num_samples=1000, k=5, d=2,  random_seed=None):\\n\",\"complete_prompt\":\"import numpy as np\\nfrom sklearn.preprocessing import StandardScaler\\nfrom sklearn.metrics import mean_squared_error\\n\\n\\ndef task_func(num_samples=1000, k=5, d=2,  random_seed=None):\\n    \\\"\\\"\\\"\\n    Generate a dataset consisting of random numbers sampled from a gaussian\\n    normal distribution that are transformed by applying a linear\\n    transformation. Standardize it with the StandardScaler of sklearn,\\n    and calculate the average square error between the original dataset\\n    and the standardized dataset.\\n\\n    Parameters:\\n    - num_samples (int): The number of samples to generate. Default is 1000.\\n    - k (float): Multiplicative Factor in linear transformation. Default is 5.\\n    - d (float): Offset in linear transformation. Default is 2.\\n    - random_seed (int): The random seed for reproducibility. Default is None.\\n\\n    Returns:\\n    float: The mean squared error between the original and standardized data.\\n           This value represents the average squared difference between each\\n           original value and its standardized counterpart. The MSE can vary\\n           significantly depending on the random seed and the specified \\n           parameters of the linear transformation.\\n\\n    Requirements:\\n    - numpy\\n    - sklearn.preprocessing.StandardScaler\\n    - sklearn.metrics.mean_squared_error\\n\\n    Example:\\n    >>> mse = task_func(num_samples=123, k=-6.4, d=12.1, random_seed=2)\\n    >>> print(mse)\\n    193.04172078372736\\n\\n    >>> mse = task_func()\\n    >>> print(mse)\\n    19.03543917135251\\n\\n    >>> mse = task_func(k=1, d=0)\\n    >>> print(mse)\\n    0.001113785307245742\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Generate a dataset consisting of random numbers sampled from a gaussian normal distribution that are transformed by applying a linear transformation. Standardize it with the StandardScaler of sklearn, and calculate the average square error between the original dataset and the standardized dataset. >>> mse = task_func() >>> print(mse) 19.03543917135251 >>> mse = task_func(k=1, d=0) >>> print(mse) 0.001113785307245742\\nThe function should output with:\\n    float: The mean squared error between the original and standardized data.\\n    This value represents the average squared difference between each\\n    original value and its standardized counterpart. The MSE can vary\\n    significantly depending on the random seed and the specified\\n    parameters of the linear transformation.\\nYou should write self-contained code starting with:\\n```\\nimport numpy as np\\nfrom sklearn.preprocessing import StandardScaler\\nfrom sklearn.metrics import mean_squared_error\\ndef task_func(num_samples=1000, k=5, d=2,  random_seed=None):\\n```\",\"libs\":\"['numpy', 'sklearn']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}