{"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":"0565b973-94a5-5c4c-803e-89e0cbbb5e53","task_key":"default--v0~2e1~2e0~5fhf--0565b973-94a5-5c4c-803e-89e0cbbb5e53","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 0565b973-94a5-5c4c-803e-89e0cbbb5e53","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import numpy as np\\nfrom sklearn.decomposition import PCA\\nimport matplotlib.pyplot as plt\\nimport seaborn as sns\\ndef task_func(n_components=2, N_SAMPLES=500, N_FEATURES=50, random_seed=None):\\n\",\"complete_prompt\":\"import numpy as np\\nfrom sklearn.decomposition import PCA\\nimport matplotlib.pyplot as plt\\nimport seaborn as sns\\n\\n\\ndef task_func(n_components=2, N_SAMPLES=500, N_FEATURES=50, random_seed=None):\\n    \\\"\\\"\\\"\\n    Generate a high-dimensional dataset, run PCA to reduce its dimensionality, and then draw a heatmap of\\n    the covariance matrix of the transformed data.\\n\\n    Parameters:\\n    n_components (int, optional): The number of components for PCA. Defaults to 2.\\n    N_SAMPLES (int, optional): Number of samples in the dataset. Defaults to 500.\\n    N_FEATURES (int, optional): Number of features in the dataset. Defaults to 50.\\n    random_seed (int, optional): Seed for the numpy and sklearn random number generator. Defaults to None.\\n\\n    Returns:\\n    tuple:\\n        transformed_data (ndarray): The transformed data of shape (N_SAMPLES, n_components).\\n        heatmap_axes (Axes): The heatmap of the covariance matrix of the transformed data or None if n_components=1.\\n\\n    Requirements:\\n    - numpy\\n    - sklearn.decomposition.PCA\\n    - matplotlib.pyplot\\n    - seaborn\\n\\n    Example:\\n    >>> transformed, ax = task_func(n_components=2, random_seed=42)\\n    >>> transformed.shape\\n    (500, 2)\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Generate a high-dimensional dataset, run PCA to reduce its dimensionality, and then draw a heatmap of the covariance matrix of the transformed data.\\nThe function should output with:\\n    tuple:\\n    transformed_data (ndarray): The transformed data of shape (N_SAMPLES, n_components).\\n    heatmap_axes (Axes): The heatmap of the covariance matrix of the transformed data or None if n_components=1.\\nYou should write self-contained code starting with:\\n```\\nimport numpy as np\\nfrom sklearn.decomposition import PCA\\nimport matplotlib.pyplot as plt\\nimport seaborn as sns\\ndef task_func(n_components=2, N_SAMPLES=500, N_FEATURES=50, random_seed=None):\\n```\",\"libs\":\"['sklearn', 'numpy', 'matplotlib', 'seaborn']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}