{"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":"ce1ecdcd-e838-56d4-91ef-1414918d4bcd","task_key":"default--v0~2e1~2e0~5fhf--ce1ecdcd-e838-56d4-91ef-1414918d4bcd","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf ce1ecdcd-e838-56d4-91ef-1414918d4bcd","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import numpy as np\\nimport pandas as pd\\nfrom sklearn.ensemble import RandomForestClassifier\\ndef task_func(\\n    feature_array,\\n    target_array,\\n    feature_names=[\\\"f1\\\", \\\"f2\\\", \\\"f3\\\", \\\"f4\\\", \\\"f5\\\"],\\n    target_name=\\\"target\\\",\\n    seed=None,\\n):\\n\",\"complete_prompt\":\"import numpy as np\\nimport pandas as pd\\nfrom sklearn.ensemble import RandomForestClassifier\\n\\n\\ndef task_func(\\n    feature_array,\\n    target_array,\\n    feature_names=[\\\"f1\\\", \\\"f2\\\", \\\"f3\\\", \\\"f4\\\", \\\"f5\\\"],\\n    target_name=\\\"target\\\",\\n    seed=None,\\n):\\n    \\\"\\\"\\\"\\n    Shuffle the columns of a given numpy array and train a Random Forest Classifier on the shuffled data.\\n\\n    Parameters:\\n    - feature_array (numpy.ndarray): 2D array containing the feature data with shape (n_samples, n_features).\\n    - target_array (numpy.ndarray): 1D array containing the target data with shape (n_samples,).\\n    - feature_names (list of str, optional): Names of the features corresponding to the columns in `feature_array`.\\n      Defaults to ['f1', 'f2', 'f3', 'f4', 'f5'].\\n    - target_name (str, optional): Name of the target column. Defaults to 'target'.\\n    - seed (int, optional): Seed for the random number generator to make shuffling reproducible. Defaults to None.\\n\\n    Returns:\\n    sklearn.ensemble.RandomForestClassifier: A trained Random Forest Classifier on the shuffled feature data.\\n\\n    Requirements:\\n    - numpy\\n    - pandas\\n    - sklearn\\n\\n    Examples:\\n    >>> feature_array = np.array([[1, 2, 3, 4, 5], [6, 7, 8, 9, 10]])\\n    >>> target_array = np.array([0, 1])\\n    >>> clf = task_func(feature_array, target_array)\\n    >>> type(clf)\\n    <class 'sklearn.ensemble._forest.RandomForestClassifier'>\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Shuffle the columns of a given numpy array and train a Random Forest Classifier on the shuffled data.\\nThe function should output with:\\n    sklearn.ensemble.RandomForestClassifier: A trained Random Forest Classifier on the shuffled feature data.\\nYou should write self-contained code starting with:\\n```\\nimport numpy as np\\nimport pandas as pd\\nfrom sklearn.ensemble import RandomForestClassifier\\ndef task_func(\\n    feature_array,\\n    target_array,\\n    feature_names=[\\\"f1\\\", \\\"f2\\\", \\\"f3\\\", \\\"f4\\\", \\\"f5\\\"],\\n    target_name=\\\"target\\\",\\n    seed=None,\\n):\\n```\",\"libs\":\"['pandas', '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":[]}