{"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":"470c3d6b-ac38-5ed7-954f-b75c86e9e1e3","task_key":"default--v0~2e1~2e0~5fhf--470c3d6b-ac38-5ed7-954f-b75c86e9e1e3","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 470c3d6b-ac38-5ed7-954f-b75c86e9e1e3","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import tensorflow as tf\\nfrom sklearn.model_selection import KFold\\nfrom sklearn.preprocessing import MinMaxScaler\\ndef task_func(X, y, n_splits, batch_size, epochs):\\n\",\"complete_prompt\":\"import tensorflow as tf\\nfrom sklearn.model_selection import KFold\\nfrom sklearn.preprocessing import MinMaxScaler\\n\\ndef task_func(X, y, n_splits, batch_size, epochs):\\n    \\\"\\\"\\\"\\n    Trains a simple neural network on provided data using k-fold cross-validation.\\n    The network has one hidden layer with 20 neurons and ReLU activation, and\\n    an output layer with sigmoid activation for binary classification.\\n\\n    Parameters:\\n        X (numpy.array): The input data.\\n        y (numpy.array): The target data.\\n        n_splits (int): The number of splits for k-fold cross-validation. Default is 5.\\n        batch_size (int): The size of the batch used during training. Default is 32.\\n        epochs (int): The number of epochs for training the model. Default is 1.\\n\\n    Returns:\\n        list: A list containing the training history of the model for each fold. Each history\\n              object includes training loss and accuracy.\\n\\n    Requirements:\\n    - tensorflow\\n    - sklearn.model_selection.KFold\\n    - sklearn.preprocessing.MinMaxScaler\\n\\n    Examples:\\n    >>> import numpy as np\\n    >>> X = np.random.rand(100, 10)\\n    >>> y = np.random.randint(0, 2, 100)\\n    >>> history = task_func(X, y, 5, 32, 1)\\n    >>> isinstance(history, list)\\n    True\\n    >>> len(history)\\n    5\\n    >>> all('loss' in hist.history.keys() for hist in history)\\n    True\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Trains a simple neural network on provided data using k-fold cross-validation. The network has one hidden layer with 20 neurons and ReLU activation, and an output layer with sigmoid activation for binary classification.\\nThe function should output with:\\n    list: A list containing the training history of the model for each fold. Each history\\n    object includes training loss and accuracy.\\nYou should write self-contained code starting with:\\n```\\nimport tensorflow as tf\\nfrom sklearn.model_selection import KFold\\nfrom sklearn.preprocessing import MinMaxScaler\\ndef task_func(X, y, n_splits, batch_size, epochs):\\n```\",\"libs\":\"['tensorflow', 'sklearn']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}