{"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":"ab132fb0-e879-5306-b784-cfbf80f9b374","task_key":"default--v0~2e1~2e0~5fhf--ab132fb0-e879-5306-b784-cfbf80f9b374","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf ab132fb0-e879-5306-b784-cfbf80f9b374","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import pandas as pd\\nfrom sklearn.model_selection import train_test_split\\ndef task_func(df, target_column, column_to_remove=\\\"c\\\", test_size=0.2):\\n\",\"complete_prompt\":\"import pandas as pd\\nfrom sklearn.model_selection import train_test_split\\n\\n\\ndef task_func(df, target_column, column_to_remove=\\\"c\\\", test_size=0.2):\\n    \\\"\\\"\\\"\\n    Split the data into train and test datasets after removing a specified column if it exists.\\n\\n    Parameters:\\n    - df (dict): The input dataframe.\\n    - target_column (str): The name of the target column.\\n    - column_to_remove (str): The name of the column to remove. Defaults to 'c'.\\n    - test_size (float): The ratio of test data in split output. Defaults to .2.\\n\\n    Returns:\\n    - X_train (pd.DataFrame): Split features for training.\\n    - X_test  (pd.DataFrame): Split features for testing.\\n    - y_train    (pd.Series): Split target values for training.\\n    - y_test     (pd.Series): Split target values for testing.\\n\\n    Requirements:\\n    - pandas\\n    - sklearn\\n\\n    Examples:\\n    >>> data = {\\n    ... 'a': [1, 2, 3, 4],\\n    ... 'b': [5, 6, 7, 8],\\n    ... 'c': [9, 10, 11, 12],\\n    ... 'target': [0, 1, 0, 1]\\n    ... }\\n    >>> X_train, _, _, _ = task_func(data, 'target')\\n    >>> type(X_train), X_train.shape\\n    (<class 'pandas.core.frame.DataFrame'>, (3, 2))\\n    >>> data = {\\n    ... 'x1': [10, 20, 30, 40],\\n    ... 'x2': [50, 60, 70, 80],\\n    ... 'x3': [90, 100, 110, 120],\\n    ... 'outcome': [1, 2, 3, 4]\\n    ... }\\n    >>> df2 = pd.DataFrame(data)\\n    >>> _, _, _, y_test = task_func(df2, 'outcome', 'x3', .25)\\n    >>> type(y_test), y_test.shape\\n    (<class 'pandas.core.series.Series'>, (1,))\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Split the data into train and test datasets after removing a specified column if it exists.\\nThe function should output with:\\n    X_train (pd.DataFrame): Split features for training.\\n    X_test  (pd.DataFrame): Split features for testing.\\n    y_train    (pd.Series): Split target values for training.\\n    y_test     (pd.Series): Split target values for testing.\\nYou should write self-contained code starting with:\\n```\\nimport pandas as pd\\nfrom sklearn.model_selection import train_test_split\\ndef task_func(df, target_column, column_to_remove=\\\"c\\\", test_size=0.2):\\n```\",\"libs\":\"['pandas', 'sklearn']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}