{"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":"noindex","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[]}},"task_id":"0e8ed6c9-e87d-55c7-81ec-abd975e01095","task_key":"default--v0~2e1~2e0~5fhf--0e8ed6c9-e87d-55c7-81ec-abd975e01095","task_revision_id":"2","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 0e8ed6c9-e87d-55c7-81ec-abd975e01095","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import pandas as pd\\nfrom sklearn.linear_model import LinearRegression\\nimport matplotlib.pyplot as plt\\ndef task_func(df):\\n\",\"complete_prompt\":\"import pandas as pd\\nfrom sklearn.linear_model import LinearRegression\\nimport matplotlib.pyplot as plt\\n\\ndef task_func(df):\\n    \\\"\\\"\\\"\\n    Performs linear regression on a DataFrame using 'date' (converted to ordinal) as the predictor for 'value'. It plots both the original and \\n    predicted values, showcasing the linear relationship.\\n\\n    Parameters:\\n        df (DataFrame): DataFrame containing 'group', 'date' (in datetime format), and 'value' columns.\\n\\n    Returns:\\n        tuple: Consists of the LinearRegression model, the predictions array, and the matplotlib Axes object of the plot.\\n               The Axes object will have a title 'Value vs Date (Linear Regression Prediction)', \\n               x-axis labeled as 'Date (ordinal)', and y-axis labeled as 'Value'.\\n\\n    Raises:\\n        ValueError: If 'df' is not a valid DataFrame, lacks the required columns, or if 'date' column is not in datetime format.\\n\\n    Requirements:\\n        - pandas\\n        - sklearn\\n        - matplotlib\\n\\n    Example:\\n        >>> df = pd.DataFrame({\\n        ...     \\\"group\\\": [\\\"A\\\", \\\"A\\\", \\\"A\\\", \\\"B\\\", \\\"B\\\"],\\n        ...     \\\"date\\\": pd.to_datetime([\\\"2022-01-02\\\", \\\"2022-01-13\\\", \\\"2022-02-01\\\", \\\"2022-02-23\\\", \\\"2022-03-05\\\"]),\\n        ...     \\\"value\\\": [10, 20, 16, 31, 56],\\n        ... })\\n        >>> model, predictions, ax = task_func(df)\\n        >>> plt.show()  # Displays the plot with original and predicted values\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Performs linear regression on a DataFrame using 'date' (converted to ordinal) as the predictor for 'value'. It plots both the original and predicted values, showcasing the linear relationship.\\nThe function should raise the exception for: ValueError: If 'df' is not a valid DataFrame, lacks the required columns, or if 'date' column is not in datetime format.\\nThe function should output with:\\n    tuple: Consists of the LinearRegression model, the predictions array, and the matplotlib Axes object of the plot.\\n    The Axes object will have a title 'Value vs Date (Linear Regression Prediction)',\\n    x-axis labeled as 'Date (ordinal)', and y-axis labeled as 'Value'.\\nYou should write self-contained code starting with:\\n```\\nimport pandas as pd\\nfrom sklearn.linear_model import LinearRegression\\nimport matplotlib.pyplot as plt\\ndef task_func(df):\\n```\",\"libs\":\"['pandas', 'matplotlib', 'sklearn']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"noindex","subproblems":[],"grids":[]}