S04-Process-Data.py 文件源码

def process(df: pd.DataFrame) -> dict:
    """
    Compute aggregate results for a given data frame and return a
    dictionary containing those results to be an entry in the results
    data frame.
    """

    sensor_index = df.ix[0]['sensor_index']

    swing = int(0.5 * len(df))
    rmse_offsets = np.array(range(-swing, swing + 1))
    rmse_values = np.array([mean_offset_rmse(df, n) for n in rmse_offsets])
    lag = 0.25 * rmse_offsets[rmse_values.argmin()]

    figure = Figure(
        title='Mean RMSE Values for Sensor #{}'.format(int(sensor_index)),
        x_axis_label='Time Difference (Hours)',
        y_axis_label='Mean RMSE Value'
    )
    figure.line(0.25 * rmse_offsets, rmse_values)
    cd.display.bokeh(figure, 0.3)

    return dict(
        sensor_index=sensor_index,
        mean_temperature=df['temperature'].mean(),
        minimzed_mean_rmse=min(rmse_values),
        lag=lag
    )