时间戳

首页 > 解决方案 > 如何在 Facebook Prophet (Python) 中检索训练有素的超参数？

python - 如何在 Facebook Prophet (Python) 中检索训练有素的超参数？

问题描述

我想在使用 Facebook Prophet 训练时间序列模型后检索超参数，以便我可以在第二个模型中使用学习值。

这是我尝试过的。

    from prophet import Prophet

    # Train the first DataFrame
    m1 = Prophet()
    m1.fit(df1)
    future = m1.make_future_dataframe(periods=365)
    forecast = m1.predict(df1)

    m2 = Prophet(
        daily_seasonality = m1.daily_seasonality,
        weekly_seasonality = m1.weekly_seasonality,
        yearly_seasonality = m1.yearly_seasonality,
        seasonality_prior_scale = m1.seasonality_prior_scale,
        changepoint_prior_scale = m1.changepoint_prior_scale,
        uncertainty_samples = m1.uncertainty_samples,
        seasonality_mode = m1.seasonality_mode,
        interval_width = m1.interval_width,
        n_changepoints = m1.n_changepoints,
    )

    # Train the second DataFrame
    m2.fit(df2)

但是，当我尝试调试 hyparameter 值时，看起来m2是用相同的值m1初始化的。

如何从中获取训练的参数m1？

标签： pythontime-seriestransfer-learningfacebook-prophet

解决方案

推荐阅读