简体   繁体   English

为什么 Amazon Forecast 无法训练预测器?

[英]Why Amazon Forecast cannot train the predictor?

While training my predictor I came across this error and I got stuck how to fix it.在训练我的预测器时,我遇到了这个错误,我被困住了如何修复它。

I have two data-series, a "Target time-series data" with 9234 rows and a single "item_id" and a second one that is "Related time-series data" with the same number of rows as I only have a single id.我有两个数据系列,一个“目标时间序列数据”有 9234 行和一个“item_id”,第二个是“相关时间序列数据”,其行数与我只有一个 id .

I'm setting de data with a window of 180 days, what is exactly the difference between the second and the first number that has appeared on the error, 9414 - 9234 = 180.我正在使用 180 天的 window 设置数据,错误中出现的第二个数字和第一个数字 9414 - 9234 = 180 之间到底有什么区别。

We were unable to train your predictor.
Please ensure there are no missing values for any items in the related time series, All items need data until 2020-03-15 00:00:00.0. For example, following items have missing data: item: brl only has 9234/9414 required datapoints starting 1994-06-07 00:00:00.0, please refer to documentation for additional details.

Once my data don't have missing data and it's on a daily basis why is it returning this error?一旦我的数据没有丢失数据并且每天都会出现,为什么它会返回此错误? My data starts on 1994-06-07 and ends on 2019-09-17.我的数据从 1994-06-07 开始,到 2019-09-17 结束。 Why should I have 9414 data points rather than 9234?为什么我应该有 9414 个数据点而不是 9234 个? Should I take out 180 days in my "Target time-series data"?我应该在“目标时间序列数据”中取出 180 天吗?

The future values of the related time-series data must be known.必须知道相关时间序列数据的未来值。

Example of a good related-time series: You know past and future days in which marketing has or will send email newsletters promoting the product you're forecasting.良好的相关时间序列示例:您知道营销部门已经或将要发送 email 时事通讯来宣传您预测的产品的过去和未来日子。 You can use this data as a related-time series.您可以将此数据用作相关时间序列。

Example of a bad related-time series: You notice that Google searches for your brand correlated with the sale of your product.不良相关时间序列示例:您注意到 Google 搜索与您的产品销售相关的品牌。 As a result you want to use it as a related-time series.因此,您希望将其用作相关时间序列。 Since you don't know how many searches will occur in the future, so you can't use this as a related time series.由于您不知道将来会发生多少次搜索,因此您不能将其用作相关的时间序列。

In you case, You have TARGET_TIME_SERIES data for 9414 days and you want to predict demand for the next 180 days.在您的情况下,您有 9414 天的 TARGET_TIME_SERIES 数据,并且您想预测未来 180 天的需求。 That means your RELATED_TIME_SERIES data should be 9594 days.这意味着您的 RELATED_TIME_SERIES 数据应该是 9594 天。

Edit: I have not tested this with amazon's forecasting product.编辑:我没有用亚马逊的预测产品对此进行测试。 I'm basing my answer on working with Facebook Prophet (which is one of the models amazon forcast uses).我的答案基于使用 Facebook Prophet(这是亚马逊预测使用的模型之一)。 Please let me know if my solution worked.请让我知道我的解决方案是否有效。

just came across this thread.刚刚遇到这个线程。 I had a question as it was mentioned that Related data could be used with FB prophet, which I am not aware of.我有一个问题,因为有人提到相关数据可以与 FB 先知一起使用,我不知道。 Could you please guide me as to how to use related data with FB prophet.您能否指导我如何使用 FB 先知的相关数据。 Would be really helpful.真的很有帮助。

BR, Nitin BR,尼丁

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM