如何在scikit-learn中预测时间序列? [英] How to predict time series in scikit-learn?

问题描述

Scikit-learn利用基于fit和predict方法的非常方便的方法.我有适合fit和predict的格式的时间序列数据.

Scikit-learn utilizes a very convenient approach based on fit and predict methods. I have time-series data in the format suited for fit and predict.

例如，我有以下Xs:

[[1.0, 2.3, 4.5], [6.7, 2.7, 1.2], ..., [3.2, 4.7, 1.1]]

和相应的ys:

[[1.0], [2.3], ..., [7.7]]

这些数据具有以下含义. ys中存储的值形成一个时间序列. Xs中的值是对应于时间的因素"，已知它们对ys中的值有一些影响(例如:温度，湿度和大气压).

These data have the following meaning. The values stored in ys form a time series. The values in Xs are corresponding time dependent "factors" that are known to have some influence on the values in ys (for example: temperature, humidity and atmospheric pressure).

现在，我当然可以使用fit(Xs,ys).但是随后我得到一个模型，其中ys中的将来值仅取决于因素，而不取决于(至少直接地)先前的Y值，这是该模型的局限性.我希望有一个模型，其中Y_n也依赖于Y_{n-1}和Y_{n-2}等.例如，我可能要使用指数移动平均线作为模型. scikit-learn中最优雅的方法是什么

Now, of course, I can use fit(Xs,ys). But then I get a model in which future values in ys depend only on factors and do not dependend on the previous Y values (at least directly) and this is a limitation of the model. I would like to have a model in which Y_n depends also on Y_{n-1} and Y_{n-2} and so on. For example I might want to use an exponential moving average as a model. What is the most elegant way to do it in scikit-learn

添加

正如评论中提到的，我可以通过添加ys来扩展Xs.但是这种方式有一些局限性.例如，如果我将y的最后5个值作为5个新列添加到X，则会丢失有关ys的时间顺序的信息.例如，在X中没有指示第5列中的值跟随第4列中的值，依此类推.作为模型，我可能希望对最后五个ys进行线性拟合，并使用找到的线性函数进行预测.但是，如果我在5列中有5个值，那就不是那么简单了.

As it has been mentioned in the comments, I can extend Xs by adding ys. But this way has some limitations. For example, if I add the last 5 values of y as 5 new columns to X, the information about time ordering of ys is lost. For example, there is no indication in X that values in the 5th column follows value in the 4th column and so on. As a model, I might want to have a linear fit of the last five ys and use the found linear function to make a prediction. But if I have 5 values in 5 columns it is not so trivial.

添加2

为了使我的问题更加清楚，我想举一个具体的例子.我想要一个线性"模型，其中y_n = c + k1*x1 + k2*x2 + k3*x3 + k4*EMOV_n，其中EMOV_n只是指数移动平均值.如何在scikit-learn中实现这个简单的模型?

To make my problem even more clear, I would like to give one concrete example. I would like to have a "linear" model in which y_n = c + k1*x1 + k2*x2 + k3*x3 + k4*EMOV_n, where EMOV_n is just an exponential moving average. How, can I implement this simple model in scikit-learn?

推荐答案

关于指数加权移动平均值，这可能是您正在寻找的 :

This might be what you're looking for, with regard to the exponentially weighted moving average:

import pandas, numpy
ewma = pandas.stats.moments.ewma
EMOV_n = ewma( ys, com=2 )

在这里，com是您可以阅读的有关此处.然后，您可以使用以下方法将EMOV_n组合为Xs:

Here, com is a parameter that you can read about here. Then you can combine EMOV_n to Xs, using something like:

Xs = numpy.vstack((Xs,EMOV_n))

然后，您可以在此处中查看各种线性模型，以及做类似的事情:

And then you can look at various linear models, here, and do something like:

from sklearn import linear_model
clf = linear_model.LinearRegression()
clf.fit ( Xs, ys )
print clf.coef_

祝你好运！

这篇关于如何在scikit-learn中预测时间序列?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！