如何找到自相关和偏自相关的滞后数？答案

【问题标题】：How to find number of lags in autocorrelation and partial autocorrelation?如何找到自相关和偏自相关的滞后数？
【发布时间】：2020-01-24 14:42:07
【问题描述】：

我正在尝试在 python 中使用 tsfresh 包来从加速度计传感器输入中提取特征，我遇到了几个需要延迟变量的特征：

tsfresh.feature_extraction.feature_calculators.agg_autocorrelation(x, param)
Where:
                  x (numpy.ndarray) – the time series to calculate the feature of
                  param (list) – contains dictionaries {“f_agg”: x, “maxlag”, n} with x str, the name of a numpy function (e.g. “mean”, “var”, “std”, “median”), its the name of the aggregator function that is applied to the autocorrelations. Further, n is an int and the maximal number of lags to consider.

tsfresh.feature_extraction.feature_calculators.autocorrelation(x, lag)
Where:
                  x (numpy.ndarray) – the time series to calculate the feature of
                  lag (int) – the lag

tsfresh.feature_extraction.feature_calculators.c3(x, lag)
Where:
                  x (numpy.ndarray) – the time series to calculate the feature of
                  lag (int) – the lag

tsfresh.feature_extraction.feature_calculators.partial_autocorrelation(x, param)
Where:
                  x (numpy.ndarray) – the time series to calculate the feature of
                  param (list) – contains dictionaries {“lag”: val} with int val indicating the lag to be returned

tsfresh.feature_extraction.feature_calculators.time_reversal_asymmetry_statistic(x, lag)
Where:
                  x (numpy.ndarray) – the time series to calculate the feature of
                  lag (int) – the lag that should be used in the calculation of the feature

那么，我想知道如何找到滞后变量？

亲切的问候

【问题讨论】：

标签： python machine-learning time-series feature-extraction autocorrelation

【解决方案1】：

TSFRESH 使用滞后变量作为参数来计算相关特征。
因此，例如在 c3 计算中，它将使用 lag=1 然后 lag=2，这样做会将具有计算数据的列添加为 tsXcolname__c3__lag_1 .
您应该在 TSFRESH 中查找如何更改此参数，即它将为每个功能计算多少滞后。我认为 c3 的标准值为 3，自相关的标准值为 9。

【讨论】：