我为Jean-Paul最受欢迎的答案写了一个Go包。它假设y值的类型为float64。

github.com/MicahParks/peakdetect

下面的示例使用了这个包，并基于上面提到的流行答案中的R示例。它在编译时没有任何依赖关系，试图保持较低的内存占用，并且在有新数据点进入时不重新处理过去的点。该项目有100%的测试覆盖率，主要来自上述R示例的输入和输出。但是，如果有人发现任何错误，请打开一个GitHub问题。

编辑:我对v0.0.5进行了性能改进，似乎快了10倍!它使用Welford的方法进行初始化，并使用类似的方法计算滞后期(滑动窗口)的平均值和总体标准偏差。特别感谢另一个帖子的回答:https://stackoverflow.com/a/14638138/14797322

下面是基于R例子的Golang例子:

package main

import (
    "fmt"
    "log"

    "github.com/MicahParks/peakdetect"
)

// This example is the equivalent of the R example from the algorithm's author.
// https://stackoverflow.com/a/54507329/14797322
func main() {
    data := []float64{1, 1, 1.1, 1, 0.9, 1, 1, 1.1, 1, 0.9, 1, 1.1, 1, 1, 0.9, 1, 1, 1.1, 1, 1, 1, 1, 1.1, 0.9, 1, 1.1, 1, 1, 0.9, 1, 1.1, 1, 1, 1.1, 1, 0.8, 0.9, 1, 1.2, 0.9, 1, 1, 1.1, 1.2, 1, 1.5, 1, 3, 2, 5, 3, 2, 1, 1, 1, 0.9, 1, 1, 3, 2.6, 4, 3, 3.2, 2, 1, 1, 0.8, 4, 4, 2, 2.5, 1, 1, 1}

    // Algorithm configuration from example.
    const (
        lag       = 30
        threshold = 5
        influence = 0
    )

    // Create then initialize the peak detector.
    detector := peakdetect.NewPeakDetector()
    err := detector.Initialize(influence, threshold, data[:lag]) // The length of the initial values is the lag.
    if err != nil {
        log.Fatalf("Failed to initialize peak detector.\nError: %s", err)
    }

    // Start processing new data points and determine what signal, if any they produce.
    //
    // This method, .Next(), is best for when data is being processed in a stream, but this simply iterates over a slice.
    nextDataPoints := data[lag:]
    for i, newPoint := range nextDataPoints {
        signal := detector.Next(newPoint)
        var signalType string
        switch signal {
        case peakdetect.SignalNegative:
            signalType = "negative"
        case peakdetect.SignalNeutral:
            signalType = "neutral"
        case peakdetect.SignalPositive:
            signalType = "positive"
        }

        println(fmt.Sprintf("Data point at index %d has the signal: %s", i+lag, signalType))
    }

    // This method, .NextBatch(), is a helper function for processing many data points at once. It's returned slice
    // should produce the same signal outputs as the loop above.
    signals := detector.NextBatch(nextDataPoints)
    println(fmt.Sprintf("1:1 ratio of batch inputs to signal outputs: %t", len(signals) == len(nextDataPoints)))
}

原文的附录1:Matlab和R翻译

Matlab代码

function [signals,avgFilter,stdFilter] = ThresholdingAlgo(y,lag,threshold,influence)
% Initialise signal results
signals = zeros(length(y),1);
% Initialise filtered series
filteredY = y(1:lag+1);
% Initialise filters
avgFilter(lag+1,1) = mean(y(1:lag+1));
stdFilter(lag+1,1) = std(y(1:lag+1));
% Loop over all datapoints y(lag+2),...,y(t)
for i=lag+2:length(y)
    % If new value is a specified number of deviations away
    if abs(y(i)-avgFilter(i-1)) > threshold*stdFilter(i-1)
        if y(i) > avgFilter(i-1)
            % Positive signal
            signals(i) = 1;
        else
            % Negative signal
            signals(i) = -1;
        end
        % Make influence lower
        filteredY(i) = influence*y(i)+(1-influence)*filteredY(i-1);
    else
        % No signal
        signals(i) = 0;
        filteredY(i) = y(i);
    end
    % Adjust the filters
    avgFilter(i) = mean(filteredY(i-lag:i));
    stdFilter(i) = std(filteredY(i-lag:i));
end
% Done, now return results
end

例子:

% Data
y = [1 1 1.1 1 0.9 1 1 1.1 1 0.9 1 1.1 1 1 0.9 1 1 1.1 1 1,...
    1 1 1.1 0.9 1 1.1 1 1 0.9 1 1.1 1 1 1.1 1 0.8 0.9 1 1.2 0.9 1,...
    1 1.1 1.2 1 1.5 1 3 2 5 3 2 1 1 1 0.9 1,...
    1 3 2.6 4 3 3.2 2 1 1 0.8 4 4 2 2.5 1 1 1];

% Settings
lag = 30;
threshold = 5;
influence = 0;

% Get results
[signals,avg,dev] = ThresholdingAlgo(y,lag,threshold,influence);

figure; subplot(2,1,1); hold on;
x = 1:length(y); ix = lag+1:length(y);
area(x(ix),avg(ix)+threshold*dev(ix),'FaceColor',[0.9 0.9 0.9],'EdgeColor','none');
area(x(ix),avg(ix)-threshold*dev(ix),'FaceColor',[1 1 1],'EdgeColor','none');
plot(x(ix),avg(ix),'LineWidth',1,'Color','cyan','LineWidth',1.5);
plot(x(ix),avg(ix)+threshold*dev(ix),'LineWidth',1,'Color','green','LineWidth',1.5);
plot(x(ix),avg(ix)-threshold*dev(ix),'LineWidth',1,'Color','green','LineWidth',1.5);
plot(1:length(y),y,'b');
subplot(2,1,2);
stairs(signals,'r','LineWidth',1.5); ylim([-1.5 1.5]);

R代码

ThresholdingAlgo <- function(y,lag,threshold,influence) {
  signals <- rep(0,length(y))
  filteredY <- y[0:lag]
  avgFilter <- NULL
  stdFilter <- NULL
  avgFilter[lag] <- mean(y[0:lag], na.rm=TRUE)
  stdFilter[lag] <- sd(y[0:lag], na.rm=TRUE)
  for (i in (lag+1):length(y)){
    if (abs(y[i]-avgFilter[i-1]) > threshold*stdFilter[i-1]) {
      if (y[i] > avgFilter[i-1]) {
        signals[i] <- 1;
      } else {
        signals[i] <- -1;
      }
      filteredY[i] <- influence*y[i]+(1-influence)*filteredY[i-1]
    } else {
      signals[i] <- 0
      filteredY[i] <- y[i]
    }
    avgFilter[i] <- mean(filteredY[(i-lag):i], na.rm=TRUE)
    stdFilter[i] <- sd(filteredY[(i-lag):i], na.rm=TRUE)
  }
  return(list("signals"=signals,"avgFilter"=avgFilter,"stdFilter"=stdFilter))
}

例子:

# Data
y <- c(1,1,1.1,1,0.9,1,1,1.1,1,0.9,1,1.1,1,1,0.9,1,1,1.1,1,1,1,1,1.1,0.9,1,1.1,1,1,0.9,
       1,1.1,1,1,1.1,1,0.8,0.9,1,1.2,0.9,1,1,1.1,1.2,1,1.5,1,3,2,5,3,2,1,1,1,0.9,1,1,3,
       2.6,4,3,3.2,2,1,1,0.8,4,4,2,2.5,1,1,1)

lag       <- 30
threshold <- 5
influence <- 0

# Run algo with lag = 30, threshold = 5, influence = 0
result <- ThresholdingAlgo(y,lag,threshold,influence)

# Plot result
par(mfrow = c(2,1),oma = c(2,2,0,0) + 0.1,mar = c(0,0,2,1) + 0.2)
plot(1:length(y),y,type="l",ylab="",xlab="") 
lines(1:length(y),result$avgFilter,type="l",col="cyan",lwd=2)
lines(1:length(y),result$avgFilter+threshold*result$stdFilter,type="l",col="green",lwd=2)
lines(1:length(y),result$avgFilter-threshold*result$stdFilter,type="l",col="green",lwd=2)
plot(result$signals,type="S",col="red",ylab="",xlab="",ylim=c(-1.5,1.5),lwd=2)

这段代码(两种语言)将为原始问题的数据产生以下结果:

附录2原答案:Matlab演示代码

(点击创建数据)

function [] = RobustThresholdingDemo()

%% SPECIFICATIONS
lag         = 5;       % lag for the smoothing
threshold   = 3.5;     % number of st.dev. away from the mean to signal
influence   = 0.3;     % when signal: how much influence for new data? (between 0 and 1)
                       % 1 is normal influence, 0.5 is half      
%% START DEMO
DemoScreen(30,lag,threshold,influence);

end

function [signals,avgFilter,stdFilter] = ThresholdingAlgo(y,lag,threshold,influence)
signals = zeros(length(y),1);
filteredY = y(1:lag+1);
avgFilter(lag+1,1) = mean(y(1:lag+1));
stdFilter(lag+1,1) = std(y(1:lag+1));
for i=lag+2:length(y)
    if abs(y(i)-avgFilter(i-1)) > threshold*stdFilter(i-1)
        if y(i) > avgFilter(i-1)
            signals(i) = 1;
        else
            signals(i) = -1;
        end
        filteredY(i) = influence*y(i)+(1-influence)*filteredY(i-1);
    else
        signals(i) = 0;
        filteredY(i) = y(i);
    end
    avgFilter(i) = mean(filteredY(i-lag:i));
    stdFilter(i) = std(filteredY(i-lag:i));
end
end

% Demo screen function
function [] = DemoScreen(n,lag,threshold,influence)
figure('Position',[200 100,1000,500]);
subplot(2,1,1);
title(sprintf(['Draw data points (%.0f max)      [settings: lag = %.0f, '...
    'threshold = %.2f, influence = %.2f]'],n,lag,threshold,influence));
ylim([0 5]); xlim([0 50]);
H = gca; subplot(2,1,1);
set(H, 'YLimMode', 'manual'); set(H, 'XLimMode', 'manual');
set(H, 'YLim', get(H,'YLim')); set(H, 'XLim', get(H,'XLim'));
xg = []; yg = [];
for i=1:n
    try
        [xi,yi] = ginput(1);
    catch
        return;
    end
    xg = [xg xi]; yg = [yg yi];
    if i == 1
        subplot(2,1,1); hold on;
        plot(H, xg(i),yg(i),'r.'); 
        text(xg(i),yg(i),num2str(i),'FontSize',7);
    end
    if length(xg) > lag
        [signals,avg,dev] = ...
            ThresholdingAlgo(yg,lag,threshold,influence);
        area(xg(lag+1:end),avg(lag+1:end)+threshold*dev(lag+1:end),...
            'FaceColor',[0.9 0.9 0.9],'EdgeColor','none');
        area(xg(lag+1:end),avg(lag+1:end)-threshold*dev(lag+1:end),...
            'FaceColor',[1 1 1],'EdgeColor','none');
        plot(xg(lag+1:end),avg(lag+1:end),'LineWidth',1,'Color','cyan');
        plot(xg(lag+1:end),avg(lag+1:end)+threshold*dev(lag+1:end),...
            'LineWidth',1,'Color','green');
        plot(xg(lag+1:end),avg(lag+1:end)-threshold*dev(lag+1:end),...
            'LineWidth',1,'Color','green');
        subplot(2,1,2); hold on; title('Signal output');
        stairs(xg(lag+1:end),signals(lag+1:end),'LineWidth',2,'Color','blue');
        ylim([-2 2]); xlim([0 50]); hold off;
    end
    subplot(2,1,1); hold on;
    for j=2:i
        plot(xg([j-1:j]),yg([j-1:j]),'r'); plot(H,xg(j),yg(j),'r.');
        text(xg(j),yg(j),num2str(j),'FontSize',7);
    end
end
end

根据@Jean-Paul提出的解决方案，我用c#实现了他的算法

public class ZScoreOutput
{
    public List<double> input;
    public List<int> signals;
    public List<double> avgFilter;
    public List<double> filtered_stddev;
}

public static class ZScore
{
    public static ZScoreOutput StartAlgo(List<double> input, int lag, double threshold, double influence)
    {
        // init variables!
        int[] signals = new int[input.Count];
        double[] filteredY = new List<double>(input).ToArray();
        double[] avgFilter = new double[input.Count];
        double[] stdFilter = new double[input.Count];

        var initialWindow = new List<double>(filteredY).Skip(0).Take(lag).ToList();

        avgFilter[lag - 1] = Mean(initialWindow);
        stdFilter[lag - 1] = StdDev(initialWindow);

        for (int i = lag; i < input.Count; i++)
        {
            if (Math.Abs(input[i] - avgFilter[i - 1]) > threshold * stdFilter[i - 1])
            {
                signals[i] = (input[i] > avgFilter[i - 1]) ? 1 : -1;
                filteredY[i] = influence * input[i] + (1 - influence) * filteredY[i - 1];
            }
            else
            {
                signals[i] = 0;
                filteredY[i] = input[i];
            }

            // Update rolling average and deviation
            var slidingWindow = new List<double>(filteredY).Skip(i - lag).Take(lag+1).ToList();

            var tmpMean = Mean(slidingWindow);
            var tmpStdDev = StdDev(slidingWindow);

            avgFilter[i] = Mean(slidingWindow);
            stdFilter[i] = StdDev(slidingWindow);
        }

        // Copy to convenience class 
        var result = new ZScoreOutput();
        result.input = input;
        result.avgFilter       = new List<double>(avgFilter);
        result.signals         = new List<int>(signals);
        result.filtered_stddev = new List<double>(stdFilter);

        return result;
    }

    private static double Mean(List<double> list)
    {
        // Simple helper function! 
        return list.Average();
    }

    private static double StdDev(List<double> values)
    {
        double ret = 0;
        if (values.Count() > 0)
        {
            double avg = values.Average();
            double sum = values.Sum(d => Math.Pow(d - avg, 2));
            ret = Math.Sqrt((sum) / (values.Count() - 1));
        }
        return ret;
    }
}

使用示例:

var input = new List<double> {1.0, 1.0, 1.1, 1.0, 0.9, 1.0, 1.0, 1.1, 1.0, 0.9, 1.0,
    1.1, 1.0, 1.0, 0.9, 1.0, 1.0, 1.1, 1.0, 1.0, 1.0, 1.0, 1.1, 0.9, 1.0, 1.1, 1.0, 1.0, 0.9,
    1.0, 1.1, 1.0, 1.0, 1.1, 1.0, 0.8, 0.9, 1.0, 1.2, 0.9, 1.0, 1.0, 1.1, 1.2, 1.0, 1.5, 1.0,
    3.0, 2.0, 5.0, 3.0, 2.0, 1.0, 1.0, 1.0, 0.9, 1.0, 1.0, 3.0, 2.6, 4.0, 3.0, 3.2, 2.0, 1.0,
    1.0, 0.8, 4.0, 4.0, 2.0, 2.5, 1.0, 1.0, 1.0};

int lag = 30;
double threshold = 5.0;
double influence = 0.0;

var output = ZScore.StartAlgo(input, lag, threshold, influence);

我为Jean-Paul最受欢迎的答案写了一个Go包。它假设y值的类型为float64。

github.com/MicahParks/peakdetect

下面的示例使用了这个包，并基于上面提到的流行答案中的R示例。它在编译时没有任何依赖关系，试图保持较低的内存占用，并且在有新数据点进入时不重新处理过去的点。该项目有100%的测试覆盖率，主要来自上述R示例的输入和输出。但是，如果有人发现任何错误，请打开一个GitHub问题。

编辑:我对v0.0.5进行了性能改进，似乎快了10倍!它使用Welford的方法进行初始化，并使用类似的方法计算滞后期(滑动窗口)的平均值和总体标准偏差。特别感谢另一个帖子的回答:https://stackoverflow.com/a/14638138/14797322

下面是基于R例子的Golang例子:

package main

import (
    "fmt"
    "log"

    "github.com/MicahParks/peakdetect"
)

// This example is the equivalent of the R example from the algorithm's author.
// https://stackoverflow.com/a/54507329/14797322
func main() {
    data := []float64{1, 1, 1.1, 1, 0.9, 1, 1, 1.1, 1, 0.9, 1, 1.1, 1, 1, 0.9, 1, 1, 1.1, 1, 1, 1, 1, 1.1, 0.9, 1, 1.1, 1, 1, 0.9, 1, 1.1, 1, 1, 1.1, 1, 0.8, 0.9, 1, 1.2, 0.9, 1, 1, 1.1, 1.2, 1, 1.5, 1, 3, 2, 5, 3, 2, 1, 1, 1, 0.9, 1, 1, 3, 2.6, 4, 3, 3.2, 2, 1, 1, 0.8, 4, 4, 2, 2.5, 1, 1, 1}

    // Algorithm configuration from example.
    const (
        lag       = 30
        threshold = 5
        influence = 0
    )

    // Create then initialize the peak detector.
    detector := peakdetect.NewPeakDetector()
    err := detector.Initialize(influence, threshold, data[:lag]) // The length of the initial values is the lag.
    if err != nil {
        log.Fatalf("Failed to initialize peak detector.\nError: %s", err)
    }

    // Start processing new data points and determine what signal, if any they produce.
    //
    // This method, .Next(), is best for when data is being processed in a stream, but this simply iterates over a slice.
    nextDataPoints := data[lag:]
    for i, newPoint := range nextDataPoints {
        signal := detector.Next(newPoint)
        var signalType string
        switch signal {
        case peakdetect.SignalNegative:
            signalType = "negative"
        case peakdetect.SignalNeutral:
            signalType = "neutral"
        case peakdetect.SignalPositive:
            signalType = "positive"
        }

        println(fmt.Sprintf("Data point at index %d has the signal: %s", i+lag, signalType))
    }

    // This method, .NextBatch(), is a helper function for processing many data points at once. It's returned slice
    // should produce the same signal outputs as the loop above.
    signals := detector.NextBatch(nextDataPoints)
    println(fmt.Sprintf("1:1 ratio of batch inputs to signal outputs: %t", len(signals) == len(nextDataPoints)))
}

不需要将极大值与平均值进行比较，还可以将极大值与相邻的最小值进行比较，其中最小值仅定义在噪声阈值之上。 如果局部最大值是>的3倍(或其他置信因子)相邻的最小值，那么这个最大值就是一个峰值。 移动窗口越宽，峰值的确定越准确。 上面使用了以窗口中间为中心的计算， 顺便说一下，而不是在窗口结束时计算(== lag)。

请注意，最大值必须被视为信号之前的增加 之后下降。

在Palshikar(2009)中发现了另一个算法:

Palshikar, G.(2009)。时间序列中峰值检测的简单算法。在Proc. 1st Int。高级数据分析，商业分析和智能(卷122)。

论文可以从这里下载。

算法是这样的:

algorithm peak1 // one peak detection algorithms that uses peak function S1 

input T = x1, x2, …, xN, N // input time-series of N points 
input k // window size around the peak 
input h // typically 1 <= h <= 3 
output O // set of peaks detected in T 

begin 
O = empty set // initially empty 

    for (i = 1; i < n; i++) do
        // compute peak function value for each of the N points in T 
        a[i] = S1(k,i,xi,T); 
    end for 

    Compute the mean m' and standard deviation s' of all positive values in array a; 

    for (i = 1; i < n; i++) do // remove local peaks which are “small” in global context 
        if (a[i] > 0 && (a[i] – m') >( h * s')) then O = O + {xi}; 
        end if 
    end for 

    Order peaks in O in terms of increasing index in T 

    // retain only one peak out of any set of peaks within distance k of each other 

    for every adjacent pair of peaks xi and xj in O do 
        if |j – i| <= k then remove the smaller value of {xi, xj} from O 
        end if 
    end for 
end

优势

本文提出了5种不同的峰值检测算法 算法在原始时间序列数据上工作(不需要平滑)

缺点

很难事先确定k和h 峰不能是平的(就像我测试数据中的第三个峰)

例子: