下面是平滑z-score算法的Groovy (Java)实现(见上面的答案)。

/**
 * "Smoothed zero-score alogrithm" shamelessly copied from https://stackoverflow.com/a/22640362/6029703
 *  Uses a rolling mean and a rolling deviation (separate) to identify peaks in a vector
 *
 * @param y - The input vector to analyze
 * @param lag - The lag of the moving window (i.e. how big the window is)
 * @param threshold - The z-score at which the algorithm signals (i.e. how many standard deviations away from the moving mean a peak (or signal) is)
 * @param influence - The influence (between 0 and 1) of new signals on the mean and standard deviation (how much a peak (or signal) should affect other values near it)
 * @return - The calculated averages (avgFilter) and deviations (stdFilter), and the signals (signals)
 */

public HashMap<String, List<Object>> thresholdingAlgo(List<Double> y, Long lag, Double threshold, Double influence) {
    //init stats instance
    SummaryStatistics stats = new SummaryStatistics()

    //the results (peaks, 1 or -1) of our algorithm
    List<Integer> signals = new ArrayList<Integer>(Collections.nCopies(y.size(), 0))
    //filter out the signals (peaks) from our original list (using influence arg)
    List<Double> filteredY = new ArrayList<Double>(y)
    //the current average of the rolling window
    List<Double> avgFilter = new ArrayList<Double>(Collections.nCopies(y.size(), 0.0d))
    //the current standard deviation of the rolling window
    List<Double> stdFilter = new ArrayList<Double>(Collections.nCopies(y.size(), 0.0d))
    //init avgFilter and stdFilter
    (0..lag-1).each { stats.addValue(y[it as int]) }
    avgFilter[lag - 1 as int] = stats.getMean()
    stdFilter[lag - 1 as int] = Math.sqrt(stats.getPopulationVariance()) //getStandardDeviation() uses sample variance (not what we want)
    stats.clear()
    //loop input starting at end of rolling window
    (lag..y.size()-1).each { i ->
        //if the distance between the current value and average is enough standard deviations (threshold) away
        if (Math.abs((y[i as int] - avgFilter[i - 1 as int]) as Double) > threshold * stdFilter[i - 1 as int]) {
            //this is a signal (i.e. peak), determine if it is a positive or negative signal
            signals[i as int] = (y[i as int] > avgFilter[i - 1 as int]) ? 1 : -1
            //filter this signal out using influence
            filteredY[i as int] = (influence * y[i as int]) + ((1-influence) * filteredY[i - 1 as int])
        } else {
            //ensure this signal remains a zero
            signals[i as int] = 0
            //ensure this value is not filtered
            filteredY[i as int] = y[i as int]
        }
        //update rolling average and deviation
        (i - lag..i-1).each { stats.addValue(filteredY[it as int] as Double) }
        avgFilter[i as int] = stats.getMean()
        stdFilter[i as int] = Math.sqrt(stats.getPopulationVariance()) //getStandardDeviation() uses sample variance (not what we want)
        stats.clear()
    }

    return [
        signals  : signals,
        avgFilter: avgFilter,
        stdFilter: stdFilter
    ]
}

下面是同一个数据集上的测试，其结果与上面的Python / numpy实现相同。

    // Data
    def y = [1d, 1d, 1.1d, 1d, 0.9d, 1d, 1d, 1.1d, 1d, 0.9d, 1d, 1.1d, 1d, 1d, 0.9d, 1d, 1d, 1.1d, 1d, 1d,
         1d, 1d, 1.1d, 0.9d, 1d, 1.1d, 1d, 1d, 0.9d, 1d, 1.1d, 1d, 1d, 1.1d, 1d, 0.8d, 0.9d, 1d, 1.2d, 0.9d, 1d,
         1d, 1.1d, 1.2d, 1d, 1.5d, 1d, 3d, 2d, 5d, 3d, 2d, 1d, 1d, 1d, 0.9d, 1d,
         1d, 3d, 2.6d, 4d, 3d, 3.2d, 2d, 1d, 1d, 0.8d, 4d, 4d, 2d, 2.5d, 1d, 1d, 1d]

    // Settings
    def lag = 30
    def threshold = 5
    def influence = 0


    def thresholdingResults = thresholdingAlgo((List<Double>) y, (Long) lag, (Double) threshold, (Double) influence)

    println y.size()
    println thresholdingResults.signals.size()
    println thresholdingResults.signals

    thresholdingResults.signals.eachWithIndex { x, idx ->
        if (x) {
            println y[idx]
        }
    }

c++实现

#include <iostream>
#include <vector>
#include <algorithm>
#include <unordered_map>
#include <cmath>
#include <iterator>
#include <numeric>

using namespace std;

typedef long double ld;
typedef unsigned int uint;
typedef std::vector<ld>::iterator vec_iter_ld;

/**
 * Overriding the ostream operator for pretty printing vectors.
 */
template<typename T>
std::ostream &operator<<(std::ostream &os, std::vector<T> vec) {
    os << "[";
    if (vec.size() != 0) {
        std::copy(vec.begin(), vec.end() - 1, std::ostream_iterator<T>(os, " "));
        os << vec.back();
    }
    os << "]";
    return os;
}

/**
 * This class calculates mean and standard deviation of a subvector.
 * This is basically stats computation of a subvector of a window size qual to "lag".
 */
class VectorStats {
public:
    /**
     * Constructor for VectorStats class.
     *
     * @param start - This is the iterator position of the start of the window,
     * @param end   - This is the iterator position of the end of the window,
     */
    VectorStats(vec_iter_ld start, vec_iter_ld end) {
        this->start = start;
        this->end = end;
        this->compute();
    }

    /**
     * This method calculates the mean and standard deviation using STL function.
     * This is the Two-Pass implementation of the Mean & Variance calculation.
     */
    void compute() {
        ld sum = std::accumulate(start, end, 0.0);
        uint slice_size = std::distance(start, end);
        ld mean = sum / slice_size;
        std::vector<ld> diff(slice_size);
        std::transform(start, end, diff.begin(), [mean](ld x) { return x - mean; });
        ld sq_sum = std::inner_product(diff.begin(), diff.end(), diff.begin(), 0.0);
        ld std_dev = std::sqrt(sq_sum / slice_size);

        this->m1 = mean;
        this->m2 = std_dev;
    }

    ld mean() {
        return m1;
    }

    ld standard_deviation() {
        return m2;
    }

private:
    vec_iter_ld start;
    vec_iter_ld end;
    ld m1;
    ld m2;
};

/**
 * This is the implementation of the Smoothed Z-Score Algorithm.
 * This is direction translation of https://stackoverflow.com/a/22640362/1461896.
 *
 * @param input - input signal
 * @param lag - the lag of the moving window
 * @param threshold - the z-score at which the algorithm signals
 * @param influence - the influence (between 0 and 1) of new signals on the mean and standard deviation
 * @return a hashmap containing the filtered signal and corresponding mean and standard deviation.
 */
unordered_map<string, vector<ld>> z_score_thresholding(vector<ld> input, int lag, ld threshold, ld influence) {
    unordered_map<string, vector<ld>> output;

    uint n = (uint) input.size();
    vector<ld> signals(input.size());
    vector<ld> filtered_input(input.begin(), input.end());
    vector<ld> filtered_mean(input.size());
    vector<ld> filtered_stddev(input.size());

    VectorStats lag_subvector_stats(input.begin(), input.begin() + lag);
    filtered_mean[lag - 1] = lag_subvector_stats.mean();
    filtered_stddev[lag - 1] = lag_subvector_stats.standard_deviation();

    for (int i = lag; i < n; i++) {
        if (abs(input[i] - filtered_mean[i - 1]) > threshold * filtered_stddev[i - 1]) {
            signals[i] = (input[i] > filtered_mean[i - 1]) ? 1.0 : -1.0;
            filtered_input[i] = influence * input[i] + (1 - influence) * filtered_input[i - 1];
        } else {
            signals[i] = 0.0;
            filtered_input[i] = input[i];
        }
        VectorStats lag_subvector_stats(filtered_input.begin() + (i - lag), filtered_input.begin() + i);
        filtered_mean[i] = lag_subvector_stats.mean();
        filtered_stddev[i] = lag_subvector_stats.standard_deviation();
    }

    output["signals"] = signals;
    output["filtered_mean"] = filtered_mean;
    output["filtered_stddev"] = filtered_stddev;

    return output;
};

int main() {
    vector<ld> input = {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;
    ld threshold = 5.0;
    ld influence = 0.0;
    unordered_map<string, vector<ld>> output = z_score_thresholding(input, lag, threshold, influence);
    cout << output["signals"] << endl;
}

以下是平滑z-score算法的Scala版本(非惯用):

/**
  * Smoothed zero-score alogrithm shamelessly copied from https://stackoverflow.com/a/22640362/6029703
  * Uses a rolling mean and a rolling deviation (separate) to identify peaks in a vector
  *
  * @param y - The input vector to analyze
  * @param lag - The lag of the moving window (i.e. how big the window is)
  * @param threshold - The z-score at which the algorithm signals (i.e. how many standard deviations away from the moving mean a peak (or signal) is)
  * @param influence - The influence (between 0 and 1) of new signals on the mean and standard deviation (how much a peak (or signal) should affect other values near it)
  * @return - The calculated averages (avgFilter) and deviations (stdFilter), and the signals (signals)
  */
private def smoothedZScore(y: Seq[Double], lag: Int, threshold: Double, influence: Double): Seq[Int] = {
  val stats = new SummaryStatistics()

  // the results (peaks, 1 or -1) of our algorithm
  val signals = mutable.ArrayBuffer.fill(y.length)(0)

  // filter out the signals (peaks) from our original list (using influence arg)
  val filteredY = y.to[mutable.ArrayBuffer]

  // the current average of the rolling window
  val avgFilter = mutable.ArrayBuffer.fill(y.length)(0d)

  // the current standard deviation of the rolling window
  val stdFilter = mutable.ArrayBuffer.fill(y.length)(0d)

  // init avgFilter and stdFilter
  y.take(lag).foreach(s => stats.addValue(s))

  avgFilter(lag - 1) = stats.getMean
  stdFilter(lag - 1) = Math.sqrt(stats.getPopulationVariance) // getStandardDeviation() uses sample variance (not what we want)

  // loop input starting at end of rolling window
  y.zipWithIndex.slice(lag, y.length - 1).foreach {
    case (s: Double, i: Int) =>
      // if the distance between the current value and average is enough standard deviations (threshold) away
      if (Math.abs(s - avgFilter(i - 1)) > threshold * stdFilter(i - 1)) {
        // this is a signal (i.e. peak), determine if it is a positive or negative signal
        signals(i) = if (s > avgFilter(i - 1)) 1 else -1
        // filter this signal out using influence
        filteredY(i) = (influence * s) + ((1 - influence) * filteredY(i - 1))
      } else {
        // ensure this signal remains a zero
        signals(i) = 0
        // ensure this value is not filtered
        filteredY(i) = s
      }

      // update rolling average and deviation
      stats.clear()
      filteredY.slice(i - lag, i).foreach(s => stats.addValue(s))
      avgFilter(i) = stats.getMean
      stdFilter(i) = Math.sqrt(stats.getPopulationVariance) // getStandardDeviation() uses sample variance (not what we want)
  }

  println(y.length)
  println(signals.length)
  println(signals)

  signals.zipWithIndex.foreach {
    case(x: Int, idx: Int) =>
      if (x == 1) {
        println(idx + " " + y(idx))
      }
  }

  val data =
    y.zipWithIndex.map { case (s: Double, i: Int) => Map("x" -> i, "y" -> s, "name" -> "y", "row" -> "data") } ++
    avgFilter.zipWithIndex.map { case (s: Double, i: Int) => Map("x" -> i, "y" -> s, "name" -> "avgFilter", "row" -> "data") } ++
    avgFilter.zipWithIndex.map { case (s: Double, i: Int) => Map("x" -> i, "y" -> (s - threshold * stdFilter(i)), "name" -> "lower", "row" -> "data") } ++
    avgFilter.zipWithIndex.map { case (s: Double, i: Int) => Map("x" -> i, "y" -> (s + threshold * stdFilter(i)), "name" -> "upper", "row" -> "data") } ++
    signals.zipWithIndex.map { case (s: Int, i: Int) => Map("x" -> i, "y" -> s, "name" -> "signal", "row" -> "signal") }

  Vegas("Smoothed Z")
    .withData(data)
    .mark(Line)
    .encodeX("x", Quant)
    .encodeY("y", Quant)
    .encodeColor(
      field="name",
      dataType=Nominal
    )
    .encodeRow("row", Ordinal)
    .show

  return signals
}

下面是一个测试，返回与Python和Groovy版本相同的结果:

val y = List(1d, 1d, 1.1d, 1d, 0.9d, 1d, 1d, 1.1d, 1d, 0.9d, 1d, 1.1d, 1d, 1d, 0.9d, 1d, 1d, 1.1d, 1d, 1d,
  1d, 1d, 1.1d, 0.9d, 1d, 1.1d, 1d, 1d, 0.9d, 1d, 1.1d, 1d, 1d, 1.1d, 1d, 0.8d, 0.9d, 1d, 1.2d, 0.9d, 1d,
  1d, 1.1d, 1.2d, 1d, 1.5d, 1d, 3d, 2d, 5d, 3d, 2d, 1d, 1d, 1d, 0.9d, 1d,
  1d, 3d, 2.6d, 4d, 3d, 3.2d, 2d, 1d, 1d, 0.8d, 4d, 4d, 2d, 2.5d, 1d, 1d, 1d)

val lag = 30
val threshold = 5d
val influence = 0d

smoothedZScore(y, lag, threshold, influence)

这里的要点

一个python/numpy的迭代版本的答案https://stackoverflow.com/a/22640362/6029703在这里。对于大数据(100000+)，此代码比计算平均和标准偏差的速度更快。

def peak_detection_smoothed_zscore_v2(x, lag, threshold, influence):
    '''
    iterative smoothed z-score algorithm
    Implementation of algorithm from https://stackoverflow.com/a/22640362/6029703
    '''
    import numpy as np
    labels = np.zeros(len(x))
    filtered_y = np.array(x)
    avg_filter = np.zeros(len(x))
    std_filter = np.zeros(len(x))
    var_filter = np.zeros(len(x))

    avg_filter[lag - 1] = np.mean(x[0:lag])
    std_filter[lag - 1] = np.std(x[0:lag])
    var_filter[lag - 1] = np.var(x[0:lag])
    for i in range(lag, len(x)):
        if abs(x[i] - avg_filter[i - 1]) > threshold * std_filter[i - 1]:
            if x[i] > avg_filter[i - 1]:
                labels[i] = 1
            else:
                labels[i] = -1
            filtered_y[i] = influence * x[i] + (1 - influence) * filtered_y[i - 1]
        else:
            labels[i] = 0
            filtered_y[i] = x[i]
        # update avg, var, std
        avg_filter[i] = avg_filter[i - 1] + 1. / lag * (filtered_y[i] - filtered_y[i - lag])
        var_filter[i] = var_filter[i - 1] + 1. / lag * ((filtered_y[i] - avg_filter[i - 1]) ** 2 - (
            filtered_y[i - lag] - avg_filter[i - 1]) ** 2 - (filtered_y[i] - filtered_y[i - lag]) ** 2 / lag)
        std_filter[i] = np.sqrt(var_filter[i])

    return dict(signals=labels,
                avgFilter=avg_filter,
                stdFilter=std_filter)

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)))
}

下面是ZSCORE算法的PHP实现:

<?php
$y = array(1,7,1.1,1,0.9,1,1,1.1,1,0.9,1,1.1,1,1,0.9,1,1,1.1,1,1,1,1,1.1,0.9,1,1.1,1,1,0.9,
       1,1.1,1,1,1.1,1,0.8,0.9,1,1.2,0.9,1,1,1.1,1.2,1,1.5,10,3,2,5,3,2,1,1,1,0.9,1,1,3,
       2.6,4,3,3.2,2,1,1,0.8,4,4,2,2.5,1,1,1);

function mean($data, $start, $len) {
    $avg = 0;
    for ($i = $start; $i < $start+ $len; $i ++)
        $avg += $data[$i];
    return $avg / $len;
}
    
function stddev($data, $start,$len) {
    $mean = mean($data,$start,$len);
    $dev = 0;
    for ($i = $start; $i < $start+$len; $i++) 
        $dev += (($data[$i] - $mean) * ($data[$i] - $mean));
    return sqrt($dev / $len);
}

function zscore($data, $len, $lag= 20, $threshold = 1, $influence = 1) {

    $signals = array();
    $avgFilter = array();
    $stdFilter = array();
    $filteredY = array();
    $avgFilter[$lag - 1] = mean($data, 0, $lag);
    $stdFilter[$lag - 1] = stddev($data, 0, $lag);
    
    for ($i = 0; $i < $len; $i++) {
        $filteredY[$i] = $data[$i];
        $signals[$i] = 0;
    }


    for ($i=$lag; $i < $len; $i++) {
        if (abs($data[$i] - $avgFilter[$i-1]) > $threshold * $stdFilter[$lag - 1]) {
            if ($data[$i] > $avgFilter[$i-1]) {
                $signals[$i] = 1;
            }
            else {
                $signals[$i] = -1;
            }
            $filteredY[$i] = $influence * $data[$i] + (1 - $influence) * $filteredY[$i-1];
        } 
        else {
            $signals[$i] = 0;
            $filteredY[$i] = $data[$i];
        }
        
        $avgFilter[$i] = mean($filteredY, $i - $lag, $lag);
        $stdFilter[$i] = stddev($filteredY, $i - $lag, $lag);
    }
    return $signals;
}

$sig = zscore($y, count($y));

print_r($y); echo "<br><br>";
print_r($sig); echo "<br><br>";

for ($i = 0; $i < count($y); $i++) echo $i. " " . $y[$i]. " ". $sig[$i]."<br>";