@Jean-Paul算法的Perl实现。

#!/usr/bin/perl

use strict;
use Data::Dumper;

sub mean {
    my $data = shift;
    my $sum = 0;
    my $mean_val = 0;
    for my $item (@$data) {
        $sum += $item;
    }
    $mean_val = $sum / (scalar @$data) if @$data;
    return $mean_val;
}

sub variance {
    my $data = shift;
    my $variance_val = 0;
    my $mean_val = mean($data);
    my $sum = 0;
    for my $item (@$data) {
        $sum += ($item - $mean_val)**2;
    }
    $variance_val = $sum / (scalar @$data) if @$data;
    return $variance_val;
}

sub std {
    my $data = shift;
    my $variance_val = variance($data);
    return sqrt($variance_val);
}

# @param y - The input vector to analyze
# @parameter lag - The lag of the moving window
# @parameter threshold - The z-score at which the algorithm signals
# @parameter influence - The influence (between 0 and 1) of new signals on the mean and standard deviation
sub thresholding_algo {
    my ($y, $lag, $threshold, $influence) = @_;

    my @signals = (0) x @$y;
    my @filteredY = @$y;
    my @avgFilter = (0) x @$y;
    my @stdFilter = (0) x @$y;

    $avgFilter[$lag - 1] = mean([@$y[0..$lag-1]]);
    $stdFilter[$lag - 1] = std([@$y[0..$lag-1]]);

    for (my $i=$lag; $i <= @$y - 1; $i++) {
        if (abs($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];
            $avgFilter[$i] = mean([@filteredY[($i-$lag)..($i-1)]]);
            $stdFilter[$i] = std([@filteredY[($i-$lag)..($i-1)]]);
        }
        else {
            $signals[$i] = 0;
            $filteredY[$i] = $y->[$i];
            $avgFilter[$i] = mean([@filteredY[($i-$lag)..($i-1)]]);
            $stdFilter[$i] = std([@filteredY[($i-$lag)..($i-1)]]);
        }
    }

    return {
        signals => \@signals,
        avgFilter => \@avgFilter,
        stdFilter => \@stdFilter
    };
}

my $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];

my $lag = 30;
my $threshold = 5;
my $influence = 0;

my $result = thresholding_algo($y, $lag, $threshold, $influence);

print Dumper $result;

下面是这个答案的平滑z-score算法的c++实现

std::vector<int> smoothedZScore(std::vector<float> input)
{   
    //lag 5 for the smoothing functions
    int lag = 5;
    //3.5 standard deviations for signal
    float threshold = 3.5;
    //between 0 and 1, where 1 is normal influence, 0.5 is half
    float influence = .5;

    if (input.size() <= lag + 2)
    {
        std::vector<int> emptyVec;
        return emptyVec;
    }

    //Initialise variables
    std::vector<int> signals(input.size(), 0.0);
    std::vector<float> filteredY(input.size(), 0.0);
    std::vector<float> avgFilter(input.size(), 0.0);
    std::vector<float> stdFilter(input.size(), 0.0);
    std::vector<float> subVecStart(input.begin(), input.begin() + lag);
    avgFilter[lag] = mean(subVecStart);
    stdFilter[lag] = stdDev(subVecStart);

    for (size_t i = lag + 1; i < input.size(); i++)
    {
        if (std::abs(input[i] - avgFilter[i - 1]) > threshold * stdFilter[i - 1])
        {
            if (input[i] > avgFilter[i - 1])
            {
                signals[i] = 1; //# Positive signal
            }
            else
            {
                signals[i] = -1; //# Negative signal
            }
            //Make influence lower
            filteredY[i] = influence* input[i] + (1 - influence) * filteredY[i - 1];
        }
        else
        {
            signals[i] = 0; //# No signal
            filteredY[i] = input[i];
        }
        //Adjust the filters
        std::vector<float> subVec(filteredY.begin() + i - lag, filteredY.begin() + i);
        avgFilter[i] = mean(subVec);
        stdFilter[i] = stdDev(subVec);
    }
    return signals;
}

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。

我认为delica的Python回答器有一个bug。我不能评论他的帖子，因为我没有代表来做这件事，编辑队列已经满了，所以我可能不是第一个注意到它的人。

avgFilter[lag - 1]和stdFilter[lag - 1]在init中设置，然后在lag == i时再次设置，而不是改变[lag]值。这个结果使得第一个信号总是1。

以下是带有轻微修正的代码:

import numpy as np

class real_time_peak_detection():
    def __init__(self, array, lag, threshold, influence):
        self.y = list(array)
        self.length = len(self.y)
        self.lag = lag
        self.threshold = threshold
        self.influence = influence
        self.signals = [0] * len(self.y)
        self.filteredY = np.array(self.y).tolist()
        self.avgFilter = [0] * len(self.y)
        self.stdFilter = [0] * len(self.y)
        self.avgFilter[self.lag - 1] = np.mean(self.y[0:self.lag]).tolist()
        self.stdFilter[self.lag - 1] = np.std(self.y[0:self.lag]).tolist()

    def thresholding_algo(self, new_value):
        self.y.append(new_value)
        i = len(self.y) - 1
        self.length = len(self.y)
        if i < self.lag:
            return 0
        elif i == self.lag:
            self.signals = [0] * len(self.y)
            self.filteredY = np.array(self.y).tolist()
            self.avgFilter = [0] * len(self.y)
            self.stdFilter = [0] * len(self.y)
            self.avgFilter[self.lag] = np.mean(self.y[0:self.lag]).tolist()
            self.stdFilter[self.lag] = np.std(self.y[0:self.lag]).tolist()
            return 0

        self.signals += [0]
        self.filteredY += [0]
        self.avgFilter += [0]
        self.stdFilter += [0]

        if abs(self.y[i] - self.avgFilter[i - 1]) > self.threshold * self.stdFilter[i - 1]:
            if self.y[i] > self.avgFilter[i - 1]:
                self.signals[i] = 1
            else:
                self.signals[i] = -1

            self.filteredY[i] = self.influence * self.y[i] + (1 - self.influence) * self.filteredY[i - 1]
            self.avgFilter[i] = np.mean(self.filteredY[(i - self.lag):i])
            self.stdFilter[i] = np.std(self.filteredY[(i - self.lag):i])
        else:
            self.signals[i] = 0
            self.filteredY[i] = self.y[i]
            self.avgFilter[i] = np.mean(self.filteredY[(i - self.lag):i])
            self.stdFilter[i] = np.std(self.filteredY[(i - self.lag):i])

        return self.signals[i]

@Jean-Paul Smoothed Z Score算法的Dart版本:

class SmoothedZScore {
  int lag = 5;
  num threshold = 10;
  num influence = 0.5;

  num sum(List<num> a) {
    num s = 0;
    for (int i = 0; i < a.length; i++) s += a[i];
    return s;
  }

  num mean(List<num> a) {
    return sum(a) / a.length;
  }

  num stddev(List<num> arr) {
    num arrMean = mean(arr);
    num dev = 0;
    for (int i = 0; i < arr.length; i++) dev += (arr[i] - arrMean) * (arr[i] - arrMean);
    return sqrt(dev / arr.length);
  }

  List<int> smoothedZScore(List<num> y) {
    if (y.length < lag + 2) {
      throw 'y data array too short($y.length) for given lag of $lag';
    }

    // init variables
    List<int> signals = List.filled(y.length, 0);
    List<num> filteredY = List<num>.from(y);
    List<num> leadIn = y.sublist(0, lag);

    var avgFilter = List<num>.filled(y.length, 0);
    var stdFilter = List<num>.filled(y.length, 0);
    avgFilter[lag - 1] = mean(leadIn);
    stdFilter[lag - 1] = stddev(leadIn);

    for (var i = lag; i < y.length; i++) {
      if ((y[i] - avgFilter[i - 1]).abs() > (threshold * stdFilter[i - 1])) {
        signals[i] = y[i] > avgFilter[i - 1] ? 1 : -1;
        // make influence lower
        filteredY[i] = influence * y[i] + (1 - influence) * filteredY[i - 1];
      } else {
        signals[i] = 0; // no signal
        filteredY[i] = y[i];
      }

      // adjust the filters
      List<num> yLag = filteredY.sublist(i - lag, i);
      avgFilter[i] = mean(yLag);
      stdFilter[i] = stddev(yLag);
    }

    return signals;
  }
}

如果你的数据在一个数据库表中，这里是一个简单的z-score算法的SQL版本:

with data_with_zscore as (
    select
        date_time,
        value,
        value / (avg(value) over ()) as pct_of_mean,
        (value - avg(value) over ()) / (stdev(value) over ()) as z_score
    from {{tablename}}  where datetime > '2018-11-26' and datetime < '2018-12-03'
)


-- select all
select * from data_with_zscore 

-- select only points greater than a certain threshold
select * from data_with_zscore where z_score > abs(2)