anomaly_detection 0.1.2 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 94e6edb7ef4ce6db5fdb7b01ab40322bc8daceb222c0388abe19704ef2ca7f99
-  data.tar.gz: 41e4c55f5f42251a25fc337941ee85ba306df15ca925ebfe6d1d59129cc650cc
+  metadata.gz: cfb709e43863f4221a67e8f675f28b5361f6bf33a0d0f6fa4f52cdc0cad01796
+  data.tar.gz: 40965f08bb75cdb673d43e42c7fc47403fbfb1b082de10cab86bac569916d5b8
 SHA512:
-  metadata.gz: a534a1903b14e7e3287b86b8da3936ee889f0e93690a55f5cbba5a384dfd06baab1ded6afb71acec6eb2461c0ac0d6645d28a5093ef33a4c28dce0319ef9ae75
-  data.tar.gz: 90fcd64ce191e8aaff1a46384e003f8eeea7b6e9732357fdd7726066bf4e3ad1a8fe91043042716f57e931b05c048d984c60178c05e38d127d21216fe5a2ee2f
+  metadata.gz: '0496d044ecbe143be64164bd88092c5a5bd660f5fec6425e9f6ea0759f2ab7dbaa41a055c9d03a78c8e5a661b86bb25629c5e7a809614ba415d941f4d63fc9cb'
+  data.tar.gz: 8cc3f28c981d0be5cdb3dbfd054910d45469d258a662e163d7b01379af93e6714874d043ff1521ae19506f742b63eb93bf631f6f895c11842c4c15028c66a4b8

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.1.3 (2022-01-03)
+
+- Switched to dist.h
+
 ## 0.1.2 (2021-10-20)
 
 - Added `plot` method

data/README.md

@@ -58,7 +58,7 @@ AnomalyDetection.detect(
 )
 ```
 
-## Plotting [unreleased]
+## Plotting
 
 Add [Vega](https://github.com/ankane/vega) to your application’s Gemfile:
 
@@ -74,7 +74,7 @@ AnomalyDetection.plot(series, anomalies)
 
 ## Credits
 
-This library was ported from the [AnomalyDetection](https://github.com/twitter/AnomalyDetection) R package and is available under the same license. It uses [cdflib](https://people.sc.fsu.edu/~jburkardt/cpp_src/cdflib/cdflib.html) for the quantile function.
+This library was ported from the [AnomalyDetection](https://github.com/twitter/AnomalyDetection) R package and is available under the same license. It uses [stl-cpp](https://github.com/ankane/stl-cpp) for seasonal-trend decomposition and [dist.h](https://github.com/ankane/dist.h) for the quantile function.
 
 ## References
 

data/ext/anomaly_detection/anomaly_detection.cpp

@@ -6,7 +6,7 @@
 #include <vector>
 
 #include "anomaly_detection.hpp"
-#include "cdflib.hpp"
+#include "dist.h"
 #include "stl.hpp"
 
 namespace anomaly_detection {
@@ -25,21 +25,7 @@ float mad(const std::vector<float>& data, float med) {
     return 1.4826 * median(res);
 }
 
-float qt(double p, double df) {
-    int which = 2;
-    double q = 1 - p;
-    double t;
-    int status;
-    double bound;
-    cdft(&which, &p, &q, &t, &df, &status, &bound);
-
-    if (status != 0) {
-        throw std::invalid_argument("Bad status");
-    }
-    return t;
-}
-
-std::vector<size_t> detect_anoms(const std::vector<float>& data, int num_obs_per_period, float k, float alpha, bool one_tail, bool upper_tail, bool verbose, std::function<void()> interrupt) {
+std::vector<size_t> detect_anoms(const std::vector<float>& data, int num_obs_per_period, float k, float alpha, bool one_tail, bool upper_tail, bool verbose, std::function<void()> check_for_interrupts) {
     auto n = data.size();
 
     // Check to make sure we have at least two periods worth of data for anomaly context
@@ -78,8 +64,7 @@ std::vector<size_t> detect_anoms(const std::vector<float>& data, int num_obs_per
 
     // Compute test statistic until r=max_outliers values have been removed from the sample
     for (auto i = 1; i <= max_outliers; i++) {
-        // Check for interrupts
-        interrupt();
+        check_for_interrupts();
 
         if (verbose) {
             std::cout << i << " / " << max_outliers << " completed" << std::endl;
@@ -129,7 +114,7 @@ std::vector<size_t> detect_anoms(const std::vector<float>& data, int num_obs_per
             p = 1.0 - alpha / (2.0 * (n - i + 1));
         }
 
-        auto t = qt(p, n - i - 1);
+        auto t = students_t_ppf(p, n - i - 1);
         auto lam = t * (n - i) / sqrt(((n - i - 1) + powf(t, 2.0)) * (n - i + 1));
 
         if (r > lam) {
@@ -145,10 +130,10 @@ std::vector<size_t> detect_anoms(const std::vector<float>& data, int num_obs_per
     return anomalies;
 }
 
-std::vector<size_t> anomalies(const std::vector<float>& x, int period, float k, float alpha, Direction direction, bool verbose, std::function<void()> interrupt) {
+std::vector<size_t> anomalies(const std::vector<float>& x, int period, float k, float alpha, Direction direction, bool verbose, std::function<void()> check_for_interrupts) {
     bool one_tail = direction != Direction::Both;
     bool upper_tail = direction == Direction::Positive;
-    return detect_anoms(x, period, k, alpha, one_tail, upper_tail, verbose, interrupt);
+    return detect_anoms(x, period, k, alpha, one_tail, upper_tail, verbose, check_for_interrupts);
 }
 
 }

data/ext/anomaly_detection/dist.h

@@ -0,0 +1,180 @@
+/*!
+ * dist.h v0.1.0
+ * https://github.com/ankane/dist.h
+ * Unlicense OR MIT License
+ */
+
+#pragma once
+
+#define _USE_MATH_DEFINES
+
+#include <assert.h>
+#include <math.h>
+
+// Winitzki, S. (2008).
+// A handy approximation for the error function and its inverse.
+// https://drive.google.com/file/d/0B2Mt7luZYBrwZlctV3A3eF82VGM/view?resourcekey=0-UQpPhwZgzP0sF4LHBDlLtg
+// from https://sites.google.com/site/winitzki
+double erf(double x) {
+    double sign = x < 0 ? -1.0 : 1.0;
+    x = x < 0 ? -x : x;
+
+    double a = 0.14;
+    double x2 = x * x;
+    return sign * sqrt(1.0 - exp(-x2 * (4.0 / M_PI + a * x2) / (1.0 + a * x2)));
+}
+
+// Winitzki, S. (2008).
+// A handy approximation for the error function and its inverse.
+// https://drive.google.com/file/d/0B2Mt7luZYBrwZlctV3A3eF82VGM/view?resourcekey=0-UQpPhwZgzP0sF4LHBDlLtg
+// from https://sites.google.com/site/winitzki
+double inverse_erf(double x) {
+    double sign = x < 0 ? -1.0 : 1.0;
+    x = x < 0 ? -x : x;
+
+    double a = 0.147;
+    double ln = log(1.0 - x * x);
+    double f1 = 2.0 / (M_PI * a);
+    double f2 = ln / 2.0;
+    double f3 = f1 + f2;
+    double f4 = 1.0 / a * ln;
+    return sign * sqrt(-f1 - f2 + sqrt(f3 * f3 - f4));
+}
+
+double normal_pdf(double x, double mean, double std_dev) {
+    double var = std_dev * std_dev;
+    return (1.0 / (var * sqrt(2.0 * M_PI))) * pow(M_E, -0.5 * pow((x - mean) / var, 2));
+}
+
+double normal_cdf(double x, double mean, double std_dev) {
+    return 0.5 * (1.0 + erf((x - mean) / (std_dev * std_dev * sqrt(2))));
+}
+
+double normal_ppf(double p, double mean, double std_dev) {
+    assert(p >= 0 && p <= 1);
+
+    return mean + (std_dev * std_dev) * sqrt(2) * inverse_erf(2.0 * p - 1.0);
+}
+
+double students_t_pdf(double x, unsigned int n) {
+    assert(n >= 1);
+
+    return tgamma((n + 1.0) / 2.0) / (sqrt(n * M_PI) * tgamma(n / 2.0)) * pow(1.0 + x * x / n, -(n + 1.0) / 2.0);
+}
+
+// Hill, G. W. (1970).
+// Algorithm 395: Student's t-distribution.
+// Communications of the ACM, 13(10), 617-619.
+double students_t_cdf(double x, unsigned int n) {
+    assert(n >= 1);
+
+    double start = x < 0 ? 0 : 1;
+    double sign = x < 0 ? 1 : -1;
+
+    double z = 1.0;
+    double t = x * x;
+    double y = t / n;
+    double b = 1.0 + y;
+
+    if ((n >= 20 && t < n) || n > 200) {
+        // asymptotic series for large or noninteger n
+        if (y > 10e-6) {
+            y = log(b);
+        }
+        double a = n - 0.5;
+        b = 48.0 * a * a;
+        y = a * y;
+        y = (((((-0.4 * y - 3.3) * y - 24.0) * y - 85.5) / (0.8 * y * y + 100.0 + b) + y + 3.0) / b + 1.0) * sqrt(y);
+        return start + sign * normal_cdf(-y, 0.0, 1.0);
+    }
+
+    if (n < 20 && t < 4.0) {
+        // nested summation of cosine series
+        y = sqrt(y);
+        double a = y;
+        if (n == 1) {
+            a = 0.0;
+        }
+
+        // loop
+        if (n > 1) {
+            n -= 2;
+            while (n > 1) {
+                a = (n - 1) / (b * n) * a + y;
+                n -= 2;
+            }
+        }
+        a = n == 0 ? a / sqrt(b) : (atan(y) + a / b) * (2.0 / M_PI);
+        return start + sign * (z - a) / 2;
+    }
+
+    // tail series expanation for large t-values
+    double a = sqrt(b);
+    y = a * n;
+    int j = 0;
+    while (a != z) {
+        j += 2;
+        z = a;
+        y = y * (j - 1) / (b * j);
+        a = a + y / (n + j);
+    }
+    z = 0.0;
+    y = 0.0;
+    a = -a;
+
+    // loop (without n + 2 and n - 2)
+    while (n > 1) {
+        a = (n - 1) / (b * n) * a + y;
+        n -= 2;
+    }
+    a = n == 0 ? a / sqrt(b) : (atan(y) + a / b) * (2.0 / M_PI);
+    return start + sign * (z - a) / 2;
+}
+
+// Hill, G. W. (1970).
+// Algorithm 396: Student's t-quantiles.
+// Communications of the ACM, 13(10), 619-620.
+double students_t_ppf(double p, unsigned int n) {
+    assert(p >= 0 && p <= 1);
+    assert(n >= 1);
+
+    // distribution is symmetric
+    double sign = p < 0.5 ? -1 : 1;
+    p = p < 0.5 ? 1 - p : p;
+
+    // two-tail to one-tail
+    p = 2.0 * (1.0 - p);
+
+    if (n == 2) {
+        return sign * sqrt(2.0 / (p * (2.0 - p)) - 2.0);
+    }
+
+    double half_pi = M_PI / 2.0;
+
+    if (n == 1) {
+        p = p * half_pi;
+        return sign * cos(p) / sin(p);
+    }
+
+    double a = 1.0 / (n - 0.5);
+    double b = 48.0 / (a * a);
+    double c = ((20700.0 * a / b - 98.0) * a - 16.0) * a + 96.36;
+    double d = ((94.5 / (b + c) - 3.0) / b + 1.0) * sqrt(a * half_pi) * n;
+    double x = d * p;
+    double y = pow(x, 2.0 / n);
+    if (y > 0.05 + a) {
+        // asymptotic inverse expansion about normal
+        x = normal_ppf(p * 0.5, 0.0, 1.0);
+        y = x * x;
+        if (n < 5) {
+            c += 0.3 * (n - 4.5) * (x + 0.6);
+        }
+        c = (((0.05 * d * x - 5.0) * x - 7.0) * x - 2.0) * x + b + c;
+        y = (((((0.4 * y + 6.3) * y + 36.0) * y + 94.5) / c - y - 3.0) / b + 1.0) * x;
+        y = a * y * y;
+        y = y > 0.002 ? exp(y) - 1.0 : 0.5 * y * y + y;
+    } else {
+        y = ((1.0 / (((n + 6.0) / (n * y) - 0.089 * d - 0.822) * (n + 2.0) * 3.0) + 0.5 / (n + 4.0)) * y - 1.0) * (n + 1.0) / (n + 2.0) + 1.0 / y;
+    }
+    return sign * sqrt(n * y);
+}

data/lib/anomaly_detection/version.rb

@@ -1,3 +1,3 @@
 module AnomalyDetection
-  VERSION = "0.1.2"
+  VERSION = "0.1.3"
 end

data/licenses/LICENSE-MIT-dist-h.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2021 Contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/licenses/UNLICENSE-dist-h.txt

@@ -0,0 +1,24 @@
+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+
+For more information, please refer to <http://unlicense.org/>

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: anomaly_detection
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-10-20 00:00:00.000000000 Z
+date: 2022-01-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rice
@@ -37,15 +37,15 @@ files:
 - README.md
 - ext/anomaly_detection/anomaly_detection.cpp
 - ext/anomaly_detection/anomaly_detection.hpp
-- ext/anomaly_detection/cdflib.cpp
-- ext/anomaly_detection/cdflib.hpp
+- ext/anomaly_detection/dist.h
 - ext/anomaly_detection/ext.cpp
 - ext/anomaly_detection/extconf.rb
 - ext/anomaly_detection/stl.hpp
 - lib/anomaly_detection.rb
 - lib/anomaly_detection/version.rb
+- licenses/LICENSE-MIT-dist-h.txt
 - licenses/LICENSE-MIT-stl-cpp.txt
-- licenses/LICENSE-cdflib.txt
+- licenses/UNLICENSE-dist-h.txt
 - licenses/UNLICENSE-stl-cpp.txt
 homepage: https://github.com/ankane/AnomalyDetection.rb
 licenses:
@@ -66,7 +66,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.22
+rubygems_version: 3.2.32
 signing_key:
 specification_version: 4
 summary: Time series anomaly detection for Ruby