summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorTim Rault <tim.rault@cengn.ca>2016-07-12 15:30:51 -0400
committerTim Rault <tim.rault@cengn.ca>2016-07-14 15:45:46 -0400
commit8f9351d780beb18aa70e2d84f6e249a0a29489cf (patch)
treef1cfa086e294c26f3e88d7cd984bd424239daa45
parentd7d5efb6fe647e117f54ce0923e4966014eaeb9a (diff)
Add Range function for Steady State detection
Added a range_value function in utilities/math.py able to compute the range of a series of y values : [y1, y2, ..., yn]. Implemented a test harness for this range_value function in the tests/utilities section. Renamed the math_slope.py and math_range.py test files to add _test.py for Jenkins. Cleaned up the code so it is compliant to the pep8 rules. Renamed the previous 'math' modules (storperf/utilities/math.py and storperf/test/utilities/math.py) as 'math_slope' to be coherent with the new notation. Change-Id: I02ccd2b87f0b72e7a28c416b593aae4d8ad97961 JIRA: STORPERF-57 JIRA: STORPERF-58 Signed-off-by: Tim Rault <tim.rault@cengn.ca>
-rw-r--r--storperf/tests/utilities/math_range_test.py120
-rw-r--r--storperf/tests/utilities/math_slope_test.py (renamed from storperf/tests/utilities/math.py)23
-rw-r--r--storperf/utilities/math.py100
3 files changed, 200 insertions, 43 deletions
diff --git a/storperf/tests/utilities/math_range_test.py b/storperf/tests/utilities/math_range_test.py
new file mode 100644
index 0000000..6484752
--- /dev/null
+++ b/storperf/tests/utilities/math_range_test.py
@@ -0,0 +1,120 @@
+##############################################################################
+# Copyright (c) 2016 CENGN and others.
+#
+# All rights reserved. This program and the accompanying materials
+# are made available under the terms of the Apache License, Version 2.0
+# which accompanies this distribution, and is available at
+# http://www.apache.org/licenses/LICENSE-2.0
+##############################################################################
+from random import uniform, randrange
+import unittest
+
+from storperf.utilities import math as math
+
+
+class MathRangeTest(unittest.TestCase):
+
+ def setUp(self):
+ unittest.TestCase.setUp(self)
+
+ def test_empty_series(self):
+ expected = 0
+ data_series = []
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_integer_series(self):
+ expected = 11946
+ data_series = [5, 351, 847, 2, 1985, 18,
+ 96, 389, 687, 1, 11947, 758, 155]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_float_series_1_decimal(self):
+ expected = 778595.5
+ data_series = [736.4, 9856.4, 684.2, 0.3, 0.9, 778595.8]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_float_series_2_decimals(self):
+ expected = 5693.47
+ data_series = [51.36, 78.40, 1158.24, 5.50, 0.98, 5694.45]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_float_series_3_decimals(self):
+ expected = 992.181
+ data_series = [4.562, 12.582, 689.452,
+ 135.162, 996.743, 65.549, 36.785]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_float_series_4_decimals(self):
+ expected = 122985.3241
+ data_series = [39.4785, 896.7845, 11956.3654,
+ 44.2398, 6589.7134, 0.3671, 122985.6912]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_float_series_5_decimals(self):
+ expected = 8956208.84494
+ data_series = [12.78496, 55.91275, 668.94378,
+ 550396.5671, 512374.9999, 8956221.6299]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_float_series_10_decimals(self):
+ expected = 5984.507397972699
+ data_series = [1.1253914785, 5985.6327894512,
+ 256.1875693287, 995.8497623415]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_float_mix(self):
+ expected = 60781.6245372199
+ data_series = [60785.9962, 899.4, 78.66, 69.58, 4.93795,
+ 587.195486, 96.7694536, 5.13755964,
+ 33.333333334, 60786.5624872199]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_float_integer_mix(self):
+ expected = 460781.05825
+ data_series = [460785.9962, 845.634, 24.1, 69.58, 89, 4.93795]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_negative_values(self):
+ expected = 596.78163
+ data_series = [-4.655, -33.3334, -596.78422, -0.00259, -66.785]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_negative_positive_mix(self):
+ expected = 58.859500000000004
+ data_series = [6.85698, -2.8945, 0, -0.15, 55.965]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_single_element(self):
+ expected = 0
+ data_series = [2.265]
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_10000_values_processing(self):
+ expected = 28001.068
+ data_series = [uniform(-10000, 10000) for i in xrange(10000)]
+ data_series.insert(randrange(len(data_series) + 1), 15000.569)
+ data_series.insert(randrange(len(data_series) + 1), -13000.499)
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
+
+ def test_processing_100_values_100_times(self):
+ expected = 35911.3134
+ for index in range(1, 100):
+ data_series = [uniform(-10000, 10000) for i in xrange(100)]
+ data_series.insert(randrange(len(data_series) + 1), 16956.3334)
+ data_series.insert(randrange(len(data_series) + 1), -18954.98)
+ actual = math.range_value(data_series)
+ self.assertEqual(expected, actual)
diff --git a/storperf/tests/utilities/math.py b/storperf/tests/utilities/math_slope_test.py
index c78538d..a34845b 100644
--- a/storperf/tests/utilities/math.py
+++ b/storperf/tests/utilities/math_slope_test.py
@@ -7,9 +7,10 @@
# http://www.apache.org/licenses/LICENSE-2.0
##############################################################################
import unittest
-from storperf.utilities.math import math
+from storperf.utilities import math as math
-class MathTest(unittest.TestCase):
+
+class MathSlopeTest(unittest.TestCase):
def setUp(self):
unittest.TestCase.setUp(self)
@@ -22,45 +23,45 @@ class MathTest(unittest.TestCase):
def test_slope_integer_series(self):
expected = 1.4
- actual = math.slope([[1,6], [2,5], [3,7], [4,10]])
+ actual = math.slope([[1, 6], [2, 5], [3, 7], [4, 10]])
self.assertEqual(expected, actual)
def test_slope_decimal_series(self):
expected = 1.4
- actual = math.slope([[1.0,6.0], [2.0,5.0], [3.0,7.0], [4.0,10.0]])
+ actual = math.slope([[1.0, 6.0], [2.0, 5.0], [3.0, 7.0], [4.0, 10.0]])
self.assertEqual(expected, actual)
def test_slope_decimal_integer_mix(self):
expected = 1.4
- actual = math.slope([[1.0,6], [2,5.0], [3,7], [4.0,10]])
+ actual = math.slope([[1.0, 6], [2, 5.0], [3, 7], [4.0, 10]])
self.assertEqual(expected, actual)
def test_slope_negative_y_series(self):
expected = 2
- actual = math.slope([[1.0,-2], [2,2], [3,2]])
+ actual = math.slope([[1.0, -2], [2, 2], [3, 2]])
self.assertEqual(expected, actual)
def test_slope_negative_x_series(self):
expected = 1.4
- actual = math.slope([[-24,6.0], [-23,5], [-22,7.0], [-21,10]])
+ actual = math.slope([[-24, 6.0], [-23, 5], [-22, 7.0], [-21, 10]])
self.assertEqual(expected, actual)
def test_slope_out_of_order_series(self):
expected = 1.4
- actual = math.slope([[2,5.0], [4,10], [3.0,7], [1,6]])
+ actual = math.slope([[2, 5.0], [4, 10], [3.0, 7], [1, 6]])
self.assertEqual(expected, actual)
def test_slope_0_in_y(self):
expected = -0.5
- actual = math.slope([[15.5,1], [16.5,0], [17.5,0]])
+ actual = math.slope([[15.5, 1], [16.5, 0], [17.5, 0]])
self.assertEqual(expected, actual)
def test_slope_0_in_x(self):
expected = 1.4
- actual = math.slope([[0,6.0], [1,5], [2,7], [3,10]])
+ actual = math.slope([[0, 6.0], [1, 5], [2, 7], [3, 10]])
self.assertEqual(expected, actual)
def test_slope_0_in_x_and_y(self):
expected = 1.5
- actual = math.slope([[0.0,0], [1,1], [2,3]])
+ actual = math.slope([[0.0, 0], [1, 1], [2, 3]])
self.assertEqual(expected, actual)
diff --git a/storperf/utilities/math.py b/storperf/utilities/math.py
index 3b124cd..031fc3e 100644
--- a/storperf/utilities/math.py
+++ b/storperf/utilities/math.py
@@ -7,46 +7,82 @@
# http://www.apache.org/licenses/LICENSE-2.0
##############################################################################
-class math(object):
- @staticmethod
- def slope(data_series):
+def slope(data_series):
+ """
+ This function implements the linear least squares algorithm described in
+ the following wikipedia article :
+ https://en.wikipedia.org/wiki/Linear_least_squares_(mathematics)
+ in the case of m equations (provided by m data points) and 2 unknown
+ variables (x and y, which represent the time and the Volume performance
+ variable being tested e.g. IOPS, latency...).
+ The data_series is currently assumed to follow the pattern :
+ [[x1,y1], [x2,y2], ..., [xm,ym]].
+ If this data pattern were to change, the data_treatement function
+ should be adjusted to ensure compatibility with the rest of the
+ Steady State Dectection module.
+ """
+
+ # In the particular case of an empty data series
+ if len(data_series) == 0:
+ beta2 = 0
+
+ else: # The general case
+ m = len(data_series)
+ # To make sure at least one element is a float number so the result
+ # of the algorithm be a float number
+ data_series[0][0] = float(data_series[0][0])
+
"""
- This function implements the linear least squares algorithm described in the following wikipedia article
- https://en.wikipedia.org/wiki/Linear_least_squares_(mathematics)
- in the case of m equations (provided by m data points) and 2 unknown variables (x and
- y, which represent the time and the Volume performance variable being
- tested e.g. IOPS, latency...)
+ It consists in solving the normal equations system (2 equations,
+ 2 unknowns) by calculating the value of beta2 (slope).
+ The formula of beta1 (the y-intercept) is given as a comment in
+ case it is needed later.
"""
+ sum_xi = 0
+ sum_xi_sq = 0
+ sum_yi_xi = 0
+ sum_yi = 0
+ for i in range(0, m):
+ xi = data_series[i][0]
+ yi = data_series[i][1]
- if len(data_series)==0: #In the particular case of an empty data series
- beta2 = 0
+ sum_xi += xi
+ sum_xi_sq += xi**2
+ sum_yi_xi += xi * yi
+ sum_yi += yi
- else: #The general case
- m = len(data_series) #given a [[x1,y1], [x2,y2], ..., [xm,ym]] data series
- data_series[0][0] = float(data_series[0][0]) #To make sure at least one element is a float number so the result of the algorithm be a float number
+ beta2 = (sum_yi * sum_xi - m * sum_yi_xi) / \
+ (sum_xi**2 - m * sum_xi_sq) # The slope
+ # beta1 = (sum_yi_xi - beta2*sum_xi_sq)/sum_xi #The y-intercept if
+ # needed
- """
- It consists in solving the normal equations system (2 equations, 2 unknowns)
- by calculating the value of beta2 (slope). The formula of beta1 (the y-intercept)
- is given as a comment in case it is needed later.
- """
- sum_xi = 0
- sum_xi_sq = 0
- sum_yi_xi = 0
- sum_yi = 0
- for i in range(0, m):
- xi = data_series[i][0]
- yi = data_series[i][1]
+ return beta2
- sum_xi += xi
- sum_xi_sq += xi**2
- sum_yi_xi += xi*yi
- sum_yi += yi
- beta2 = (sum_yi*sum_xi - m*sum_yi_xi)/(sum_xi**2 - m*sum_xi_sq) #The slope
- #beta1 = (sum_yi_xi - beta2*sum_xi_sq)/sum_xi #The y-intercept if needed
+def range_value(data_series):
+ """
+ This function implements a range algorithm that returns a float number
+ representing the range of the data_series that is passed to it.
+ The data_series being passed is assumed to follow the following data
+ pattern : [y1, y2, y3, ..., ym] where yi represents the ith
+ measuring point of the y variable. The y variable represents the
+ Volume performance being tested (e.g. IOPS, latency...).
+ If this data pattern were to change, the data_treatment function
+ should be adjusted to ensure compatibility with the rest of the
+ Steady State Dectection module.
+ The conversion of the data series from the original pattern to the
+ [y1, y2, y3, ..., ym] pattern is done outside this function
+ so the original pattern can be changed without breaking this function.
+ """
- return beta2
+ # In the particular case of an empty data series
+ if len(data_series) == 0:
+ range_value = 0
+ else: # The general case
+ max_value = max(data_series)
+ min_value = min(data_series)
+ range_value = max_value - min_value
+ return range_value