| #!/usr/bin/env python | |
| # Copyright (C) 2007, 2012 Apple Inc. All rights reserved. | |
| # | |
| # Redistribution and use in source and binary forms, with or without | |
| # modification, are permitted provided that the following conditions | |
| # are met: | |
| # 1. Redistributions of source code must retain the above copyright | |
| # notice, this list of conditions and the following disclaimer. | |
| # 2. Redistributions in binary form must reproduce the above copyright | |
| # notice, this list of conditions and the following disclaimer in the | |
| # documentation and/or other materials provided with the distribution. | |
| # | |
| # THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY | |
| # EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE | |
| # IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR | |
| # PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR | |
| # CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, | |
| # EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, | |
| # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | |
| # PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY | |
| # OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | |
| # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE | |
| # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | |
| import math | |
| import sys | |
| import re | |
| import fileinput | |
| from optparse import OptionParser | |
| usage = "usage: %prog [options] [FILES]\n Compute the mean and 95% confidence interval of a sample set.\n Standard input or files must contain two or more decimal numbers, one per line." | |
| parser = OptionParser(usage=usage) | |
| parser.add_option("-u", "--unit", dest="unit", default="", | |
| help="assume values are in units of UNIT", metavar="UNIT") | |
| parser.add_option("-v", "--verbose", | |
| action="store_true", dest="verbose", default=False, | |
| help="print all values (with units)") | |
| (options, files) = parser.parse_args() | |
| def sum(items): | |
| return reduce(lambda x,y: x+y, items) | |
| def arithmeticMean(items): | |
| return sum(items) / len(items) | |
| def standardDeviation(mean, items): | |
| deltaSquares = [(item - mean) ** 2 for item in items] | |
| return math.sqrt(sum(deltaSquares) / (len(items) - 1)) | |
| def standardError(stdDev, items): | |
| return stdDev / math.sqrt(len(items)) | |
| # t-distribution for 2-sided 95% confidence intervals | |
| tDistribution = [float('NaN'), float('NaN'), 12.71, 4.30, 3.18, 2.78, 2.57, 2.45, 2.36, 2.31, 2.26, 2.23, 2.20, 2.18, 2.16, 2.14, 2.13, 2.12, 2.11, 2.10, 2.09, 2.09, 2.08, 2.07, 2.07, 2.06, 2.06, 2.06, 2.05, 2.05, 2.05, 2.04, 2.04, 2.04, 2.03, 2.03, 2.03, 2.03, 2.03, 2.02, 2.02, 2.02, 2.02, 2.02, 2.02, 2.02, 2.01, 2.01, 2.01, 2.01, 2.01, 2.01, 2.01, 2.01, 2.01, 2.00, 2.00, 2.00, 2.00, 2.00, 2.00, 2.00, 2.00, 2.00, 2.00, 2.00, 2.00, 2.00, 2.00, 2.00, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.99, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.98, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.97, 1.96] | |
| tMax = len(tDistribution) | |
| tLimit = 1.96 | |
| def tDist(n): | |
| if n > tMax: | |
| return tLimit | |
| return tDistribution[n] | |
| def twoSidedConfidenceInterval(items): | |
| mean = arithmeticMean(items) | |
| stdDev = standardDeviation(mean, items) | |
| stdErr = standardError(stdDev, items) | |
| return tDist(len(items)) * stdErr | |
| results = [] | |
| decimalNumberPattern = re.compile(r"\d+\.?\d*") | |
| for line in fileinput.input(files): | |
| match = re.search(decimalNumberPattern, line) | |
| if match: | |
| results.append(float(match.group(0))) | |
| if len(results) == 0: | |
| parser.print_help() | |
| quit() | |
| mean = arithmeticMean(results) | |
| confidenceInterval = twoSidedConfidenceInterval(results) | |
| confidencePercent = 100 * confidenceInterval / mean | |
| if options.verbose: | |
| length = 7 | |
| for item in results: | |
| line = " %.2f %s" % (item, options.unit) | |
| print line | |
| length = len(line) if len(line) > length else length | |
| print "-" * length | |
| prefix = "Mean: " if options.verbose else "" | |
| print "%s%.2f %s +/- %.2f %s (%.1f%%)" % (prefix, mean, options.unit, confidenceInterval, options.unit, confidencePercent) | |