/usr/bin/dlda-landscape is in python-mlpy 2.2.0~dfsg1-3build2.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 | #!/usr/bin/python
# NOTE:
# Unlike the other Classifiers Dlda has the number of features to be used (nf)
# as the only parameter. This means that, using an adequate resampling method and
# paramethers, this tool can give a reliable estimation about the predictivity of
# the model.
from numpy import *
from optparse import OptionParser
from mlpy import *
# Command line parsing
parser = OptionParser()
parser.add_option("-d", "--data", metavar = "FILE", action = "store", type = "string",
dest = "data", help = "data - required")
parser.add_option("-n", "--normalize", action = "store_true", default = False,
dest = "norm", help = "normalize data")
parser.add_option("-s", "--standardize", action = "store_true", default = False,
dest = "std", help = "standardize data")
parser.add_option("-k", action = "store", type = "int",
dest = "k", help = "k for k-fold cross validation")
parser.add_option("-c", action = "store", type = "int", nargs = 2, metavar = "SETS PAIRS",
dest = "c", help = "sets and pairs for monte carlo cross validation")
parser.add_option("-S", "--stratified", action = "store_true", default = False,
dest = "strat", help = "for stratified cv")
parser.add_option("-v", "--verbose", action = "store_true", default = False,
dest = "verb", help = "print partial results every resampling step")
parser.add_option("-m", "--min", action = "store", type = "int",
dest = "min", help = "min value for nf parameter [default %default]", default = 1)
parser.add_option("-M", "--max", action = "store", type = "int",
dest = "max", help = "max value for nf parameter [default %default]", default = 10)
parser.add_option("-p", "--steps", action = "store", type = "int",
dest = "steps", help = "amplitude of steps for nf parameter [default %default]", default = 1)
parser.add_option("-l", "--lists", action = "store_true", default = False,
dest = "lists", help = "Canberra distance indicator")
parser.add_option("-a", "--auc", action = "store_true", default = False,
dest = "auc", help = "wmw_auc indicator")
parser.add_option("-b", "--bal", action = "store_true", default = False,
dest = "bal", help = "parameter of DLDA classifier refering to the balancement\
of training and test sets")
(options, args) = parser.parse_args()
if not options.data:
parser.error("option -d [data] is required")
if not (options.k or options.c):
parser.error("option -k (k-fold) or -c (monte carlo) for resampling is required")
if (options.k and options.c):
parser.error("option -k (k-fold) and -c (monte carlo) are mutually exclusive")
if options.min < 1:
parser.error("option -m must be >= 1")
if options.steps > options.max - options.min:
parser.error("option -p must be <= (option -M - option -m)")
if options.min > options.max:
parser.error("option -m must be <= option -M")
# Number of Features
NF = [] # nf in a list of the NF that i want to add to the model at each compute
NF.append(0)
while (options.min + sum(NF) + options.steps) <= options.max: #check that the nf at the next step is not > options.max
NF.append(options.steps)
# Data
x, y = data_fromfile(options.data)
if options.max > x.shape[1]:
parser.error("max number of features must be <= number of features in data file")
if options.std:
x = data_standardize(x)
if options.norm:
x = data_normalize(x)
# Resampling
if options.strat:
if options.k:
print "stratified %d-fold cv" % options.k
res = kfoldS(cl = y, sets = options.k)
elif options.c:
print "stratified monte carlo cv (%d sets, %d pairs)" %(options.c[0], options.c[1])
res = montecarloS(cl = y, sets = options.c[0], pairs = options.c[1])
else:
if options.k:
print "%d-fold cv" % options.k
res = kfold(nsamples = y.shape[0], sets = options.k)
elif options.c:
print "monte carlo cv (%d sets, %d pairs)" %(options.c[0], options.c[1])
res = montecarlo(nsamples = y.shape[0], sets = options.c[0], pairs = options.c[1])
if options.lists:
R = Ranking(method='onestep')
lp = empty((len(res), x.shape[1]), dtype = int)
##########
MCC = empty((len(NF),len(res)))
ERR = empty((len(NF),len(res)))
AUC = zeros((len(NF),len(res)))
for t, r in enumerate(res):
xtr, ytr, xts, yts = x[r[0]], y[r[0]], x[r[1]], y[r[1]]
d = Dlda(nf = options.min, bal = options.bal)
for rig, i in enumerate(NF):
p = None
d.compute(xtr, ytr, i)
p = d.predict(xts)
ERR[rig, t] = err(yts, p)
MCC[rig, t] = mcc(yts, p)
if options.auc:
AUC[rig, t] = wmw_auc(yts, d.realpred)
if (options.verb or (t == len(res)-1)):
print 'Results are averaged on', (t + 1), 'indipendent train & test sets'
for l in range(ERR.shape[0]):
print "Numb. of Features %s: error %f, mcc %f, auc %f" \
%(((l * options.steps) + options.min),\
(mean(ERR[l, range(t + 1)])),\
(mean(MCC[l, range(t + 1)])),\
(mean(AUC[l, range(t + 1)])))
|