def test_pickle(self):
d = orange.ExampleTable("iris")
ba = orange.BayesLearner(d)
s = pickle.dumps(ba)
ba2 = pickle.loads(s)
for e in d:
self.assertEqual(ba(e), ba2(e))
ba1 = orange.BayesLearner()
s = pickle.dumps(ba1)
ba2 = pickle.loads(s)
def applyLearner(self):
self.warning(0)
if float(self.m_estimator.m) < 0:
self.warning(0, "Parameter m should be positive")
self.learner = None
elif float(self.windowProportion) < 0 or float(
self.windowProportion) > 1:
self.warning(
0, "Window proportion for LOESS should be between 0.0 and 1.0")
self.learner = None
else:
self.learner = orange.BayesLearner(
name=self.name, adjustThreshold=self.adjustThreshold)
self.learner.estimatorConstructor = self.estMethods[
self.probEstimation][1]
if self.condProbEstimation:
self.learner.conditionalEstimatorConstructor = self.condEstMethods[
self.condProbEstimation][1]
self.learner.conditionalEstimatorConstructorContinuous = orange.ConditionalProbabilityEstimatorConstructor_loess(
windowProportion=self.windowProportion,
nPoints=self.loessPoints)
if self.preprocessor:
self.learner = self.preprocessor.wrapLearner(self.learner)
self.send("Learner", self.learner)
self.applyData()
self.changed = False
def createInstance(self):
bayes = orange.BayesLearner()
if hasattr(self, "estimatorConstructor"):
bayes.estimatorConstructor = self.estimatorConstructor
if hasattr(self, "m"):
if hasattr(bayes.estimatorConstructor, "m"):
raise AttributeError(
"invalid combination of attributes: 'estimatorConstructor' does not expect 'm'"
)
else:
self.estimatorConstructor.m = self.m
elif hasattr(self, "m"):
bayes.estimatorConstructor = orange.ProbabilityEstimatorConstructor_m(
m=self.m)
if hasattr(self, "conditionalEstimatorConstructor"):
bayes.conditionalEstimatorConstructor = self.conditionalEstimatorConstructor
elif bayes.estimatorConstructor:
bayes.conditionalEstimatorConstructor = orange.ConditionalProbabilityEstimatorConstructor_ByRows(
)
bayes.conditionalEstimatorConstructor.estimatorConstructor = bayes.estimatorConstructor
if hasattr(self, "conditionalEstimatorConstructorContinuous"):
bayes.conditionalEstimatorConstructorContinuous = self.conditionalEstimatorConstructorContinuous
return bayes
def __call__(self, data, weight=None):
disc = orange.Preprocessor_discretize(
data, method=orange.EntropyDiscretization())
#show_values(disc, "Entropy based discretization")
model = orange.BayesLearner(disc, weight, adjustThreshold=0)
#print "model.distribution", model.distribution
#print "model.conditionalDistributions", model.conditionalDistributions
return Classifier(classifier=model)
def test_learning_cont(self):
d = orange.ExampleTable("iris")
bal = orange.BayesLearner()
ba = bal(d)
corr = 0
for e in d:
if ba(e) == e.getclass():
corr += 1
self.assertGreater(corr, 125)
def test_Learner(self):
b = orange.BayesLearner()
self.assertEqual(b.name, "bayes")
b.name = "foo"
self.assertEqual(b.name, "foo")
b.name = "BayesLearner"
self.assertEqual(b.name, "BayesLearner")
b.name = "x.BayesLearner"
self.assertEqual(b.name, "x.BayesLearner")
b.name = ""
self.assertEqual(b.name, "")
def test_named_const(self):
ba = orange.BayesLearner()
self.assertEqual(ba.loess_distribution_method,
orange.BayesLearner.DistributionMethod.Fixed)
s = pickle.dumps(ba)
ba2 = pickle.loads(s)
self.assertEqual(ba2.loess_distribution_method,
orange.BayesLearner.DistributionMethod.Fixed)
ba.loess_distribution_method = orange.BayesLearner.DistributionMethod.Uniform
s = pickle.dumps(ba)
ba2 = pickle.loads(s)
self.assertEqual(ba2.loess_distribution_method,
orange.BayesLearner.DistributionMethod.Uniform)
def classify():
import orange, orngTree
testData = orange.ExampleTable('data/audioTest.tab')
trainData = orange.ExampleTable('data/audioTrain.tab')
bayes = orange.BayesLearner(trainData)
bayes.name = "bayes"
tree = orngTree.TreeLearner(trainData)
tree.name = "tree"
classifiers = [bayes, tree]
return classifiers, trainData, testData
def __call__(self, data, weight=0):
import orngLookup
if self.alternativeMeasure:
raise SystemError, "alternativeMeasure not implemented yet"
keepDuplicates = getattr(self, "keepDuplicates", 0)
data = orange.ExampleTable(data)
if not weight:
# This is here for backward compatibility
if hasattr(self, "weight"):
weight = self.weight
else:
weight = orange.newmetaid()
data.addMetaAttribute(weight)
if self.redundancyRemover:
data = self.redundancyRemover(data, weight)
if not keepDuplicates:
data.removeDuplicates(weight)
induced = 0
featureGenerator = FeatureGenerator(
featureInducer=self.featureInducer,
subsetsGenerator=self.subsetsGenerator)
while (1):
newFeatures = featureGenerator(data, weight)
if not newFeatures or not len(newFeatures):
break
best = orngMisc.selectBest(newFeatures,
orngMisc.compare2_lastBigger)[0]
if len(best.getValueFrom.boundset()) == len(
data.domain.attributes):
break
induced += 1
best.name = "c%d" % induced
data = replaceWithInduced(best, data)
if not keepDuplicates:
data.removeDuplicates(weight)
if self.learnerForUnknown:
learnerForUnknown = self.learnerForUnknown
else:
learnerForUnknown = orange.BayesLearner()
return orngLookup.lookupFromExamples(data, weight, learnerForUnknown)
def __call__(self, examples, weight = 0,fulldata=0):
if not(examples.domain.classVar.varType == 1 and len(examples.domain.classVar.values)==2):
raise "BasicBayes learner only works with binary discrete class."
for attr in examples.domain.attributes:
if not(attr.varType == 1):
raise "BasicBayes learner does not work with continuous attributes."
translate = orng2Array.DomainTranslation(self.translation_mode_d,self.translation_mode_c)
if fulldata != 0:
translate.analyse(fulldata, weight)
else:
translate.analyse(examples, weight)
translate.prepareLR()
(beta, coeffs) = self._process(orange.BayesLearner(examples), examples)
return BasicBayesClassifier(beta,coeffs,translate)
def bayes_classifier(sequence):
f = open('header.tab', 'r')
feature_header = f.read()
f.close()
f = open('new_seq.tab', 'w')
f.write(feature_header)
f.write('unknow\t')
features = bayes_pre(sequence)
for feature in features:
f.write(str(feature))
f.write('\t')
f.close()
data = orange.ExampleTable("data3_v5.tab")
learner = orange.BayesLearner()
classifier = learner(data)
new_data = orange.ExampleTable("new_seq.tab")
p = [str(classifier(new_data[0])), orange.GetProbabilities]
return p
def cross_validation():
k = 10
d = list(data)
nps = len(d) / 10
acs = []
for i in range(k):
random.shuffle(d)
subsamples = list(split(d, nps))
accurancy = 0
for j in range(k):
validation = subsamples[j]
training = []
for s in subsamples:
if s == validation: continue
training += s
l = orange.BayesLearner(training)
thisa = 0
for ex in validation:
if ex.getclass() == l(ex):
thisa += 1
accurancy += float(thisa) / len(validation)
acs.append(accurancy)
print sum(acs) / float(k) / float(k)
def train_classifier(data, type, filter):
if type == "tree" or type == "c4.5" or type == "decision_tree":
learner = orange.C45Learner()
elif type == "bayes" or type == "naive" or type == "naive_bayes":
learner = orange.BayesLearner()
elif type == "svm" or type == "linear_svm":
learner = Orange.classification.svm.LinearSVMLearner()
#elif type == "logreg" or type == "regression":
# learner = Orange.classification.logreg.LogRegLearner()
else:
print "Invalid Learner Type\n"
exit()
if filter == 0:
classifier = learner(data)
else:
filtered_learner = Orange.feature.selection.FilteredLearner(
learner,
filter=Orange.feature.selection.FilterBestN(n=filter),
name='filtered')
classifier = filtered_learner(data)
return classifier
def __call__(self, data, weight=None): ma = orngFSS.attMeasure(data) filtered = orngFSS.selectBestNAtts(data, ma, self.N) model = orange.BayesLearner(filtered) return BayesFSS_Classifier(classifier=model, N=self.N, name=self.name)
def __init__(self, discr = orange.EntropyDiscretization(), learnr = orange.BayesLearner()):
self.disc = discr
self.learner = learnr
print
impdata = imputer(data)
for i in range(20, 25):
print data[i]
print impdata[i]
print
print "\n*** BAYES and AVERAGE IMPUTATION ***\n"
imputer = orange.ImputerConstructor_model()
imputer.learnerContinuous = orange.MajorityLearner()
imputer.learnerDiscrete = orange.BayesLearner()
imputer = imputer(data)
print "Example w/ missing values"
print data[19]
print "Imputed:"
print imputer(data[19])
print
impdata = imputer(data)
for i in range(20, 25):
print data[i]
print impdata[i]
print
def bayes(input_dict):
import orange
output_dict = {}
output_dict['bayesout'] = orange.BayesLearner(name="Naive Bayes (Orange)",
hovername="DOlgo ime bajesa")
return output_dict
import orange, orngWrap, orngTest, orngStat
data = orange.ExampleTable("bupa")
learner = orange.BayesLearner()
thresh = orngWrap.ThresholdLearner(learner=learner)
thresh80 = orngWrap.ThresholdLearner_fixed(learner=learner, threshold=.8)
res = orngTest.crossValidation([learner, thresh, thresh80], data)
CAs = orngStat.CA(res)
print "W/out threshold adjustement: %5.3f" % CAs[0]
print "With adjusted thredhold: %5.3f" % CAs[1]
print "With threshold at 0.80: %5.3f" % CAs[2]
if self.data is not None:
class_var = self.data.domain.class_var
if self.method == 0 and not \
isinstance(class_var, orange.EnumVariable):
self.warning(0, "Cannot use 'Boosting' on non discrete class")
return False
return True
def commit(self):
wrapped = None
classifier = None
if self.learner:
wrapped = self.METHODS[self.method][1](self.learner, t=self.t)
self.send("Learner", wrapped)
if self.data and wrapped and self.checkMethod():
classifier = wrapped(self.data)
self.send("Classifier", classifier)
if __name__ == "__main__":
app = QApplication(sys.argv)
w = OWEnsemble()
w.setLearner(orange.BayesLearner())
w.setData(orange.ExampleTable("../../doc/datasets/iris"))
w.show()
app.exec_()
def __call__(self, examples, weight=0):
# next function changes data set to a extended with unknown values
def createLogRegExampleTable(data, weightID):
setsOfData = []
for at in data.domain.attributes:
# za vsak atribut kreiraj nov newExampleTable newData
# v dataOrig, dataFinal in newData dodaj nov atribut -- continuous variable
if at.varType == orange.VarTypes.Continuous:
atDisc = orange.FloatVariable(at.name + "Disc")
newDomain = orange.Domain(data.domain.attributes +
[atDisc, data.domain.classVar])
newDomain.addmetas(data.domain.getmetas())
newData = orange.ExampleTable(newDomain, data)
altData = orange.ExampleTable(newDomain, data)
for i, d in enumerate(newData):
d[atDisc] = 0
d[weightID] = 1 * data[i][weightID]
for i, d in enumerate(altData):
d[atDisc] = 1
d[at] = 0
d[weightID] = 0.000001 * data[i][weightID]
elif at.varType == orange.VarTypes.Discrete:
# v dataOrig, dataFinal in newData atributu "at" dodaj ee eno vreednost, ki ima vrednost kar ime atributa + "X"
atNew = orange.EnumVariable(at.name,
values=at.values +
[at.name + "X"])
newDomain = orange.Domain(
filter(lambda x: x != at, data.domain.attributes) +
[atNew, data.domain.classVar])
newDomain.addmetas(data.domain.getmetas())
newData = orange.ExampleTable(newDomain, data)
altData = orange.ExampleTable(newDomain, data)
for i, d in enumerate(newData):
d[atNew] = data[i][at]
d[weightID] = 1 * data[i][weightID]
for i, d in enumerate(altData):
d[atNew] = at.name + "X"
d[weightID] = 0.000001 * data[i][weightID]
newData.extend(altData)
setsOfData.append(newData)
return setsOfData
learner = LogRegLearner(imputer=orange.ImputerConstructor_average(),
removeSingular=self.removeSingular)
# get Original Model
orig_model = learner(examples, weight)
if orig_model.fit_status:
print "Warning: model did not converge"
# get extended Model (you should not change data)
if weight == 0:
weight = orange.newmetaid()
examples.addMetaAttribute(weight, 1.0)
extended_set_of_examples = createLogRegExampleTable(examples, weight)
extended_models = [learner(extended_examples, weight) \
for extended_examples in extended_set_of_examples]
## print examples[0]
## printOUT(orig_model)
## print orig_model.domain
## print orig_model.beta
## print orig_model.beta[orig_model.continuizedDomain.attributes[-1]]
## for i,m in enumerate(extended_models):
## print examples.domain.attributes[i]
## printOUT(m)
# izracunas odstopanja
# get sum of all betas
beta = 0
betas_ap = []
for m in extended_models:
beta_add = m.beta[m.continuizedDomain.attributes[-1]]
betas_ap.append(beta_add)
beta = beta + beta_add
# substract it from intercept
#print "beta", beta
logistic_prior = orig_model.beta[0] + beta
# compare it to bayes prior
bayes = orange.BayesLearner(examples)
bayes_prior = math.log(bayes.distribution[1] / bayes.distribution[0])
# normalize errors
## print "bayes", bayes_prior
## print "lr", orig_model.beta[0]
## print "lr2", logistic_prior
## print "dist", orange.Distribution(examples.domain.classVar,examples)
## print "prej", betas_ap
# error normalization - to avoid errors due to assumption of independence of unknown values
dif = bayes_prior - logistic_prior
positives = sum(filter(lambda x: x >= 0, betas_ap))
negatives = -sum(filter(lambda x: x < 0, betas_ap))
if not negatives == 0:
kPN = positives / negatives
diffNegatives = dif / (1 + kPN)
diffPositives = kPN * diffNegatives
kNegatives = (negatives - diffNegatives) / negatives
kPositives = positives / (positives - diffPositives)
## print kNegatives
## print kPositives
for i, b in enumerate(betas_ap):
if b < 0: betas_ap[i] *= kNegatives
else: betas_ap[i] *= kPositives
#print "potem", betas_ap
# vrni originalni model in pripadajoce apriorne niclele
return (orig_model, betas_ap)
# Description: Demonstrates the use of discretization
# Category: discretization
# Classes: entropyDiscretization, DiscretizedLearner
# Uses: iris.tab
import orange
import orngDisc
data = orange.ExampleTable("iris.tab")
disc_data = orngDisc.entropyDiscretization(data)
disc_learner = orngDisc.DiscretizedLearner(orange.BayesLearner(),
name="disc-bayes")
learner = orange.BayesLearner(name="bayes")
learners = [learner, disc_learner]
import orngTest, orngStat
results = orngTest.crossValidation(learners, data)
print "Classification Accuracy:"
for i in range(len(learners)):
print("%15s: %5.3f") % (learners[i].name, orngStat.CA(results)[i])
# Description: Demostration of use of cross-validation as provided in orngEval module
# Category: evaluation
# Uses: voting.tab
# Classes: orngTest.crossValidation
# Referenced: c_performance.htm
import orange, orngTest, orngStat, orngTree
# set up the learners
bayes = orange.BayesLearner()
tree = orngTree.TreeLearner(mForPruning=2)
bayes.name = "bayes"
tree.name = "tree"
learners = [bayes, tree]
# compute accuracies on data
data = orange.ExampleTable("voting")
results = orngTest.crossValidation(learners, data, folds=10)
# output the results
print "Learner CA IS Brier AUC"
for i in range(len(learners)):
print "%-8s %5.3f %5.3f %5.3f %5.3f" % (learners[i].name, \
orngStat.CA(results)[i], orngStat.IS(results)[i],
orngStat.BrierScore(results)[i], orngStat.AUC(results)[i])
import orange, orngTest, orngStat
import random
data = orange.ExampleTable("voting")
bayes = orange.BayesLearner(name="bayes")
tree = orange.TreeLearner(name="tree")
majority = orange.MajorityLearner(name="default")
learners = [bayes, tree, majority]
names = [x.name for x in learners]
def printResults(res):
CAs = orngStat.CA(res, reportSE=1)
for i in range(len(names)):
print "%s: %5.3f+-%5.3f " % (names[i], CAs[i][0], 1.96 * CAs[i][1]),
print
print "\nproportionsTest that will always give the same results"
for i in range(3):
res = orngTest.proportionTest(learners, data, 0.7)
printResults(res)
print "\nproportionsTest that will give different results, but the same each time the script is run"
myRandom = orange.RandomGenerator()
for i in range(3):
res = orngTest.proportionTest(learners,
data,
0.7,
randomGenerator=myRandom)
else:
return learner
def __init__(self, name='Naive Bayes with FSS', N=5):
self.name = name
self.N = 5
def __call__(self, data, weight=None):
ma = orngFSS.attMeasure(data)
filtered = orngFSS.selectBestNAtts(data, ma, self.N)
model = orange.BayesLearner(filtered)
return BayesFSS_Classifier(classifier=model, N=self.N, name=self.name)
class BayesFSS_Classifier:
def __init__(self, **kwds):
self.__dict__.update(kwds)
def __call__(self, example, resultType = orange.GetValue):
return self.classifier(example, resultType)
# test above wraper on a data set
import orngStat, orngTest
data = orange.ExampleTable("voting")
learners = (orange.BayesLearner(name='Naive Bayes'), BayesFSS(name="with FSS"))
results = orngTest.crossValidation(learners, data)
# output the results
print "Learner CA"
for i in range(len(learners)):
print "%-12s %5.3f" % (learners[i].name, orngStat.CA(results)[i])
def learner(self, data):
return orange.BayesLearner(data)
import matplotlib
fig = plt.figure()
ax1 = fig.add_subplot(111)
ax1.scatter(X11, X12, s=10, c='b', marker="+")
ax1.scatter(X21, X22, s=10, c='c', marker="o")
ax1.scatter(X31, X32, s=10, c='y', marker="x")
plt.title('Plot of Three Classes of Data')
plt.show()
########################
# Build Classifier
########################
import orange, orngTest, orngStat, orngTree
classifier = orange.BayesLearner(data)
bayes = orange.BayesLearner()
bayes.name = "bayes"
learners = [bayes]
results = orngTest.crossValidation(learners, data_test, folds=10)
########################
# Compute the misclassified observations
########################
X, Y = data_test.to_numpy("A/C")
data_scored = []
for i in range(len(results.results)):
if results.results[i].classes[0] == results.results[i].actual_class:
data_scored.append(1)
def __call__(self, examples, weight=0):
# next function changes data set to a extended with unknown values
def createLogRegExampleTable(data, weightID):
finalData = orange.ExampleTable(data)
origData = orange.ExampleTable(data)
for at in data.domain.attributes:
# za vsak atribut kreiraj nov newExampleTable newData
# v dataOrig, dataFinal in newData dodaj nov atribut -- continuous variable
if at.varType == orange.VarTypes.Continuous:
atDisc = orange.FloatVariable(at.name + "Disc")
newDomain = orange.Domain(origData.domain.attributes +
[atDisc, data.domain.classVar])
newDomain.addmetas(newData.domain.getmetas())
finalData = orange.ExampleTable(newDomain, finalData)
newData = orange.ExampleTable(newDomain, origData)
origData = orange.ExampleTable(newDomain, origData)
for d in origData:
d[atDisc] = 0
for d in finalData:
d[atDisc] = 0
for i, d in enumerate(newData):
d[atDisc] = 1
d[at] = 0
d[weightID] = 100 * data[i][weightID]
elif at.varType == orange.VarTypes.Discrete:
# v dataOrig, dataFinal in newData atributu "at" dodaj ee eno vreednost, ki ima vrednost kar ime atributa + "X"
atNew = orange.EnumVariable(at.name,
values=at.values +
[at.name + "X"])
newDomain = orange.Domain(
filter(lambda x: x != at, origData.domain.attributes) +
[atNew, origData.domain.classVar])
newDomain.addmetas(origData.domain.getmetas())
temp_finalData = orange.ExampleTable(finalData)
finalData = orange.ExampleTable(newDomain, finalData)
newData = orange.ExampleTable(newDomain, origData)
temp_origData = orange.ExampleTable(origData)
origData = orange.ExampleTable(newDomain, origData)
for i, d in enumerate(origData):
d[atNew] = temp_origData[i][at]
for i, d in enumerate(finalData):
d[atNew] = temp_finalData[i][at]
for i, d in enumerate(newData):
d[atNew] = at.name + "X"
d[weightID] = 10 * data[i][weightID]
finalData.extend(newData)
return finalData
learner = LogRegLearner(imputer=orange.ImputerConstructor_average(),
removeSingular=self.removeSingular)
# get Original Model
orig_model = learner(examples, weight)
# get extended Model (you should not change data)
if weight == 0:
weight = orange.newmetaid()
examples.addMetaAttribute(weight, 1.0)
extended_examples = createLogRegExampleTable(examples, weight)
extended_model = learner(extended_examples, weight)
## print examples[0]
## printOUT(orig_model)
## print orig_model.domain
## print orig_model.beta
## printOUT(extended_model)
# izracunas odstopanja
# get sum of all betas
beta = 0
betas_ap = []
for m in extended_models:
beta_add = m.beta[m.continuizedDomain.attributes[-1]]
betas_ap.append(beta_add)
beta = beta + beta_add
# substract it from intercept
#print "beta", beta
logistic_prior = orig_model.beta[0] + beta
# compare it to bayes prior
bayes = orange.BayesLearner(examples)
bayes_prior = math.log(bayes.distribution[1] / bayes.distribution[0])
# normalize errors
#print "bayes", bayes_prior
#print "lr", orig_model.beta[0]
#print "lr2", logistic_prior
#print "dist", orange.Distribution(examples.domain.classVar,examples)
k = (bayes_prior - orig_model.beta[0]) / (logistic_prior -
orig_model.beta[0])
#print "prej", betas_ap
betas_ap = [k * x for x in betas_ap]
#print "potem", betas_ap
# vrni originalni model in pripadajoce apriorne niclele
return (orig_model, betas_ap)
it.moveBy(0, -header.height() - graph.height())
self.showNomogram()
# Callbacks
def showNomogram(self):
if self.bnomogram and self.cl:
#self.bnomogram.hide()
self.bnomogram.show()
self.bnomogram.update()
# test widget appearance
if __name__ == "__main__":
import orngLR, orngSVM
a = QApplication(sys.argv)
ow = OWNomogram()
a.setMainWidget(ow)
data = orange.ExampleTable("../../doc/datasets/heart_disease.tab")
bayes = orange.BayesLearner(data)
bayes.setattr("data", data)
ow.classifier(bayes)
# here you can test setting some stuff
a.exec_()
# save settings
ow.saveSettings()
def main():
version = "%prog version 0.1"
usage = "usage: %prog [options] [input] [options [classification]]"
desc = "QUICK START: To extract data from a trial, 'cd' to the \
trial's directory and type: 'sqk --classify'. To extract data \
from one channel of the trial (ch 1 in this case), type: \
'sqk --classify --channel=1'."
# Parse command line options.
parser = optparse.OptionParser(usage, version=version, description=desc)
parser.add_option("-C", "--classify",
dest="classify",
action="store_true",
default=False,
help="Classify the trial. IMPORTANT: Trial folder must " \
"be the current directory.")
parser.add_option("-m", "--channel", metavar="<CH>",
dest="channel",
action="store",
type="int",
default=0,
help="Specify which channel to extract data from. " \
"Default (%default) extracts data from both " \
"channels. Must choose 0 (both channels), 1, or 2.")
parser.add_option("-l", "--log",
dest="log", action="store_true", default=False,
help="Parses a log file if it exists and adds time and" \
" duration information to the data file.")
parser.add_option("-T",
"--traindata",
metavar="<DATA_FILE>",
dest="trainData",
action="store",
default=os.path.join(TRAIN_PATH, 'traindata'),
help="Specify training data set. Default is %default")
parser.add_option("-L", "--learner", metavar="<TYPE>",
dest="learner",
action="store",
default="svm",
help="Specify the classifier algorithm. Options include:" \
" 'bayes' (Naive Bayes), 'knn' (k-Nearest Neighbor)," \
" 'svm' (SVM), 'forest' (random forest). " \
"Default is %default.")
parser.add_option("-f",
"--file",
metavar="<AUDIO_FILE>",
dest="audio",
action="store",
help="Extract features and classify audio file (wav)")
parser.add_option("-p", "--path", metavar="<PATH>",
dest="path",
action="store",
help="Extract features and classify all files in a " \
"directory. To extract from current directory: " \
"'usv.py -p .' ")
parser.add_option("-r", "--rate", metavar="<SAMPLE_RATE>",
dest="sampleRate",
action="store",
default="11025",
help="Specify the sample rate of input files. Default is " \
"%default (Hz).")
parser.add_option("-t",
"--train",
metavar="<CLASS>",
dest="exampleClass",
action="store",
type='string',
help="Label the training example(s).")
parser.add_option("-d", "--data", metavar="<DATA_FILE>",
dest="data",
action="store",
default="data.tab",
help="Write to data file (.tab format). Default is " \
"'%default' or 'traindata.tab' for training data.")
parser.add_option("-S", "--seg-resamp",
dest="segment",
action="store_true",
default=False,
help="Resample to 11025 Hz and split into multiple files " \
"based on silence. IMPORTANT: Trial folder must " \
"be the current directory.")
(opts, args) = parser.parse_args()
if opts.channel and not (opts.classify or opts.segment):
parser.error("'--channel' option requires '--classify' option'")
if opts.log and not opts.classify:
parser.error("'--log' option requires '--classify' option'")
# Open train data file or create it if it doesn't exist.
if opts.exampleClass and opts.data == "data.tab":
opts.data = os.path.join(TRAIN_PATH, 'traindata.tab')
if opts.audio or opts.path:
if not opts.segment:
print 'Opening %r. . .' % (opts.data)
data = open(opts.data, "a+")
elif opts.segment:
print "Resampling and segmenting trial. . ."
elif opts.classify:
print "Classifying trial. . ."
else:
parser.error('No input file or path specified.')
# If user specifies an audio file (-f AUDIO_FILE)
if opts.audio:
file_name, ext = os.path.splitext(opts.audio)
# Add MFCC 1-12 to data.
if not opts.segment:
write_features(opts.audio, opts.sampleRate, data)
# If classification is specified, write to data.
if opts.exampleClass:
data.write(opts.exampleClass.lower() + "\n")
print "Classified %r as %r." % (opts.audio,
opts.exampleClass.lower())
# Else if user chooses to segment file (-S)
elif opts.segment:
print "Resampling and segmenting %s. . ." % (opts.audio)
if opts.channel == 0:
run_commands(
seg_resamp(opts.audio,
int(opts.sampleRate),
outfile=file_name + '_call.wav',
directory=file_name + "_ch1_2",
ch1=True,
ch2=True))
elif opts.channel == 1:
run_commands(
seg_resamp(opts.audio,
int(opts.sampleRate),
outfile=file_name + '_ch1_.wav',
directory=file_name + "_ch1",
ch1=True,
ch2=False))
elif opts.channel == 2:
run_commands(
seg_resamp(opts.audio,
int(opts.sampleRate),
outfile=file_name + '_ch2_.wav',
directory=file_name + "_ch2",
ch1=False,
ch2=True))
print "Wrote to './%s'." % (file_name + "_calls")
else:
print "Invalid data for %r. Skipping. . ." % opts.audio
data.write('\n')
# Else if user specifies path (-p PATH)
elif opts.path:
# Read all wav files in specified path
try:
for root, dirs, files in os.walk(opts.path):
for basename in files:
if fnmatch.fnmatch(basename, "*.[wW][aA][vV]"):
audiofile = os.path.join(root, basename)
# Skip small files
if os.path.getsize(audiofile) < 100:
continue
file_name, ext = os.path.splitext(audiofile)
# Add MFCC 1-12 to data.
if not opts.segment:
write_features(audiofile, opts.sampleRate, data)
# Write filename
data.write(str(os.path.basename(audiofile)) + "\t")
# If classification is specified, write to file.
if opts.exampleClass:
data.write(opts.exampleClass.lower() + "\n")
print "Classified %r as %r." % (
audiofile, opts.exampleClass.lower())
# If user specifies resample and segment
elif opts.segment:
print "Resampling and segmenting %r. . ." % (
audiofile)
if opts.channel == 0:
run_commands(
seg_resamp(
audiofile,
int(opts.sampleRate),
outfile=os.path.basename(file_name) +
'_call.wav',
directory=os.path.basename(file_name) +
"_ch1_2",
ch1=True,
ch2=True))
elif opts.channel == 1:
run_commands(
seg_resamp(
audiofile,
int(opts.sampleRate),
outfile=os.path.basename(file_name) +
'_ch1_.wav',
directory=os.path.basename(file_name) +
"_ch1",
ch1=True,
ch2=False))
elif opts.channel == 2:
run_commands(
seg_resamp(
audiofile,
int(opts.sampleRate),
outfile=os.path.basename(file_name) +
'_ch2_.wav',
directory=os.path.basename(file_name) +
"_ch2",
ch1=False,
ch2=True))
else:
data.write('\n')
except (FloatingPointError, IOError):
print "An error occurred. Skipping %. . .r" % audiofile
# Else if user chooses to segment and resample the trial (current dir)
elif opts.segment:
for audiofile in glob(os.path.join('./', "*.[wW][aA][vV]")):
file_name, ext = os.path.splitext(audiofile)
print "Resampling and segmenting %r. . ." % (file_name)
if opts.channel == 0:
run_commands(
seg_resamp(audiofile,
int(opts.sampleRate),
outfile=file_name + '_call.wav',
directory=file_name + "_ch1_2",
ch1=True,
ch2=True))
elif opts.channel == 1:
run_commands(
seg_resamp(audiofile,
int(opts.sampleRate),
outfile=file_name + '_ch1_.wav',
directory=file_name + "_ch1",
ch1=True,
ch2=False))
elif opts.channel == 2:
run_commands(
seg_resamp(audiofile,
int(opts.sampleRate),
outfile=file_name + '_ch2_.wav',
directory=file_name + "_ch2",
ch1=False,
ch2=True))
# Else if user chooses to classify the trial
elif opts.classify:
# TODO: Should not be able to classify if no data files in folder
try:
traindata = orange.ExampleTable(opts.trainData)
except SystemError:
print "Training data not found."
sys.exit(1)
# The logger
if opts.log:
logs = glob(os.path.join(os.getcwd(), "*.[lL][oO][gG]"))
if len(logs) > 1:
print "ERROR: Multiple log files."
sys.exit(1)
log = usv.avisoftlog.RecLog(open(logs[0], 'r'))
# The classifier
print "Constructing %s classifier \
(may take several minutes). . ." % (opts.learner)
if opts.learner.lower() == "bayes":
classifier = orange.BayesLearner(traindata)
classifier.name = "naive_bayes"
elif opts.learner.lower() == "knn":
classifier = Orange.classification.knn.kNNLearner(traindata)
classifier.name = "kNN"
elif opts.learner.lower() == "svm":
svm = SVMLearner(name="SVM",
kernel_type=kernels.RBF,
C=128,
gamma=2,
nu=0.1)
classifier = svm(traindata)
classifier.name = "SVM"
elif opts.learner.lower() == "tree":
classifier = orngTree.TreeLearner(traindata)
classifier.name = "tree"
elif opts.learner.lower() == "forest":
classifier = Orange.ensemble.forest.RandomForestLearner(traindata)
classifier.name = "random_forest"
# Create data summary file
if opts.channel == 0:
datasummary_name = os.path.splitext(opts.data)[0] + "_ch1_2.tab"
elif opts.channel == 1:
datasummary_name = os.path.splitext(opts.data)[0] + "_ch1.tab"
elif opts.channel == 2:
datasummary_name = os.path.splitext(opts.data)[0] + "_ch2.tab"
if os.path.exists(datasummary_name):
print "Data file %r already exists." % (datasummary_name)
print "Exiting . . ."
sys.exit(1)
else:
summary = open(datasummary_name, "a+")
# Write metadata
summary.write("# data = %s\n" % (datasummary_name))
summary.write("# channel = %d\n" % (opts.channel))
summary.write("# sample_rate = %s\n" % (opts.sampleRate))
summary.write("# classifier = %s\n" % (classifier.name))
# Write header
summary.write("FILE\t")
for i in range(len(traindata.domain.classVar.values)):
summary.write(traindata.domain.classVar.values[i].upper() + "\t")
if opts.log:
summary.write("start: " + str(log.start.time) + "\t")
summary.write("Duration" + "\t")
summary.write("\n")
totals = [0] * len(traindata.domain.classVar.values)
proportions = [0.0] * len(totals)
for root, dirs, files in os.walk(os.getcwd()):
# For each file's directory in this trial
for dir in dirs:
data = open(os.path.join(dir, dir + '.tab'), 'w+')
if opts.channel == 0:
calls = glob(os.path.join(dir, "*ch1_2*.[wW][aA][vV]"))
elif opts.channel == 1:
calls = glob(os.path.join(dir, "*ch1*.[wW][aA][vV]"))
elif opts.channel == 2:
calls = glob(os.path.join(dir, "*ch2*.[wW][aA][vV]"))
# For each call
for c in calls:
# Skip small files
if os.path.getsize(c) < 100:
print "Skipping %s (not enough data)" % c
continue
# Write feature data
write_features(c, opts.sampleRate, data)
data.close() # Ensures that data is saved
# Write filenames and classifications
data = open(os.path.join(dir, dir + '.tab'), 'a+')
datatable = orange.ExampleTable(
os.path.join(dir, dir + '.tab'))
classification = classifier(datatable[calls.index(c)])
data.write(str(os.path.basename(c)) + '\t')
data.write(str(classification))
data.write('\n')
try:
data.close()
except UnboundLocalError:
parser.error(
'No directories in this folder. Did you remember to segment the files?'
)
# Write class count data to summary table
for dir in dirs:
if opts.channel == 0:
data_files = glob(os.path.join(dir, "*ch1_2.tab"))
elif opts.channel == 1:
data_files = glob(os.path.join(dir, "*ch1.tab"))
elif opts.channel == 2:
data_files = glob(os.path.join(dir, "*ch2.tab"))
for c in data_files:
if os.path.getsize(c) == 0:
continue
file_name, ext = os.path.splitext(os.path.basename(c))
summary.write(file_name + '\t')
callsdata = orange.ExampleTable(os.path.join("./", c))
# Vector of class counts
counts = [0] * len(callsdata.domain.classVar.values)
for e in callsdata:
counts[int(e.getclass())] += 1
# Write counts
for i in range(len(callsdata.domain.classVar.values)):
summary.write(str(counts[i]) + "\t")
totals[i] += counts[i]
# Write log data
if opts.log:
tmp = str(os.path.basename(dir)).lower()
entry = tmp[0:tmp.find("_")] + ".wav"
summary.write(str(log.getevent(entry).time) + "\t")
summary.write(log.getevent(entry).duration + "\t")
log.close()
summary.write('\n')
# Write totals. Exclude BGNOISE.
summary.write("TOTAL" + "\t\t")
for i in range(1, len(totals)):
summary.write(str(totals[i]) + "\t")
if opts.log:
summary.write("end: " + str(log.end.time) + "\t")
summary.write("\n")
# Write proportions. Exclude BGNOISE.
summary.write("P" + "\t\t")
for i in range(1, len(proportions)):
try:
proportions[i] = float(
totals[i]) / float(sum(totals) - totals[0])
except ZeroDivisionError:
proportions[i] = 0.0
summary.write("%.4f\t" % (proportions[i]))
summary.write("\n")
summary.close()
# Open data file when finished
subprocess.call('open %s' % (datasummary_name), shell=True)
else:
data.write("\n")
if not opts.segment:
data.close()
print "Success!"
# Description: Demostrates the use of classification scores
# Category: evaluation
# Uses: voting.tab
# Referenced: orngStat.htm
import orange, orngTest, orngTree
learners = [orange.BayesLearner(name = "bayes"),
orngTree.TreeLearner(name="tree"),
orange.MajorityLearner(name="majrty")]
voting = orange.ExampleTable("voting")
res = orngTest.crossValidation(learners, voting)
vehicle = orange.ExampleTable("vehicle")
resVeh = orngTest.crossValidation(learners, vehicle)
import orngStat
CAs = orngStat.CA(res)
APs = orngStat.AP(res)
Briers = orngStat.BrierScore(res)
ISs = orngStat.IS(res)
print
print "method\tCA\tAP\tBrier\tIS"
for l in range(len(learners)):
print "%s\t%5.3f\t%5.3f\t%5.3f\t%6.3f" % (learners[l].name, CAs[l], APs[l], Briers[l], ISs[l])
CAs = orngStat.CA(res, reportSE=True)