def metric(self):
totalTimer = Timer()
with totalTimer:
model = mlpy.Perceptron(**self.build_opts)
model.learn(self.data_split[0], self.data_split[1])
if len(self.data) >= 2:
predictions = model.pred(self.data[1])
metric = {}
metric["runtime"] = totalTimer.ElapsedTime()
if len(self.data) == 3:
confusionMatrix = Metrics.ConfusionMatrix(self.data[2],
predictions)
metric['ACC'] = Metrics.AverageAccuracy(confusionMatrix)
metric['MCC'] = Metrics.MCCMultiClass(confusionMatrix)
metric['Precision'] = Metrics.AvgPrecision(confusionMatrix)
metric['Recall'] = Metrics.AvgRecall(confusionMatrix)
metric['MSE'] = Metrics.SimpleMeanSquaredError(
self.data[2], predictions)
return metric
printStats(model.pred(xTest),yTest,modelName)
##To do: model predicted XX% automation error XX% classifer error
except:
print "Error in", modelName
directory = raw_input("What directory are the XML files located:\n")
regexParse = raw_input("How would you like to parse the words, leave it blank if you would like to parse by whitespace:\n")
if(regexParse == ""):
regexParse = None
[vocab,indexToWord,fullDataPoints] = parseDataPoints(directory,regexParse)
[X,Y] = packageData(fullDataPoints,regexParse,vocab, indexToWord)
testModel(mlpy.Perceptron(alpha=0.1, thr=0.05, maxiters=1000), X, Y, "Perceptron")
testModel(mlpy.ElasticNetC(lmb=0.01, eps=0.001),X,Y, "ElasticNet")
testModel(mlpy.LibLinear(solver_type='l2r_l2loss_svc_dual', C=1), X, Y, "LibLinear")
testModel(mlpy.DLDA(delta=0.1), X, Y, "DLDA")
testModel(mlpy.Golub(), X, Y, "Golub")
testModel(mlpy.Parzen(),X,Y,"Parzen")
testModel(mlpy.KNN(2),X,Y,"KNN")
testModel(mlpy.ClassTree(),X,Y,"Classification Tree")
testModel(mlpy.MaximumLikelihoodC(),X,Y,"Maximum Likelihood Classifer")
def BuildModel(self, data, responses):
# Create and train the classifier.
model = mlpy.Perceptron(alpha=0.1, thr=0.05, maxiters=self.iterations)
model.learn(data, responses)
return model
def BuildModel(self, data, responses):
# Create and train the classifier.
model = mlpy.Perceptron(**self.opts)
model.learn(data, responses)
return model
print 'training sample: ', len(train)
x, y, fnames = prepareData(train)
print 'control sample: ', len(control)
xcontrol, ycontrol, fnames = prepareData(control)
print '\ntest algorithms:'
ld = mlpy.LDAC()
ld.learn(x, y)
test = ld.pred(xcontrol) # test points
print 'LDAC: %.1f percent predicted' % (100 * len(test[test == ycontrol]) /
float(len(test)))
dic['ld'].append(100 * len(test[test == ycontrol]) / float(len(test)))
perc = mlpy.Perceptron()
perc.learn(x, y)
test = perc.pred(xcontrol) # test points
print 'Perceptron: %.1f percent predicted' % (
100 * len(test[test == ycontrol]) / len(test))
dic['perc'].append(100 * len(test[test == ycontrol]) / len(test))
elnet = mlpy.ElasticNetC(lmb=0.01, eps=0.001)
elnet.learn(x, y)
test = elnet.pred(xcontrol) # test points
print 'Elastic Net: %.1f percent predicted' % (
100 * len(test[test == ycontrol]) / len(test))
dic['elnet'].append(100 * len(test[test == ycontrol]) / len(test))
da = mlpy.DLDA(delta=0.1)
da.learn(x, y)
featData = []
pairs_feat = []
nonepairs_feat = []
pairs_category = []
nonepairs_category = []
truePairings = [(e.strip(), f.strip()) for (
e, f) in zip(open(opts.english_pairs, "r"), open(opts.foreign_pairs, "r"))]
with open(opts.fileName, "r") as pairs:
i = 1
for line in pairs:
(e, f, features) = line.split("|||")
features = [float(feat) for feat in features.strip().split(" ")]
if ((e.strip(), f.strip()) in truePairings):
pairs_feat.append(features)
pairs_category.append(1)
else:
if (i % 350 == 0):
nonepairs_feat.append(features)
nonepairs_category.append(-1)
i += 1
x = np.concatenate((pairs_feat, nonepairs_feat), axis=0)
y = np.concatenate((pairs_category, nonepairs_category))
p = mlpy.Perceptron(alpha=0.1, thr=0.05, maxiters=100) # basic perceptron
p.learn(x, y)
w = p.w()
print "\n".join([str(weights) for weights in w])