def metric(self):
totalTimer = Timer()
with totalTimer:
model = mlpy.Golub()
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
def BuildModel(self, data, labels): # Create and train the classifier. golub = mlpy.Golub() golub.learn(data, labels) return golub
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")
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)
test = da.pred(xcontrol) # test points
print 'DLDA: %.1f percent predicted' % (100 * len(test[test == ycontrol]) /
len(test))
dic['da'].append(100 * len(test[test == ycontrol]) / len(test))
golub = mlpy.Golub()
golub.learn(x, y)
test = golub.pred(xcontrol) # test points
print 'Golub: %.1f percent predicted' % (
100 * len(test[test == ycontrol]) / len(test))
dic['golub'].append(100 * len(test[test == ycontrol]) / len(test))
knn = mlpy.KNN(k=7)
knn.learn(x, y)
test = knn.pred(xcontrol) # test points
print 'KNN: %.1f percent predicted' % (100 * len(test[test == ycontrol]) /
len(test))
dic['knn'].append(100 * len(test[test == ycontrol]) / len(test))
tree = mlpy.ClassTree(stumps=0, minsize=100)
tree.learn(x, y)