class Recognizer():
def __init__(self):
self.trainer = None
def train(self, dataFileName):
self.trainer = Trainer(dataFileName)
self.trainer.trainAll()
self.trainer.dump()
def load(self):
trainer = Trainer()
trainer.load()
self.trainer = trainer
def classify(self, X, label1, label2):
'''
输入向量X， 在label1, label2间预测它的类属性
'''
positiveLabel = min(label1, label2)
negativeLabel = max(label1, label2)
svm = self.trainer.getSvmInstance(positiveLabel, negativeLabel)
y = svm.predict(X)
if y == 1:
return positiveLabel
elif y == -1:
return negativeLabel
else:
raise
def predict(self, X):
count_dict = {} #{label : times}
for i in range(10):
for j in range(i, 10, 1):
if i == j:
continue
label = self.classify(X, i, j)
if count_dict.has_key(label):
count_dict[label] += 1
else:
count_dict[label] = 1
maxTime = -1
maxLabel = -1
for label in count_dict:
time = count_dict[label]
if time > maxTime:
maxTime = time
maxLabel = label
return maxLabel
def test_getSvm(self):
return
trainer = Trainer()
trainer.load()
svm1 = trainer.getSvmInstance(6, 7)
dataSet = DigitDataSet()
dataSet.load(os.path.join('..', 'data', 'sample')).map(6, 7)
svm2 = SVM()
svm2.train(dataSet, 2, 0.0001)
m,n = dataSet.shape()
for i in range(m):
X = dataSet.getData(i)
y1= svm1.predict(X)
y2 = svm2.predict(X)
self.assertTrue(y1 == y2)
