本文整理汇总了Python中Features.getLength方法的典型用法代码示例。如果您正苦于以下问题：Python Features.getLength方法的具体用法？Python Features.getLength怎么用？Python Features.getLength使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类Features的用法示例。
在下文中一共展示了Features.getLength方法的6个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: main
# 需要导入模块: import Features [as 别名]
# 或者: from Features import getLength [as 别名]
def main():
arguments = validateInput(sys.argv)
maxIterations, regularization, stepSize, lmbd, featureSet = arguments
print maxIterations, regularization, stepSize, lmbd, featureSet
trainData = readFile('train.csv')
validationData = readFile('validation.csv')
testData = readFile('test.csv')
trainSize = trainData.shape[0]
validationSize = validationData.shape[0]
testSize = testData.shape[0]
print "Number of training examples: " + str(trainSize)
# Extract Features
Features.extractFeatures(trainData[:,0], featureSet)
print "Extracted Features:"
if featureSet == 1 or featureSet == 3:
print "Unigram: " + str(Features.getLength(1))
if featureSet == 2 or featureSet == 3:
print "Bigram: " + str(Features.getLength(2))
# Construct Input Matrices X
xTrain = Features.getMatrix(trainData[:,0], featureSet)
print "Train Matrix built"
xValidation = Features.getMatrix(validationData[:,0], featureSet)
print "Validation Matrix built"
xTest = Features.getMatrix(testData[:,0], featureSet)
print "Test Matrix built"
yTrain = extractLabel(trainData[:,1])
yVailidation = extractLabel(validationData[:,1])
yTest = extractLabel(testData[:,1])
# Train the model
theta = GD(xTrain, yTrain, trainSize, maxIterations, regularization, stepSize, lmbd, featureSet)
print "Final Theta: " + str(theta)
# Classify
trainResult = predict(xTrain, trainSize, theta, featureSet)
print "Train Result: " + str(trainResult)
validationResult = predict(xValidation, validationSize, theta, featureSet)
print "Validation Result: " + str(validationResult)
testResult = predict(xTest, testSize, theta, featureSet)
print "Test Result: " + str(testResult)
# Performance
print "\nPerformance on training data:"
performance(trainResult, trainData[:,1])
print "\nPerformance on validation data:"
performance(validationResult, validationData[:,1])
print "\nPerformance on test data:"
performance(testResult, testData[:,1])示例2: classify
# 需要导入模块: import Features [as 别名]
# 或者: from Features import getLength [as 别名]
def classify(data, weights, featureSet, algorithm):
length = Features.getLength(featureSet)
results = np.zeros(data.shape[0])
for i in range(data.shape[0]):
if algorithm == 1:
vector = Features.getVector(data[i,0], featureSet)
vector.append(length)
results[i] = predict_one(weights, vector, 0)
else:
vector = Features.getVector(data[i,0], featureSet)
results[i] = predict_one(weights, vector, length)
return results 示例3: perceptron
# 需要导入模块: import Features [as 别名]
# 或者: from Features import getLength [as 别名]
def perceptron(data, maxIterations, featureSet):
length = Features.getLength(featureSet)
rate = 0.1
weights = np.zeros((1,length+1))
i = 0
while i < maxIterations:
for j in range(data.shape[0]):
#print weights
vector = Features.getVector(data[j,0], featureSet)
vector.append(length)
sign = predict_one(weights, vector, 0)
if (data[j,1] == '+' and sign == -1) or (data[j,1] == '-' and sign == 1):
for index in vector:
weights[0,index] = weights[0,index] - rate*sign
i += 1
return weights 示例4: winnow
# 需要导入模块: import Features [as 别名]
# 或者: from Features import getLength [as 别名]
def winnow(data, maxIterations, featureSet):
length = Features.getLength(featureSet)
threshold = length
weights = np.ones((1,length))
i = 0
while i < maxIterations:
for j in range(data.shape[0]):
#print weights
vector = Features.getVector(data[j,0], featureSet)
sign = predict_one(weights, vector, threshold)
if data[j,1] == '+' and sign == -1:
for index in vector:
weights[0,index] = weights[0,index]*2
elif data[j,1] == '-' and sign == 1:
for index in vector:
weights[0,index] = weights[0,index]/2
i += 1
return weights示例5: GD
# 需要导入模块: import Features [as 别名]
# 或者: from Features import getLength [as 别名]
def GD(x, y, m, maxIterations, regularization, stepSize, lmbd, featureSet):
n = Features.getLength(featureSet) + 1
theta = np.zeros(n)
for i in range(0, maxIterations):
gradient = np.zeros(n)
for j in range(m):
if y[j]*dotProduct(theta, x[j]) <= 1:
for item in x[j]:
gradient[item] = gradient[item] + y[j]
bias = gradient[0]
if regularization == 'l2':
gradient = gradient - lmbd*theta
elif regularization == 'l1':
gradient = gradient - lmbd*np.sign(theta)
gradient[0] = bias
theta = theta + stepSize*gradient
print "Theta: " + str(theta)
return theta示例6: main
# 需要导入模块: import Features [as 别名]
# 或者: from Features import getLength [as 别名]
def main():
arguments = validateInput(sys.argv)
algorithm, maxIterations, featureSet = arguments
print algorithm, maxIterations, featureSet
# ====================================
# WRITE CODE FOR YOUR EXPERIMENTS HERE
# ====================================
trainData = readFile('train.csv')
validationData = readFile('validation.csv')
testData = readFile('test.csv')
# Extract features
Features.extractFeatures(trainData[:,0], featureSet)
length = Features.getLength(featureSet)
# Learn (Get weight vector)
if algorithm == 1:
weights = perceptron(trainData, maxIterations, featureSet)
else:
weights = winnow(trainData, maxIterations, featureSet)
# Classify
trainResult = classify(trainData, weights, featureSet, algorithm)
validationResult = classify(validationData, weights, featureSet, algorithm)
testResult = classify(testData, weights, featureSet, algorithm)
# Performance
print "\nPerformance on training data:"
performance(trainResult, trainData[:,1])
print "\nPerformance on validation data:"
performance(validationResult, validationData[:,1])
print "\nPerformance on test data:"
performance(testResult, testData[:,1])