def test_repe_test(times, features, classes):
every_f1_test = {}
array_means_test = np.array([])
array_vars_test = np.array([])
iii = 0
while iii < times:
x_train, y_train, x_cv, y_cv, x_test, y_test = TrainCvTest. \
separate_databases(features, classes)
clf = svm.trainSVM(x_train, y_train, call=True)
F1Test = FScore.F1Score(x_test, y_test, clf)
mTest = np.array([])
for key in F1Test.keys():
if key not in every_f1_test:
every_f1_test[key] = F1Test[key]
else:
every_f1_test[key] = np.append(every_f1_test[key], F1Test[key])
mTest = np.append(mTest, F1Test[key])
array_means_test = np.append(array_means_test, mTest.mean())
array_vars_test = np.append(array_vars_test, mTest.var())
iii += 1
return every_f1_test, array_means_test, array_vars_test
def classify_new_sounds(folder_of_test_sounds, target_class):
new_descriptors = {target_class: load_description(folder_of_test_sounds)}
new_normalized_features, new_y_class, new_features_names = preprocess(new_descriptors)
new_y_class = np.array([target_class]*len(new_y_class))
descriptors = load_descriptors(maximum='Inf', reverbs=True)
normalized_features, yClass, features_names = preprocess(descriptors)
clf = trainSVM(normalized_features, yClass, call=True)
F1 = F1Score(new_normalized_features, new_y_class, clf)
return F1
def calcsvmMatrix(svm,C,toler,maxIter,train_x,train_y):
svmMatrix=np.mat(np.zeros((40,40)))
for i in range(40):
for j in range(40):
if i==j:
continue
else:
#print(i,j)
train_x_new=np.vstack((train_x[i*6:i*6+6,:],train_x[j*6:j*6+6,:]))
train_y_new=np.hstack((train_y[i*6:i*6+6],train_y[j*6:j*6+6]))
svmClassifier = svm.trainSVM(train_x_new, train_y_new, C, toler, maxIter, kernelOption = ('linear', 0))
print(svmClassifier.b)
print(svmClassifier.alphas)
#svmMatrix[i,j]=svmClassifier
return svmMatrix
def recall(XData, YData, clf=1):
if clf == 1:
clf = svm.trainSVM(XData, YData, True)
predictions = []
for iii in np.arange(YData.size):
predictions = np.append(predictions, clf.predict(XData[iii, :])[0])
tp = true_pos(predictions, YData)
fn = false_neg(predictions, YData)
recall = {}
for key in tp.keys():
recall[key] = tp[key] / float(tp[key] + fn[key])
return recall
def precision(XData, YData, clf=1):
if clf == 1:
clf = svm.trainSVM(XData, YData, True)
predictions = []
for iii in np.arange(YData.size):
predictions = np.append(predictions, clf.predict(XData[iii, :])[0])
tp = true_pos(predictions, YData)
fp = false_pos(predictions, YData)
precision_ = {}
for key in tp.keys():
try:
precision_[key] = tp[key] / float(tp[key] + fp[key])
except:
precision_[key] = -1
return precision_
def test_repe_train_and_cv(times, features, classes):
every_f1_train = {}
every_f1_cv = {}
array_means_train = np.array([])
array_vars_train = np.array([])
array_means_cv = np.array([])
array_vars_cv = np.array([])
iii = 0
while iii < times:
x_train, y_train, x_cv, y_cv, x_test, y_test = TrainCvTest. \
separate_databases(features, classes)
clf = svm.trainSVM(x_train, y_train, call=True)
F1Train = FScore.F1Score(x_train, y_train, clf)
mTest = np.array([])
for key in F1Train.keys():
if key not in every_f1_cv:
every_f1_train[key] = F1Train[key]
else:
every_f1_train[key] = np.append(every_f1_train[key], F1Train[key])
mTest = np.append(mTest, F1Train[key])
array_means_train = np.append(array_means_train, mTest.mean())
array_vars_train = np.append(array_vars_train, mTest.var())
F1CV = FScore.F1Score(x_cv, y_cv, clf)
mCV = np.array([])
for key in F1CV.keys():
if key not in every_f1_cv:
every_f1_cv[key] = F1CV[key]
else:
every_f1_cv[key] = np.append(every_f1_cv[key], F1CV[key])
mCV = np.append(mCV, F1CV[key])
array_means_cv = np.append(array_means_cv, mCV.mean())
array_vars_cv = np.append(array_vars_cv, mCV.var())
iii += 1
return every_f1_train, every_f1_cv, array_means_train, \
array_vars_train, array_means_cv, array_vars_cv
labels = []
# fileIn = open('../data/testSet.txt')
fileIn = open('../data/lr_data')
for line in fileIn.readlines():
lineArr = line.strip().split('\t')
dataSet.append([float(lineArr[0]), float(lineArr[1])])
labels.append(float(lineArr[2]))
dataSet = mat(dataSet)
labels = mat(labels).T
train_x = dataSet[0:81, :]
train_y = labels[0:81, :]
test_x = dataSet[80:101, :]
test_y = labels[80:101, :]
## step 2: training...
print "step 2: training..."
C = 0.6
toler = 0.001
maxIter = 50
svmClassifier = svm.trainSVM(train_x, train_y, C, toler, maxIter, kernelOption=('linear', 0))
## step 3: testing
print "step 3: testing..."
accuracy = svm.testSVM(svmClassifier, test_x, test_y)
## step 4: show the result
print "step 4: show the result..."
print 'The classify accuracy is: %.3f%%' % (accuracy * 100)
svm.showSVM(svmClassifier)
lineArr = line.strip().split('\t')
dataSet.append([float(lineArr[0]), float(lineArr[1])])
labels.append(float(lineArr[2]))
dataSet = mat(dataSet)
labels = mat(labels).T
train_x = dataSet[0:81, :]
train_y = labels[0:81, :]
test_x = dataSet[80:101, :]
test_y = labels[80:101, :]
## step 2: training
print("step 2: training...")
C = 0.6
toler = 0.001
maxIter = 50
svmClassifier = svm.trainSVM(train_x,
train_y,
C,
toler,
maxIter,
kernelOption=('linear', 0))
## step 3: testing
print("step 3: testing...")
accuracy = svm.testSVM(svmClassifier, test_x, test_y)
## step 4: show the result
print("step 4: show the result...")
print('The classify accuracy is: %.3f%%' % (accuracy * 100))
svm.showSVM(svmClassifier)
print "step 1: load data..."
dataSet = []
labels = []
fileIn = open('D:/soft/python/testSet.txt')
for line in fileIn.readlines():
lineArr = line.strip().split('\t')
dataSet.append([float(lineArr[0]), float(lineArr[1])])
labels.append(float(lineArr[2]))
dataSet = mat(dataSet)## numPy 函数， 将数组转化为矩阵
labels = mat(labels).T
train_x = dataSet[0:81, :]
train_y = labels[0:81, :]
test_x = dataSet[80:101, :]
test_y = labels[80:101, :]
## step 2: training...
print "step 2: training..."
C = 0.6
toler = 0.001 ## 迭代的终止条件
maxIter = 50
svmClassifier = svm.trainSVM(train_x, train_y, C, toler, maxIter, kernelOption = ('linear', 0)) ## //() 元组就像不可更改的列表list【】
## step 3: testing
print "step 3: testing..."
accuracy = svm.testSVM(svmClassifier, test_x, test_y)
## step 4: show the result
print "step 4: show the result..."
print 'The classify accuracy is: %.3f%%' % (accuracy * 100)
svm.showSVM(svmClassifier)
# print(type(data))
# print(label.shape)
# print(datas.shape)
if __name__ == '__main__':
# data,label = svm.loadDataSet("testSet.txt")
print("step 1:load data...")
train, test, train_label, test_label = loadDataSet("testSet.txt")
print("step 2: training...")
C = 0.6
toler = 0.001
maxIter = 40
svmClassifier, b, alpha = svm.trainSVM(train,
train_label,
C,
toler,
maxIter,
kernelOption=('linear', 0))
# # print(b)
# # print(alpha[alpha>0])
joblib.dump(svmClassifier, "train_model.m") # 保存模型
# svmClassifier = joblib.load("train_model.m")#加载模型
# # ## step 3: testing
print("step 3: testing...")
test_accuracy = svm.testSVM(svmClassifier, test, test_label)
# print(accuracy)
print('The classify test_accuracy is: %.3f%%' % (test_accuracy * 100))
## step 4: show the result
print("step 4: show the result...")
svm.showSVM(svmClassifier)
