def test():
from PreProcess.createDataset import createDataSet
from os import path
from FeatureSelection import afterFeatureSelection2
from PreProcess.minmax2 import minmaxscaler
from PreProcess.createDataset import featureAndLabel
# filePath = path.abspath(path.join(path.dirname(__file__), path.pardir, r'DataSet', r'MDP', r'D1', r'KC1.arff'))
filePath = r'/home/chyq/Document/MyProject/DataSet/MDP/D1/KC1.arff'
data, trainsetWithLabel, testsetWithLabel, relation, attribute = createDataSet(
filePath, 5)
# featureSet = bagging.bagIt(trainset)
# 分离出训练集、测试集的feature, label
train_feature, train_label = featureAndLabel(trainsetWithLabel)
test_feature, test_label = featureAndLabel(testsetWithLabel)
# 做normalization 得出的结果在trainset, test。
trainset, x_min, x_max = minmaxscaler(train_feature, lower=-1)
testset = minmaxscaler(test_feature,
x_feature_min=x_min,
x_feature_max=x_max)
from sklearn import preprocessing
# trainset = preprocessing.scale(train_feature)
# testset = preprocessing.scale(test_feature)
# x = list(trainset[:, 12])
# y = list(trainset[:, 16])
# plt.scatter(x, y)
plt.hist(trainset[:, 13])
plt.show()
def test():
from PreProcess.createDataset import createDataSet
from os import path
from FeatureSelection import afterFeatureSelection2
from PreProcess.minmax2 import minmaxscaler
from PreProcess.createDataset import featureAndLabel
filePath = path.abspath(
path.join(path.dirname(__file__), path.pardir, r'DataSet', r'MDP',
r'D1', r'KC1.arff'))
data, trainsetWithLabel, testsetWithLabel, relation, attribute = createDataSet(
filePath, 5)
# featureSet = bagging.bagIt(trainset)
# 分离出训练集、测试集的feature, label
train_feature, train_label = featureAndLabel(trainsetWithLabel)
test_feature, test_label = featureAndLabel(testsetWithLabel)
# 做normalization 得出的结果在trainset, test。
trainset, x_min, x_max = minmaxscaler(train_feature)
testset = minmaxscaler(test_feature,
x_feature_min=x_min,
x_feature_max=x_max)
toDelete = spearman(trainset)
print toDelete
def test():
from PreProcess.createDataset import createDataSet
from os import path
from FeatureSelection import FeatureSelectionProcess
from PreProcess.minmax2 import minmaxscaler
from PreProcess.createDataset import featureAndLabel
from Fsvmcil import create_weight
import arff
filePath = path.abspath(path.join(path.dirname(__file__), path.pardir, r'DataSet', r'MDP', r'D2', r'PC5.arff'))
data, trainsetWithLabel, testsetWithLabel, relation, attribute = createDataSet(filePath, 10)
# 分离出训练集、测试集的feature, label
train_feature, train_label = featureAndLabel(trainsetWithLabel)
test_feature, test_label = featureAndLabel(testsetWithLabel)
# 做normalization 得出的结果在trainset, test。
trainset, x_min, x_max = minmaxscaler(train_feature)
testset = minmaxscaler(test_feature, x_feature_min=x_min, x_feature_max=x_max)
featured_trainset, featured_attribute = FeatureSelectionProcess.selectedSet(trainset, train_label, attribute,
trainset)
featured_trainset = np.array(featured_trainset)
featured_trainset = featured_trainset[:, :-1]
import LibsvmFormat
x, y = LibsvmFormat.formatlib(featured_trainset, train_label)
xtest, ytest = LibsvmFormat.formatlib(testset, test_label)
# W=create_weight(featured_trainset, train_label)
best_para = geneticFeature(x, y, xtest, ytest, featured_trainset, train_label)
print best_para
def test():
from PreProcess import createDataset
from os import path
filePath = path.abspath(
path.join(path.dirname(__file__), path.pardir, r'DataSet', r'MDP',
r'PROMISE', r'cm1.arff'))
trainset, testset = createDataset.createDataSet(filePath, 5)
r = selectedSet(trainset)
def test():
from PreProcess import createDataset
from FeatureSelection import bagging
from os import path
filePath = path.abspath(path.join(path.dirname(__file__), path.pardir, r'DataSet', r'MDP', r'PROMISE', r'cm1.arff'))
trainset, testset = createDataset.createDataSet(filePath, 5)
featureSet = bagging.bagIt(trainset)
avgWeight(featureSet, 20)
def test():
from PreProcess.createDataset import createDataSet
from os import path
from FeatureSelection import afterFeatureSelection
from PreProcess.minmax2 import minmaxscaler
from PreProcess.createDataset import featureAndLabel
filePath = path.abspath(
path.join(path.dirname(__file__), path.pardir, r'DataSet', r'MDP',
r'D1', r'KC1.arff'))
data, trainset, testset, relation, attribute = createDataSet(filePath, 5)
# featureSet = bagging.bagIt(trainset)
train_feature, train_label = featureAndLabel(trainset)
test_feature, test_label = featureAndLabel(testset)
trainset, x_min, x_max = minmaxscaler(train_feature)
testset = minmaxscaler(test_feature,
x_feature_min=x_min,
x_feature_max=x_max)
featured_trainset, attribute = afterFeatureSelection.selectedSet(
trainset, train_label, attribute)
from Evaluation.eva import evaluationRes
predicted_label_f = originSVM(featured_trainset, train_label, testset,
test_label)
# print predicted_label_f
# print testset
a, b = evaluationRes(predicted_label_f, test_label)
print a, b
print "--------------------------------------------"
predicted_label_nf = originSVM(trainset, train_label, testset, test_label)
c, d = evaluationRes(predicted_label_nf, test_label)
print c, d
def test():
from PreProcess.createDataset import createDataSet
from os import path
from FeatureSelection import FeatureSelectionProcess
from PreProcess.minmax2 import minmaxscaler
from PreProcess.createDataset import featureAndLabel
filePath = path.abspath(
path.join(path.dirname(__file__), path.pardir, r'DataSet', r'MDP',
r'D1', r'KC1.arff'))
data, trainsetWithLabel, testsetWithLabel, relation, attribute = createDataSet(
filePath, 5)
# featureSet = bagging.bagIt(trainset)
# 分离出训练集、测试集的feature, label
train_feature, train_label = featureAndLabel(trainsetWithLabel)
test_feature, test_label = featureAndLabel(testsetWithLabel)
# 做normalization 得出的结果在trainset, test。
trainset, x_min, x_max = minmaxscaler(train_feature)
testset = minmaxscaler(test_feature,
x_feature_min=x_min,
x_feature_max=x_max)
# from sklearn import preprocessing
# trainset = preprocessing.scale(train_feature)
# testset = preprocessing.scale(test_feature)
############################
# 1.
# 生成原始的arff,包括训练集、测试集
origin_train = np.c_[trainset, train_label]
testData = np.c_[testset, test_label]
arff_obj = {
'relation': relation,
'attributes': attribute,
'data': origin_train
}
import arff
tr0 = arff.dumps(arff_obj)
try:
f1 = open(
'/home/chyq/Document/MyProject/DataSet/MDP/my/my_kc1_origin.arff',
'w')
f1.write(tr0)
finally:
f1.close()
arff_obj = {
'relation': relation,
'attributes': attribute,
'data': testData
}
te = arff.dumps(arff_obj)
try:
f2 = open(
'/home/chyq/Document/MyProject/DataSet/MDP/my/my_kc1_test.arff',
'w')
f2.write(te)
finally:
f2.close()
#############################
2.
# 生成Bagging+Correlation 的特征子集，需要注意的是，attribute已经经过了处理。数量和featureed_trainset是一样的
featured_trainset, featured_attribute = FeatureSelectionProcess.selectedSet(
trainset, train_label, attribute, trainset)
print "bagging+corr", len(featured_attribute)
arff_obj = {
'relation': relation,
'attributes': featured_attribute,
'data': featured_trainset
}
# 写入to1
to1 = arff.dumps(arff_obj)
try:
f = open(
'/home/chyq/Document/MyProject/DataSet/MDP/my/my_kc1_featured.arff',
'w')
f.write(to1)
finally:
f.close()
#############################
# 3.
# 下边这里的代码：是用于检索出那些重复的下标，放进toDelete内
# 事实证明，是否经过了featureSelection，对计算Corr几乎没有影响
from FeatureSelection import correlation
toDelete = correlation.corr(trainset)
Corr_attribute = []
for i in range(len(attribute)):
if i not in toDelete:
Corr_attribute.append(attribute[i])
print "corr len", len(Corr_attribute)
t = np.c_[trainset, train_label]
noCorr_data = np.delete(t, toDelete, axis=1)
arff_obj = {
'relation': relation,
'attributes': Corr_attribute,
'data': noCorr_data
}
# arff_obj = {'relation': relation, 'attributes': attribute, 'data': featured_trainset}
to2 = arff.dumps(arff_obj)
try:
f = open(
'/home/chyq/Document/MyProject/DataSet/MDP/my/my_kc1_corr.arff',
'w')
f.write(to2)
finally:
f.close()
####################
# 4.
from FeatureSelection import afterFeatureSelection3
featured_trainset, featured_attribute = afterFeatureSelection3.selectedSet(
trainset, train_label, attribute, train_feature)
arff_obj = {
'relation': relation,
'attributes': featured_attribute,
'data': featured_trainset
}
print "info_gain", len(featured_attribute)
# 写入to3
to3 = arff.dumps(arff_obj)
try:
f = open(
'/home/chyq/Document/MyProject/DataSet/MDP/my/my_kc1_info.arff',
'w')
f.write(to3)
finally:
f.close()
######
# 5
# 写入一个文件，方便读取
from Algo import Fsvmcil
Fsvmcil.create_weight(trainset, train_label)
def baggingAlgo():
filePath = path.abspath(
path.join(path.dirname(__file__), path.pardir, r'DataSet', r'MDP',
r'D2', r'PC5.arff'))
data, trainsetWithLabel, testsetWithLabel, relation, attribute = createDataSet(
filePath, 10)
# 分离出训练集、测试集的feature, label
train_feature, train_label = featureAndLabel(trainsetWithLabel)
test_feature, test_label = featureAndLabel(testsetWithLabel)
# 做normalization 得出的结果在trainset, test。
trainset, x_min, x_max = minmaxscaler(train_feature)
testset = minmaxscaler(test_feature,
x_feature_min=x_min,
x_feature_max=x_max)
featured_trainset, featured_attribute = FeatureSelectionProcess.selectedSet(
trainset, train_label, attribute, trainset)
featured_trainset = np.array(featured_trainset)
featured_trainset = featured_trainset[:, :-1]
import LibsvmFormat
x, y = LibsvmFormat.formatlib(featured_trainset, train_label)
xtest, ytest = LibsvmFormat.formatlib(testset, test_label)
# W = []
W_Knn = create_weightknn(featured_trainset, train_label, 10)
best_para_knn = genetic(x, y, xtest, ytest, W_Knn)
W_fsvmcil = create_weight(featured_trainset, train_label)
best_para_fsvmcvil = genetic(x, y, xtest, ytest, W_fsvmcil)
best_para_feature = geneticFeature(x, y, xtest, ytest)
print best_para_knn, best_para_fsvmcvil, best_para_feature
#############
prob = svm_problem(W_Knn, y, x)
p = '-c {0} -g {1}'.format(best_para_knn[1][0], best_para_knn[1][1])
para = svm_parameter(p)
model1 = svm_train(prob, para)
p_label1, p_acc, p_val = svm_predict(ytest, xtest, model1)
prob = svm_problem(W_fsvmcil, y, x)
p = '-c {0} -g {1}'.format(best_para_fsvmcvil[1][0],
best_para_fsvmcvil[1][1])
para = svm_parameter(p)
model2 = svm_train(prob, para)
p_label2, p_acc, p_val = svm_predict(ytest, xtest, model2)
W_featureW = wf.create_weight(featured_trainset)
prob = svm_problem(W_featureW, y, x)
p = '-c {0} -g {1}'.format(best_para_feature[1][0],
best_para_feature[1][1])
para = svm_parameter(p)
model3 = svm_train(prob, para)
p_label3, p_acc, p_val = svm_predict(ytest, xtest, model3)
result = []
for i in range(len(p_label1)):
judge = 0
if p_label1[i] == 1.0:
judge += 1
if p_label2[i] == 1.0:
judge += 1
if p_label3[i] == 1.0:
judge += 1
if judge >= 2:
result.append(1.0)
else:
result.append(-1.0)
return result
