#print "start"
train_data = pd.read_csv(datapath, header=None, index_col=None)
X = np.array(train_data)
Y = list(map(lambda x: 1, xrange(len(train_data) // 2)))
Y2 = list(map(lambda x: 0, xrange(len(train_data) // 2)))
Y.extend(Y2)
Y = np.array(Y)
svc = svm.SVC(probability=True)
parameters = {'kernel': ['rbf'], 'C': [math.pow(2,e) for e in range(-5,15,2)], 'gamma': [math.pow(2,e) for e in range(-15, -5, 2)]}
#parameters = {'kernel': ['rbf'], 'C':map(lambda x:2**x,np.linspace(-2,5,7)), 'gamma':map(lambda x:2**x,np.linspace(-5,2,7))}
clf = GridSearchCV(svc, parameters, cv=crossvalidation_values, n_jobs=CPU_values, scoring='accuracy')
clf.fit(X, Y)
C=clf.best_params_['C']
gamma=clf.best_params_['gamma']
y_predict=cross_val_predict(svm.SVC(kernel='rbf',C=C,gamma=gamma),X,Y,cv=crossvalidation_values,n_jobs=CPU_values)
y_predict_prob=cross_val_predict(svm.SVC(kernel='rbf',C=C,gamma=gamma,probability=True),X,Y,cv=crossvalidation_values,n_jobs=CPU_values,method='predict_proba')
joblib.dump(clf,path+classifier+mode+outputname+".model")
predict_save=[Y.astype(int),y_predict.astype(int),y_predict_prob[:,1]]
predict_save=np.array(predict_save).T
pd.DataFrame(predict_save).to_csv('Before_'+path+classifier+mode+outputname+"_"+'_predict_crossvalidation.csv',header=None,index=False)
ROC_AUC_area=metrics.roc_auc_score(Y,y_predict_prob[:,1])
ACC=metrics.accuracy_score(Y,y_predict)
precision, recall, SN, SP, GM, TP, TN, FP, FN = performance(Y, y_predict)
F1_Score=metrics.f1_score(Y, y_predict)
F_measure=F1_Score
MCC=metrics.matthews_corrcoef(Y, y_predict)
pos=TP+FN
neg=FP+TN
savedata=[[['SVM'+"C:"+str(C)+"gamma:"+str(gamma),ACC,precision, recall,SN, SP, GM,F_measure,F1_Score,MCC,ROC_AUC_area,TP,FN,FP,TN,pos,neg]]]
easy_excel.save(classifier+"_crossvalidation",[str(X.shape[1])],savedata,path+'cross_validation_'+classifier+"_"+outputname+'.xls')
F_measure = F1_Score
MCC = metrics.matthews_corrcoef(Y, y_predict)
pos = TP + FN
neg = FP + TN
savedata = [[[
'xgboost' + "n_estimators:" + str(n_estimators) + "max_depth:" +
str(max_depth) + "learning_rate:" + str(learning_rate), ACC,
precision, recall, SN, SP, GM, F_measure, F1_Score, MCC,
ROC_AUC_area, TP, FN, FP, TN, pos, neg
]]]
if ACC > bestACC:
bestACC = ACC
bestn_estimators = n_estimators
bestlearning_rate = learning_rate
best_savedata = savedata
bestmax_depth = max_depth
best_dimension = X.shape[1]
print savedata
print X.shape[1]
with open(classifier + mode + "all_dimension_results.txt", 'a') as f:
f.write(str(savedata) + "\n")
all_dimension_results.append(savedata)
print bestACC
print bestn_estimators
print bestlearning_rate
print bestmax_depth
print best_dimension
easy_excel.save(
"xgboost_jackknife", [str(best_dimension)], best_savedata,
path + classifier + mode + 'jackknife_' + outputname + '.xls')
TN_all = TN_all + TN
FP_all = FP_all + FP
FN_all = FN_all + FN
F_measure_all = F_measure_all + F_measure
F1_Score_all = F1_Score_all + F1_Score
pos_all = pos_all + pos
neg_all = neg_all + neg
MCC_all = MCC_all + MCC
all_y = [
np.array(Y_all).astype(int),
np.array(y_pred_all).astype(int),
np.array(y_pred_prob_all).astype(list)[:, 1]
]
pd.DataFrame(np.matrix(all_y).T).to_csv(path + outputname + "_predict.csv",
header=None,
index=False)
fpr, tpr, thresholds = roc_curve(
np.array(Y_all).T, list(np.array(y_pred_prob_all).astype(list)[:, 1]))
roc_auc = auc(fpr, tpr)
savedata = [[[
'svm' + "C:" + str(C) + "gamma:" + str(gamma), ACC_all / divided_num,
precision_all / divided_num, recall_all / divided_num,
SN_all / divided_num, SP_all / divided_num, GM_all / divided_num,
F_measure_all / divided_num, F1_Score_all / divided_num,
MCC_all / divided_num, roc_auc, TP_all, FN_all, FP_all, TN_all,
pos_all, neg_all
]]]
print savedata
easy_excel.save("svm_independent_test", [str(X_train.shape[1])], savedata,
path + outputname + '.xls')
predict_save=np.array(predict_save).T
pd.DataFrame(predict_save).to_csv(path+classifier+mode+outputname+"_"+'_predict_crossvalidation.csv',header=None,index=False)
ROC_AUC_area=metrics.roc_auc_score(Y,y_predict)
ACC=metrics.accuracy_score(Y,y_predict)
precision, recall, SN, SP, GM, TP, TN, FP, FN = performance(Y, y_predict)
F1_Score=metrics.f1_score(Y, y_predict)
F_measure=F1_Score
MCC=metrics.matthews_corrcoef(Y, y_predict)
pos=TP+FN
neg=FP+TN
savedata=[[['xgboost'+"n_estimators:"+str(n_estimators)+"max_depth:"+str(max_depth)+"learning_rate:"+str(learning_rate),ACC,precision, recall,SN, SP, GM,F_measure,F1_Score,MCC,ROC_AUC_area,TP,FN,FP,TN,pos,neg]]]
if ACC>bestACC:
bestACC=ACC
bestn_estimators=n_estimators
bestlearning_rate=learning_rate
best_savedata=savedata
bestmax_depth=max_depth
best_dimension=X.shape[1]
print savedata
print X.shape[1]
with open(classifier+mode+"all_dimension_results.txt",'a') as f:
f.write(str(savedata)+"\n")
all_dimension_results.append(savedata)
print bestACC
print bestn_estimators
print bestlearning_rate
print bestmax_depth
print best_dimension
easy_excel.save("xgboost_crossvalidation",[str(best_dimension)],best_savedata,path+classifier+mode+'cross_validation_'+name+'.xls')
def SVM_distance(inputname,outputname,distance,crossvalidation_values,CPU_values,SVM_distance_results):
datapath =inputname
classifier="SVM"
mode="crossvalidation"
print "start"
train_data = pd.read_csv(datapath, header=None, index_col=None)
print len(train_data)
Y = list(map(lambda x: 1, xrange(len(train_data) // 2)))
Y2 = list(map(lambda x: 0, xrange(len(train_data) // 2)))
Y.extend(Y2)
Y = np.array(Y)
F, pval = f_classif(train_data, Y)
idx = np.argsort(F)
selected_list_=idx[::-1]
F_sort_value=[F[e] for e in selected_list_]
with open(SVM_distance_results+outputname+"all_dimension_results.txt",'w') as f:
f.write(str(F_sort_value)+"\n")
with open(SVM_distance_results+outputname+"all_dimension_results.txt",'a') as f:
f.write(str(selected_list_)+"\n")
print "deal with data"
selected_list_=[a for a,b in zip(selected_list_,F_sort_value) if not math.isnan(b)]
with open(SVM_distance_results+outputname+"all_dimension_results.txt",'a') as f:
f.write(str(selected_list_)+"\n")
bestACC=0
best_c=0
best_g=0
best_dimension=0
all_dimension_results=[]
select_list=[]
best_savedata=""
select_num1=0;
for select_num in range(0,len(selected_list_),distance):
if select_num > 0:
for select_num1 in range(select_num-distance+1,select_num+1):
temp_data=selected_list_[select_num1]
select_list.append(int(temp_data))
train_data2=train_data.values
X_train=pd.DataFrame(train_data2)
X_train=X_train.iloc[:,select_list]
X = np.array(X_train)
else:
temp_data=selected_list_[select_num]
select_list.append(int(temp_data))
train_data2=train_data.values
X_train=pd.DataFrame(train_data2)
X_train=X_train.iloc[:,select_list]
X = np.array(X_train)
svc = svm.SVC(probability=True)
parameters = {'kernel': ['rbf'], 'C':map(lambda x:2**x,np.linspace(-2,5,7)), 'gamma':map(lambda x:2**x,np.linspace(-5,2,7))}
clf = GridSearchCV(svc, parameters, cv=crossvalidation_values, n_jobs=CPU_values, scoring='accuracy')
clf.fit(X, Y)
C=clf.best_params_['C']
gamma=clf.best_params_['gamma']
y_predict=cross_val_predict(svm.SVC(kernel='rbf',C=C,gamma=gamma),X,Y,cv=crossvalidation_values,n_jobs=CPU_values)
y_predict_prob=cross_val_predict(svm.SVC(kernel='rbf',C=C,gamma=gamma,probability=True),X,Y,cv=crossvalidation_values,n_jobs=CPU_values,method='predict_proba')
joblib.dump(clf,SVM_distance_results+outputname+"_"+classifier+mode+str(select_num+1)+".model")
predict_save=[Y.astype(int),y_predict.astype(int),y_predict_prob[:,1]]
predict_save=np.array(predict_save).T
#pd.DataFrame(predict_save).to_csv('Before_'+path+classifier+mode+outputname+"_"+'_predict_crossvalidation.csv',header=None,index=False)
ROC_AUC_area=metrics.roc_auc_score(Y,y_predict_prob[:,1])
ACC=metrics.accuracy_score(Y,y_predict)
precision, recall, SN, SP, GM, TP, TN, FP, FN = performance(Y, y_predict)
F1_Score=metrics.f1_score(Y, y_predict)
F_measure=F1_Score
MCC=metrics.matthews_corrcoef(Y, y_predict)
pos=TP+FN
neg=FP+TN
savedata=[[['SVM'+"C:"+str(C)+"gamma:"+str(gamma),ACC,precision, recall,SN, SP, GM,F_measure,F1_Score,MCC,ROC_AUC_area,TP,FN,FP,TN,pos,neg]]]
if ACC>bestACC:
bestACC=ACC
best_c=C
best_g=gamma
best_savedata=savedata
best_dimension=X.shape[1]
print savedata
print X.shape[1]
with open(SVM_distance_results+outputname+"all_dimension_results.txt",'a') as f:
f.write(str(savedata)+"\n")
all_dimension_results.append(savedata)
print bestACC
print best_c
print best_g
print best_dimension
y_predict1=cross_val_predict(svm.SVC(kernel='rbf',C=best_c,gamma=best_g),X,Y,cv=crossvalidation_values,n_jobs=CPU_values)
y_predict_prob1=cross_val_predict(svm.SVC(kernel='rbf',C=best_c,gamma=best_g,probability=True),X,Y,cv=crossvalidation_values,n_jobs=CPU_values,method='predict_proba')
predict_save1=[Y.astype(int),y_predict1.astype(int),y_predict_prob1[:,1]]
predict_save1=np.array(predict_save1).T
pd.DataFrame(predict_save1).to_csv(SVM_distance_results+outputname+"_"+classifier+mode+'_best_dim_pro_features.csv',header=None,index=False)
easy_excel.save("SVM_crossvalidation",[str(best_dimension)],best_savedata,SVM_distance_results+outputname+"_"+classifier+mode+'_best_ACC.xls')
return y_predict_prob1[:,1]
X,
Y,
cv=10,
n_jobs=-1).mean()
ACC = metrics.accuracy_score(Y, y_predict)
precision, recall, SN, SP, GM, TP, TN, FP, FN = performance(
Y, y_predict)
F1_Score = metrics.f1_score(Y, y_predict)
F_measure = F1_Score
MCC = metrics.matthews_corrcoef(Y, y_predict)
pos = TP + FN
neg = FP + TN
whole_result.append([[
'svm' + "C:" + str(C) + "gamma:" + str(gamma), ACC, precision,
recall, SN, SP, GM, F_measure, F1_Score, MCC, ROC_AUC_area, TP,
FN, FP, TN, pos, neg
]])
whole_dimension.append(str(X.shape[1]))
print whole_result
easy_excel.save("svm_crossvalidation", whole_dimension, whole_result,
'svm.xls')
# print RFH_PseDNC
# RFH_=pd.read_csv(sys.argv[1],header=None,index_col=None)
# RFH_=pd.DataFrame(RFH_).astype(float)
# PseDNC_=pd.read_csv(sys.argv[2],header=None,index_col=None)
# print len(PseDNC_.values[0])
# RFH_PseDNC=pd.concat([RFH_,PseDNC_],axis=1)
# pd.DataFrame(RFH_PseDNC).to_csv(sys.argv[3],header=None,index=False)
# print RFH_PseDNC
print u'>>>', name, 'is training...searching best parms...'
if isMultipleThread:
new_thread = ClassifyThread(name, grid_search, X_train, y_train, test_x=X_test, test_y=y_test)
new_thread.start()
threads.append(new_thread)
else:
loop_classifier(name, grid_search, X_train, y_train, test_x=X_test, test_y=y_test)
else:
experiment = '交叉验证结果'
print u'>>>', name, 'is cross validating...searching best parms...'
if isMultipleThread:
new_thread = ClassifyThread(name, grid_search, X, y, cv=cv)
new_thread.start()
threads.append(new_thread)
else:
loop_classifier(name, grid_search, X, y, cv=cv)
print 'Time cost: ', clock() - sec
# 等待所有线程完成
for t in threads:
t.join()
dimensions.append(str(dimension))
big_results.append(results)
print 'Time cost: ', clock() - sec
# 保存结果至Excel
print '====================='
if easy_excel.save(experiment, dimensions, big_results, excel_name):
print 'Save excel result file successfully.'
else:
print 'Failed. Please close excel result file first.'
X_predict = clf.predict(X)
X_predict_proba = clf.predict_proba(X)
print X_predict_proba
#print X_predict
#print len(X_predict)
pd.DataFrame(X_predict_proba[:,
1]).to_csv(outputname1 + 'predict_proba.csv',
header=None,
index=False)
ROC_AUC_area = metrics.roc_auc_score(Y, X_predict_proba[:, 1])
ACC = metrics.accuracy_score(Y, X_predict)
precision, recall, SN, SP, GM, TP, TN, FP, FN = performance(Y, X_predict)
F1_Score = metrics.f1_score(Y, X_predict)
F_measure = F1_Score
MCC = metrics.matthews_corrcoef(Y, X_predict)
pos = TP + FN
neg = FP + TN
C = clf.best_params_['C']
gamma = clf.best_params_['gamma']
print X.shape[1]
print name1
print ACC
savedata = [[[
'SVM' + "C:" + str(C) + "gamma:" + str(gamma), ACC, precision, recall,
SN, SP, GM, F_measure, F1_Score, MCC, ROC_AUC_area, TP, FN, FP, TN,
pos, neg
]]]
easy_excel.save(
"SVM_crossvalidation", [str(X.shape[1])], savedata,
'SVM_crossvalidation' + name1 + '_Predict_' + name + '.xls')
else:
loop_classifier(name,
grid_search,
X_train,
y_train,
test_x=X_test,
test_y=y_test)
else:
experiment = '交叉验证结果'
print u'>>>', name, 'is cross validating...searching best parms...'
if isMultipleThread:
new_thread = ClassifyThread(name, grid_search, X, y, cv=cv)
new_thread.start()
threads.append(new_thread)
else:
loop_classifier(name, grid_search, X, y, cv=cv)
print 'Time cost: ', clock() - sec
# 等待所有线程完成
for t in threads:
t.join()
dimensions.append(str(dimension))
big_results.append(results)
print 'Time cost: ', clock() - sec
# 保存结果至Excel
print '====================='
if easy_excel.save(experiment, dimensions, big_results, excel_name):
print 'Save excel result file successfully.'
else:
print 'Failed. Please close excel result file first.'
def SVM_calssfier(input_feature, proba_dir, model_dir, result_dir,
crossvalidation_values, CPU_values, output_name, t):
#print(input_feature)
#output_name = input_feature.split("\\")[-1].split(".")[0]
#print(output_name)
classifier = 'SVM'
X = input_feature
Y = list(map(lambda x: 1, xrange(len(input_feature) // 2)))
Y2 = list(map(lambda x: 0, xrange(len(input_feature) // 2)))
Y.extend(Y2)
Y = np.array(Y)
d = input_feature.shape[1]
svc = svm.SVC(probability=True)
parameters = {
'kernel': ['rbf'],
'C': map(lambda x: 2**x, np.linspace(-2, 5, 7)),
'gamma': map(lambda x: 2**x, np.linspace(-5, 2, 7))
}
clf = GridSearchCV(svc,
parameters,
cv=crossvalidation_values,
n_jobs=CPU_values,
scoring='accuracy')
clf.fit(X, Y)
C = clf.best_params_['C']
gamma = clf.best_params_['gamma']
y_predict = cross_val_predict(svm.SVC(kernel='rbf', C=C, gamma=gamma),
X,
Y,
cv=crossvalidation_values,
n_jobs=CPU_values)
y_predict_prob = cross_val_predict(svm.SVC(kernel='rbf',
C=C,
gamma=gamma,
probability=True),
X,
Y,
cv=crossvalidation_values,
n_jobs=CPU_values,
method='predict_proba')
joblib.dump(clf, model_dir + "\\" + str(t) + "time.model")
predict_save = [y_predict_prob[:, 0], y_predict_prob[:, 1]]
predict_save = np.array(predict_save).T
pd.DataFrame(predict_save).to_csv(proba_dir + str(t) + 'time.csv',
header=None,
index=False)
ROC_AUC_area = metrics.roc_auc_score(Y, y_predict_prob[:, 1])
ACC = metrics.accuracy_score(Y, y_predict)
precision, recall, SN, SP, GM, TP, TN, FP, FN = performance(Y, y_predict)
F1_Score = metrics.f1_score(Y, y_predict)
F_measure = F1_Score
MCC = metrics.matthews_corrcoef(Y, y_predict)
pos = TP + FN
neg = FP + TN
savedata = [[[
'SVM' + "C:" + str(C) + "gamma:" + str(gamma), ACC, precision, recall,
SN, SP, GM, F_measure, F1_Score, MCC, ROC_AUC_area, TP, FN, FP, TN,
pos, neg
]]]
#print(savedata)
#print(result_dir+output_name+'cross_validation_'+str(d)+'D_'+str(t)+'time.xls')
easy_excel.save(
classifier + "_crossvalidation", [str(X.shape[1])], savedata,
result_dir + output_name + 'cross_validation_' + str(d) + 'D_' +
str(t) + 'time.xls')
DecisionTreeClassifier(max_depth=5),
RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1, n_jobs=-1),
AdaBoostClassifier(),
LinearSVC(),
GaussianNB()]
# 导入原始数据
second = clock()
X, y = get_data(input_file)
results = []
print 'Time cost on loading data: ', clock() - second
# 对数据切分或交叉验证，得出结果
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=split_rate, random_state=0)
for name, model in zip(names, classifiers):
if cv == 0:
print u'>>>', name, 'is training...'
out = loop_classifier(name, model, X_train, y_train, test_x=X_test, test_y=y_test)
else:
print u'>>>', name, 'is cross validating...'
out = loop_classifier(name, model, X, y, cv=cv)
if out is not None:
results.append(out)
# 保存结果至Excel
print '====================='
if easy_excel.save(str(X_train.shape[1]), results):
print 'Save "results.xls" successfully.'
else:
print 'Fail to save "results.xls". Please close "results.xls" first.'