def SVM_validation(X_train, y_train, X_val, y_val, sample_amount, data_ratio,
C_parameter, gamma_parameter):
#sample_amount = 40000
#data_ratio = 1.2
label_1_amount = int(sample_amount * (data_ratio / (data_ratio + 1)))
label_2_amount = int(sample_amount - label_1_amount)
tpr_list_temp = []
fpr_list_temp = []
BER_list_temp = []
f1_score_list_temp = []
iter_max = 4
count = 0
while (count < iter_max):
sample_feature, sample_label = choose_data_seperately(
X_train, y_train, label_1_amount, label_2_amount)
Precall, f1_score, BER, FPR, y_pred = SVM_base_fuction(
sample_feature, sample_label, X_val, y_val, 2**C_parameter,
2**gamma_parameter)
tpr_list_temp.append(Precall)
fpr_list_temp.append(FPR)
BER_list_temp.append(BER)
f1_score_list_temp.append(f1_score)
count = count + 1
tpr = (sum(tpr_list_temp) / len(tpr_list_temp))
fpr = (sum(fpr_list_temp) / len(fpr_list_temp))
BER = (sum(BER_list_temp) / len(BER_list_temp))
f1_score = (sum(f1_score_list_temp) / len(f1_score_list_temp))
return tpr, fpr, BER, f1_score
def kNN_validation(X_train, y_train, X_val, y_val, sample_amount, data_ratio,
k_value):
#sample_amount = 40000
#data_ratio = 1.2
label_1_amount = int(sample_amount * (data_ratio / (data_ratio + 1)))
label_2_amount = int(sample_amount - label_1_amount)
tpr_list_temp = []
fpr_list_temp = []
BER_list_temp = []
f1_score_list_temp = []
iter_max = 10
count = 0
while (count < iter_max):
sample_feature, sample_label = choose_data_seperately(
X_train, y_train, label_1_amount, label_2_amount)
Precall, f1_score, BER, FPR = kNN_base_function(
sample_feature, sample_label, X_val, y_val, k_value)
tpr_list_temp.append(Precall)
fpr_list_temp.append(FPR)
BER_list_temp.append(BER)
f1_score_list_temp.append(f1_score)
count = count + 1
tpr = (sum(tpr_list_temp) / len(tpr_list_temp))
fpr = (sum(fpr_list_temp) / len(fpr_list_temp))
BER = (sum(BER_list_temp) / len(BER_list_temp))
f1_score = (sum(f1_score_list_temp) / len(f1_score_list_temp))
return tpr, fpr, BER, f1_score
def parameter_adjust(X_train, y_train, sample_amount, data_ratio):
start = time.time()
label_1_amount = int(sample_amount * (data_ratio / (data_ratio + 1)))
label_2_amount = int(sample_amount - label_1_amount)
Result_List = CalParList(3, "gamma_exp", "C_exp", "time")
for gamma_exp in [-15, -13, -11, -9, -7, -5, -3, -1, 1, 3]:
for C_exp in [-5, -3, -1, 1, 3, 5, 7, 9, 11, 13, 15]:
start1 = time.time()
sample_feature, sample_label = choose_data_seperately(
X_train, y_train, label_1_amount, label_2_amount)
tpr, fpr, BER, f1_score, time_var = SVM_cross_validation(
sample_feature, sample_label, 2**C_exp, 2**gamma_exp)
Result_List.list_append(tpr, f1_score, BER, fpr, gamma_exp, C_exp,
time_var)
#print("fit time:%5.1fminute"%(temp))
print("the total executing time:%5.1fminute" %
((time.time() - start) / 60))
result = Result_List.return_result()
return result
def kNN_data_ratio_adjust(training_feature, training_label, k_value):
start = time.time()
label_1_amount = 40000
label_2_amount = 10000
Result_List = CalParList(4, "label_1_amount", "label_2_amount", "ratio",
"time")
iter_amount = 5
train_data = pd.concat([training_feature, training_label['label']],
axis=1,
join='outer')
while (label_1_amount > 2000):
count = 0
Cal_Result_List = CalList()
time_list_temp = []
while (count < iter_amount):
start1 = time.time()
sample_feature, sample_label = choose_data_seperately(
training_feature, training_label, label_1_amount,
label_2_amount)
Precall, FPR, BER, f1_score, time_var = kNN_cross_validation(
sample_feature, sample_label, k_value)
Cal_Result_List.list_append(Precall, f1_score, BER, FPR)
time_list_temp.append(time_var)
count = count + 1
Precall, FPR, BER, f1_score = Cal_Result_List.list_average_cal()
time_ave = sum(time_list_temp) / len(time_list_temp)
Result_List.list_append(Precall, f1_score, BER, FPR, label_1_amount,
label_2_amount,
label_1_amount / label_2_amount, time_ave)
#print("current data labe 1 size:%d ,fit time:%5.1fminute"%(t,(time.time()-start1)/60))
if (label_1_amount > 10000):
label_1_amount = label_1_amount - 5000
else:
label_1_amount = label_1_amount - 2500
print("the total executing time:%5.1fminute" %
((time.time() - start) / 60))
result = Result_List.return_result()
return result
def parameter_adjust(X_train, y_train, sample_amount, data_ratio):
start = time.time()
tpr_list = []
fpr_list = []
BER_list = []
f1_score_list = []
time_list = []
gamma_exp_list = []
C_exp_list = []
label_1_amount = int(sample_amount * (data_ratio / (data_ratio + 1)))
label_2_amount = int(sample_amount - label_1_amount)
for gamma_exp in [-15, -13, -11, -9, -7, -5, -3, -1, 1, 3]:
for C_exp in [-5, -3, -1, 1, 3, 5, 7, 9, 11, 13, 15]:
start1 = time.time()
sample_feature, sample_label = choose_data_seperately(
X_train, y_train, label_1_amount, label_2_amount)
tpr, fpr, BER, f1_score, time_var = SVM_cross_validation(
sample_feature, sample_label, 2**C_exp, 2**gamma_exp)
time_list.append(time_var)
tpr_list.append(tpr)
f1_score_list.append(f1_score)
BER_list.append(BER)
fpr_list.append(fpr)
gamma_exp_list.append(gamma_exp)
C_exp_list.append(C_exp)
#print("fit time:%5.1fminute"%(temp))
print("the total executing time:%5.1fminute" %
((time.time() - start) / 60))
result = {
"gamma_exp": gamma_exp_list,
"C_exp": C_exp_list,
"TPR": tpr_list,
"FPR": fpr_list,
"f1_score": f1_score_list,
"BER": BER_list,
"time": time_list
}
columns = ["gamma_exp", "C_exp", "f1_score", "TPR", "FPR", "BER", "time"]
result = pd.DataFrame(data=result, columns=columns)
return result
def SVC_data_ratio_adjust(X_train, y_train, sample_amount):
start = time.time()
Result_List = CalParList(4, "label_1_amount", "label_2_amount", "ratio",
"time")
iter_amount = 5
data_ratio = 4
while (data_ratio > 0.2):
count = 0
Cal_Result_List = CalList()
time_list_temp = []
label_1_amount = int(sample_amount * (data_ratio / (data_ratio + 1)))
label_2_amount = int(sample_amount - label_1_amount)
while (count < iter_amount):
start1 = time.time()
sample_feature, sample_label = choose_data_seperately(
X_train, y_train, label_1_amount, label_2_amount)
tpr, fpr, BER, f1_score, time_var = SVM_cross_validation(
sample_feature, sample_label, 1, 'auto')
time_list_temp.append(time_var)
Cal_Result_List.list_append(tpr, f1_score, BER, fpr)
count = count + 1
Precall, FPR, BER, f1_score = Cal_Result_List.list_average_cal()
time_ave = sum(time_list_temp) / len(time_list_temp)
Result_List.list_append(Precall, f1_score, BER, FPR, label_1_amount,
label_2_amount,
label_1_amount / label_2_amount, time_ave)
if (data_ratio > 2):
data_ratio = data_ratio / 2
elif (data_ratio < 0.8):
data_ratio = data_ratio - 0.25
else:
data_ratio = data_ratio - 0.1
print("the total executing time:%5.1fminute" %
((time.time() - start) / 60))
result = Result_List.return_result()
return result
def kNN_k_parameter_adjust_with_specific_data_ratio(X_train, y_train,
data_ratio):
tpr_list = []
fpr_list = []
BER_list = []
f1_score_list = []
count = 0
iter_count = 5
while (count < iter_count):
label_1_amount = int(20000 * data_ratio)
label_2_amount = 20000
sample_feature, sample_label = choose_data_seperately(
X_train, y_train, label_1_amount, label_2_amount)
result = kNN_k_parameter_adjust(sample_feature, sample_label)
if (count == 0):
tpr_list = result['TPR']
fpr_list = result['FPR']
f1_score_list = result['f1_score']
BER_list = result['BER']
else:
tpr_list = (count * tpr_list + result['TPR']) / (count + 1)
fpr_list = (count * fpr_list + result['FPR']) / (count + 1)
f1_score_list = (count * f1_score_list +
result['f1_score']) / (count + 1)
BER_list = (count * BER_list + result['BER']) / (count + 1)
count = count + 1
result_total = {
"k_value": result['k_value'],
"TPR": tpr_list,
"FPR": fpr_list,
"f1_score": f1_score_list,
"BER": BER_list
}
columns = ["k_value", "f1_score", "TPR", "FPR", "BER"]
result = pd.DataFrame(data=result, columns=columns)
return result
def kNN_validation(X_train, y_train, X_val, y_val, sample_amount, data_ratio,
k_value):
#sample_amount = 40000
#data_ratio = 1.2
label_1_amount = int(sample_amount * (data_ratio / (data_ratio + 1)))
label_2_amount = int(sample_amount - label_1_amount)
Cal_Result_List = CalList()
iter_max = 10
count = 0
while (count < iter_max):
sample_feature, sample_label = choose_data_seperately(
X_train, y_train, label_1_amount, label_2_amount)
Precall, f1_score, BER, FPR = kNN_base_function(
sample_feature, sample_label, X_val, y_val, k_value)
Cal_Result_List.list_append(Precall, f1_score, BER, FPR)
count = count + 1
Precall, FPR, BER, f1_score = Cal_Result_List.list_average_cal()
return Precall, FPR, BER, f1_score
def SVM_validation(X_train, y_train, X_val, y_val, sample_amount, data_ratio,
C_parameter, gamma_parameter):
#sample_amount = 40000
#data_ratio = 1.2
label_1_amount = int(sample_amount * (data_ratio / (data_ratio + 1)))
label_2_amount = int(sample_amount - label_1_amount)
Cal_Result_List = CalList()
iter_max = 4
count = 0
while (count < iter_max):
sample_feature, sample_label = choose_data_seperately(
X_train, y_train, label_1_amount, label_2_amount)
Precall, f1_score, BER, FPR, y_pred = SVM_base_fuction(
sample_feature, sample_label, X_val, y_val, 2**C_parameter,
2**gamma_parameter)
Cal_Result_List.list_append(Precall, f1_score, BER, FPR)
count = count + 1
Precall, FPR, BER, f1_score = Cal_Result_List.list_average_cal()
return Precall, FPR, BER, f1_score
def kNN_data_ratio_adjust(training_feature, training_label, k_value):
start = time.time()
label_1_amount = 40000
label_2_amount = 10000
label_1_amount_list = []
label_2_amount_list = []
ratio_list = []
tpr_list = []
fpr_list = []
BER_list = []
f1_score_list = []
time_list = []
iter_amount = 5
train_data = pd.concat([training_feature, training_label['label']],
axis=1,
join='outer')
while (label_1_amount > 2000):
count = 0
tpr_list_temp = []
fpr_list_temp = []
BER_list_temp = []
f1_score_list_temp = []
time_list_temp = []
while (count < iter_amount):
start1 = time.time()
sample_feature, sample_label = choose_data_seperately(
training_feature, training_label, label_1_amount,
label_2_amount)
Precall, FPR, BER, f1_score, time_var = kNN_cross_validation(
sample_feature, sample_label, k_value)
time_list_temp.append(time_var)
tpr_list_temp.append(Precall)
fpr_list_temp.append(FPR)
BER_list_temp.append(BER)
f1_score_list_temp.append(f1_score)
count = count + 1
label_1_amount_list.append(label_1_amount)
label_2_amount_list.append(label_2_amount)
ratio_list.append(label_1_amount / label_2_amount)
tpr_list.append(sum(tpr_list_temp) / len(tpr_list_temp))
fpr_list.append(sum(fpr_list_temp) / len(fpr_list_temp))
BER_list.append(sum(BER_list_temp) / len(BER_list_temp))
f1_score_list.append(sum(f1_score_list_temp) / len(f1_score_list_temp))
time_list.append(sum(time_list_temp) / len(time_list_temp))
#print("current data labe 1 size:%d ,fit time:%5.1fminute"%(t,(time.time()-start1)/60))
if (label_1_amount > 10000):
label_1_amount = label_1_amount - 5000
else:
label_1_amount = label_1_amount - 2500
print("the total executing time:%5.1fminute" %
((time.time() - start) / 60))
result = {
"label_1_amount": label_1_amount_list,
"label_2_amount": label_2_amount_list,
"label 1: label 2 ratio": ratio_list,
"TPR": tpr_list,
"FPR": fpr_list,
"f1_score": f1_score_list,
"BER": BER_list,
"time": time_list
}
columns = [
"label_1_amount", "label_2_amount", "label 1: label 2 ratio",
"f1_score", "TPR", "FPR", "BER", "time"
]
result = pd.DataFrame(data=result, columns=columns)
return result
def SVC_data_ratio_adjust(X_train, y_train, sample_amount):
start = time.time()
tpr_list = []
fpr_list = []
BER_list = []
f1_score_list = []
time_list = []
label_1_amount_list = []
label_2_amount_list = []
ratio_list = []
iter_amount = 5
data_ratio = 4
while (data_ratio > 0.2):
count = 0
tpr_list_temp = []
fpr_list_temp = []
BER_list_temp = []
f1_score_list_temp = []
time_list_temp = []
label_1_amount = int(sample_amount * (data_ratio / (data_ratio + 1)))
label_2_amount = int(sample_amount - label_1_amount)
while (count < iter_amount):
start1 = time.time()
sample_feature, sample_label = choose_data_seperately(
X_train, y_train, label_1_amount, label_2_amount)
tpr, fpr, BER, f1_score, time_var = SVM_cross_validation(
sample_feature, sample_label, 1, 'auto')
time_list_temp.append(time_var)
tpr_list_temp.append(tpr)
fpr_list_temp.append(fpr)
BER_list_temp.append(BER)
f1_score_list_temp.append(f1_score)
count = count + 1
label_1_amount_list.append(label_1_amount)
label_2_amount_list.append(label_2_amount)
ratio_list.append(label_1_amount / label_2_amount)
tpr_list.append(sum(tpr_list_temp) / len(tpr_list_temp))
fpr_list.append(sum(fpr_list_temp) / len(fpr_list_temp))
BER_list.append(sum(BER_list_temp) / len(BER_list_temp))
f1_score_list.append(sum(f1_score_list_temp) / len(f1_score_list_temp))
time_list.append(sum(time_list_temp) / len(time_list_temp))
if (data_ratio > 2):
data_ratio = data_ratio / 2
elif (data_ratio < 0.8):
data_ratio = data_ratio - 0.25
else:
data_ratio = data_ratio - 0.1
print("the total executing time:%5.1fminute" %
((time.time() - start) / 60))
result = {
"label_1_amount": label_1_amount_list,
"label_2_amount": label_2_amount_list,
"label 1: label 2 ratio": ratio_list,
"TPR": tpr_list,
"FPR": fpr_list,
"f1_score": f1_score_list,
"BER": BER_list,
"time": time_list
}
columns = [
"label_1_amount", "label_2_amount", "label 1: label 2 ratio",
"f1_score", "TPR", "FPR", "BER", "time"
]
result = pd.DataFrame(data=result, columns=columns)
return result