def Plot_Roc_Undersampling_RF(dataSet,MinorityData,MajorityData,numattrs,minorClassValue, data_name,KNN_matrix,classificator_name):
Undersampling_levels = [10, 15,25, 50, 75, 100, 125, 150, 175, 200, 300, 400, 500, 600, 700, 800, 1000, 2000]
# 18 точек в каждой roc
fprs = []
tprs = []
for N in Undersampling_levels:
print('undersampling ', N)
underSampled_majority_Data = []
Undersampled_Smoted_Dataset = []
underSampled_majority_Data = UnderSampling.underSampling(len(MinorityData), MajorityData, N)
Undersampled_Dataset = unite_data(MinorityData, underSampled_majority_Data)
print('total number of samples ',len(Undersampled_Dataset))
#fp, tp, precision = LogReg_c.Classifier(Undersampled_Dataset, numattrs)
fp, tp = RandomForest_c.Classifier(Undersampled_Dataset, numattrs)
#ДЛЯ КАЖДОГО СЛУЧАЯ ВЫБРАТЬ СВОЙ КЛАССИФИКАТОР ЗАМЕНОЙ ЭТОЙ СТРОКИ И ЛЕГЕНДЫ ДЛЯ ЭТОЙ КРИВОЙ
if fp == 0 and tp == 0:
pass
else:
fprs.append(fp)
tprs.append(tp)
plt.scatter(fp, tp, s=10, c='g',marker='v')
fprs.append(1)
tprs.append(1)
'''
for j in range(len(fprs)):
if (j <= len(fprs)-2) and (fprs[j] > fprs[j+1]):
fprs.pop(j)
tprs.pop(j)
print('points\n',fprs,'\n',tprs)
'''
fprs.sort()
roc_auc = 0
try:
roc_auc = metrics.auc(fprs, tprs)
except Exception:
pass
plt.plot(fprs, tprs, color = 'g',label='Under-'+classificator_name+', AUC = '+"%.4f" % roc_auc,lw=1)
plt.rcParams['font.size'] = 12
plt.title(data_name+' ROC')
plt.xlabel('% False Positive')
plt.ylabel('% True Positive')
plt.xticks([0,0.2,0.4,0.6,0.8,1])
plt.yticks([0,0.2,0.4,0.6,0.8,1])
plt.grid(False)
plt.legend(loc=0)
def Plot_Smote_ROC_LR(dataSet,MinorityData,MajorityData,numattrs,minorClassValue, data_name,KNN_matrix, classificator_name):
Undersampling_levels = [10, 15,25, 50, 75, 100, 125, 150, 175, 200, 300, 400, 500, 600, 700, 800, 1000, 2000]
# 18 точек в каждой roc
Smote_level = 300
#ЛУЧШИЙ ПАРАМЕТР ДЛЯ ЭТОГО КЛАССИФИКАТОРА
fprs = []
tprs = []
Synthetic_minority_Data = SMOTE_c.SMOTE(len(MinorityData), Smote_level, MinorityData, numattrs, minorClassValue, KNN_matrix, 5)
Final_minority_Data = unite_data(Synthetic_minority_Data, MinorityData)
final_min_len = len(Final_minority_Data)
for N in Undersampling_levels:
print('undersampling ', N)
underSampled_majority_Data = UnderSampling.underSampling(final_min_len, MajorityData, N)
Undersampled_Smoted_Dataset = unite_data(Final_minority_Data, underSampled_majority_Data)
print('total number of samples ',len(Undersampled_Smoted_Dataset))
fp, tp, precision = LogReg_c.Classifier(Undersampled_Smoted_Dataset, numattrs)
#fp, tp = RandomForest_c.Classifier(Undersampled_Dataset, numattrs)
if fp == 0 and tp == 0:
pass
else:
fprs.append(fp)
tprs.append(tp)
plt.scatter(fp, tp, s=10, c='b', marker='o')
fprs.append(1)
tprs.append(1)
'''
for j in range(len(fprs)):
if (j <= len(fprs)-2) and (fprs[j] > fprs[j+1]):
fprs.pop(j)
tprs.pop(j)
print('points\n',fprs,'\n',tprs)
'''
fprs.sort()
roc_auc = 0
try:
roc_auc = metrics.auc(fprs, tprs)
except Exception:
pass
plt.plot(fprs, tprs, color = 'b',label=str(Smote_level)+'-Smote-'+classificator_name+', AUC = '+"%.4f" % roc_auc,lw=1)
plt.rcParams['font.size'] = 12
plt.title(data_name+' ROC')
plt.xlabel('% False Positive')
plt.ylabel('% True Positive')
plt.xticks([0,0.2,0.4,0.6,0.8,1])
plt.yticks([0,0.2,0.4,0.6,0.8,1])
plt.grid(False)
plt.legend(loc=0)
def performSampling(dataFile,classColumnNumber,numattrs,minorClassValue,N=400):
dataSet, MinorityData, MajorityData = getSeparatedSamples(dataFile, classColumnNumber, minorClassValue)
NumberofMinorSamples = len(MinorityData)
print("Number of Minor samples present in the Dataset: ", NumberofMinorSamples)
#Only UnderSampling
uSamplingDataset = UnderSampling.underSampling(len(MinorityData), dataSet, minorClassValue, numattrs, N)
createNewDatasetFileUnderSampling(uSamplingDataset)
C45.treeClassifier2(dataSet, numattrs, 'UnderSampling')
#UnderSampling and SMOTE
underSamplingDataset = UnderSampling.underSampling(len(MinorityData), dataSet, minorClassValue, numattrs, N)
uSDataset = SMOTE.SMOTE(len(MinorityData), N, MinorityData, numattrs, underSamplingDataset, 5, minorClassValue)
uSmoteDataset = generateFinalSyntheticDataset(underSamplingDataset, uSDataset)
createNewDatasetFileUnderSamplingSmote(uSmoteDataset)
C45.treeClassifier2(uSmoteDataset, numattrs, 'SMOTEUndersampling')
#NaiveBayes
NaiveBayes.naiveBayes(MajorityData, MinorityData, numattrs)
def Plot_ROC_RandomOverSampling_RF(dataSet,MinorityData,MajorityData,numattrs,minorClassValue, data_name,classificator_name):
Undersampling_levels = [10, 15,25, 50, 75, 100, 125, 150, 175, 200, 300, 400, 500, 600, 700, 800, 1000, 2000]
# 18 точек в каждой roc
Oversampling_level = 500
#ЛУЧШИЙ ПАРАМЕТР ДЛЯ ЭТОГО КЛАССИФИКАТОРА на этих данных
Oversampled_minority_Data = []
print('minority ', len(MinorityData))
N = int(len(MinorityData)*Oversampling_level/100)
print('to choose from min ',N )
random_Minority_indeces = np.random.choice(range(len(MinorityData)), N, replace=True)
#берем N произвольных разных образцов меньшего класса
print('выбрал индексы мин класса')
num = len(random_Minority_indeces)
print ('chosen ', num)
for index in random_Minority_indeces:
Oversampled_minority_Data.append(MinorityData[index])
Final_minority_Data = unite_data(Oversampled_minority_Data, MinorityData)
final_min_len = len(Final_minority_Data)
print('total min ', final_min_len)
fprs = []
tprs = []
for N in Undersampling_levels:
print('undersampling ', N)
underSampled_majority_Data = UnderSampling.underSampling(final_min_len, MajorityData, N)
UnderOversampled_Dataset = unite_data(Final_minority_Data, underSampled_majority_Data)
print('total number of samples ',len(UnderOversampled_Dataset))
fp, tp = RandomForest_c.Classifier(UnderOversampled_Dataset, numattrs)
if fp == 0 and tp == 0:
pass
else:
fprs.append(fp)
tprs.append(tp)
plt.scatter(fp, tp, s=10, c='y', marker='s')
fprs.append(1)
tprs.append(1)
'''
for j in range(len(fprs)):
if (j <= len(fprs)-2) and (fprs[j] > fprs[j+1]):
fprs.pop(j)
tprs.pop(j)
print('points\n',fprs,'\n',tprs)
'''
fprs.sort()
roc_auc = 0
try:
roc_auc = metrics.auc(fprs, tprs)
except Exception:
pass
plt.plot(fprs, tprs, color = 'y',label=str(Oversampling_level)+'-Over-'+classificator_name+', AUC = '+"%.4f" % roc_auc,lw=1)
plt.rcParams['font.size'] = 12
plt.title(data_name+' ROC')
plt.xlabel('% False Positive')
plt.ylabel('% True Positive')
plt.xticks([0,0.2,0.4,0.6,0.8,1])
plt.yticks([0,0.2,0.4,0.6,0.8,1])
plt.grid(False)
plt.legend(loc=0)
def Plot_Smote_ROC_parameters_LR(dataSet,MinorityData,MajorityData,numattrs,minorClassValue, data_name,KNN_matrix,classificator_name):
#Для замены классификатора изменить две строки в данном коде и последний аргумент при вызове
Undersampling_levels = [10, 15,25, 50, 75, 100, 125, 150, 175, 200, 300, 400, 500, 600, 700, 800, 1000, 2000]
# 18 точек в каждой roc
Smote_levels = [100, 200, 300, 400, 500]
colors = ['r','g','c','b','y']
markers = ['o', 'v' ,'+', '*','s']
i = -1
fp, tp, precision = LogReg_c.Classifier(dataSet, numattrs)
#fp, tp = RandomForest_c.Classifier(dataSet, numattrs)
if fp == 0 and tp == 0:
pass
else:
plt.plot(fp, tp, 'kx')#классификация на исходных данных
for SN in Smote_levels:
#for SN in [100]:
fprs = []
tprs = []
precisions = []
i += 1
print('\n Smote number level ', SN)
Final_minority_Data =[]
Synthetic_minority_Data = []
Synthetic_minority_Data = SMOTE_c.SMOTE(len(MinorityData), SN, MinorityData, numattrs, minorClassValue, KNN_matrix, 5)
Final_minority_Data = unite_data(Synthetic_minority_Data, MinorityData)
f_min_len = len(Final_minority_Data)
for N in Undersampling_levels:
print('undersampling ', N)
underSampled_majority_Data = []
Undersampled_Smoted_Dataset = []
underSampled_majority_Data = UnderSampling.underSampling(f_min_len, MajorityData, N)
Undersampled_Smoted_Dataset = unite_data(Final_minority_Data, underSampled_majority_Data)
print('total number of samples ',len(Undersampled_Smoted_Dataset))
fp, tp, precision = LogReg_c.Classifier(Undersampled_Smoted_Dataset, numattrs)
#fp, tp = RandomForest_c.Classifier(Undersampled_Smoted_Dataset, numattrs)
if fp == 0 and tp == 0:
pass
else:
fprs.append(fp)
tprs.append(tp)
plt.scatter(fp, tp, s=10, c=colors[i],marker=markers[i])
fprs.append(1)
tprs.append(1)
#print('points',fprs, '\n', tprs)
#fprs, tprs = clean_points(fprs, tprs)
#print('points\n',fprs,'\n',tprs)
#fprs.sort()
#print('points',fprs, '\n', tprs)
for j in range(len(fprs)):
if (j <= len(fprs)-2) and (fprs[j] > fprs[j+1]):
fprs.pop(j)
tprs.pop(j)
roc_auc = 0
try:
roc_auc = metrics.auc(fprs, tprs)
except Exception:
pass
plt.plot(fprs, tprs, color = colors[i],label=str(SN)+'-Smote, AUC = '+"%.4f" % roc_auc,lw=1)
plt.rcParams['font.size'] = 12
plt.title(data_name+' ROC curves with '+classificator_name)
plt.xlabel('% False Positive')
plt.ylabel('% True Positive')
plt.xticks([0,0.2,0.4,0.6,0.8,1])
plt.yticks([0,0.2,0.4,0.6,0.8,1])
plt.grid(False)
plt.legend(loc=0)
plt.savefig(data_name+' Smote_parameters ROC with '+classificator_name+'.png')
#plt.savefig('ROC curves for '+classificator_type+' classificator'+'.pdf')
plt.show()
''' Uncomment this and replace plotting line to plot the precision-recall curve with LogReg