def main(filename, xtrains_percent = 0.2, maxfeature = None, fit_ylabel = False, nn_estimator = 100, sepaLabel = True,
treeLabel = False, seed = 42, pcaLabel = False, n_comp = 2, sepa2 = False, time_label = False, stream = False,
sfl = False, anomaly_rate = None, max_samples = None, sample_nor = None):
inf = float("inf")
all_start = time.time()
rng = np.random.RandomState(seed)
#httpとsmtpのみ別の方法でデータ取得
if filename == 'C:\Users\Riku Anegawa\Desktop/Dropbox/http.mat' or filename == 'C:\Users\Riku Anegawa\Desktop/Dropbox/smtp.mat':
mat = {}
f = h5py.File(filename)
for k, v in f.items():
mat[k] = np.array(v)
X = mat['X'].T
y2 = mat['y'][0]
y3 = []
for i in range(len(y2)):
y3.append(int(y2[i]))
y = np.reshape(y3, [len(y3), 1])
else:
mat = scipy.io.loadmat(filename)
X = mat['X']
y = mat['y']
rate = xtrains_percent
if maxfeature == None:
max_feat = len(X[0])
else:
max_feat = int(maxfeature)
if not treeLabel:
print('X_train\'s rate : ' + str(rate))
print('max_features : ' + str(max_feat))
print('fit_ylabel : ' + str(fit_ylabel))
print('nn_estimator : ' + str(nn_estimator))
print('sepaLabel : ' + str(sepaLabel))
clf = IsolationForest(random_state=rng)
clf.n_estimators = nn_estimator
clf.verbose = 0
clf.max_features = max_feat
if max_samples != None:
clf.max_samples = max_samples
else:
clf.max_samples = 1.
# print(X.shape)
if (str(filename) == 'C:\Users\Riku Anegawa\Desktop/Dropbox/shuttle.mat'):
clf.contamination = 0.07
elif (str(filename) == 'C:\Users\Riku Anegawa\Desktop/Dropbox/http.mat'):
clf.contamination = 0.004
elif (str(filename) == 'C:\Users\Riku Anegawa\Desktop/Dropbox/pima.mat'):
clf.contamination = 0.35
elif (str(filename) == 'C:\Users\Riku Anegawa\Desktop/Dropbox/mammography.mat'):
clf.contamination = 0.02
elif (str(filename) == 'C:\Users\Riku Anegawa\Desktop/Dropbox/cover.mat'):
clf.contamination = 0.009
elif (str(filename) == 'C:\Users\Riku Anegawa\Desktop/Dropbox/breastw.mat'):
clf.contamination = 0.35
elif (str(filename) == 'C:\Users\Riku Anegawa\Desktop/Dropbox/arrhythmia.mat'):
clf.contamination = 0.15
elif (str(filename) == 'C:\Users\Riku Anegawa\Desktop/Dropbox/ionosphere.mat'):
clf.contamination = 0.36
elif (str(filename) == 'C:\Users\Riku Anegawa\Desktop/Dropbox/satellite.mat'):
clf.contamination = 0.32
elif (str(filename) == 'C:\Users\Riku Anegawa\Desktop/Dropbox/annthyroid.mat'):
clf.contamination = 0.07
elif (str(filename) == 'C:\Users\Riku Anegawa\Desktop/Dropbox/smtp.mat'):
clf.contamination = 0.03 / 100
else:
raise Exception("error! cannot file it.")
#交差検証を何回行うか(例:8:2なら5回)
#もっとうまい方法ありそう
hoge = 1 / rate
cross_count = int(np.ceil(hoge))
if cross_count > hoge:
cross_count = cross_count - 1
#cross_count分のauc,acc合計
sum_auc_roc = 0
sum_accuracy = 0
FPR_sum = 0
TPR_sum = 0
TNR_sum = 0
FNR_sum = 0
pca_fit_time = 0
pca_transform_train_time = 0
pca_transform_test_time = 0
test_time = 0
fit_time = 0
#ここはデータを交差検証用に分割するだけ
if sepaLabel == True: # separated
# data cut
X_anomaly = []
X_normal = []
for i in range(len(X)):
if y[i] == 1:
X_anomaly.append(X[i])
else:
X_normal.append(X[i])
#データ全体のcontaminationを操作
#基本使わないゾ！
zentai = False
anomaly_rate_all = None
if zentai:
if anomaly_rate_all != clf.contamination:
clf.contamination = anomaly_rate_all
if anomaly_rate_all < clf.contamination:
#異常系をカットしますよ〜〜
k = int(np.ceil(len(X_normal) * (anomaly_rate_all / (1 - anomaly_rate_all))))
anomaly_hoge = random.sample(X_anomaly, k) # ランダムに抽出
normal_hoge = X_normal
else:
#正常系をカットしましょうね〜〜
n_normal = int(len(X_anomaly) / anomaly_rate_all) - len(X_anomaly)
normal_rate = n_normal / len(X_normal)
k = int(np.ceil(len(X_normal) * normal_rate))
normal_hoge = random.sample(X_normal, k) # ランダムに抽出
anomaly_hoge = X_anomaly
X_anomaly = anomaly_hoge
X_normal = normal_hoge
if sample_nor != None:
X_normal = random.sample(X_normal, sample_nor)
cont = clf.contamination
sample_ano = (cont/(1-cont)) * sample_nor
X_anomaly = random.sample(X_anomaly, int(sample_ano))
# print("size : " + str(len(X_normal)+len(X_anomaly)))
cutter_anomaly = len(X_anomaly) * rate
cutter_normal = len(X_normal) * rate
X_sepa_ano = []
X_sepa_nor = []
for i in range(cross_count):
head2 = int(cutter_normal * i)
tail2 = int(cutter_normal * (i+1)) - 1
X_sepa_nor.append(X_normal[head2:tail2+1])
# print(len(X_sepa_nor))
# print(len(X_sepa_nor[0]))
# print(len(X_sepa_nor[0][0]))
head = int(cutter_anomaly * i)
tail = int(cutter_anomaly * (i+1)) - 1
X_sepa_ano.append(X_anomaly[head:tail+1])
# print(len(X_sepa_nor))
# print(len(X_sepa_nor[0]))
# print(len(X_sepa_ano))
# print(len(X_sepa_ano[0]))
# print("")
else:
X_sepa = []
y_sepa = []
cutter = len(X)*rate
for i in range(cross_count):
head = int(cutter*i)
tail = int(cutter*(i+1))-1
X_sepa.append(X[head:tail+1])
y_sepa.append(y[head:tail+1])
for count in range(cross_count):
if sepaLabel:
X_train = []
X_train_correct = []
X_test = []
X_test_correct = []
# 学習データの異常系含有率を変更
for i in range(cross_count):
if i != count:
train_flag = True
if anomaly_rate is not None:
if clf.contamination != anomaly_rate:
train_flag = False
if clf.contamination != anomaly_rate:
all = len(X_sepa_nor[i]) + len(X_sepa_ano[i])
cont = len(X_sepa_ano[i]) / all
# print(cont)
# print(anomaly_rate)
if cont > anomaly_rate:# 異常系を減らす
k = int(np.ceil(len(X_sepa_nor[i]) * (anomaly_rate / (1 - anomaly_rate))))
if len(X_sepa_ano[i]) < k:
k = len(X_sepa_ano[i])
anomaly_hoge = random.sample(X_sepa_ano[i], k) # ランダムに抽出
normal_hoge = X_sepa_nor[i]
else: # 正常系を減らす
k = int(len(X_sepa_ano[i]) / anomaly_rate) - len(X_sepa_ano[i])
normal_hoge = random.sample(X_sepa_nor[i], k) # ランダムに抽出
anomaly_hoge = X_sepa_ano[i]
# k = int(len(X_sepa_ano[i]) * (1-anomaly_rate)/anomaly_rate)
# normal_rate = n_normal / len(X_sepa_nor[i])
# k = int(np.ceil(len(X_sepa_nor[i]) * normal_rate))
# X_sepa_nor[i] = normal_hoge
X_train.extend(anomaly_hoge)
# print("aaaaa")
# print(X_train)
for j in range(len(anomaly_hoge)):
X_train_correct.append(-1)
X_train.extend(normal_hoge)
for j in range(len(normal_hoge)):
X_train_correct.append(1)
if train_flag:
X_train.extend(X_sepa_ano[i])
for j in range(len(X_sepa_ano[i])):
X_train_correct.append(-1)
X_train.extend(X_sepa_nor[i])
for j in range(len(X_sepa_nor[i])):
X_train_correct.append(1)
else:
# X_test.extend(X_sepa_ano[i])
# for j in range(len(X_sepa_ano[i])):
# X_test_correct.append(-1)
# X_test.extend(X_sepa_nor[i])
# for j in range(len(X_sepa_nor[i])):
# X_test_correct.append(1)
#テストデータの含有率も変えます？？
anomaly_rate2 = None
test_flag = True
if anomaly_rate2 is not None:
clf.contamination = anomaly_rate2
if clf.contamination != anomaly_rate2:
test_flag = False
if clf.contamination > anomaly_rate2: # 異常系を減らす
k = int(np.ceil(len(X_sepa_nor[i]) * (anomaly_rate / (1 - anomaly_rate))))
anomaly_hoge = random.sample(X_sepa_ano[i], k) # ランダムに抽出
normal_hoge = X_sepa_nor[i]
# X_sepa_ano[i] = anomaly_hoge
# X_sepa_ano[i] = []
# X_sepa_ano[i].extend(anomaly_hoge)
else: # 正常系を減らす
n_normal = int(len(X_sepa_ano[i]) / anomaly_rate) - len(X_sepa_ano[i])
normal_rate = n_normal / len(X_sepa_nor[i])
k = int(np.ceil(len(X_sepa_nor[i]) * normal_rate))
normal_hoge = random.sample(X_sepa_nor[i], k) # ランダムに抽出
anomaly_hoge = X_sepa_ano[i]
# X_sepa_nor[i] = normal_hoge
X_test.extend(anomaly_hoge)
for j in range(len(anomaly_hoge)):
X_test_correct.append(-1)
X_test.extend(normal_hoge)
for j in range(len(normal_hoge)):
X_test_correct.append(1)
if test_flag:
X_test.extend(X_sepa_ano[i])
for j in range(len(X_sepa_ano[i])):
X_test_correct.append(-1)
X_test.extend(X_sepa_nor[i])
for j in range(len(X_sepa_nor[i])):
X_test_correct.append(1)
#シャッフルするかどうか
if sfl:
X_train_set = []
X_test_set = []
for i in range(len(X_train)):
buf = []
buf.append(X_train[i])
buf.append(X_train_correct[i])
X_train_set.append(buf)
for i in range(len(X_test)):
buf = []
buf.append(X_test[i])
buf.append(X_test_correct[i])
X_test_set.append(buf)
random.shuffle(X_train_set)
random.shuffle(X_test_set)
X_train = []
X_test = []
X_train_correct = []
X_test_correct = []
for i in range(len(X_train_set)):
X_train.append(X_train_set[i][0])
X_train_correct.append(X_train_set[i][1])
for i in range(len(X_test_set)):
X_test.append(X_test_set[i][0])
X_test_correct.append(X_test_set[i][1])
else: #mixed
X_train = []
X_train_correct = []
X_test = []
X_test_correct = []
for i in range(cross_count):
if i != count:
# print(X_train)
X_train.extend(X_sepa[i])
X_train_correct.extend(y_sepa[i])
else:#i == count
# print(i, 1111111)
X_test.extend(X_sepa[i])
X_test_correct.extend(y_sepa[i])
for q in range(len(X_train_correct)):
j = X_train_correct[q]
if (j == 1):
X_train_correct[q] = -1
else:
X_train_correct[q] = 1
for w in range(len(X_test_correct)):
j = X_test_correct[w]
if (j == 1):
X_test_correct[w] = -1
else:
X_test_correct[w] = 1
# owari
# finished cutting data
if pcaLabel:
pca_fit_start = time.time()
pca = PCA(copy=True, iterated_power='auto', n_components=n_comp, random_state=None,
svd_solver='auto', tol=0.0, whiten=False)
# print("X_train: " + str(X_train))
pca.fit(X_train)
pca_fit_finish = time.time()
pca_transform_train_start = time.time()
X_train = pca.transform(X_train)
pca_transform_train_finish = time.time()
clf.max_features = n_comp
pca_fit_time += (pca_fit_finish - pca_fit_start)
pca_transform_train_time += (pca_transform_train_finish - pca_transform_train_start)
#variance and kurtosis
#尖度や分散の大きな軸を選択したい方はこちら
varLabel = False
kurtosisLabel = False
if varLabel or kurtosisLabel:
var = []
kurtosis_set = []
skewness_set = []
for i in range(len(X_train[0])):
data = []
for j in range(len(X_train)):
data.append(X_train[j][i])
data = np.array(data)
ave = np.average(data)
std = np.std(data)
# if math.isnan(((data - ave) ** 3 / (std ** 3))[0]):
# if ave != 0 or std != 0:
# print("ave : " + str(ave))
# print("std : " + str(std))
if std == 0:
kurtosis = -10000
else:
kurtosis = np.average((data - ave) ** 3) / (std ** 3)
skewness = np.average((data - ave) ** 4) / (std ** 4) - 3
var.append(std)
kurtosis_set.append(kurtosis)
skewness_set.append(skewness)
var_rank = np.argsort(var)[::-1]
kurtosis_rank = np.argsort(kurtosis_set)[::-1]
skewness_rank = np.argsort(skewness_set)[::-1] #歪度を使う予定は今のとこないかな〜
hoge = []
for i in range(clf.max_features):
if varLabel:
hoge.append(np.array(X_train)[:,var_rank[i]])
elif kurtosisLabel:
hoge.append(np.array(X_train)[:,kurtosis_rank[i]])
X_train = np.array(hoge).T
fit_start = time.time()
#fit_ylabelはFalseで固定
if fit_ylabel:
clf.fit(X_train, X_train_correct, sample_weight=None)
else :
# print(X_train)
clf.fit(X_train, y = None, sample_weight=None)
fit_finish = time.time()
fit_time += (fit_finish - fit_start)
if stream:
sum_score_auc = []
sum_score_acc = []
for i in range(len(X_test)):
if pcaLabel:
pca_transform_test_start = time.time()
a = [X_test[i]]
X_test_pca = pca.transform(a)
pca_transform_test_finish = time.time()
pca_transform_test_time += (pca_transform_test_finish - pca_transform_test_start)
else:
X_test_pca = [X_test[i]]
test_start = time.time()
y_pred_test, a_score = clf.predict(X_test_pca)
test_finish = time.time()
test_time += (test_finish - test_start)
sum_score_auc.append(a_score)
sum_score_acc.append(y_pred_test)
a_score = sum_score_auc
y_pred_test = sum_score_acc
else: #batch
if pcaLabel:
pca_transform_test_start = time.time()
X_test = pca.transform(X_test) # stream version
pca_transform_test_finish = time.time()
pca_transform_test_time += (pca_transform_test_finish - pca_transform_test_start)
test_start = time.time()
y_pred_test, a_score = clf.predict(X_test)
# a_score = clf.decision_function(X_test)
test_finish = time.time()
test_time += (test_finish - test_start)
acc = calc_accuracy(X_test_correct, y_pred_test, treeLabel)
AUC_roc = calc_AUC(X_test_correct, a_score, treeLabel)
FPR, TPR, TNR, FNR = calc_FN(X_test_correct, y_pred_test)
FNR_sum += FNR
FPR_sum += FPR
sum_auc_roc += AUC_roc
sum_accuracy += acc
# # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# # plot the line, the samples, and the nearest vectors to the plane
#
# X_train = np.array(X_train)
# X_test = np.array(X_test)
#
# lim = True
# x = (-200, 200)
# y = (-200, 300)
#
# for i,j in zip(range(2), [True, False]):
# small = j # trueがsmallestね
#
# plt.subplot(2, 2, i+1)
# if small:
# plt.title("smallest")
# else:
# plt.title("largest")
#
# if small:
# # b1 = plt.scatter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, X_test.shape[1]-1], X_test[:, X_test.shape[1]-2], c='green', s=20, edgecolor='k')
# else:
# # b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# plt.legend([b2],["testing observations"],
# loc="upper left")
# # plt.legend([b1], ["training observations"],
# # loc="upper left")
#
#
#
# plt.subplot(2, 2, i+3)
# if small:
# b1 = plt.scatter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, X_test.shape[1] - 1], X_test[:, X_test.shape[1] - 2], c='green', s=20, edgecolor='k')
# else:
# b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# # plt.legend([b2], ["testing observations"],
# # loc="upper left")
# plt.legend([b1], ["training observations"],
# loc="upper left")
# plt.show()ter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, X_test.shape[1]-1], X_test[:, X_test.shape[1]-2], c='green', s=20, edgecolor='k')
# else:
# # b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# plt.legend([b2],["testing observations"],
# loc="upper left")
# # plt.legend([b1], ["training observations"],
# # loc="upper left")
#
#
#
# plt.subplot(2, 2, i+3)
# if small:
# b1 = plt.scatter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, X_test.shape[1] - 1], X_test[:, X_test.shape[1] - 2], c='green', s=20, edgecolor='k')
# else:
# b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# # plt.legend([b2], ["testing observations"],
# # loc="upper left")
# plt.legend([b1], ["training observations"],
# loc="upper left")
# plt.show()
# # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
auc2_roc = sum_auc_roc / cross_count
acc2 = sum_accuracy / cross_count
fnr = FNR_sum / cross_count
fpr = FPR_sum / cross_count
#calc time
all_finish = time.time()
all_time = all_finish - all_start
pca_fit_time = pca_fit_time / cross_count
pca_transform_train_time = pca_transform_train_time / cross_count
pca_transform_test_time = pca_transform_test_time / cross_count
test_time = test_time / cross_count
fit_time = fit_time / cross_count
sum_train_time = fit_time + pca_fit_time + pca_transform_train_time
sum_test_time = pca_transform_test_time + test_time
# print("sum_train_time : " + str(sum_train_time))
# print("pca_transform_train_time : " + str(pca_transform_train_time))
# print("pca_fit_time : " + str(pca_fit_time))
# print("test_time : " + str(test_time))
# print("fit_time : " + str(fit_time))
# print("all_time : " + str(all_time))
if time_label:
# return all_time, pca_fit_time + pca_transform_train_time, fit_time, pca_transform_test_time, test_time, sum_train_time, sum_test_time
return all_time
elif treeLabel:
# if math.isnan(auc2_roc):
# raise Exception("error! auc is NaN!.")
# return auc2_roc
return fnr
# return fpr
else:
return auc2_roc, acc2
def main(filename,
xtrains_percent=0.8,
maxfeature=3,
fit_ylabel=False,
nn_estimator=100,
sepaLabel=True,
treeLabel=False,
seed=42,
pcaLabel=False,
n_comp=2,
sepa2=False,
time_label=False,
stream=False,
sfl=False):
inf = float("inf")
all_start = time.time()
rng = np.random.RandomState(seed)
# httpとsmtpのみ別の方法でデータ取得
if filename == '/home/anegawa/Dropbox/http.mat' or filename == '/home/anegawa/Dropbox/smtp.mat':
mat = {}
f = h5py.File(filename)
for k, v in f.items():
mat[k] = np.array(v)
X = mat['X'].T
y2 = mat['y'][0]
y3 = []
for i in range(len(y2)):
y3.append(int(y2[i]))
y = np.reshape(y3, [len(y3), 1])
else:
mat = scipy.io.loadmat(filename)
X = mat['X']
y = mat['y']
rate = xtrains_percent
max_feat = int(maxfeature)
if max_feat == 3:
max_feat = X.shape[1]
if not treeLabel:
print('X_train\'s rate : ' + str(rate))
print('max_features : ' + str(max_feat))
print('fit_ylabel : ' + str(fit_ylabel))
print('nn_estimator : ' + str(nn_estimator))
print('sepaLabel : ' + str(sepaLabel))
clf = IsolationForest(random_state=rng)
clf.n_estimators = nn_estimator
clf.verbose = 0
clf.max_features = max_feat
if (str(filename) == '/home/anegawa/Dropbox/shuttle.mat'):
clf.contamination = 0.07
elif (str(filename) == '/home/anegawa/Dropbox/http.mat'):
clf.contamination = 0.004
elif (str(filename) == '/home/anegawa/Dropbox/pima.mat'):
clf.contamination = 0.35
elif (str(filename) == '/home/anegawa/Dropbox/mammography.mat'):
clf.contamination = 0.02
elif (str(filename) == '/home/anegawa/Dropbox/cover.mat'):
clf.contamination = 0.009
elif (str(filename) == '/home/anegawa/Dropbox/breastw.mat'):
clf.contamination = 0.35
elif (str(filename) == '/home/anegawa/Dropbox/arrhythmia.mat'):
clf.contamination = 0.15
elif (str(filename) == '/home/anegawa/Dropbox/ionosphere.mat'):
clf.contamination = 0.36
elif (str(filename) == '/home/anegawa/Dropbox/satellite.mat'):
clf.contamination = 0.32
elif (str(filename) == '/home/anegawa/Dropbox/annthyroid.mat'):
clf.contamination = 0.07
elif (str(filename) == '/home/anegawa/Dropbox/smtp.mat'):
clf.contamination = 0.03 / 100
else:
raise Exception("error! cannot file it.")
# 交差検証を何回行うか(例:8:2なら5回)
# もっとうまい方法ありそう
hoge = 1 / (1 - rate)
cross_count = int(np.ceil(hoge))
if cross_count > hoge:
cross_count = cross_count - 1
# cross_count分のauc,acc合計
sum_auc = 0
sum_accuracy = 0
pca_fit_time = 0
pca_transform_train_time = 0
pca_transform_test_time = 0
test_time = 0
fit_time = 0
if sepaLabel == True: # separated
# data cut
X_anomaly = []
X_normal = []
for i in range(len(X)):
if y[i] == 1:
X_anomaly.append(X[i])
else:
X_normal.append(X[i])
cutter_anomaly = int(np.ceil(len(X_anomaly) * rate))
cutter_normal = int(np.ceil(len(X_normal) * rate))
for count in range(cross_count):
if sepaLabel:
part_anomaly = int(np.ceil(cutter_anomaly * count))
part_normal = int(np.ceil(cutter_normal * count))
X_train = []
X_train_correct = []
X_test = []
X_test_correct = []
for i, k in zip(range(len(X_anomaly)),
range(part_anomaly,
part_anomaly + len(X_anomaly))):
while k >= len(X_anomaly):
k = k - len(X_anomaly)
if i < cutter_anomaly:
X_train.append(X_anomaly[k])
X_train_correct.append(-1)
else:
X_test.append(X_anomaly[k])
X_test_correct.append(-1)
for i, k in zip(range(len(X_normal)),
range(part_normal, part_normal + len(X_normal))):
while k >= len(X_normal):
k = k - len(X_normal)
if i < cutter_normal:
X_train.append(X_normal[k])
X_train_correct.append(1)
else:
X_test.append(X_normal[k])
X_test_correct.append(1)
# シャッフルするかどうか
if sfl:
X_train_set = []
X_test_set = []
for i in range(len(X_train)):
buf = []
buf.append(X_train[i])
buf.append(X_train_correct[i])
X_train_set.append(buf)
for i in range(len(X_test)):
buf = []
buf.append(X_test[i])
buf.append(X_test_correct[i])
X_test_set.append(buf)
random.shuffle(X_train_set)
random.shuffle(X_test_set)
X_train = []
X_test = []
X_train_correct = []
X_test_correct = []
for i in range(len(X_train_set)):
X_train.append(X_train_set[i][0])
X_train_correct.append(X_train_set[i][1])
for i in range(len(X_test_set)):
X_test.append(X_test_set[i][0])
X_test_correct.append(X_test_set[i][1])
else: # mixed
cutter = len(X) * rate
part = int(np.ceil(cutter * count))
X_train = []
X_train_correct = []
X_test = []
X_test_correct = []
for i, k in zip(range(len(X)), range(part, part + len(X))):
while k >= len(X):
k = k - len(X)
if i < len(X) * rate:
X_train.append(X[k])
X_train_correct.append(y[k])
else:
X_test.append(X[k])
X_test_correct.append(y[k])
for q in range(len(X_train_correct)):
j = X_train_correct[q]
if (j == 1):
X_train_correct[q] = -1
else:
X_train_correct[q] = 1
for w in range(len(X_test_correct)):
j = X_test_correct[w]
if (j == 1):
X_test_correct[w] = -1
else:
X_test_correct[w] = 1
# owari
# finished cutting data
if pcaLabel:
if sepa2:
# if False:
pca2 = PCA(copy=True,
iterated_power='auto',
random_state=None,
svd_solver='auto',
tol=0.0,
whiten=False)
pca2.fit(X_train_normal)
component = pca2.components_
component2 = np.sort(pca2.components_)
if n_comp < len(component2):
pca2.components_ = component2[0:n_comp]
X_train = pca2.transform(X_train)
X_test = pca2.transform(X_test)
else:
pca_fit_start = time.time()
pca = PCA(copy=True,
iterated_power='auto',
n_components=n_comp,
random_state=None,
svd_solver='auto',
tol=0.0,
whiten=False)
pca.fit(X_train)
pca_fit_finish = time.time()
pca_transform_train_start = time.time()
X_train = pca.transform(X_train)
pca_transform_train_finish = time.time()
clf.max_features = n_comp
pca_fit_time += (pca_fit_finish - pca_fit_start)
pca_transform_train_time += (pca_transform_train_finish -
pca_transform_train_start)
fit_start = time.time()
# fit_ylabelはFalseで固定
if fit_ylabel:
clf.fit(X_train, X_train_correct, sample_weight=None)
else:
clf.fit(X_train, y=None, sample_weight=None)
fit_finish = time.time()
fit_time += (fit_finish - fit_start)
if stream:
sum_score_auc = []
sum_score_acc = []
for i in range(len(X_test)):
if pcaLabel:
pca_transform_test_start = time.time()
a = [X_test[i]]
X_test_pca = pca.transform(a)
pca_transform_test_finish = time.time()
pca_transform_test_time += (pca_transform_test_finish -
pca_transform_test_start)
else:
X_test_pca = [X_test[i]]
test_start = time.time()
y_pred_test, a_score = clf.predict(X_test_pca)
test_finish = time.time()
test_time += (test_finish - test_start)
sum_score_auc.append(a_score)
sum_score_acc.append(y_pred_test)
a_score = sum_score_auc
y_pred_test = sum_score_acc
else: # batch
if pcaLabel:
pca_transform_test_start = time.time()
X_test = pca.transform(X_test) # stream version
pca_transform_test_finish = time.time()
pca_transform_test_time += (pca_transform_test_finish -
pca_transform_test_start)
test_start = time.time()
y_pred_test, a_score = clf.predict(X_test)
# a_score = clf.decision_function(X_test)
test_finish = time.time()
test_time += (test_finish - test_start)
acc = calc_accuracy(X_test_correct, y_pred_test, treeLabel)
AUC = calc_AUC(X_test_correct, a_score, treeLabel)
sum_auc += AUC
sum_accuracy += acc
# # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# # plot the line, the samples, and the nearest vectors to the plane
#
# X_train = np.array(X_train)
# X_test = np.array(X_test)
#
# lim = True
# x = (-200, 200)
# y = (-200, 300)
#
# for i,j in zip(range(2), [True, False]):
# small = j # trueがsmallestね
#
# plt.subplot(2, 2, i+1)
# if small:
# plt.title("smallest")
# else:
# plt.title("largest")
#
# if small:
# # b1 = plt.scatter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, X_test.shape[1]-1], X_test[:, X_test.shape[1]-2], c='green', s=20, edgecolor='k')
# else:
# # b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# plt.legend([b2],["testing observations"],
# loc="upper left")
# # plt.legend([b1], ["training observations"],
# # loc="upper left")
#
#
#
# plt.subplot(2, 2, i+3)
# if small:
# b1 = plt.scatter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, X_test.shape[1] - 1], X_test[:, X_test.shape[1] - 2], c='green', s=20, edgecolor='k')
# else:
# b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# # plt.legend([b2], ["testing observations"],
# # loc="upper left")
# plt.legend([b1], ["training observations"],
# loc="upper left")
# plt.show()ter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, X_test.shape[1]-1], X_test[:, X_test.shape[1]-2], c='green', s=20, edgecolor='k')
# else:
# # b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# plt.legend([b2],["testing observations"],
# loc="upper left")
# # plt.legend([b1], ["training observations"],
# # loc="upper left")
#
#
#
# plt.subplot(2, 2, i+3)
# if small:
# b1 = plt.scatter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, X_test.shape[1] - 1], X_test[:, X_test.shape[1] - 2], c='green', s=20, edgecolor='k')
# else:
# b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# # plt.legend([b2], ["testing observations"],
# # loc="upper left")
# plt.legend([b1], ["training observations"],
# loc="upper left")
# plt.show()
# # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
auc2 = sum_auc / cross_count
acc2 = sum_accuracy / cross_count
# calc time
all_finish = time.time()
all_time = all_finish - all_start
pca_fit_time = pca_fit_time / cross_count
pca_transform_train_time = pca_transform_train_time / cross_count
pca_transform_test_time = pca_transform_test_time / cross_count
test_time = test_time / cross_count
fit_time = fit_time / cross_count
sum_train_time = fit_time + pca_fit_time + pca_transform_train_time
sum_test_time = pca_transform_test_time + test_time
# print("sum_train_time : " + str(sum_train_time))
# print("pca_transform_train_time : " + str(pca_transform_train_time))
# print("pca_fit_time : " + str(pca_fit_time))
# print("test_time : " + str(test_time))
# print("fit_time : " + str(fit_time))
# print("all_time : " + str(all_time))
if time_label:
return all_time, pca_fit_time + pca_transform_train_time, fit_time, pca_transform_test_time, test_time, sum_train_time, sum_test_time
elif treeLabel:
if math.isnan(auc2):
raise Exception("error! auc is NaN!.")
return auc2
else:
return auc2, acc2
def main(filename,
xtrains_percent=0.8,
maxfeature=1,
fit_ylabel=False,
nn_estimator=100,
sepaLabel=True,
treeLabel=False,
seed=42,
pcaLabel=False,
n_comp=2,
sepa2=False,
time_label=False,
stream=False,
sfl=False):
mugen = float("inf")
all_start = time.time()
rng = np.random.RandomState(seed)
# httpとsmtpは別の方法でデータ取得
if filename == '/home/anegawa/Dropbox/http.mat' or filename == '/home/anegawa/Dropbox/smtp.mat':
mat = {}
f = h5py.File(filename)
for k, v in f.items():
mat[k] = np.array(v)
X = mat['X'].T
y2 = mat['y'][0]
y3 = []
for i in range(len(y2)):
y3.append(int(y2[i]))
y = np.reshape(y3, [len(y3), 1])
else:
mat = scipy.io.loadmat(filename)
X = mat['X']
y = mat['y']
rate = xtrains_percent
max_feat = int(maxfeature)
if max_feat == 3:
max_feat = X.shape[1]
if treeLabel:
anegawa = 0
else:
print('X_train\'s rate : ' + str(rate))
print('max_features : ' + str(max_feat))
print('fit_ylabel : ' + str(fit_ylabel))
print('nn_estimator : ' + str(nn_estimator))
print('sepaLabel : ' + str(sepaLabel))
clf = IsolationForest(random_state=rng)
clf.n_estimators = nn_estimator
clf.verbose = 0
clf.max_features = max_feat
if (str(filename) == '/home/anegawa/Dropbox/shuttle.mat'):
clf.contamination = 0.07
elif (str(filename) == '/home/anegawa/Dropbox/http.mat'):
clf.contamination = 0.004
elif (str(filename) == '/home/anegawa/Dropbox/pima.mat'):
clf.contamination = 0.35
elif (str(filename) == '/home/anegawa/Dropbox/mammography.mat'):
clf.contamination = 0.02
elif (str(filename) == '/home/anegawa/Dropbox/cover.mat'):
clf.contamination = 0.009
elif (str(filename) == '/home/anegawa/Dropbox/breastw.mat'):
clf.contamination = 0.35
elif (str(filename) == '/home/anegawa/Dropbox/arrhythmia.mat'):
clf.contamination = 0.15
elif (str(filename) == '/home/anegawa/Dropbox/ionosphere.mat'):
clf.contamination = 0.36
elif (str(filename) == '/home/anegawa/Dropbox/satellite.mat'):
clf.contamination = 0.32
elif (str(filename) == '/home/anegawa/Dropbox/annthyroid.mat'):
clf.contamination = 0.07
elif (str(filename) == '/home/anegawa/Dropbox/smtp.mat'):
clf.contamination = 0.03 / 100
else:
print('cannot file it.')
# Generate train data
a = rng.randn(400, 2)
X = 0.3 * a
X_train = np.r_[X + 2, X - 2]
# X_train = np.ones([400, 2])
# Generate some regular novel observations
X = 0.3 * rng.randn(400, 2)
X_test = np.r_[X + 2, X - 2]
# X_test = np.ones([400, 2])
# Generate some abnormal novel observations
X_outliers = np.random.exponential(1. / 0.001, size=[20, 2])
# X_outliers = rng.uniform(low=-4, high=4, size=(20, 2))
# X_outliers = np.zeros([20, 2])
X_test = np.r_[X_test, X_outliers]
X_train_correct = np.ones([X_train.shape])
hoge = 1 / (1 - rate)
cross_count = int(np.ceil(hoge))
if cross_count > hoge:
cross_count = cross_count - 1
sum_auc = 0
sum_accuracy = 0
pca_fit_time = 0
pca_transform_train_time = 0
pca_transform_test_time = 0
test_time = 0
fit_time = 0
sum_train_time = 0
# for count in range(cross_count):
if sepaLabel == True: # separated
# data cut
X_anomaly = []
X_normal = []
for i in range(len(X)):
if y[i] == 1:
X_anomaly.append(X[i])
else:
X_normal.append(X[i])
cutter_anomaly = int(np.ceil(len(X_anomaly) * rate))
cutter_normal = int(np.ceil(len(X_normal) * rate))
for count in range(cross_count):
part_anomaly = int(np.ceil(cutter_anomaly * count))
part_normal = int(np.ceil(cutter_normal * count))
X_train = []
X_train_correct = []
X_test = []
X_test_correct = []
for i, k in zip(range(len(X_anomaly)),
range(part_anomaly,
part_anomaly + len(X_anomaly))):
while k >= len(X_anomaly):
k = k - len(X_anomaly)
if i < cutter_anomaly:
X_train.append(X_anomaly[k])
X_train_correct.append(-1)
else:
X_test.append(X_anomaly[k])
X_test_correct.append(-1)
for i, k in zip(range(len(X_normal)),
range(part_normal, part_normal + len(X_normal))):
while k >= len(X_normal):
k = k - len(X_normal)
if i < cutter_normal:
X_train.append(X_normal[k])
X_train_correct.append(1)
else:
X_test.append(X_normal[k])
X_test_correct.append(1)
if sfl:
X_train_set = []
X_test_set = []
for i in range(len(X_train)):
buf = []
buf.append(X_train[i])
buf.append(X_train_correct[i])
X_train_set.append(buf)
for i in range(len(X_test)):
buf = []
buf.append(X_test[i])
buf.append(X_test_correct[i])
X_test_set.append(buf)
random.shuffle(X_train_set)
random.shuffle(X_test_set)
X_train = []
X_test = []
X_train_correct = []
X_test_correct = []
for i in range(len(X_train_set)):
X_train.append(X_train_set[i][0])
X_train_correct.append(X_train_set[i][1])
for i in range(len(X_test_set)):
X_test.append(X_test_set[i][0])
X_test_correct.append(X_test_set[i][1])
else: # mixed
cutter = len(X) * rate # test start this index at the first time
for count in range(cross_count):
part = int(np.ceil(cutter * count))
# while part >= len(X):
# part = part - len(X)
X_train = []
X_train_correct = []
X_test = []
X_test_correct = []
for i, k in zip(range(len(X)), range(part, part + len(X))):
while k >= len(X):
k = k - len(X)
if i < len(X) * rate:
X_train.append(X[k])
X_train_correct.append(y[k])
else:
X_test.append(X[k])
X_test_correct.append(y[k])
for q in range(len(X_train_correct)):
j = X_train_correct[q]
if (j == 1):
X_train_correct[q] = -1
else:
X_train_correct[q] = 1
for w in range(len(X_test_correct)):
j = X_test_correct[w]
if (j == 1):
X_test_correct[w] = -1
else:
X_test_correct[w] = 1
# owari
# finished cutting data
if pcaLabel:
pca_fit_start = time.time()
pca = PCA(copy=True,
iterated_power='auto',
n_components=n_comp,
random_state=None,
svd_solver='auto',
tol=0.0,
whiten=False)
pca2 = PCA(copy=True,
iterated_power='auto',
random_state=None,
svd_solver='auto',
tol=0.0,
whiten=False)
if sepa2:
# if False:
print("こっち入ってるけどええんか!?")
pca2.fit(X_train_normal)
component = pca2.components_
component2 = np.sort(pca2.components_)
if n_comp < len(component2):
pca2.components_ = component2[0:n_comp]
# print(pca2.components_.shape)
X_train = pca2.transform(X_train)
X_test = pca2.transform(X_test)
else:
pca.fit(X_train)
pca_fit_finish = time.time()
pca_transform_train_start = time.time()
X_train = pca.transform(X_train)
pca_transform_train_finish = time.time()
# a = X_test[0]
# X_test = pca.transform(a)
# if not stream:
# pca_transform_test_start = time.time()
# X_test = pca.transform(X_test) #stream version
# pca_transform_test_finish = time.time()
# pca_transform_test_time += (pca_transform_test_finish - pca_transform_test_start)
clf.max_features = n_comp
pca_fit_time += (pca_fit_finish - pca_fit_start)
pca_transform_train_time += (pca_transform_train_finish -
pca_transform_train_start)
fit_start = time.time()
if fit_ylabel:
clf.fit(X_train, X_train_correct, sample_weight=None)
else:
clf.fit(X_train, y=None, sample_weight=None)
fit_finish = time.time()
fit_time += (fit_finish - fit_start)
# if pcaLabel and stream:
if stream:
sum_score_auc = []
sum_score_acc = []
# print(X_test[0:1])
for i in range(len(X_test)):
if pcaLabel:
pca_transform_test_start = time.time()
a = [X_test[i]]
X_test_pca = pca.transform(a)
pca_transform_test_finish = time.time()
pca_transform_test_time += (pca_transform_test_finish -
pca_transform_test_start)
else:
X_test_pca = [X_test[i]]
test_start = time.time()
y_pred_test, a_score = clf.predict(X_test_pca)
test_finish = time.time()
test_time += (test_finish - test_start)
sum_score_auc.append(a_score)
sum_score_acc.append(y_pred_test)
a_score = sum_score_auc
y_pred_test = sum_score_acc
else:
if pcaLabel:
pca_transform_test_start = time.time()
X_test = pca.transform(X_test) # stream version
pca_transform_test_finish = time.time()
pca_transform_test_time += (pca_transform_test_finish -
pca_transform_test_start)
test_start = time.time()
y_pred_test, a_score = clf.predict(X_test)
test_finish = time.time()
test_time += (test_finish - test_start)
# a_score = clf.decision_function(X_test)
acc = calc_accuracy(X_test_correct, y_pred_test, treeLabel)
AUC = calc_AUC(X_test_correct, a_score, treeLabel)
sum_auc += AUC
sum_accuracy = acc
# return AUC
# # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# # plot the line, the samples, and the nearest vectors to the plane
# xx, yy = np.meshgrid(np.linspace(-200, 200, 1000), np.linspace(-200, 200, 1000))
# # clf.max_features = 2
# # print(yy.ravel())
# # Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
#
# # Z = Z.reshape(xx.shape)
#
# plt.figure(figsize=(100, 200))
# plt.suptitle("satellite")
# # plt.contourf(xx, yy, Z, cmap=plt.cm.Blues_r)
#
# X_train = np.array(X_train)
# X_test = np.array(X_test)
#
# lim = True
# x = (-200, 200)
# y = (-200, 300)
#
# for i,j in zip(range(2), [True, False]):
# small = j # trueがsmallestね
#
# plt.subplot(2, 2, i+1)
# if small:
# plt.title("smallest")
# else:
# plt.title("largest")
#
# if small:
# # b1 = plt.scat
# # plot the line, the samples, and the nearest vectors to the plane
# xx, yy = np.meshgrid(np.linspace(-200, 200, 1000), np.linspace(-200, 200, 1000))
# # clf.max_features = 2
# # print(yy.ravel())
# # Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
#
# # Z = Z.reshape(xx.shape)
#
# plt.figure(figsize=(100, 200))
# plt.suptitle("satellite")
# # plt.contourf(xx, yy, Z, cmap=plt.cm.Blues_r)
#
# X_train = np.array(X_train)
# X_test = np.array(X_test)
#
# lim = True
# x = (-200, 200)
# y = (-200, 300)
#
# for i,j in zip(range(2), [True, False]):
# small = j # trueがsmallestね
#
# plt.subplot(2, 2, i+1)
# if small:
# plt.title("smallest")
# else:
# plt.title("largest")
#
# if small:
# # b1 = plt.scatter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, X_test.shape[1]-1], X_test[:, X_test.shape[1]-2], c='green', s=20, edgecolor='k')
# else:
# # b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# plt.legend([b2],["testing observations"],
# loc="upper left")
# # plt.legend([b1], ["training observations"],
# # loc="upper left")
#
#
#
# plt.subplot(2, 2, i+3)
# if small:
# b1 = plt.scatter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, X_test.shape[1] - 1], X_test[:, X_test.shape[1] - 2], c='green', s=20, edgecolor='k')
# else:
# b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# # plt.legend([b2], ["testing observations"],
# # loc="upper left")
# plt.legend([b1], ["training observations"],
# loc="upper left")
# plt.show()ter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, X_test.shape[1]-1], X_test[:, X_test.shape[1]-2], c='green', s=20, edgecolor='k')
# else:
# # b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# plt.legend([b2],["testing observations"],
# loc="upper left")
# # plt.legend([b1], ["training observations"],
# # loc="upper left")
#
#
#
# plt.subplot(2, 2, i+3)
# if small:
# b1 = plt.scatter(X_train[:, X_train.shape[1]-1], X_train[:, X_train.shape[1]-2], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, X_test.shape[1] - 1], X_test[:, X_test.shape[1] - 2], c='green', s=20, edgecolor='k')
# else:
# b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
# # b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
# # c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c='red', s=20, edgecolor='k')
# plt.axis('tight')
# if lim:
# plt.xlim(x)
# plt.ylim(y)
# # plt.legend([b1, b2],
# # ["training observations",
# # "testing observations"],
# # loc="upper left")
# # plt.legend([b2], ["testing observations"],
# # loc="upper left")
# plt.legend([b1], ["training observations"],
# loc="upper left")
# plt.show()
# # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
auc2 = sum_auc / cross_count
# print(sum_accuracy)
acc2 = sum_accuracy / cross_count
# calc time
all_finish = time.time()
all_time = all_finish - all_start
pca_fit_time = pca_fit_time / cross_count
pca_transform_train_time = pca_transform_train_time / cross_count
pca_transform_test_time = pca_transform_test_time / cross_count
test_time = test_time / cross_count
fit_time = fit_time / cross_count
sum_train_time = fit_time + pca_fit_time + pca_transform_train_time
sum_test_time = pca_transform_test_time + test_time
# print("sum_train_time : " + str(sum_train_time))
# print("pca_transform_train_time : " + str(pca_transform_train_time))
# print("pca_fit_time : " + str(pca_fit_time))
# print("test_time : " + str(test_time))
# print("fit_time : " + str(fit_time))
# print("all_time : " + str(all_time))
# return
if time_label:
return all_time, pca_fit_time + pca_transform_train_time, fit_time, pca_transform_test_time, test_time, sum_train_time, sum_test_time
elif treeLabel:
if math.isnan(auc2):
majikayo = True
return auc2
else:
return auc2, acc2
