def LOF(dataset):
data = get_table_content(dataset)
model = LocalOutlierFactor(n_neighbors=4, contamination=0.1, novelty=True)
model.fit(numpy.array(data)[:, 0:2])
y = model._predict(numpy.array(data)[:, 0:2]) # 若样本点正常，返回1，不正常，返回-1
print(y)
pass
def LOF(Data):
model = LocalOutlierFactor(n_neighbors=10,
contamination='auto',
novelty=True) #定义一个LOF模型，异常比例是10%
model.fit(Data)
z = model._predict(Data) #若样本点正常，返回1，不正常，返回-1
index = z == 1
P = Data[index, :] #剩余点
P = np.array(list(set([tuple(t) for t in P])))
D = np.array([z])
return P, D
def lof_see(X, test_bi_pca, labels, min_samples):
for mSample in min_samples:
clf = LocalOutlierFactor(n_neighbors=mSample, contamination=0.1)
clf_predict = LocalOutlierFactor(n_neighbors=mSample,
contamination=0.1,
novelty=True).fit(bi_df_pca_unique)
test_labels = clf_predict._predict(test_bi_pca)
test_labels[test_labels > -1] = 0
print(mSample)
print(data_utils.show_performance(labels, test_labels))
print("Silhouette Coefficient: %0.3f" %
metrics.silhouette_score(X, clf.fit_predict(X)))
print("Calinski-Harabaz Index: %0.3f" %
metrics.calinski_harabaz_score(X, clf.fit_predict(X)))
print('--')
return None
feature_set.append(dsc)
print("features extraction: %d/%d" % (i, len(image_set)))
i += 1
return np.asarray(feature_set)
if __name__ == "__main__":
train, test, test_label, num_test_norm, num_test_anom = load_data()
train = extract_feature(train)
test = extract_feature(test)
clf = LocalOutlierFactor(n_neighbors=10, leaf_size=50)
clf.fit(train)
pred_train = clf._predict(train)
pred_test = clf._predict(test)
print(pred_train)
print(pred_test)
tp, fp, tn, fn = 0., 0., 0., 0.
for i in range(len(test)):
if (test_label[i] == 1):
if (pred_test[i] == -1):
tp += 1
elif (pred_test[i] == 1):
fn += 1
elif (test_label[i] == 0):
if (pred_test[i] == -1):
fp += 1
elif (pred_test[i] == 1):
test = extract_feature(TEST_FOLDER)
# train = train.astype('float32') / 255.
# test = test.astype('float32') / 255.
# train = train.reshape((len(train), np.prod(train.shape[1:])))
# test = test.reshape((len(test), np.prod(test.shape[1:])))
num_test_anom = len(test_label)
train, test_norm, train_name, test_name_norm = train_test_split(
train, train_name, test_size=0.2, random_state=30)
num_test_norm = len(test_name_norm)
test = np.concatenate((test, test_norm), axis=0)
test_label = np.concatenate((test_label, np.zeros(len(test_norm))), axis=0)
clf = LocalOutlierFactor(n_neighbors=20)
clf.fit(train)
pred_test = clf._predict(test)
print(pred_test)
tp, fp, tn, fn = 0., 0., 0., 0.
for i in range(0, len(test) - len(test_norm)):
if (pred_test[i] == -1):
tp += 1
elif (pred_test[i] == 1):
fn += 1
for i in range(len(test) - len(test_norm), len(test)):
if (pred_test[i] == -1):
fp += 1
elif (pred_test[i] == 1):
tn += 1
print('\nPrecesion: %.3f' % (tp / (tp + fp)))
