PyOD进行异常值检测使用实例

 from pyod.models.knn import KNN 
 from pyod.utils.data import generate_data
 from pyod.utils.data import evaluate_print

contamination = 0.1  # percentage of outliers
 n_train = 200  # number of training points
 n_test = 100  # number of testing points
 X_train, X_test, y_train, y_test = generate_data(
     n_train=n_train, n_test=n_test, contamination=contamination)

clf_name = 'KNN'
 clf = KNN()
 clf.fit(X_train)

print("\nOn Training Data:")
 evaluate_print(clf_name, y_train, clf.decision_scores_)
 print("\nOn Test Data:")
 evaluate_print(clf_name, y_test, clf.decision_function(X_test))

from pyod.utils.data import visualize
 
 visualize(clf_name, X_train, y_train, X_test, y_test, clf.labels_,
           clf.predict(X_test), show_figure=True, save_figure=False)

import numpy as np
 from sklearn.model_selection import train_test_split
 from scipy.io import loadmat
 
 from pyod.models.knn import KNN
 from pyod.models.combination import aom, moa, average, maximization, median
 from pyod.utils.utility import standardizer
 from pyod.utils.data import generate_data
 from pyod.utils.data import evaluate_print
 
 X, y = generate_data(train_only=True)  # load data
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
 
 # standardizing data for processing
 X_train_norm, X_test_norm = standardizer(X_train, X_test)
 
 n_clf = 20  # number of base detectors
 
 # Initialize 20 base detectors for combination
 k_list = [10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140,
             150, 160, 170, 180, 190, 200]
 
 train_scores = np.zeros([X_train.shape[0], n_clf])
 test_scores = np.zeros([X_test.shape[0], n_clf])
 
 print('Combining {n_clf} kNN detectors'.format(n_clf=n_clf))
 
 for i in range(n_clf):
     k = k_list[i]
 
     clf = KNN(n_neighbors=k, method='largest')
     clf.fit(X_train_norm)
 
     train_scores[:, i] = clf.decision_scores_
     test_scores[:, i] = clf.decision_function(X_test_norm)
 
 # Decision scores have to be normalized before combination
 train_scores_norm, test_scores_norm = standardizer(train_scores,
                                                     test_scores)
 # Combination by average
 y_by_average = average(test_scores_norm)
 evaluate_print('Combination by Average', y_test, y_by_average)
 
 # Combination by max
 y_by_maximization = maximization(test_scores_norm)
 evaluate_print('Combination by Maximization', y_test, y_by_maximization)
 
 # Combination by median
 y_by_median = median(test_scores_norm)
 evaluate_print('Combination by Median', y_test, y_by_median)
 
 # Combination by aom
 y_by_aom = aom(test_scores_norm, n_buckets=5)
 evaluate_print('Combination by AOM', y_test, y_by_aom)
 
 # Combination by moa
 y_by_moa = moa(test_scores_norm, n_buckets=5)
 evaluate_print('Combination by MOA', y_test, y_by_moa)

pip install combo