sklearn 異常檢測demo代碼走讀
# 0基礎學python，讀代碼學習python組件api import time import numpy as np import matplotlib import matplotlib.pyplot as plt from sklearn import svm from sklearn.datasets import make_moons, make_blobs from sklearn.covariance import EllipticEnvelope from sklearn.ensemble import IsolationForest from sklearn.neighbors import LocalOutlierFactor print(__doc__) matplotlib.rcParams['contour.negative_linestyle'] = 'solid' # Example settings n_samples = 300 outliers_fraction = 0.15 n_outliers = int(outliers_fraction * n_samples) n_inliers = n_samples - n_outliers # define outlier/anomaly detection methods to be compared # 四種異常檢測算法，之后的文章詳細介紹 anomaly_algorithms = [ ("Robust covariance", EllipticEnvelope(contamination=outliers_fraction)), ("One-Class SVM", svm.OneClassSVM(nu=outliers_fraction, kernel="rbf", gamma=0.1)), ("Isolation Forest", IsolationForest(contamination=outliers_fraction, random_state=42)), ("Local Outlier Factor", LocalOutlierFactor( n_neighbors=35, contamination=outliers_fraction))] # Define datasets blobs_params = dict(random_state=0, n_samples=n_inliers, n_features=2) datasets = [ # make_blobes用於生成聚類數據。centers表示聚類中心，cluster_std表示聚類數據方差。返回值(數據, 類別) # **用於傳遞dict key-value參數，*用於傳遞元組不定數量參數。 make_blobs(centers=[[0, 0], [0, 0]], cluster_std=0.5, **blobs_params)[0], make_blobs(centers=[[2, 2], [-2, -2]], cluster_std=[0.5, 0.5], **blobs_params)[0], make_blobs(centers=[[2, 2], [-2, -2]], cluster_std=[1.5, .3], **blobs_params)[0], # make_moons用於生成月亮形數據。返回值數據(x, y) 4. * (make_moons(n_samples=n_samples, noise=.05, random_state=0)[0] - np.array([0.5, 0.25])), 14. * (np.random.RandomState(42).rand(n_samples, 2) - 0.5)] # Compare given classifiers under given settings # np.meshgrid生產成網格數據 # 如輸入x = [0, 1, 2, 3] y = [0, 1, 2]，則輸出 # xx 0 1 2 3 yy 0 0 0 0 # 0 1 2 3 1 1 1 1 # 0 1 2 3 2 2 2 2 xx, yy = np.meshgrid(np.linspace(-7, 7, 150), np.linspace(-7, 7, 150)) # figure生成畫布，subplots_adjust子圖的間距調整，左邊距，右邊距，下邊距，上邊距，列間距，行間距 plt.figure(figsize=(len(anomaly_algorithms) * 2 + 3, 12.5)) plt.subplots_adjust(left=.02, right=.98, bottom=.001, top=.96, wspace=.05, hspace=.01) plot_num = 1 rng = np.random.RandomState(42) for i_dataset, X in enumerate(datasets): # Add outliers # np.concatenate數組拼接。axis=0行增加，axis=1列增加（對應行拼接）。 X = np.concatenate([X, rng.uniform(low=-6, high=6, size=(n_outliers, 2))], axis=0) for name, algorithm in anomaly_algorithms: t0 = time.time() # 專門用於評估執行時間，無用代碼 algorithm.fit(X) t1 = time.time() # 定位子圖位置。參數：列，行，序號 plt.subplot(len(datasets), len(anomaly_algorithms), plot_num) if i_dataset == 0: plt.title(name, size=18) # fit the data and tag outliers # 訓練與預測 if name == "Local Outlier Factor": y_pred = algorithm.fit_predict(X) else: y_pred = algorithm.fit(X).predict(X) # plot the levels lines and the points # 用訓練的模型預測網格數據點，主要是要得到聚類模型邊緣 if name != "Local Outlier Factor": # LOF does not implement predict # ravel()多維數組平鋪為一維數組。np.c_ cloumn列連接，np.r_ row行連接。 Z = algorithm.predict(np.c_[xx.ravel(), yy.ravel()]) # reshape這里把一維數組轉化為二維數組 Z = Z.reshape(xx.shape) # plt.contour畫等高線。Z表示對應點類別，可以理解為不同的高度，plt.contour就是要畫出不同高度間的分界線。 plt.contour(xx, yy, Z, levels=[0], linewidths=2, colors='black') colors = np.array(['#377eb8', '#ff7f00']) plt.scatter(X[:, 0], X[:, 1], s=10, color=colors[(y_pred + 1) // 2]) # x軸范圍 plt.xlim(-7, 7) plt.ylim(-7, 7) # x軸坐標 plt.xticks(()) plt.yticks(()) # 坐標圖上顯示的文字 plt.text(.99, .01, ('%.2fs' % (t1 - t0)).lstrip('0'), transform=plt.gca().transAxes, size=15, horizontalalignment='right') plot_num += 1 plt.show()
執行結果
