Upload New File

session-2-anomalies/2_Clustering.py

+
+# load libraries 
+import numpy as np
+from sklearn.cluster import KMeans
+from scipy.spatial import distance
+from sklearn.metrics import accuracy_score,f1_score,roc_auc_score
+
+# load data set 
+data = np.loadtxt('crimerate_binary.csv', delimiter=',')
+[n,p] = data.shape
+
+# split data into a training set and a testing set
+size_train = int(0.75*n) # we use first 75% data for training, the rest for testing
+sample_train = data[0:size_train,0:-1]
+label_train = data[0:size_train,-1]
+sample_test = data[size_train:,0:-1]
+label_test = data[size_train:,-1]
+
+# ----------------------------------------
+# clustering-based anomaly detection 
+# tutorial slides, page 61 - 67
+# use k-means clustering for detection 
+# ----------------------------------------
+
+# step 1. choose number of clusters for k-means clustering algorithm
+numcluster = 2
+
+# step 2. run k-means clustering algorithm on both training & testing data 
+sample = data[:,0:-1]
+label = data[:,-1]
+kmeans = KMeans(n_clusters=numcluster, random_state=0).fit(sample)
+
+# step 3. compute center of each cluster
+center = kmeans.cluster_centers_
+
+# step 4. compute distance from examples to their assigned cluster centers
+discenter = distance.cdist(center,sample) 
+# treat the distance as anomalous scores 
+adscore = np.min(discenter,axis=0) 
+# now just pick out distnace of testing examples because that's what we care about 
+adscore = adscore[len(label_train):]
+# evaluate AUC score 
+auc_score = roc_auc_score(label_test, adscore)
+# to get detection error and f1-score, we need to threshold anomalous score 
+# the range of adscore is [0.65, 4.10]
+threshold = 1.2
+adscore[adscore <= threshold] = 0
+adscore[adscore > threshold] = 1
+# now evaluate error and f1-score 
+err = 1 - accuracy_score(label_test,adscore) 
+f1score = f1_score(label_test,adscore) 
+
+# step 5. print results 
+print('\nClustering-based Approach (K-means)')
+print('Detection Error = %.4f' % err)
+print('F1 Score = %.4f' % f1score)
+print('AUC Score = %.4f' % auc_score)
+
+
+# -----------
+# Assignment 
+# -----------
+# 1. play with different number of clusters (line 26),  what do you observe?
+# 2. play with different thresholds (line 50), what do you observe?
+
+
+
+
+