Commit 34c27045 authored by Wolf's avatar Wolf
Browse files

Upload New File

parent 043bf40d
# load libraries
import numpy as np
from sklearn.neighbors import NearestNeighbors
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]
# ------------------------------------
# Neighborhood-based anomaly detection
# tutorial slides, page 85 - 93
# ------------------------------------
# step 1. choose number of neighbors
num_neighbor = 30
# step 2. construct a neighborhood using ONLY NORMAL examples
nbrs = NearestNeighbors(n_neighbors=num_neighbor, algorithm='ball_tree').fit(sample_train[label_train==0,:])
# the following code trains the model using both normal and abnormal examples
# nbrs = NearestNeighbors(n_neighbors=num_neighbor, algorithm='ball_tree').fit(sample_train)
# step 3. compute distance from each testing example to its num_neighbor neighbors
distances, indices = nbrs.kneighbors(sample_test)
# treat average distance as anomalous score
adscore = np.sum(distances,axis=1)/num_neighbor
# get 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 [0.9, 3.3]
threshold = 2
adscore[adscore <= threshold] = 0
adscore[adscore > threshold] = 1
# evaluate detection error and f1-score
# now evaluate error and f1-score
err = 1 - accuracy_score(label_test,adscore)
f1score = f1_score(label_test,adscore)
# step 4. print results
print('\nNeighborhood-based Approach')
print('Detection Error = %.4f' % err)
print('F1 Score = %.4f' % f1score)
print('AUC Score = %.4f' % auc_score)
# -----------
# Assignment
# -----------
# 1. construct neighborhood using both normal and abnormal examples (replace line 27 with line 29), what do you observe?
# 2. play with different size of neighborhood (line 24), what do you observe?
# 3. play with different thresholds (line 39), what do you observe?
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment