1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
|
# netdata python.d.plugin configuration for anomalies
#
# This file is in YaML format. Generally the format is:
#
# name: value
#
# There are 2 sections:
# - global variables
# - one or more JOBS
#
# JOBS allow you to collect values from multiple sources.
# Each source will have its own set of charts.
#
# JOB parameters have to be indented (using spaces only, example below).
# ----------------------------------------------------------------------
# Global Variables
# These variables set the defaults for all JOBs, however each JOB
# may define its own, overriding the defaults.
# update_every sets the default data collection frequency.
# If unset, the python.d.plugin default is used.
# update_every: 2
# priority controls the order of charts at the netdata dashboard.
# Lower numbers move the charts towards the top of the page.
# If unset, the default for python.d.plugin is used.
# priority: 60000
# ----------------------------------------------------------------------
# JOBS (data collection sources)
# Pull data from local Netdata node.
anomalies:
name: 'Anomalies'
# Host to pull data from.
host: '127.0.0.1:19999'
# Username and Password for Netdata if using basic auth.
# username: '???'
# password: '???'
# Use http or https to pull data
protocol: 'http'
# SSL verify parameter for requests.get() calls
tls_verify: true
# What charts to pull data for - A regex like 'system\..*|' or 'system\..*|apps.cpu|apps.mem' etc.
charts_regex: 'system\..*'
# Charts to exclude, useful if you would like to exclude some specific charts.
# Note: should be a ',' separated string like 'chart.name,chart.name'.
charts_to_exclude: 'system.uptime,system.entropy'
# What model to use - can be one of 'pca', 'hbos', 'iforest', 'cblof', 'loda', 'copod' or 'feature_bagging'.
# More details here: https://pyod.readthedocs.io/en/latest/pyod.models.html.
model: 'pca'
# Max number of observations to train on, to help cap compute cost of training model if you set a very large train_n_secs.
train_max_n: 100000
# How often to re-train the model (assuming update_every=1 then train_every_n=1800 represents (re)training every 30 minutes).
# Note: If you want to turn off re-training set train_every_n=0 and after initial training the models will not be retrained.
train_every_n: 1800
# The length of the window of data to train on (14400 = last 4 hours).
train_n_secs: 14400
# How many prediction steps after a train event to just use previous prediction value for.
# Used to reduce possibility of the training step itself appearing as an anomaly on the charts.
train_no_prediction_n: 10
# If you would like to train the model for the first time on a specific window then you can define it using the below two variables.
# Start of training data for initial model.
# initial_train_data_after: 1604578857
# End of training data for initial model.
# initial_train_data_before: 1604593257
# If you would like to ignore recent data in training then you can offset it by offset_n_secs.
offset_n_secs: 0
# How many lagged values of each dimension to include in the 'feature vector' each model is trained on.
lags_n: 5
# How much smoothing to apply to each dimension in the 'feature vector' each model is trained on.
smooth_n: 3
# How many differences to take in preprocessing your data.
# More info on differencing here: https://en.wikipedia.org/wiki/Autoregressive_integrated_moving_average#Differencing
# diffs_n=0 would mean training models on the raw values of each dimension.
# diffs_n=1 means everything is done in terms of differences.
diffs_n: 1
# What is the typical proportion of anomalies in your data on average?
# This parameter can control the sensitivity of your models to anomalies.
# Some discussion here: https://github.com/yzhao062/pyod/issues/144
contamination: 0.001
# Set to true to include an "average_prob" dimension on anomalies probability chart which is
# just the average of all anomaly probabilities at each time step
include_average_prob: true
# Define any custom models you would like to create anomaly probabilities for, some examples below to show how.
# For example below example creates two custom models, one to run anomaly detection user and system cpu for our demo servers
# and one on the cpu and mem apps metrics for the python.d.plugin.
# custom_models:
# - name: 'demos_cpu'
# dimensions: 'london.my-netdata.io::system.cpu|user,london.my-netdata.io::system.cpu|system,newyork.my-netdata.io::system.cpu|user,newyork.my-netdata.io::system.cpu|system'
# - name: 'apps_python_d_plugin'
# dimensions: 'apps.cpu|python.d.plugin,apps.mem|python.d.plugin'
# Set to true to normalize, using min-max standardization, features used for the custom models.
# Useful if your custom models contain dimensions on very different scales an model you use does
# not internally do its own normalization. Usually best to leave as false.
# custom_models_normalize: false
# Standalone Custom models example as an additional collector job.
# custom:
# name: 'custom'
# host: '127.0.0.1:19999'
# protocol: 'http'
# charts_regex: 'None'
# charts_to_exclude: 'None'
# model: 'pca'
# train_max_n: 100000
# train_every_n: 1800
# train_n_secs: 14400
# offset_n_secs: 0
# lags_n: 5
# smooth_n: 3
# diffs_n: 1
# contamination: 0.001
# custom_models:
# - name: 'user_netdata'
# dimensions: 'users.cpu|netdata,users.mem|netdata,users.threads|netdata,users.processes|netdata,users.sockets|netdata'
# - name: 'apps_python_d_plugin'
# dimensions: 'apps.cpu|python.d.plugin,apps.mem|python.d.plugin,apps.threads|python.d.plugin,apps.processes|python.d.plugin,apps.sockets|python.d.plugin'
# Pull data from some demo nodes for cross node custom models.
# demos:
# name: 'demos'
# host: '127.0.0.1:19999'
# protocol: 'http'
# charts_regex: 'None'
# charts_to_exclude: 'None'
# model: 'pca'
# train_max_n: 100000
# train_every_n: 1800
# train_n_secs: 14400
# offset_n_secs: 0
# lags_n: 5
# smooth_n: 3
# diffs_n: 1
# contamination: 0.001
# custom_models:
# - name: 'system.cpu'
# dimensions: 'london.my-netdata.io::system.cpu|user,london.my-netdata.io::system.cpu|system,newyork.my-netdata.io::system.cpu|user,newyork.my-netdata.io::system.cpu|system'
# - name: 'system.ip'
# dimensions: 'london.my-netdata.io::system.ip|received,london.my-netdata.io::system.ip|sent,newyork.my-netdata.io::system.ip|received,newyork.my-netdata.io::system.ip|sent'
# - name: 'system.net'
# dimensions: 'london.my-netdata.io::system.net|received,london.my-netdata.io::system.net|sent,newyork.my-netdata.io::system.net|received,newyork.my-netdata.io::system.net|sent'
# - name: 'system.io'
# dimensions: 'london.my-netdata.io::system.io|in,london.my-netdata.io::system.io|out,newyork.my-netdata.io::system.io|in,newyork.my-netdata.io::system.io|out'
# Example additional job if you want to also pull data from a child streaming to your
# local parent or even a remote node so long as the Netdata REST API is accessible.
# mychildnode1:
# name: 'mychildnode1'
# host: '127.0.0.1:19999/host/mychildnode1'
# protocol: 'http'
# charts_regex: 'system\..*'
# charts_to_exclude: 'None'
# model: 'pca'
# train_max_n: 100000
# train_every_n: 1800
# train_n_secs: 14400
# offset_n_secs: 0
# lags_n: 5
# smooth_n: 3
# diffs_n: 1
# contamination: 0.001
|
