-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path1_ede_analysis_y2.yaml
218 lines (208 loc) · 6.81 KB
/
1_ede_analysis_y2.yaml
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
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
Connector:
PREndpoint: 194.102.62.155 #hal720m.sage.ieat.ro
Dask:
SchedulerEndpoint: local # if not local add DASK schedueler endpoint
Scale: 3 # Number of workers if local otherwise ignored
SchedulerPort: 8787 # This is the default point
EnforceCheck: False # Irrelevant for local
MPort: 9200 # Moitoring port
KafkaEndpoint: 10.9.8.136
KafkaPort: 9092
KafkaTopic: edetopic
# Query: { "query": 'node_disk_written_bytes_total[5m]'} # Query for specific metrics
Query: {"query": '{__name__=~"node.+"}[1m]'}
MetricsInterval: "1m" # Metrics datapoint interval definition
QSize: 0
Index: time
QDelay: "10s" # Polling period for metrics fetching
Local: /Users/Gabriel/Dropbox/Research/ASPIDE/Datasets/ECI Chaos/Distributed Phase 1/finalized/single_node/training/df_anomaly.csv # Define the path to the local file for training
Mode:
Training: True
Validate: False
Detect: False
#Filter:
# Columns: # Which columns remain
# - "col1"
# - "col2"
# - "col4"
# Rows:
# ld: 145607979
# gd: 145607979
# DColumns:
# Dlist: "/Users/Gabriel/Documents/workspaces/Event-Detection-Engine/experiments/ede_exp/notebooks/exp_dss/yaml_test.yaml"
# DColumns: # Which columns to delete
# - node_boot_time_seconds_10.211.55.101:9100
# - node_boot_time_seconds_10.211.55.102:9100
# - node_boot_time_seconds_10.211.55.103:9100
# Fillna: True # fill none values with 0
# Dropna: True # delete columns with None values
# LowVariance: True
# DWild:
# Regex: 'load' # filter based on wildcard (regex)
# Keep: True
#Augmentation:
# Scaler: # if not used set to false
# StandardScaler: # All scalers from scikitlearn
# copy: True
# with_mean: True
# with_std: True
# Operations:
# STD:
# - cpu_load1:
# - node_load1_10.211.55.101:9100
# - node_load1_10.211.55.102:9100
# - node_load1_10.211.55.103:9100
# - memory:
# - node_memory_Active_anon_bytes_10.211.55.101:9100
# - node_memory_Active_anon_bytes_10.211.55.101:9100
# - node_memory_Active_anon_bytes_10.211.55.101:9100
# Mean:
# - network_flags:
# - node_network_flags_10.211.55.101:9100
# - node_network_flags_10.211.55.102:9100
# - node_network_flags_10.211.55.103:9100
# - network_out:
# - node_network_mtu_bytes_10.211.55.101:9100
# - node_network_mtu_bytes_10.211.55.102:9100
# - node_network_mtu_bytes_10.211.55.103:9100
# Median:
# - memory_file:
# - node_memory_Active_file_bytes_10.211.55.101:9100
# - node_memory_Active_file_bytes_10.211.55.102:9100
# - node_memory_Active_file_bytes_10.211.55.103:9100
# - memory_buffered:
# - node_memory_Buffers_bytes_10.211.55.101:9100
# - node_memory_Buffers_bytes_10.211.55.102:9100
# - node_memory_Buffers_bytes_10.211.55.103:9100
# RemoveFiltered: True
#
# Method: !!python/object/apply:edeuser.user_methods.wrapper_add_columns # user defined operation
# kwds:
# columns: !!python/tuple [node_load15_10.211.55.101:9100, node_load15_10.211.55.102:9100]
# column_name: sum_load15
# Categorical:
# - col1
# - col2
# OH: True
# Analysis example
Analysis:
Methods:
# - Method: !!python/object/apply:edeuser.user_methods.wrapper_analysis_corr
# kwds:
# name: Pearson1
# annot: False
# cmap: RdBu_r
# columns:
# - node_load1_10.211.55.101:9100
# - node_load1_10.211.55.102:9100
# - node_load1_10.211.55.103:9100
# - node_memory_Cached_bytes_10.211.55.101:9100
# - node_memory_Cached_bytes_10.211.55.102:9100
# - node_memory_Cached_bytes_10.211.55.103:9100
# - time
# location: /Users/Gabriel/Documents/workspaces/Event-Detection-Engine/edeuser/analysis
# - Method: !!python/object/apply:edeuser.user_methods.wrapper_analysis_plot
# kwds:
# name: line1
# columns:
# - node_load1_10.211.55.101:9100
# - node_load1_10.211.55.102:9100
# - node_load1_10.211.55.103:9100
# - time
# location: /Users/Gabriel/Documents/workspaces/Event-Detection-Engine/edeuser/analysis
- Method: !!python/object/apply:edeuser.user_methods.wrapper_improved_pearson
kwds:
name: Test_Training
dcol:
- target
location: /Users/Gabriel/Documents/workspaces/Event-Detection-Engine/edeuser/analysis
show: False
- Method: !!python/object/apply:edeuser.user_methods.wrapper_rank2
kwds:
name: Test_rank
dcol:
- target
location: /Users/Gabriel/Documents/workspaces/Event-Detection-Engine/edeuser/analysis
algorithm: spearman
show: False
- Method: !!python/object/apply:edeuser.user_methods.wrapper_rank1
kwds:
name: Test_rank1
dcol:
- target
location: /Users/Gabriel/Documents/workspaces/Event-Detection-Engine/edeuser/analysis
algorithm: shapiro
- Method: !!python/object/apply:edeuser.user_methods.wrapper_pca_plot
kwds:
name: Test_PCA
location: /Users/Gabriel/Documents/workspaces/Event-Detection-Engine/edeuser/analysis
projection: 3
target: target
# show: False
- Method: !!python/object/apply:edeuser.user_methods.wrapper_manifold
kwds:
name: Test_manifold
target: target
location: /Users/Gabriel/Documents/workspaces/Event-Detection-Engine/edeuser/analysis
manifold: tsne
n_neighbors: 10
# - Method: !!python/object/apply:edeuser.user_methods.wrapper_manifold
# kwds:
# name: Test_manifold
# target: target
# location: /Users/Gabriel/Documents/workspaces/Event-Detection-Engine/edeuser/analysis
# manifold: hessian
- Method: !!python/object/apply:edeuser.user_methods.wrapper_plot_on_features
kwds:
name: complete_columns
target: target
location: /Users/Gabriel/Documents/workspaces/Event-Detection-Engine/edeuser/analysis
Solo: True
# Clustering example
Training:
Type: clustering
Method: isoforest
Export: clustering_1
MethodSettings:
n_estimators: 10
max_samples: 10
contamination: 0.1
verbose: True
bootstrap: True
Detect:
Method: isoforest
Type: clustering
Load: clustering_1
Scaler: StandardScaler # Same as for training
Point:
Memory:
cached:
gd: 231313
ld: 312334
buffered:
gd: 231313
ld: 312334
used:
gd: 231313
ld: 312334
Load:
shortterm:
gd: 231313
ld: 312334
midterm:
gd: 231313
ld: 312334
Network:
tx:
gd: 231313
ld: 312334
rx:
gd: 231313
ld: 312334
Misc:
heap: 512m
checkpoint: True
delay: 10s
interval: 30m
resetindex: False
point: False