-
Notifications
You must be signed in to change notification settings - Fork 0
/
6_ede_classification_predict_y3.yaml
193 lines (180 loc) · 5.74 KB
/
6_ede_classification_predict_y3.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
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": '{__name__=~"node.+"}[1m]'}
MetricsInterval: "1m" # Metrics datapoint interval definition
QSize: 0
Index: time
QDelay: "10s" # Polling period for metrics fetching
# Local: /Users/Gabriel/Documents/workspaces/Event-Detection-Engine/data/demo_data.csv # Define the path to the local file for training
Mode:
Training: False
Validate: False
Detect: True
Filter:
# 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 woth none values
DWild:
Regex: '10.251.0.114' # filter based on wildcard (regex)
Keep: True
DColumns:
Dlist: /Users/Gabriel/Documents/workspaces/Event-Detection-Engine/data/low_variance.yaml
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
# Classification example
#Training:
# Type: classification
# Method: !!python/object/apply:sklearn.ensemble.AdaBoostClassifier # DONT forger ../apply
# _sklearn_version: '0.22.1'
# n_estimators: 100
# learning_rate: 1
# algorithm: SAMME.R
# Target: target
# Export: classification_2
# ValidRatio: 0.2
# TrainScore: True # expensive if set to false only test scores are computed
# ReturnEstimators: True
# CV:
# Type: StratifiedKFold # user defined all from sklearn, if int than used standard
# Params:
# n_splits: 5
# shuffle: True
# random_state: 5
# Scorers:
# Scorer_list:
# - Scorer:
# Scorer_name: AUC
# skScorer: roc_auc
# - Scorer:
# Scorer_name: Jaccard_Index
# skScorer: jaccard
# - Scorer:
# Scorer_name: Balanced_Acc
# skScorer: balanced_accuracy
# User_scorer1: f1_score # key is user defined, can be changed same as Scorer_name
Training:
Type: classification
Method: !!python/object/apply:sklearn.ensemble.RandomForestClassifier # DONT forger ../apply
_sklearn_version: '0.24.2'
n_estimators: 100
criterion: "gini"
min_sample_split: 2
min_sample_leaf: 1
max_features: "log2"
n_jobs: -1
random_state: 42
verbose: 1
Target: target
Export: classification_y2
ValidRatio: 0.2
TrainScore: True # expensive if set to false only test scores are computed
ReturnEstimators: True
CV:
Type: StratifiedKFold # user defined all from sklearn, if int than used standard
Params:
n_splits: 5
shuffle: True
random_state: 5
Scorers:
Scorer_list:
- Scorer:
Scorer_name: F1_weighted
skScorer: f1_weighted
- Scorer:
Scorer_name: Jaccard_Index
skScorer: jaccard_weighted # changes in scoring sklearn, for multiclass add suffix micro, weighted or sample
- Scorer:
Scorer_name: AUC
skScorer: roc_auc_ovr_weighted
User_scorer1: balanced_accuracy_score # key is user defined, can be changed same as Scorer_name
LearningCurve:
sizes: !!python/object/apply:numpy.core.function_base.linspace
kwds:
start: 0.3
stop: 1.0
num: 10
scorer: f1_weighted
n_jobs: 5
ValidationCurve:
param_name: n_estimators
param_range:
- 10
- 20
- 60
- 100
- 200
- 600
scoring: f1_weighted
n_jobs: 8
PrecisionRecallCurve: 1
ROCAUC: 1
RFE:
scorer: f1_weighted
step: 10
DecisionBoundary: 1
Verbose: 1
Detect:
Method: RandomForestClassifier
Type: classification
Load: classification_y2_0
Scaler: StandardScaler # Same as for training
# Analysis: True # Start Shapely value based analysis
Analysis: # if plotting of heatmap, summary and feature importance is require, if not set False or use previous example
Plot: True
Misc:
heap: 512m
checkpoint: True
delay: 15s
interval: 30m
resetindex: False
point: False