-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathede_hpo.yaml
147 lines (135 loc) · 3.23 KB
/
ede_hpo.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
Connector:
PREndpoint: hal720m.sage.ieat.ro
Dask:
SchedulerEndpoint: local # if not local add DASK schedueler endpoint
Scale: 3 # Number of workers if local othervise 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
Augmentation:
Scaler: # if not used set to false
StandardScaler: # All scalers from scikitlearn
copy: True
with_mean: True
with_std: true
# For HPO methods
Training:
Type: hpo
HPOMethod: Random # random, grid, bayesian, tpot
HPOParam:
n_iter: 2
n_jobs: -1
refit: Balanced_Acc # if multi metric used, refit should be metric name, mandatory
verbose: True
Method: randomforest
ParamDistribution:
n_estimators:
- 10
- 100
max_depth:
- 2
- 3
Target: target
Export: hpo_1
# CV: 8
CV:
Type: StratifiedKFold # user defined all from sklearn
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
# TPOT Optimizer
#Training:
# Type: tpot
# TPOTParam:
# generations: 2
# population_size: 2
# offspring_size: 2
# mutation_rate: 0.9
# crossover_rate: 0.1
# scoring: balanced_accuracy # Scoring different from HPO check TPOT documentation
# max_time_mins: 1
# max_eval_time_mins: 5
# random_state: 42
# n_jobs: -1
# verbosity: 2
# config_dict: TPOT light # "TPOT light", "TPOT MDR", "TPOT sparse" or None
# use_dask: True
# Target: target
# Export: tpotopt
# # CV: 8
# CV:
# Type: StratifiedKFold # user defined all from sklearn
# Params:
# n_splits: 5
# shuffle: True
# random_state: 5
Detect:
Method: RandomForest
Type: classification
Load: hpo_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
# Not yet Implemented
#Validation:
# DataSource: /path/to/data # if datasource is not defined use default from data connector, last column is ground truth named "Target"
# Treashold: 0.2 # improvement percent
# Models:
# - m1
# - m2
Misc:
heap: 512m
checkpoint: True
delay: 15s
interval: 30m
resetindex: False
point: False