-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path7_ede_hpo_y2.yaml
131 lines (120 loc) · 3.38 KB
/
7_ede_hpo_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
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:
Fillna: True # fill none values with 0
Dropna: True # delete columns woth none values
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, evol
# HPOParam:
# n_iter: 2
# n_jobs: -1
# refit: F1_weighted # 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:
# Type: StratifiedKFold # user defined all from sklearn
# 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
Training:
Type: hpo
HPOMethod: Evol # Random, Grid, Bayesian, tpot, Evol
HPOParam:
n_jobs: 1 # must be number, not -1 for all
scoring: f1_weighted
gene_mutation_prob: 0.20
gene_crossover_prob: 0.5
tournament_size: 4
generations_number: 30
population_size: 40 # if multi metric used, refit should be metric name, mandatory
verbose: 4
Method: randomforest
ParamDistribution:
n_estimators:
- 10
- 100
max_depth:
- 2
- 3
Target: target
Export: hpo_1_y2
CV:
Type: StratifiedKFold # user defined all from sklearn
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
Detect:
Method: RandomForest
Type: classification
Load: hpo_1
Scaler: StandardScaler # Same as for training
Misc:
heap: 512m
checkpoint: True
delay: 15s
interval: 30m
resetindex: False
point: False