This repository has been archived by the owner on Mar 10, 2022. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 1
/
small_ole.yaml
65 lines (58 loc) · 1.71 KB
/
small_ole.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
dataset:
# Type: String
# Meaning: Name of the used dataset
# Possible values: String ended with a ".csv" extension
filename: small_ole.csv
model_details:
# Type: String
# Meaning: Objective of the model
# Possible values: "MALICE", "CLASSIFICATION"
objective: MALICE
# Type: Boolean
# Meaning: Activation status of the retraining
# Possible values: "True", "False"
retraining: False
# Type: Nested lists
# Meaning: Combination of extractors and their preprocessors
# Possible values: All implemented extractors and preprocessors
extractors_preprocessors:
- GENERAL_OLE_DETAILS:
- N_GRAMS
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- IDENTITY
- N_GRAMS
- K_BINS_DISCRETIZER
- IDENTITY
- OLE_MACROS:
- N_GRAMS
dimensionality_reduction:
# Type: String
# Meaning: Dimensionality reduction algorithm
# Possible values: All implemented algorithms
algorithm: PCA
# Type: Integer or float
# Meaning: Number of components to return or included variation (PCA-only)
# Possible values: Between 0 and the number of the extracted features
components_count: 0.999999
machine_learning:
# Type: String
# Meaning: Machine learning algorithm
# Possible values: All implemented algorithms
algorithm: RANDOM_FOREST
# Type: Float
# Meaning: Ratio of samples used for training
# Possible values: Between 0 and 1
split_ratio: 0.8