TimeEval-algorithms/dbstream/manifest.json at main · TimeEval/TimeEval-algorithms · GitHub

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
{
    "title": "DBStream",
    "description": "A simple density-based clustering algorithm that assigns data points to micro-clusters with a given radius and implements shared-density-based reclustering.",
    "inputDimensionality": "multivariate",
    "version": "0.3.0",
    "authors": "Michael Hahsler, Matthew Bolanos, John Forrest, Matthias Carnein, Dennis Assenmacher, Dalibor Krleža, Richard Schulz",
    "language": "R",
    "type": "Detector",
    "learningType": "Unsupervised",
    "mainFile": "algorithm.r",
    "executionStep": {
        "modelInput": "none",
        "parameters": [
            {
                "name": "window_size",
                "type": "int",
                "defaultValue": 20,
                "optional": "True",
                "description": "The length of the subsequences the dataset should be splitted in."
            },
            {
                "name": "radius",
                "type": "float",
                "defaultValue": 0.1,
                "optional": "True",
                "description": "The radius of micro-clusters."
            },
            {
                "name": "lambda",
                "type": "float",
                "defaultValue": 0.001,
                "optional": "True",
                "description": "The lambda used in the fading function."
            },
            {
                "name": "distance_metric",
                "type": "enum[Euclidean,Manhattan,Maximum]",
                "defaultValue": "Euclidean",
                "optional": "True",
                "description": "The metric used to calculate distances. If shared_density is TRUE this has to be Euclidian."
            },
            {
                "name": "shared_density",
                "type": "boolean",
                "defaultValue": "True",
                "optional": "True",
                "description": "Record shared density information. If set to TRUE then shared density is used for reclustering, otherwise reachability is used (overlapping clusters with less than r∗(1−alpha) distance are clustered together)"
            },
            {
                "name": "n_clusters",
                "type": "int",
                "defaultValue": 0,
                "optional": "True",
                "description": "The number of macro clusters to be returned if macro is true."
            },
            {
                "name": "alpha",
                "type": "float",
                "defaultValue": 0.1,
                "optional": "True",
                "description": "For shared density: The minimum proportion of shared points between to clus-ters to warrant combining them (a suitable value for 2D data is .3). For reacha-bility clustering it is a distance factor"
            },
            {
                "name": "min_weight",
                "type": "float",
                "defaultValue": 0.0,
                "optional": "True",
                "description": "The proportion of the total weight a macro-cluster needs to have not to be noise(between 0 and 1)."
            },
            {
                "name": "random_state",
                "type": "int",
                "defaultValue": 42,
                "optional": "true",
                "description": "Seed for random number generation."
            }
        ]
    }
}