TreeEnsembleClassifier - 1 vs 3

Files changed (1) hide show
  1. TreeEnsembleClassifier1 → TreeEnsembleClassifier3 +13 -1
TreeEnsembleClassifier1 → TreeEnsembleClassifier3 RENAMED
@@ -1 +1 @@
1
- Tree Ensemble classifier. Returns the top class for each of N inputs.
1
+ Tree Ensemble classifier. Returns the top class for each of N inputs.
2
2
  The attributes named 'nodes_X' form a sequence of tuples, associated by
3
3
  index into the sequences, which must all be of equal length. These tuples
4
4
  define the nodes.
5
5
  Similarly, all fields prefixed with 'class_' are tuples of votes at the leaves.
6
6
  A leaf may have multiple votes, where each vote is weighted by
7
7
  the associated class_weights index.
8
8
  One and only one of classlabels_strings or classlabels_int64s
9
9
  will be defined. The class_ids are indices into this list.
10
+ All fields ending with <i>_as_tensor</i> can be used instead of the
11
+ same parameter without the suffix if the element type is double and not float.
10
12
  **Attributes**
11
13
  * **base_values**:
14
+ Base values for classification, added to final class score; the size
15
+ must be the same as the classes or can be left unassigned (assumed
16
+ 0)
17
+ * **base_values_as_tensor**:
12
18
  Base values for classification, added to final class score; the size
13
19
  must be the same as the classes or can be left unassigned (assumed
14
20
  0)
15
21
  * **class_ids**:
16
22
  The index of the class list that each weight is for.
17
23
  * **class_nodeids**:
18
24
  node id that this weight is for.
19
25
  * **class_treeids**:
20
26
  The id of the tree that this node is in.
21
27
  * **class_weights**:
28
+ The weight for the class in class_id.
29
+ * **class_weights_as_tensor**:
22
30
  The weight for the class in class_id.
23
31
  * **classlabels_int64s**:
24
32
  Class labels if using integer labels.<br>One and only one of the
25
33
  'classlabels_*' attributes must be defined.
26
34
  * **classlabels_strings**:
27
35
  Class labels if using string labels.<br>One and only one of the
28
36
  'classlabels_*' attributes must be defined.
29
37
  * **nodes_falsenodeids**:
30
38
  Child node if expression is false.
31
39
  * **nodes_featureids**:
32
40
  Feature id for each node.
33
41
  * **nodes_hitrates**:
42
+ Popularity of each node, used for performance and may be omitted.
43
+ * **nodes_hitrates_as_tensor**:
34
44
  Popularity of each node, used for performance and may be omitted.
35
45
  * **nodes_missing_value_tracks_true**:
36
46
  For each node, define what to do in the presence of a missing value:
37
47
  if a value is missing (NaN), use the 'true' or 'false' branch based
38
48
  on the value in this array.<br>This attribute may be left undefined,
39
49
  and the defalt value is false (0) for all nodes.
40
50
  * **nodes_modes**:
41
51
  The node kind, that is, the comparison to make at the node. There is
42
52
  no comparison to make at a leaf node.<br>One of 'BRANCH_LEQ',
43
53
  'BRANCH_LT', 'BRANCH_GTE', 'BRANCH_GT', 'BRANCH_EQ', 'BRANCH_NEQ',
44
54
  'LEAF'
45
55
  * **nodes_nodeids**:
46
56
  Node id for each node. Ids may restart at zero for each tree, but it
47
57
  not required to.
48
58
  * **nodes_treeids**:
49
59
  Tree id for each node.
50
60
  * **nodes_truenodeids**:
51
61
  Child node if expression is true.
52
62
  * **nodes_values**:
63
+ Thresholds to do the splitting on for each node.
64
+ * **nodes_values_as_tensor**:
53
65
  Thresholds to do the splitting on for each node.
54
66
  * **post_transform**:
55
67
  Indicates the transform to apply to the score. <br> One of 'NONE,'
56
68
  'SOFTMAX,' 'LOGISTIC,' 'SOFTMAX_ZERO,' or 'PROBIT.'
57
69
  **Inputs**
58
70
  * **X** (heterogeneous) - **T1**:
59
71
  Input of shape [N,F]
60
72
  **Outputs**
61
73
  * **Y** (heterogeneous) - **T2**:
62
74
  N, Top class for each point
63
75
  * **Z** (heterogeneous) - **tensor(float)**:
64
76
  The class score for each class, for each point, a tensor of shape
65
77
  [N,E].
66
78
  **Type Constraints**
67
79
  * **T1** in (
68
80
  tensor(double),
69
81
  tensor(float),
70
82
  tensor(int32),
71
83
  tensor(int64)
72
84
  ):
73
85
  The input type must be a tensor of a numeric type.
74
86
  * **T2** in (
75
87
  tensor(int64),
76
88
  tensor(string)
77
89
  ):
78
90
  The output type will be a tensor of strings or integers, depending
79
91
  on which of the classlabels_* attributes is used.