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
|
"""
This module contains the TreePredictor class which is used for prediction.
"""
# Author: Nicolas Hug
import numpy as np
from .common import Y_DTYPE
from ._predictor import _predict_from_numeric_data
from ._predictor import _predict_from_binned_data
from ._predictor import _compute_partial_dependence
class TreePredictor:
"""Tree class used for predictions.
Parameters
----------
nodes : ndarray of PREDICTOR_RECORD_DTYPE
The nodes of the tree.
"""
def __init__(self, nodes):
self.nodes = nodes
def get_n_leaf_nodes(self):
"""Return number of leaves."""
return int(self.nodes['is_leaf'].sum())
def get_max_depth(self):
"""Return maximum depth among all leaves."""
return int(self.nodes['depth'].max())
def predict(self, X):
"""Predict raw values for non-binned data.
Parameters
----------
X : ndarray, shape (n_samples, n_features)
The input samples.
Returns
-------
y : ndarray, shape (n_samples,)
The raw predicted values.
"""
out = np.empty(X.shape[0], dtype=Y_DTYPE)
_predict_from_numeric_data(self.nodes, X, out)
return out
def predict_binned(self, X, missing_values_bin_idx):
"""Predict raw values for binned data.
Parameters
----------
X : ndarray, shape (n_samples, n_features)
The input samples.
missing_values_bin_idx : uint8
Index of the bin that is used for missing values. This is the
index of the last bin and is always equal to max_bins (as passed
to the GBDT classes), or equivalently to n_bins - 1.
Returns
-------
y : ndarray, shape (n_samples,)
The raw predicted values.
"""
out = np.empty(X.shape[0], dtype=Y_DTYPE)
_predict_from_binned_data(self.nodes, X, missing_values_bin_idx, out)
return out
def compute_partial_dependence(self, grid, target_features, out):
"""Fast partial dependence computation.
Parameters
----------
grid : ndarray, shape (n_samples, n_target_features)
The grid points on which the partial dependence should be
evaluated.
target_features : ndarray, shape (n_target_features)
The set of target features for which the partial dependence
should be evaluated.
out : ndarray, shape (n_samples)
The value of the partial dependence function on each grid
point.
"""
_compute_partial_dependence(self.nodes, grid, target_features, out)
|
