Bases: Metalearner_Base
A Gaussian Process based Metalearner.
This class should be passed to an ensemble function/class like Stacking for combining predictions.
Warning
Can only be utilized for binary and multi-class tasks.
Does not work on multi-label annotations!
Reference - Implementation
https://scikit-learn.org/stable/modules/generated/sklearn.gaussian_process.GaussianProcessClassifier.html
Scikit-learn: Machine Learning in Python, Pedregosa et al., JMLR 12, pp. 2825-2830, 2011.
https://jmlr.csail.mit.edu/papers/v12/pedregosa11a.html
Source code in aucmedi/ensemble/metalearner/gaussian_process.py
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 | class GaussianProcess(Metalearner_Base):
""" A Gaussian Process based Metalearner.
This class should be passed to an ensemble function/class like Stacking for combining predictions.
!!! warning
Can only be utilized for binary and multi-class tasks.
Does not work on multi-label annotations!
???+ abstract "Reference - Implementation"
https://scikit-learn.org/stable/modules/generated/sklearn.gaussian_process.GaussianProcessClassifier.html
Scikit-learn: Machine Learning in Python, Pedregosa et al., JMLR 12, pp. 2825-2830, 2011.
https://jmlr.csail.mit.edu/papers/v12/pedregosa11a.html
"""
#---------------------------------------------#
# Initialization #
#---------------------------------------------#
def __init__(self):
self.model = GaussianProcessClassifier(random_state=0,
multi_class="one_vs_rest")
#---------------------------------------------#
# Training #
#---------------------------------------------#
def train(self, x, y):
# Preprocess to sparse encoding
y = np.argmax(y, axis=-1)
# Train model
self.model = self.model.fit(x, y)
#---------------------------------------------#
# Prediction #
#---------------------------------------------#
def predict(self, data):
# Compute prediction probabilities via fitted model
pred = self.model.predict_proba(data)
# Return results as NumPy array
return pred
#---------------------------------------------#
# Dump Model to Disk #
#---------------------------------------------#
def dump(self, path):
# Dump model to disk via pickle
with open(path, "wb") as pickle_writer:
pickle.dump(self.model, pickle_writer)
#---------------------------------------------#
# Load Model from Disk #
#---------------------------------------------#
def load(self, path):
# Load model from disk via pickle
with open(path, "rb") as pickle_reader:
self.model = pickle.load(pickle_reader)
|