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
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
|
from sklearn.datasets import make_classification
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import RandomForestClassifier as RFC
from sklearn.svm import SVC
from bayes_opt import BayesianOptimization
from colorama import Fore
def get_data():
"""Synthetic binary classification dataset."""
data, targets = make_classification(
n_samples=1000,
n_features=45,
n_informative=12,
n_redundant=7,
random_state=134985745,
)
return data, targets
def svc_cv(C, gamma, data, targets):
"""SVC cross validation.
This function will instantiate a SVC classifier with parameters C and
gamma. Combined with data and targets this will in turn be used to perform
cross validation. The result of cross validation is returned.
Our goal is to find combinations of C and gamma that maximizes the roc_auc
metric.
"""
estimator = SVC(C=C, gamma=gamma, random_state=2)
cval = cross_val_score(estimator, data, targets, scoring='roc_auc', cv=4)
return cval.mean()
def rfc_cv(n_estimators, min_samples_split, max_features, data, targets):
"""Random Forest cross validation.
This function will instantiate a random forest classifier with parameters
n_estimators, min_samples_split, and max_features. Combined with data and
targets this will in turn be used to perform cross validation. The result
of cross validation is returned.
Our goal is to find combinations of n_estimators, min_samples_split, and
max_features that minimizes the log loss.
"""
estimator = RFC(
n_estimators=n_estimators,
min_samples_split=min_samples_split,
max_features=max_features,
random_state=2
)
cval = cross_val_score(estimator, data, targets,
scoring='neg_log_loss', cv=4)
return cval.mean()
def optimize_svc(data, targets):
"""Apply Bayesian Optimization to SVC parameters."""
def svc_crossval(expC, expGamma):
"""Wrapper of SVC cross validation.
Notice how we transform between regular and log scale. While this
is not technically necessary, it greatly improves the performance
of the optimizer.
"""
C = 10 ** expC
gamma = 10 ** expGamma
return svc_cv(C=C, gamma=gamma, data=data, targets=targets)
optimizer = BayesianOptimization(
f=svc_crossval,
pbounds={"expC": (-3, 2), "expGamma": (-4, -1)},
random_state=1234,
verbose=2
)
optimizer.maximize(n_iter=10)
print("Final result:", optimizer.max)
def optimize_rfc(data, targets):
"""Apply Bayesian Optimization to Random Forest parameters."""
def rfc_crossval(n_estimators, min_samples_split, max_features):
"""Wrapper of RandomForest cross validation.
Notice how we ensure n_estimators and min_samples_split are casted
to integer before we pass them along. Moreover, to avoid max_features
taking values outside the (0, 1) range, we also ensure it is capped
accordingly.
"""
return rfc_cv(
n_estimators=int(n_estimators),
min_samples_split=int(min_samples_split),
max_features=max(min(max_features, 0.999), 1e-3),
data=data,
targets=targets,
)
optimizer = BayesianOptimization(
f=rfc_crossval,
pbounds={
"n_estimators": (10, 250),
"min_samples_split": (2, 25),
"max_features": (0.1, 0.999),
},
random_state=1234,
verbose=2
)
optimizer.maximize(n_iter=10)
print("Final result:", optimizer.max)
if __name__ == "__main__":
data, targets = get_data()
print(Fore.YELLOW + "--- Optimizing SVM ---")
optimize_svc(data, targets)
print(Fore.GREEN("--- Optimizing Random Forest ---"))
optimize_rfc(data, targets)
|
