-
Notifications
You must be signed in to change notification settings - Fork 2
/
experiment22_GNB.py
80 lines (66 loc) · 2.42 KB
/
experiment22_GNB.py
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
import csm
import numpy as np
import helper as h
from tqdm import tqdm
import multiprocessing
from csm import OOB, UOB, SampleWeightedMetaEstimator, Dumb, MDET, SEA, StratifiedBagging
from strlearn.evaluators import TestThenTrain
from sklearn.naive_bayes import GaussianNB
from strlearn.metrics import (
balanced_accuracy_score,
f1_score,
geometric_mean_score_1,
precision,
recall,
specificity
)
import sys
from sklearn.base import clone
from sklearn.tree import DecisionTreeClassifier
from skmultiflow.trees import HoeffdingTree
if len(sys.argv) != 2:
print("PODAJ RS")
exit()
else:
random_state = int(sys.argv[1])
print(random_state)
# Select streams and methods
streams = h.toystreams(random_state)
print(len(streams))
none_knorau2 = SEA(base_estimator=StratifiedBagging(base_estimator=GaussianNB(
), random_state=42, oversampler="None"), oversampled="None", des="KNORAU2")
rus_knorau2 = SEA(base_estimator=StratifiedBagging(base_estimator=GaussianNB(
), random_state=42, oversampler="RUS"), oversampled="RUS", des="KNORAU2")
cnn_knorau2 = SEA(base_estimator=StratifiedBagging(base_estimator=GaussianNB(
), random_state=42, oversampler="CNN"), oversampled="CNN", des="KNORAU2")
none_knorae2 = SEA(base_estimator=StratifiedBagging(base_estimator=GaussianNB(
), random_state=42, oversampler="None"), oversampled="None", des="KNORAE2")
rus_knorae2 = SEA(base_estimator=StratifiedBagging(base_estimator=GaussianNB(
), random_state=42, oversampler="RUS"), oversampled="RUS", des="KNORAE2")
cnn_knorae2 = SEA(base_estimator=StratifiedBagging(base_estimator=GaussianNB(), random_state=42, oversampler = "CNN"), oversampled="CNN" ,des="KNORAE2")
clfs = (none_knorau2, rus_knorau2, cnn_knorau2, none_knorae2, rus_knorae2, cnn_knorae2)
# Define worker
def worker(i, stream_n):
stream = streams[stream_n]
cclfs = [clone(clf) for clf in clfs]
print("Starting stream %i/%i" % (i + 1, len(streams)))
eval = TestThenTrain(metrics=(
balanced_accuracy_score,
geometric_mean_score_1,
f1_score,
precision,
recall,
specificity
))
eval.process(
stream,
cclfs
)
print("Done stream %i/%i" % (i + 1, len(streams)))
results = eval.scores
np.save("results/experiment22_GNB/%s" % stream, results)
jobs = []
for i, stream_n in enumerate(streams):
p = multiprocessing.Process(target=worker, args=(i, stream_n))
jobs.append(p)
p.start()