mlsauce/examples/stump_classifier.py at master · Techtonique/mlsauce · GitHub

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
import numpy as np
from sklearn.datasets import load_digits, load_breast_cancer, load_wine, load_iris
from sklearn.model_selection import train_test_split
from time import time
from os import chdir
from sklearn import metrics
import os

print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")


#wd="/workspace/mlsauce/mlsauce/examples"
#
#chdir(wd)

import mlsauce as ms


# data 1
breast_cancer = load_breast_cancer()
X = breast_cancer.data
y = breast_cancer.target
# split data into training test and test set
np.random.seed(15029)
X_train, X_test, y_train, y_test = train_test_split(X, y,
                                                    test_size=0.2)

obj = ms.StumpClassifier(bins=-1)
print(obj.get_params())
start = time()
obj.fit(X_train, y_train)
print(time()-start)
start = time()
print(obj.score(X_test, y_test))
print(time()-start)


# data 2
wine = load_wine()
Z = wine.data
t = wine.target
np.random.seed(879423)
X_train, X_test, y_train, y_test = train_test_split(Z, t,
                                                    test_size=0.2)

obj = ms.StumpClassifier(bins=-1)
start = time()
obj.fit(X_train, y_train)
print(time()-start)
start = time()
print(obj.score(X_test, y_test))
print(time()-start)


# data 3
iris = load_iris()
Z = iris.data
t = iris.target
np.random.seed(734563)
X_train, X_test, y_train, y_test = train_test_split(Z, t,
                                                    test_size=0.2)


obj = ms.StumpClassifier(bins=-1)
start = time()
obj.fit(X_train, y_train)
print(time()-start)
start = time()
print(obj.score(X_test, y_test))
print(time()-start)


# data 4
digits = load_digits()
X = digits.data
y = digits.target
# split data into training test and test set
np.random.seed(15029)
X_train, X_test, y_train, y_test = train_test_split(X, y,
                                                    test_size=0.2)

obj = ms.StumpClassifier(bins=-1)
print(obj.get_params())
start = time()
obj.fit(X_train, y_train)
print(time()-start)
start = time()
print(obj.score(X_test, y_test))
print(time()-start)