forked from cnchi/HappyML
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathclassification.py
147 lines (114 loc) · 4.24 KB
/
classification.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
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
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
# -*- coding: utf-8 -*-
"""
Created on Tue Jul 30 16:15:31 2019
@author: 俊男
"""
# In[] Naive Bayesian Classifier default with Gaussian Kernal
from sklearn.naive_bayes import BernoulliNB, MultinomialNB, GaussianNB
import pandas as pd
class NaiveBayesClassifier:
__classifier = None
__y_columns = None
def __init__(self, type="gaussian"):
algorithm_dict = {
"bernoulli" : BernoulliNB(),
"multinomial" : MultinomialNB(),
"gaussian" : GaussianNB()
}
self.__classifier = algorithm_dict[type]
@property
def classifier(self):
return self.__classifier
@classifier.setter
def classifier(self, classifier):
self.__classifier = classifier
def fit(self, x_train, y_train):
self.classifier.fit(x_train, y_train.values.ravel())
self.__y_columns = y_train.columns
return self
def predict(self, x_test):
return pd.DataFrame(self.classifier.predict(x_test), index=x_test.index, columns=self.__y_columns)
# In[] Support Vecor Machine (SVM) Classifier default with Gaussian Radial Basis Function (Gaussian RBF)
from sklearn.svm import SVC
import time
class SVM:
__classifier = None
__penalty_C = None
__kernel = None
__degree = None
__gamma = None
__coef0 = None
__y_columns = None
def __init__(self, C=1.0, kernel="rbf", degree=3, gamma="scale", coef0=0.0, random_state=int(time.time())):
self.__penalty_C = C
self.__kernel = kernel
self.__degree = degree
self.__gamma = gamma
self.__coef0 = coef0
self.__classifier = SVC(C=self.__penalty_C,
kernel=self.__kernel,
degree=self.__degree,
gamma=self.__gamma,
coef0=self.__coef0,
random_state=random_state)
@property
def classifier(self):
return self.__classifier
@classifier.setter
def classifier(self, classifier):
self.__classifier = classifier
def fit(self, x_train, y_train):
self.classifier.fit(x_train, y_train.values.ravel())
self.__y_columns = y_train.columns
return self
def predict(self, x_test):
return pd.DataFrame(self.classifier.predict(x_test), index=x_test.index, columns=self.__y_columns)
# In[] Decision Tree
from sklearn.tree import DecisionTreeClassifier
import time
class DecisionTree:
__classifier = None
__criterion = None
__y_columns = None
def __init__(self, criterion="entropy", random_state=int(time.time())):
self.__criterion = criterion
self.__classifier = DecisionTreeClassifier(criterion=self.__criterion, random_state=random_state)
@property
def classifier(self):
return self.__classifier
@classifier.setter
def classifier(self, classifier):
self.__classifier = classifier
def fit(self, x_train, y_train):
self.classifier.fit(x_train, y_train)
self.__y_columns = y_train.columns
return self
def predict(self, x_test):
return pd.DataFrame(self.classifier.predict(x_test), index=x_test.index, columns=self.__y_columns)
# In[] Random Forest
from sklearn.ensemble import RandomForestClassifier
import time
class RandomForest:
__classifier = None
__n_estimators = None
__criterion = None
__y_columns = None
def __init__(self, n_estimators=10, criterion="entropy"):
self.__n_estimators = n_estimators
self.__criterion = criterion
self.__classifier = RandomForestClassifier(n_estimators=self.__n_estimators, criterion=self.__criterion, random_state=int(time.time()))
@property
def classifier(self):
return self.__classifier
@classifier.setter
def classifier(self, classifier):
self.__classifier = classifier
@property
def n_estimators(self):
return self.__n_estimators
def fit(self, x_train, y_train):
self.classifier.fit(x_train, y_train.values.ravel())
self.__y_columns = y_train.columns
return self
def predict(self, x_test):
return pd.DataFrame(self.classifier.predict(x_test), index=x_test.index, columns=self.__y_columns)