forked from prashant-kikani/temperature-prediction
-
Notifications
You must be signed in to change notification settings - Fork 0
/
mainfile1.py
168 lines (145 loc) · 5.26 KB
/
mainfile1.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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
import numpy as np
import nltk
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn import preprocessing, svm
from sklearn.tree import DecisionTreeClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.neighbors import KNeighborsClassifier
from nltk.classify.scikitlearn import SklearnClassifier
from sklearn.naive_bayes import MultinomialNB, GaussianNB, BernoulliNB
# from sklearn.cross_validation import cross_val_score
from sklearn import linear_model
from sklearn.svm import SVC
class classify(object):
def __init__(self, X, y):
self.X = np.array(X)
self.y = np.array(y)
# print(self.X)
# print(self.y)
self.acc = []
def split(self, testpr = 0.3):
self.X_tr, self.X_te, self.y_tr, self.y_te = train_test_split(self.X, self.y, test_size=testpr)
# print(self.X_te, self.X_tr, self.y_tr, self.y_te)
self.X_tr = np.array(self.X_tr, dtype='int32')
self.X_te = np.array(self.X_te, dtype='int32')
self.y_tr = np.array(self.y_tr, dtype='int32')
self.y_te = np.array(self.y_te, dtype='int32')
self.length = len(self.X_tr)
def getbest(self):
data = self.X
data1 = data
# data1[c] = data1[c].append(len(data1[c]),self.y[c])
# data = data1
# print(data)
'''
data = []
for c in range(self.length):
p = ()
p += self.X_te[c]
p += self.y_te[c]
data.append(p)
nbc = nltk.NaiveBayesClassifier.train(data[:self.length * 0.7])
nbcacc = nltk.classify.accuracy(nbc, data[self.length * 0.7:])
# nbcacc = accuracy_score(self.y_te, ynbc)
self.acc.append(("NaiveBayes", nbcacc))
'''
knn = KNeighborsClassifier(n_neighbors=3)
# score = cross_val_score(knn, self.X_tr, self.y_tr, cv=3, scoring='accuracy')
# print("scores ", score)
knn.fit(self.X_tr, self.y_tr)
yknn = knn.predict(self.X_te)
knnacc = accuracy_score(self.y_te, yknn)
self.acc.append(("knn", knnacc))
clf = svm.SVR()
clf.fit(self.X_tr, self.y_tr)
svr = clf.score(self.X_te, self.y_te)
self.acc.append(("SVR", svr))
clf = LinearDiscriminantAnalysis()
clf.fit(self.X_tr, self.y_tr)
lda = clf.score(self.X_te, self.y_te)
self.acc.append(("LDA", lda))
clf = GaussianNB()
clf.fit(self.X_tr, self.y_tr)
xx = clf.predict(self.X_te)
gnb = accuracy_score(self.y_te, xx)
self.acc.append(("GaussianNB", gnb))
clf = BernoulliNB()
clf.fit(self.X_tr, self.y_tr)
xx = clf.predict(self.X_te)
gnb = accuracy_score(self.y_te, xx)
self.acc.append(("BernoulliNB", gnb))
clf = MultinomialNB()
clf.fit(self.X_tr, self.y_tr)
xx = clf.predict(self.X_te)
gnb = accuracy_score(self.y_te, xx)
self.acc.append(("MultinomialNB", gnb))
clf = linear_model.LinearRegression()
clf.fit(self.X_tr, self.y_tr)
lrgacc = clf.score(self.X_te, self.y_te)
self.acc.append(("LinearReg", lrgacc))
clf = linear_model.LogisticRegression()
clf.fit(self.X_tr.astype('int'), self.y_tr.astype('int'))
logacc = clf.score(self.X_te.astype('int'), self.y_te.astype('int'))
self.acc.append(("LogisticReg", logacc))
clf = linear_model.SGDClassifier()
clf.fit(self.X_tr, self.y_tr)
ysgd = clf.predict(self.X_te)
sgdacc = accuracy_score(self.y_te, ysgd)
self.acc.append(("SGDC", sgdacc))
clf = DecisionTreeClassifier()
clf.fit(self.X_tr, self.y_tr)
dtc = clf.score(self.X_te, self.y_te)
self.acc.append(("DecisionTree", dtc))
clf = SVC(kernel='rbf')
clf.fit(self.X_tr, self.y_tr)
ysvc = clf.predict(self.X_te)
svcaccr = accuracy_score(self.y_te, ysvc)
self.acc.append(("SVC-rbf", svcaccr))
clf = SVC(kernel='linear')
clf.fit(self.X_tr, self.y_tr)
ysvc = clf.predict(self.X_te)
svcaccl = accuracy_score(self.y_te, ysvc)
self.acc.append(("SVC-linear", svcaccl))
'''clf = SVC(kernel='poly', degree=5)
clf.fit(self.X_tr, self.y_tr)
ysvc = clf.predict(self.X_te)
print("svcp", ysvc)
svcaccp = accuracy_score(self.y_te, ysvc)
self.acc.append(("SVC-poly", svcaccp))'''
self.acc.sort(key=lambda tup: tup[1], reverse=True)
for i in self.acc:
print(i[0], " ", i[1] * 100)
'''
file = pd.read_csv('cars.csv', na_values=" NaN")
file = file.replace('', np.nan)
cy = file['Cylinders']
dis = file['Displacement']
hor = file['Horsepower']
wei = file['Weight']
acce = file['Acceleration']
lenn = len(cy)
X = []
y1 = file['MPG']
y = []
for i in y1:
y.append(i)
for i in range(lenn):
pp = []
# wei[i] = int(wei[i])
pp.append(cy[i])
pp.append(dis[i])
pp.append(hor[i])
pp.append(wei[i])
pp.append(acce[i])
X.append(pp)
# print(X)
# print(y)
# X = [[-1, -1, 0, 5, 7, 8], [-2, -1, 2, 3, 8, -1], [1, 1, 0, 0, 2, 3], [2, 1, 2, 5, 0, -1], [2, 1, 2, 0, 2, 3],
# [3, 8, -1, -1, -1, 0]]
# y = [1, 1, 2, 2, 3, 3]
obj = classify(X, y)
obj.split(0.25)
obj.getbest()
'''