trainingTest_IrisFiles.py
1.58 KB
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
from sklearn.naive_bayes import MultinomialNB, BernoulliNB
def scores(list1, list2):
errores = 0
aciertos = 0
if len(list1) != len(list2):
print("ERROR. LENGTH MISMATCH")
for i in range(len(list1)):
if list1[i] == list2[i]:
aciertos += 1
else:
errores += 1
cocienteErrores = errores / len(list1)
return [aciertos, errores, cocienteErrores]
data = []
lista = []
with open("C:\Users\cmendezc\Dropbox (UNAM-CCG)\Actividades_CCG\LICENCIATURA_LCG\BioInfo-I\lcg-bioinfoI-bionlp\clasificacion-automatica\iris-datasetdata.txt", encoding='utf8') \
as dataFile:
for line in dataFile:
listaFloat = []
line = line.strip('\n')
lista = line.split('\t')
for elem in lista:
listaFloat.append(float(elem))
data.append(listaFloat)
print(data)
target = []
with open("C:\\Users\\cmendezc\\Documents\\GENOMICAS\\LICENCIATURA_LCGPDCB\\dataSet_Iris\\true_Classes.txt", encoding='utf8') \
as classFile:
for line in classFile:
line = line.strip('\n')
target.append(line)
myMultinomialNB = MultinomialNB()
myBernoulliNB = BernoulliNB()
y_pred = myMultinomialNB.fit(data, target).predict(data)
'''
for i in range(len(iris.target)):
print(str(iris.target[i]) + "\t" + str(y_pred[i]) + "\t" + str(iris.data[i]))
'''
myRandomForest = RandomForestClassifier()
y_pred = myRandomForest.fit(data, target).predict(data)
results = scores(target, y_pred)
print("Errores: {}".format(results[1]))
print("Aciertos: {}".format(results[0]))
print("Cociente error: {}".format(results[2]))