def get_confusion_matrix(model, test_images, test_labels):
""" 用测试集评估模型，得到混淆矩阵
Args:
model (NearestNeighbor): 训练好的模型
test_images (list[np.ndarray]): 测试集图片
test_labels (list[int]): 测试集标签
Returns:
np.array: 混淆矩阵
"""
pred_labels = []
for i, image in enumerate(test_images):
pred_labels.append(predict(model, image))
if (i + 1) % 10 == 0:
print(i)
return ConfMat(test_labels, pred_labels)
from data import Data
from naivebayes import NaiveBayes
from maxapost import MaxAPost
from confmat import ConfMat
filename = "datasets/weatherNominal.td"
## filename = "datasets/titanic.td"
## filename = "datasets/cmc.td"
## filename = "datasets/german.td"
## filename = "datasets/markbasksex.td"
d = Data(filename)
d.report()
## pr = NaiveBayes(d)
pr = MaxAPost(d)
pr.train()
## pr.show()
cm = ConfMat(pr.clsscnts)
for (v, c_true) in d.test_set:
c_pred = pr.predict(v)[0]
# print(v, c_pred, "( true class:", c_true, ")")
cm.mat[c_pred, c_true] += 1
# pr.show()
cm.report()
from naivebayes import NaiveBayes
from maxapost import MaxAPost
from data import Data
#filename = "ds/weatherNominalTr.txt"
filename = "ds/titanicTr.txt"
d = Data(filename, 75)
prmap = MaxAPost(d)
prmap.train()
prnb = NaiveBayes(d)
prnb.train()
cmmap = ConfMat(prmap.clsscnts)
cmnb = ConfMat(prnb.clsscnts)
comparing = set([])
for (v, c_true) in d.test_set:
c_pred_map = tuple(prmap.predict(v))
c_pred_nb = tuple(prnb.predict(v))
if len(c_pred_map) and len(c_pred_nb):
warn = (c_pred_map[0] != c_pred_nb[0])
cmmap.mat[c_pred_map[0], c_true] += 1
cmnb.mat[c_pred_nb[0], c_true] += 1
else:
warn = True
if warn:
comparing.add((v, c_true, c_pred_map, c_pred_nb))
print