class EmgModel:
def __init__(self, labels):
self.model = Knn(k=5)
self.labels = labels
self.all_data = list()
self.all_target = list()
for pose in labels:
label = labels[pose]
data = self.load_data(label)
target = [pose] * len(data)
self.all_data += data
self.all_target += target
def run(self):
# 训练数据和测试数据分离
train_data = self.all_data[0::2]
train_target = self.all_target[0::2]
predict_data = self.all_data[1::2]
predict_target = self.all_target[1::2]
# 模型训练
self.model.fit(train_data, train_target)
# 模型预测
y = self.model.predict(predict_data)
num = 0
for i in range(len(y)):
if predict_target[i] == y[i]:
num += 1
cm = metrics.confusion_matrix(y, predict_target)
print("混淆矩阵")
print(cm)
print("分类报告")
cr = metrics.classification_report(y, predict_target)
print(cr)
print("准确率：%s %%" % ((num / len(predict_target)) * 100))
def load_data(self, label):
parent_dir = "data/%s" % label
res = []
for file in os.listdir(parent_dir):
filename = "%s/%s" % (parent_dir, file)
f = open(filename, 'r')
data = []
for line in f.readlines():
row = line.replace('\n', '').replace("[",
"").replace("]",
"").split(",")
row = [float(x) for x in row]
data.append(row)
f.close()
data = np.array(data).T
res.append(data)
return res
def main():
knn = Knn(7)
knn.fit(x, y)
img = mpimg.imread(sys.argv[1])
for j in range(img.shape[0] / 50 + 1):
for i in range(img.shape[1] / 50 + 1):
h, b = np.histogram(img[j * 50:(j * 50) + 50,
i * 50:(i * 50) + 50])
if (knn.predict(h) == 1):
img[j * 50:(j * 50) + 50, i * 50:(i * 50) + 50, 1] = 0
plt.imshow(img)
plt.show()
def cross_validation(origiData, origiLabel, splitNum):
lastIndex = 0
offset = int(len(origiData) / splitNum)
accurateRateSum = 0
for i in range(1, splitNum + 1):
# 切割数据集 分为splitNum-1个训练集和1个测试集
tempData = np.split(origiData, (lastIndex, i * offset + 1))
tempLabel = np.split(origiLabel, (lastIndex, i * offset + 1))
testData = tempData[1]
testLabel = tempLabel[1]
trainData = np.concatenate([tempData[0], tempData[2]])
trainLabel = np.concatenate([tempLabel[0], tempLabel[2]])
# 迭代区间的开始索引值
lastIndex = i * offset
# 使用knn进行预测
knn = Knn(trainData, trainLabel, 10)
predictRsl = knn.predict(testData)
accuracy = caculate_accuracy(predictRsl, testLabel)
accurateRateSum += accuracy
# 返回预测结果的平均值
return accurateRateSum / splitNum
#!/usr/bin/env python
import sys
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
from Knn import Knn
from img.data import x, y
if len(sys.argv) < 2:
print "Informar caminho da imagem"
exit()
knn = Knn(7)
knn.fit(x, y)
img = mpimg.imread(sys.argv[1])
for j in range(img.shape[0] / 50 + 1):
for i in range(img.shape[1] / 50 + 1):
h, b = np.histogram(img[j * 50:(j * 50) + 50, i * 50:(i * 50) + 50])
if (knn.predict(h) == 1):
img[j * 50:(j * 50) + 50, i * 50:(i * 50) + 50, 1] = 0
plt.imshow(img)
plt.show()
import matplotlib.pyplot as plt
iris = datasets.load_digits()
# print(print(iris))
X, y = iris.data, iris.target
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=1000)
# print(X_train.shape)
# print(X_train[0])
# plt.figure()
# plt.scatter(X[:,[0]], X[:,[1]], c=y)
# plt.show()
acc = 0
for k in [3, 5, 7]:
clf = Knn(k)
clf.fit(X_train, y_train)
predictions = clf.predict(X_test)
t_acc = np.sum(predictions == y_test) / len(y_test)
if t_acc > acc:
acc = t_acc
best_k = k
print(acc)
print(best_k)
