def predict(modelpath):
trainx, trainy = Dataset.GetDatafromDict()
X_train, X_test, Y_train, Y_test = train_test_split(trainx,
trainy,
test_size=0.3,
random_state=0)
nomtrainx, nomtrainy = Preprocess(X_test, Y_test)
model = joblib.load(filename=modelpath)
# TestSample=len(Y_test)
# possample=[ Y_train[i] for i in range(TestSample) if Y_test[i]==0]
# negsample=[ Y_train[i] for i in range(TestSample) if Y_test[i]==1]
TestSample = len(Y_test)
possample = np.sum(Y_test)
negsample = TestSample - possample
res = model.predict(nomtrainx)
TP, TN, FP, FN = 0, 0, 0, 0
for id, i in enumerate(res):
if res[i] == Y_test[id] and Y_test[id] == 1:
TP += 1
elif res[i] == Y_test[id] and Y_test[id] == 0:
TN += 1
elif res[i] != Y_test[id] and Y_test[id] == 0:
FP += 1
else:
FN += 1
print("预测结果 :{}---原始数据:{}".format(STATUS[res[id]], STATUS[Y_test[id]]))
print("result:acc={} , recall={}".format((TP + TN) / TestSample,
TP / (TP + FN)))
def train():
# trainx,trainy=CreatTrainDataset()
trainx, trainy = Dataset.GetDatafromDict()
X_train, X_test, Y_train, Y_test = train_test_split(trainx,
trainy,
test_size=0.3,
random_state=0)
#保持样本的随机性
radom_sample = [i for i in range(len(Y_train))]
random.shuffle(radom_sample)
X_train = X_train[radom_sample]
Y_train = Y_train[radom_sample]
nomtrainx, nomtrainy = Preprocess(X_train, Y_train)
print(nomtrainx.shape, nomtrainy.shape)
# 1、创建了一个线性逻辑分类器实例去拟合数据
logreg = linear_model.LogisticRegression(C=1e5, max_iter=200)
# 2、测试数据集
test_data = np.expand_dims(trainx[2], axis=0)
# 3、训练拟合函数
logreg.fit(nomtrainx, nomtrainy)
# 4、保存模型
joblib.dump(filename='LR.model', value=logreg)
# 5、预测结果
out = logreg.predict(test_data)
print(out)
return weight
def loadData():
train_x = []
train_y = []
fileIn = open('./data/testdata.txt')
for line in fileIn.readlines():
lineArr = line.strip().split()
train_x.append([1.0, float(lineArr[0]), float(lineArr[1])])
train_y.append(float(lineArr[2]))
return mat(train_x), mat(train_y).transpose()
if __name__ == "__main__":
STATUS = ['非ST', 'ST']
save_model = "weights.pkl"
train, label = Dataset.GetDatafromDict()
trainarrayx = mat(train)
labelarray = mat(label).transpose()
logistreg = LR(trainarrayx, labelarray)
# print(trainarrayx.shape,labelarray.shape)
opts = {"alpha": 0.001, "maxIter": 200, "optimizeType": "gradDescent"}
logistreg.train(opts, save_model)
weights = logistreg.load_weight(save_model)
res = logistreg.predict(weights, trainarrayx, labelarray)
for i in range(len(res)):
print("预测结果 :{}---原始数据:{}".format(STATUS[res[i]], STATUS[label[i]]))
