使用python神经网络对鸢尾花数据进行学习并预测

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from keras.models import Sequential
from keras import optimizers, losses
from keras.layers import Dense
from sklearn.model_selection import train_test_split

#获取鸢尾花数据
data = load_iris()

#将数据拆分
iris_target = data['target']
iris_data = data['data']


#将数据分离一部分用于测试预测
s, s_test, e, e_test = train_test_split(iris_data, iris_target, test_size=0.1)
#获取优化器
adam = optimizers.Adam()

#创建学习模型
module = Sequential()

#添加‘神经元’
module.add(Dense(input_shape=(4,), units=20, activation="relu"))
module.add(Dense(units=20, activation="relu"))
module.add(Dense(units=3, activation='sigmoid'))

#部署损失函数  以及优化器
module.compile(loss='sparse_categorical_crossentropy', optimizer=adam)

#传入数据开始'学习'
module.fit(s, e, batch_size=10, epochs=1000)

#进行预测
end = module.predict(s_test)
end = np.argmax(end, axis=1)
print(list(end))
print(list(e_test))