import keras
import numpy as np
import matplotlib.pyplot as plt

from keras.models import Sequential
from keras.layers import Dense

#  生成随机点
x_data = np.random.rand(100)
noise = np.random.normal(0,0.01,x_data.shape)
y_data = x_data*0.1+0.5+noise

# 显示
plt.scatter(x_data,y_data)
plt.show()

# 构建序列模型
model = Sequential()
# 添加一个全连接层 
model.add(Dense(units=1,input_dim=1))
# 模型参数
model.compile(optimizer='sgd',loss='mse')

for step in range(3001):
    cost = model.train_on_batch(x_data,y_data)
    # 每500个batch打印一次cost
    if step%500==0:
        print('cost:',cost)

# 打印权值和偏置
W,b = model.layers[0].get_weights()
print('W:',W,'b:',b)


y_pred = model.predict(x_data)
plt.scatter(x_data,y_data)
plt.plot(x_data,y_pred,'r-',lw=3)
plt.show()

#  生成随机点
x_data = np.linspace(-0.5,0.5,200)
noise = np.random.normal(0,0.02,x_data.shape)
y_data = np.square(x_data)+noise

# 显示
plt.scatter(x_data,y_data)
plt.show()

from keras.layers import Dense,Activation
from keras.optimizers import SGD

# 构建序列模型
model = Sequential()
# 添加一个全连接层 
model.add(Dense(units=10,input_dim=1,activation='tanh')) # activation很重要
model.add(Dense(units=1,activation='tanh'))
sgd = SGD(lr=0.5)  # 很重要
# 模型参数
model.compile(optimizer=sgd,loss='mse')

for step in range(3001):
    cost = model.train_on_batch(x_data,y_data)
    # 每500个batch打印一次cost
    if step%500==0:
        print('cost:',cost)

# 打印权值和偏置
#W,b = model.layers[0].get_weights()
#print('W:',W,'b:',b)


y_pred = model.predict(x_data)
plt.scatter(x_data,y_data)
plt.plot(x_data,y_pred,'r-',lw=3)
plt.show()