数据挖掘从入门到放弃（七）：TensorFlow和keras实现线性回归LinearRegression

from __future__ import absolute_import, division, print_function
import tensorflow as tf
import numpy as np
rng = np.random
 
# Parameters.
learning_rate = 0.01
training_steps = 1000
display_step = 50
 
# Training Data.
X = np.array([1.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,7.042,10.791,5.313,7.997,5.654,9.27,3.1])
Y = np.array([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,2.827,3.465,1.65,2.904,2.42,2.94,1.3])
 
# Weight and Bias, initialized randomly.
# 手动设置权重w和偏置b
W = tf.Variable(rng.randn(), name="weight")
b = tf.Variable(rng.randn(), name="bias")
 
# Linear regression (Wx + b).
# 定义线性函数
def linear_regression(x):
    return W * x + b
 
# Mean square error.
def mean_square(y_pred, y_true):
    return tf.reduce_mean(tf.square(y_pred - y_true))
 
# Stochastic Gradient Descent Optimizer.
optimizer = tf.optimizers.SGD(learning_rate)
 
# Optimization process. 
def run_optimization():
    # Wrap computation inside a GradientTape for automatic differentiation.
    with tf.GradientTape() as g:
        pred = linear_regression(X)
        loss = mean_square(pred, Y)
 
    # Compute gradients.
    gradients = g.gradient(loss, [W, b])
    
    # Update W and b following gradients.
    optimizer.apply_gradients(zip(gradients, [W, b]))
 
 
# Run training for the given number of steps.
# 开始训练，按照预定义的步长
for step in range(1, training_steps + 1):
    # Run the optimization to update W and b values.
    run_optimization()
    
    if step % display_step == 0:
        pred = linear_regression(X)
        loss = mean_square(pred, Y)
        print("step: %i, loss: %f, W: %f, b: %f" % (step, loss, W.numpy(), b.numpy()))
 
 
import matplotlib.pyplot as plt
# Graphic display 画图看效果
plt.plot(X, Y, 'ro', label='Original data')
plt.plot(X, np.array(W * X + b), label='Fitted line')
plt.legend()
plt.show()

# tf中reduce函数计算均值
tf.reduce_mean(
  input_tensor, 
  axis=None, 
  keep_dims=False, 
  name=None, 
  reduction_indices=None
)
 
# 举个例子：n的输出[1 5 6]
m = np.array([(1,7,4),(2,3,9)])
n=tf.reduce_mean(m,axis=0)
print(m,n)

#举个例子：计算y=x^2在x = 3时的导数：
 
x = tf.constant(3.0)
with tf.GradientTape() as g:
  g.watch(x)
  y = x * x
dy_dx = g.gradient(y, x) 
# y’ = 2*x = 2*3 = 6
 
 
#GradientTape会监控可训练变量：
with tf.GradientTape() as tape:
    predictions = model(images)
    loss = loss_object(labels, predictions)
gradients = tape.gradient(loss, model.trainable_variables)

import tensorflow as tf
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import pandas as pd
import seaborn as sns
 
# X和Y的值
X = np.array([1.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,
              7.042,10.791,5.313,7.997,5.654,9.27,3.1])
Y = np.array([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,
              2.827,3.465,1.65,2.904,2.42,2.94,1.3])
 
data=pd.DataFrame(np.vstack((X,Y))).T # 两个array合并后转秩，才能得到一个df
data.rename(columns={0:'data_input',1:'data_output'},inplace=True) # 队列名重命名
print(data)
 
#  画个图瞅瞅分布
sns.scatterplot(x="data_input",y="data_output",data=data)
 
# 定义顺序模型方法（装饰类），中间层即输出层1，输入层1，
model=tf.keras.Sequential()
model.add(tf.keras.layers.Dense(1,input_shape=(1,)))
model.summary()
# 设置优化器和损失函数
model.compile(optimizer="adam",loss="mse")
history=model.fit(x,y,epochs=500)
 
# 画图看效果
data_predict=model.predict(data.data_input)
plt.plot(data.data_input,data.data_output, 'ro', label='Original data')
plt.plot(data.data_input, data_predict, label='Fitted line')
plt.legend()
plt.show()

# 两个array合并后转秩，才能得到一个df
data=pd.DataFrame(np.vstack((X,Y))).T 
 
# 熟练操作dataframe函数
data.rename(columns={0:'data_input',1:'data_output'},inplace=True) 
 
# 随机生成dataframe
df = pd.DataFrame(np.random.randint(70,100,(3,5)), 
                  index=["地区1", "地区2", "地区3"], 
                  columns=["北京","天津", "上海","沈阳", "广州"])