使用tensorflow的线性回归的例子（十四）

弹性网回归Elastic Net Regression

这个脚本展示如何用TensorFlow求解弹性网回归。 =+y=Ax+b

我们使用iris数据集,特别地:

```

y = Sepal Length

x = Pedal Length, Petal Width, Sepal Width¶

#List3-42

import matplotlib.pyplot as plt

import numpy as np

import tensorflow as tf

from sklearn import datasets

from tensorflow.python.framework import ops

ops.reset_default_graph()

#tf.set_random_seed(42)

np.random.seed(42)

# Load the data

# iris.data = [(Sepal Length, Sepal Width, Petal Length, Petal Width)]

iris = datasets.load_iris()

x_vals = np.array([[x[1], x[2], x[3]] for x in iris.data])

y_vals = np.array([y[0] for y in iris.data])

def model(x,w,b):

    # Declare model operations

    model_output = tf.add(tf.matmul(x, w), b)

    return model_output

def loss1(x,y,w,b):

    # Declare the elastic net loss function

    elastic_param1 = tf.constant(1.)

    elastic_param2 = tf.constant(1.)

    l1_a_loss = tf.reduce_mean(tf.abs(w))

    l2_a_loss = tf.reduce_mean(tf.square(w))

    e1_term = tf.multiply(elastic_param1, l1_a_loss)

    e2_term = tf.multiply(elastic_param2, l2_a_loss)

    loss = tf.expand_dims(tf.add(tf.add(tf.reduce_mean(tf.square(y - model(x,w,b))), e1_term), e2_term), 0)

    return loss

def grad1(x,y,w,b):

    with tf.GradientTape() as tape:

        loss_1 = loss1(x,y,w,b)

return tape.gradient(loss_1,[w,b])

# make results reproducible

seed = 13

np.random.seed(seed)

#tf.set_random_seed(seed)

# Declare batch size

batch_size = 50

# Create variables for linear regression

w1 = tf.Variable(tf.random.normal(shape=[3,1]),tf.float32)

b1 = tf.Variable(tf.random.normal(shape=[1,1]),tf.float32)

optimizer = tf.optimizers.Adam(0.001)

# Training loop

loss_vec = []

for i in range(5000):

    rand_index = np.random.choice(len(x_vals), size=batch_size)

    rand_x = x_vals[rand_index]

    rand_y = np.transpose([y_vals[rand_index]])

    x=tf.cast(rand_x,tf.float32)

    y=tf.cast(rand_y,tf.float32)

    grads1=grad1(x,y,w1,b1)

    optimizer.apply_gradients(zip(grads1,[w1,b1]))

    #sess.run(train_step, feed_dict={x_data: rand_x, y_target: rand_y})

    temp_loss1 = loss1(x, y,w1,b1).numpy()

    #sess.run(loss, feed_dict={x_data: rand_x, y_target: rand_y})

    loss_vec.append(temp_loss1)

    if (i+1)%25==0:

        print('Step #' + str(i+1) + ' A = ' + str(w1.numpy()) + ' b = ' + str(b1.numpy()))

        print('Loss = ' + str(temp_loss1))

# Get the optimal coefficients

[[sw_coef], [pl_coef], [pw_ceof]] = w1.numpy()

[y_intercept] = b1.numpy()

# Plot loss over time

plt.plot(loss_vec, 'k-')

plt.title('Loss per Generation')

plt.xlabel('Generation')

plt.ylabel('Loss')

plt.show()