#用tensorflow實現(xiàn)彈性網(wǎng)絡(luò)算法(多變量) 
#使用鳶尾花數(shù)據(jù)集，后三個特征作為特征，用來預(yù)測第一個特征。 
 
 
#1 導(dǎo)入必要的編程庫，創(chuàng)建計算圖，加載數(shù)據(jù)集 
import matplotlib.pyplot as plt 
import tensorflow as tf 
import numpy as np 
from sklearn import datasets 
from tensorflow.python.framework import ops 
 
ops.get_default_graph() 
sess = tf.Session() 
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]) 
 
 
#2 聲明學(xué)習(xí)率，批量大小，占位符和模型變量,模型輸出 
learning_rate = 0.001 
batch_size = 50 
x_data = tf.placeholder(shape=[None, 3], dtype=tf.float32) #占位符大小為3 
y_target = tf.placeholder(shape=[None, 1], dtype=tf.float32) 
A = tf.Variable(tf.random_normal(shape=[3,1])) 
b = tf.Variable(tf.random_normal(shape=[1,1])) 
model_output = tf.add(tf.matmul(x_data, A), b) 
 
 
#3 對于彈性網(wǎng)絡(luò)回歸算法，損失函數(shù)包括L1正則和L2正則 
elastic_param1 = tf.constant(1.) 
elastic_param2 = tf.constant(1.) 
l1_a_loss = tf.reduce_mean(abs(A)) 
l2_a_loss = tf.reduce_mean(tf.square(A)) 
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_target - model_output)), e1_term), e2_term), 0) 
 
 
 
#4 初始化變量， 聲明優(yōu)化器， 然后遍歷迭代運行， 訓(xùn)練擬合得到參數(shù) 
init = tf.global_variables_initializer() 
sess.run(init) 
my_opt = tf.train.GradientDescentOptimizer(learning_rate) 
train_step = my_opt.minimize(loss) 
 
loss_vec = [] 
for i in range(1000): 
   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]]) 
   sess.run(train_step, feed_dict={x_data:rand_x, y_target:rand_y}) 
   temp_loss = sess.run(loss, feed_dict={x_data:rand_x, y_target:rand_y}) 
   loss_vec.append(temp_loss) 
   if (i+1)%250 == 0: 
     print('Step#' + str(i+1) +'A = ' + str(sess.run(A)) + 'b=' + str(sess.run(b))) 
     print('Loss= ' +str(temp_loss)) 
      
 
#現(xiàn)在能觀察到， 隨著訓(xùn)練迭代后損失函數(shù)已收斂。 
plt.plot(loss_vec, 'k--') 
plt.title('Loss per Generation') 
plt.xlabel('Generation') 
plt.ylabel('Loss') 
plt.show()