第7章 Tensorflow支持向量机

##Tensorflow实现支持向量机

#现有一组鸢尾花数据集，这组数据集有100个样本点，我们用SVM来预测这些鸢尾花数据集中哪些是山鸢尾花。

#（1）加载数据集
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
from sklearn import datasets
sess = tf.Session()
#加载数据
# iris.data = [(Sepal Length, Sepal Width, Petal Length, Petal Width)]
iris = datasets.load_iris()
x_vals = np.array([[x[0],x[3]] for x in iris.data])
y_vals = np.array([1 if y==0 else -1 for y in iris.target])

#（2）分离测试集和训练集
train_indices = np.random.choice(len(x_vals),
                                round(len(x_vals)*0.8),
                                 replace=False)
test_indices = np.array(list(set(range(len(x_vals)))-set(train_indices)))
x_vals_train = x_vals[train_indices]
x_vals_test = x_vals[test_indices]
y_vals_train = y_vals[train_indices]
y_vals_test = y_vals[test_indices]

#（3）定义模型和loss函数
batch_size = 100
#初始化batch
x_data = tf.placeholder(shape=[None,2],dtype=tf.float32)
y_target = tf.placeholder(shape=[None,1],dtype=tf.float32)
#创建变量
A = tf.Variable(tf.random_normal(shape=[2,1]))
b = tf.Variable(tf.random_normal(shape=[1,1]))
#定义线性模型
model_output = tf.subtract(tf.matmul(x_data,A),b)
#声明向量L2范数函数的平方
l2_norm = tf.reduce_sum(tf.square(A))
#Loss = max(0,1-pred*actual)+alpha*L2_norm(A)^2
alpha = tf.constant([0.01])
classification_term = tf.reduce_mean(tf.maximum(0.,tf.subtract(1.,tf.multiply(model_output,y_target))))
loss = tf.add(classification_term,tf.multiply(alpha,l2_norm))

#（4）训练数据
my_opt = tf.train.GradientDescentOptimizer(0.01)
train_step = my_opt.minimize(loss)
init  = tf.global_variables_initializer()
sess.run(init)
#训练循环体
loss_vec = []
train_accuracy = []
test_accuracy = []
for i in range(20000):
    rand_index = np.random.choice(len(x_vals_train),size=batch_size)
    rand_x = x_vals_train[rand_index]
    rand_y = np.transpose([y_vals_train[rand_index]])
    sess.run(train_step,feed_dict={x_data:rand_x,y_target:rand_y})

#（5）绘制图像
[[a1],[a2]] = sess.run(A)
[[b]] = sess.run(b)
slope = -a2 / a1;
y_intercept = b / a1
best_fit = []
x1_vals = [d[1] for d in x_vals]
for i in x1_vals:
    best_fit.append(slope*i+y_intercept)
#单独的I.setosa
setosa_x = [d[1] for i,d in enumerate(x_vals) if y_vals[i] == 1]
setosa_y = [d[0] for i,d in enumerate(x_vals) if y_vals[i] == 1]
not_setosa_x = [d[1] for i,d in enumerate(x_vals) if y_vals[i] == -1]
not_setosa_y = [d[0] for i,d in enumerate(x_vals) if y_vals[i] == -1]
plt.plot(setosa_x,setosa_y,'o',label='I.setosa')
plt.plot(not_setosa_x,not_setosa_y,'x',label='Non-setosa')
plt.plot(x1_vals,best_fit,'r-',label='Linear Separator',linewidth=3)
plt.ylim([0,10])
plt.legend(loc='lower right')
plt.title('Sepal Length vs Petal Width')
plt.xlabel('Petal Width')
plt.ylabel('Sepal Length')
plt.show()

输出结果：