戴明回归算法和线性回归算法的区别在于损失函数;戴明回归最小化到回归直线的(垂直)距离,线性回归算法则是最小化到回归直线的竖直距离.
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)sess = tf.Session()iris = datasets.load_iris()
x_vals = np.array([x[3] for x in iris.data])
y_vals = np.array([y[0] for y in iris.data])
batch_size = 50
x_data = tf.placeholder(shape=[None, 1], dtype=tf.float32)
y_target = tf.placeholder(shape=[None, 1], dtype=tf.float32)
A = tf.Variable(tf.random_normal(shape=[1,1]))
b = tf.Variable(tf.random_normal(shape=[1,1]))
model_output = tf.add(tf.matmul(x_data, A), b)
# Declare Demming loss function
demming_numerator = tf.abs(tf.subtract(y_target, tf.add(tf.matmul(x_data, A), b)))
demming_denominator = tf.sqrt(tf.add(tf.square(A),1))
loss = tf.reduce_mean(tf.truediv(demming_numerator, demming_denominator))
my_opt = tf.train.GradientDescentOptimizer(0.15)
train_step = my_opt.minimize(loss)
init = tf.global_variables_initializer()
sess.run(init)
# Training loop
loss_vec = []
for i in range(1000):
rand_index = np.random.choice(len(x_vals), size=batch_size)
rand_x = np.transpose([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)%50 == 0:
print('Step #' + str(i+1) + ' A = ' + str(sess.run(A)) + ' b = ' + str(sess.run(b)))
print('Loss = ' + str(temp_loss))
# Get the optimal coefficients
[slope] = sess.run(A)
[y_intercept] = sess.run(b)
# Get best fit line
best_fit = []
for i in x_vals:
best_fit.append(slope*i+y_intercept)