TensorFlow 단순회귀분석

1 개요

TensorFlow 단순선형회귀분석

• 텐서플로우는 '통계분석 패키지'라기 보다는 '범용모델 학습 라이브러리'이므로 접근방법이 상당히 다르다.

2 예시 1

import tensorflow as tf

learning_rate = 0.02
x_data = [1,2,3]
y_data = [1,2,3]

W = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
b = tf.Variable(tf.zeros([1]))
y = W * x_data + b

loss = tf.reduce_mean(tf.square(y - y_data))
train = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss)

sess = tf.Session()
sess.run( tf.global_variables_initializer() )

for step in range(2001):
    sess.run(train)
    if step % 200 == 0:
        print(step, sess.run(W), sess.run(b))
# 0 [ 0.69967157] [ 0.0295405]
# 200 [ 0.97727495] [ 0.05165951]
# 400 [ 0.99133259] [ 0.0197031]
# 600 [ 0.99669421] [ 0.00751483]
# 800 [ 0.99873918] [ 0.00286615]
# 1000 [ 0.99951905] [ 0.00109322]
# 1200 [ 0.99981648] [ 0.00041713]
# 1400 [ 0.99992996] [ 0.00015933]
# 1600 [ 0.99997312] [  6.09436174e-05]
# 1800 [ 0.99998975] [  2.34372128e-05]
# 2000 [ 0.99999601] [  8.96838174e-06]

→ 수행결과는 약간 다를 수 있음 (W 초기값이 랜덤이기 때문)

3 예시 2

import tensorflow as tf

learning_rate = 0.02
x_data = [1.47, 1.50, 1.52, 1.55, 1.57, 1.60, 1.63, 1.65, 1.68, 1.70, 1.73, 1.75, 1.78, 1.80, 1.83]
y_data = [52.21, 53.12, 54.48, 55.84, 57.20, 58.57, 59.93, 61.29, 63.11, 64.47, 66.28, 68.10, 69.92, 72.19, 74.46]

W = tf.Variable(0.0)
b = tf.Variable(0.0)
y = W * x_data + b

loss = tf.reduce_mean(tf.square(y - y_data))
train = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss)

sess = tf.Session()
sess.run( tf.global_variables_initializer() )

for step in range(80001):
    sess.run(train)
    if step % 10000 == 0:
        print(step, sess.run(W), sess.run(b))
# 0 4.12865 2.48312
# 10000 52.1455 -23.9476
# 20000 58.7961 -34.9614
# 30000 60.6001 -37.9489
# 40000 61.0897 -38.7597
# 50000 61.2225 -38.9796
# 60000 61.2588 -39.0398
# 70000 61.2619 -39.0449
# 80000 61.2619 -39.0449

4 같이 보기

• TensorFlow 회귀분석
• sklearn 단순선형회귀분석
• statsmodels 단순선형회귀분석