모두를 위한 딥러닝 제13강 ML lab 05: TensorFlow로 Logistic Classification의 구현하기 (new)

# bias를 제거한 Logistic Regression 공식 

- 아래 2개의 예제들은 bias를 제거하지 않은 원래의 식으로 진행하였음.

# Logistic Regression 모델 구현
- 입력 feature가 2개인 Binary Classifier 모델 구현

import tensorflow as tf

x_data = [[1, 2],
          [2, 3],
          [3, 1],
          [4, 3],
          [5, 3],
          [6, 2]]
y_data = [[0],
          [0],
          [0],
          [1],
          [1],
          [1]]

# placeholders for a tensor that will be always fed.
X = tf.placeholder(tf.float32, shape=[None, 2])
Y = tf.placeholder(tf.float32, shape=[None, 1])

W = tf.Variable(tf.random_normal([2, 1]), name='weight')
b = tf.Variable(tf.random_normal([1]), name='bias')

# Hypothesis using sigmoid: tf.div(1., 1. + tf.exp(tf.matmul(X, W)))
hypothesis = tf.sigmoid(tf.matmul(X, W) + b)

# cost/loss function
cost = -tf.reduce_mean(Y * tf.log(hypothesis) + (1 - Y) * tf.log(1 - hypothesis))

# Gradient descent
train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost)

# Accuracy computation
# True if hypothesis>0.5 else False
predicted = tf.cast(hypothesis > 0.5, dtype=tf.float32)
accuracy = tf.reduce_mean(tf.cast(tf.equal(predicted, Y), dtype=tf.float32))

# Launch graph
with tf.Session() as sess:
    # Initialize TensorFlow variables
    sess.run(tf.global_variables_initializer())

    for step in range(10001):
        cost_val, _ = sess.run([cost, train], feed_dict={X: x_data, Y: y_data})
        if step % 200 == 0:
            print(step, cost_val)

    # Accuracy report
    h, c, a = sess.run([hypothesis, predicted, accuracy], feed_dict={X: x_data, Y: y_data})
    print("\nHypothesis: ", h, "\nCorrect (Y): ", c, "\nAccuracy: ", a)

'''
0 1.73078
200 0.571512
400 0.507414
600 0.471824
800 0.447585
...
9200 0.159066
9400 0.15656
9600 0.154132
9800 0.151778
10000 0.149496

Hypothesis:  [[ 0.03074029]
 [ 0.15884677]
 [ 0.30486736]
 [ 0.78138196]
 [ 0.93957496]
 [ 0.98016882]]
Correct (Y):  [[ 0.]
 [ 0.]
 [ 0.]
 [ 1.]
 [ 1.]
 [ 1.]]
Accuracy:  1.0
'''

# Logistic Regression 모델 구현
- 입력 feature가 8개인 Binary Classifier 모델 구현(당뇨병 진단)

import tensorflow as tf
import numpy as np

xy = np.loadtxt('data-03-diabetes.csv', delimiter=',', dtype=np.float32)
x_data = xy[:, 0:-1]
y_data = xy[:, [-1]]

print(x_data.shape, y_data.shape)

# placeholders for a tensor that will be always fed.
X = tf.placeholder(tf.float32, shape=[None, 8])
Y = tf.placeholder(tf.float32, shape=[None, 1])

W = tf.Variable(tf.random_normal([8, 1]), name='weight')
b = tf.Variable(tf.random_normal([1]), name='bias')

# Hypothesis using sigmoid: tf.div(1., 1. + tf.exp(-tf.matmul(X, W)))
hypothesis = tf.sigmoid(tf.matmul(X, W) + b)

# cost/loss function
cost = -tf.reduce_mean(Y * tf.log(hypothesis) + (1 - Y) * tf.log(1 - hypothesis))

# Gradient descent를 이용한 W갱신
train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost)

# Accuracy computation
# True if hypothesis>0.5 else False
predicted = tf.cast(hypothesis > 0.5, dtype=tf.float32)
accuracy = tf.reduce_mean(tf.cast(tf.equal(predicted, Y), dtype=tf.float32))

# Launch graph
with tf.Session() as sess:
    # Initialize TensorFlow variables
    sess.run(tf.global_variables_initializer())

    for step in range(10001):
        cost_val, _ = sess.run([cost, train], feed_dict={X: x_data, Y: y_data})
        if step % 200 == 0:
            print(step, cost_val)

    # Accuracy report
    h, c, a = sess.run([hypothesis, predicted, accuracy],
                       feed_dict={X: x_data, Y: y_data})
    print("\nHypothesis: ", h, "\nCorrect (Y): ", c, "\nAccuracy: ", a)

'''
0 0.82794
200 0.755181
400 0.726355
600 0.705179
800 0.686631
...
9600 0.492056
9800 0.491396
10000 0.490767

...

 [ 1.]
 [ 1.]
 [ 1.]]
Accuracy:  0.762846
'''

사진 참고 : https://youtu.be/2FeWGgnyLSw