TensorFlow로 Logistic Classification의 구현하기

Logistic classification

Tensorflow

-예습 복습에 따른 시험 합격 불합격 예측

x_data=[예습횟수,복습횟수]

y_data=[불합격or합격]

import os
 
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
 
import tensorflow as tf
 
# y_data는 0과 1의 값만 가진다.
x_data = [[1, 2], [2, 3], [3, 1], [4, 3], [5, 3], [6, 2]]
y_data = [[0], [0], [0], [1], [1], [1]]
 
# placeholder : Shape 주의! x_data [6, 2] / y_data [6, 1]
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 : Sigmoid 사용
# 직접 구현할 경우 : tf.div(1., 1. + tf.exp(tf.matmul(X, W) + b))
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))
 
# Minimize : Gradient Descent 사용
train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost)
 
# 정확도 측정 (hypothesis > 0.5 기준)
# tf.cast() : true/false를 1.0/0.0 으로 반환
predicted = tf.cast(hypothesis > 0.5, dtype=tf.float32)
accuracy = tf.reduce_mean(tf.cast(tf.equal(predicted, Y), dtype=tf.float32))
 
# 세션 시작
with tf.Session() as sess:
    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)
            # 10000 0.158035
 
    # 정확도 측정
    h, c, a = sess.run([hypothesis, predicted, accuracy], feed_dict={X:x_data, Y:y_data})
    print("\nHypothesis: ", h, "\nCorrect (Y): ", c, "\nAccuracy: ", a)
    # Hypothesis: [[0.03441257]
    #              [0.16354376]
    #              [0.32198268]
    #              [0.77366924]
    #              [0.93461043]
    #              [0.97851723]]
    # Correct(Y): [[0.]
    #              [0.]
    #              [0.]
    #              [1.]
    #              [1.]
    #              [1.]]
    # Accuracy: 1.0
 
 

-당뇨 데이터를 활용한 당뇨 예측

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
 
import tensorflow as tf
import numpy as np
 
# 당뇨병 데이터 읽어오기
xy = np.loadtxt('data-03-diabetes.csv', delimiter=',', dtype=np.float32)
x_data = xy[:, 0:-1]
y_data = xy[:, [-1]]
 
# Placeholders : Shape 주의! 총 8개의 x_data와 1개의 y_data
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
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))
train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost)
 
# 정확도 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))
 
# 세션 시작
with tf.Session() as sess:
    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)
            # 10000 0.480384
 
    # 정확도 77%
    _, _, a = sess.run([hypothesis, predicted, accuracy], feed_dict={X: x_data, Y: y_data})
    print("Accuracy: ", a)
    # Accuracy: 0.769433