[ML] TensorFlow로 파일에서 데이터 읽어오기

우선 파일을 읽어오는 소스는 다음과 같다.

file_input_linear_regression.py

# Lab 4 Multi-variable linear regression
import tensorflow as tf
import numpy as np
xy = np.loadtxt('data-01-test-score.csv', delimiter=',', dtype=np.float32)
x_data = xy[:, 0:-1]
y_data = xy[:, [-1]]
# placeholders for a tensor that will be always fed.
X = tf.placeholder(tf.float32, shape=[None, 3])
Y = tf.placeholder(tf.float32, shape=[None, 1])
W = tf.Variable(tf.random_normal([3, 1]), name='weight')
b = tf.Variable(tf.random_normal([1]), name='bias')
# Hypothesis
hypothesis = tf.matmul(X, W) + b
# Simplified cost/loss function
cost = tf.reduce_mean(tf.square(hypothesis - Y))
# Minimiz
optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-5)
train = optimizer.minimize(cost)
# Launch the graph in a session.
sess = tf.Session()
 
# Initializes global variables in the graph.
sess.run(tf.global_variables_initializer())
 
# Set up feed_dict variables inside the loop.
for step in range(2001):
    cost_val, hy_val, _ = sess.run([cost, hypothesis, train], feed_dict={X: x_data, Y: y_data})
    if step % 10 == 0:
        print(step, "Cost : ", cost_val, "\nPrediction:\n", hy_val)
# Ask my score
print("Your score will be ", sess.run(hypothesis, feed_dict={X: [[100, 70, 101]]}))
 
print("Other scores will be ", sess.run(hypothesis, feed_dict={X: [[60, 70, 110], [90, 100, 80]]}))
 

data-01-test-score.csv 파일은 다음과 같다.

reader_linear_regression.py

import tensorflow as tf
 
filename_queue = tf.train.string_input_producer(
    ['data-01-test-score.csv'], shuffle=False, name='filename_queue')
 
reader = tf.TextLineReader()
key, value = reader.read(filename_queue)

 
# Default values, in case of empty columns. Also specifies the type of the decoded result.
record_defaults = [[0.], [0.], [0.], [0.]]
xy = tf.decode_csv(value, record_defaults=record_defaults)
 
# collect batches of csv in
train_x_batch, train_y_batch = \
    tf.train.batch([xy[0:-1], xy[-1:]], batch_size=10)
 
# placeholders for a tensor that will be always fed.
X = tf.placeholder(tf.float32, shape=[None, 3])
Y = tf.placeholder(tf.float32, shape=[None, 1])
 
W = tf.Variable(tf.random_normal([3, 1]), name='weight')
b = tf.Variable(tf.random_normal([1]), name='bias')
 
# Hypothesis
hypothesis = tf.matmul(X, W) + b
 
# Simplified cost/loss function
cost = tf.reduce_mean(tf.square(hypothesis - Y))
 
# Minimize
optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-5)
train = optimizer.minimize(cost)
 
# Launch the graph in a session.
sess = tf.Session()
# Initializes global variables in the graph.
sess.run(tf.global_variables_initializer())
 
# Start populating the filename queue.
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
 
for step in range(2001):
    x_batch, y_batch = sess.run([train_x_batch, train_y_batch])
    cost_val, hy_val, _ = sess.run([cost, hypothesis, train], feed_dict={X: x_batch, Y: y_batch})
    if step % 10 == 0:
        print(step, "Cost: ", cost_val, "\nPrediction:\n", hy_val)
 
coord.request_stop()
coord.join(threads)