[머신러닝/딥러닝] 파일에서 Tensorflow로 데이터 읽어오기

※ 김성훈 교수님의 [모두를 위한 딥러닝] 강의 정리

 - https://www.youtube.com/watch?reload=9&v=BS6O0zOGX4E&feature=youtu.be&list=PLlMkM4tgfjnLSOjrEJN31gZATbcj_MpUm&fbclid=IwAR07UnOxQEOxSKkH6bQ8PzYj2vDop_J0Pbzkg3IVQeQ_zTKcXdNOwaSf_k0

 - 참고자료 : Andrew Ng's ML class

  1) https://class.coursera.org/ml-003/lecture

  2) http://holehouse.org/mlclass/ (note)

 

1. Loading data from file

import tensorflow as tf

import numpy as np

tf.set_random_seed(777) # for reproducibility

xy = np.loadtxt('data-01-test-score.csv', delimiter=',', dtype=np.float32)

x_data = xy[:, 0:-1]

y_data = xy[:, [-1]]

# Make sure the shape and data are OK

print(x_data, "\nx_data shape:", x_data.shape)

print(y_data, "\ny_data shape:", y_data.shape)

# 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())

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)

1950, Cost: 2.8077145

Prediction:

array([[154.30186],
       [183.31505],
       [181.97646],
       [194.59978],
       [142.33385],
       [ 99.34767]], dtype=float32))

1960, Cost: 2.7977974

Prediction:

array([[154.296  ],
       [183.31776],
       [181.97401],
       [194.59859],
       [142.33716],
       [ 99.35353]], dtype=float32))

1970, Cost: 2.787885

Prediction:

array([[154.29016],
       [183.32051],
       [181.97154],
       [194.5974 ],
       [142.34042],
       [ 99.35938]], dtype=float32))

1980, Cost: 2.778064

Prediction:

array([[154.28435],
       [183.32324],
       [181.9691 ],
       [194.59624],
       [142.3437 ],
       [ 99.3652 ]], dtype=float32))

1990, Cost: 2.7683241

Prediction:

array([[154.27856],
       [183.32594],
       [181.96667],
       [194.59506],
       [142.34695],
       [ 99.37102]], dtype=float32))

2000, Cost: 2.7586195

Prediction:

array([[154.27278 ],
       [183.32866 ],
       [181.96426 ],
       [194.5939  ],
       [142.35019 ],
       [ 99.376816]], dtype=float32))

 

2. Loading data from multi-file

import tensorflow as tf

tf.set_random_seed(777) # for reproducibility

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)

# 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]]}))

1980, Cost: 2.2382462

Prediction:

array([[152.35132],
       [183.37514],
       [180.53424],
       [197.20535],
       [139.35315],
       [103.52445],
       [152.35132],
       [183.37514],
       [180.53424],
       [197.20535]], dtype=float32))

1990, Cost: 3.407795

Prediction:

array([[139.34067],
       [103.51443],
       [152.33455],
       [183.35727],
       [180.5155 ],
       [197.18425],
       [139.34067],
       [103.51443],
       [152.33455],
       [183.35727]], dtype=float32))

2000, Cost: 3.3214183

Prediction:

array([[180.62273],
       [197.30028],
       [139.42564],
       [103.57615],
       [152.42416],
       [183.46718],
       [180.62273],
       [197.30028],
       [139.42564],
       [103.57615]], dtype=float32))

'Your score will be ', array([[182.8681]], dtype=float32))
'Other scores will be ', array([[169.80573], [177.92252]], dtype=float32))