can anyone help me in resolving the error which I am getting while running this tensorflow program

Question

program for applying linear regression on dataset using tensorflow
# About housing_data: 
# dataset characterisitics:multivariate
#Associate task:          regression
#Number of instance:      506
#number of attribut:      14

#Attribute Information:

#1. CRIM: per capita crime rate by town
#2. ZN: proportion of residential land zoned for lots over 25,000 sq.ft.
#3. INDUS: proportion of non-retail business acres per town
#4. CHAS: Charles River dummy variable
#5. NOX: nitric oxides concentration (parts per 10 million)
#6. RM: average number of rooms per dwelling
#7. AGE: proportion of owner-occupied units built prior to 1940
#8. DIS: weighted distances to five Boston employment centres
#9. RAD: index of accessibility to radial highways
#10. TAX: full-value property-tax rate per $10,000
#11. PTRATIO: pupil-teacher ratio by town
#12. B: 1000(Bk - 0.63)^2 where Bk is the proportion of blacks by town
#13. LSTAT: % lower status of the population
#14. MEDV: Median value of owner-occupied homes in $1000's

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

batch_size=50

#make queue of file
filename_queue = tf.train.string_input_producer(
tf.train.match_filenames_once("housing_data.csv"),
shuffle=True)

line_reader = tf.TextLineReader(skip_header_lines=1)

_, csv_row = line_reader.read(filename_queue)

record_defaults = [[0.0], [0.0], [0.0], [0.0], [0.0],[0.0],[0.0],[0.0],[0.0],
              [0.0], [0.0], [0.0], [0.0], [0.0]]

CRIM,ZN,INDUS,CHAS,NOX,RM,AGE,DIS,RAD,TAX,PTRATIO,B,LSTAT,MEDV = tf.decode_csv(
                        csv_row, record_defaults=record_defaults)

# Turn the features back into a tensor.
features =    tf.pack([CRIM,ZN,INDUS,CHAS,NOX,RM,AGE,DIS,RAD,TAX,PTRATIO,B,LSTAT,MEDV])

#variable which we need to fill when we are ready to comput the graph
x=tf.placeholder(tf.float32)
y=tf.placeholder(tf.float32)

W = tf.Variable(tf.random_normal([1]), name='weight')
b = tf.Variable(tf.random_normal([1]), name='bias')
y_pred = tf.add(tf.mul(x, W), b)

error=tf.reduce_sum((y-y_pred)**2/506)

learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(error)

#create the session to use the graph
with tf.Session() as sess:
  # Here we tell tensorflow that we want to initialize all
  # the variables in the graph so we can use them 
  #tf.initialize_all_variables().run()
  sess.run(tf.initialize_all_variables())
  sess.run([features,MEDV])

  coord = tf.train.Coordinator()
  threads = tf.train.start_queue_runners(coord=coord)

  sess.run([features,MEDV])

  #gradient descent loop for 500 iteration
  for _ in range(500):
      #select random mini batch
      indices=np.random.choice(506,batch_size)
      x_batch,y_batch=features[indices],MEDV[indices]

      #do gradient descent
    _,loss_val=sess.run([optimizer,error],feed_dict={x:x_batch,y:y_batch})

    print _,loss_val




coord.request_stop()
coord.join(threads)

---------------------------error----------------------------------------

When I am running this code I am getting following error.
error:
 Traceback (most recent call last):
 File "linear_reg_tf.py", line 92, in <module>
 x_batch,y_batch=features[indices],MEDV[indices]
 File "/usr/local/lib/python2.7/dist-packages/tensorflow/pytho/ops/array_ops.py", line 161, in _SliceHelper
raise TypeError("Bad slice index %s of type %s" % (s, type(s)))
TypeError: Bad slice index [468 105 218 124 492 428 464 194 110  76 165   127 480 414  88 332  54  68

195 162 223 65 340 279 390 390 1 127 290 82 430 154 202 389 478 42 410 25 161 42 143 256 481 417 263 92 335 101 430 334] of type

Answer 1

Maybe instead of x_batch,y_batch=features[indices],MEDV[indices] you can try

x_batch,y_batch = [], []
for index in indices:
    x_batch.append(features[index])
    y_batch.append(MEDV[index])

Answer 2

this code is working but I want to know if we want to test some new data then how we will test or how to split the data into training set and test set

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

batch_size=50

filename_queue = tf.train.string_input_producer(
    tf.train.match_filenames_once("housing_data.csv"),
    shuffle=True)


# for each column below.
line_reader = tf.TextLineReader(skip_header_lines=1)

_, csv_row = line_reader.read(filename_queue)

# Type information and column names based on the decoded CSV.
 record_defaults = [[0.0], [0.0], [0.0], [0.0], [0.0],[0.0],[0.0],[0.0],[0.0],
              [0.0], [0.0], [0.0], [0.0], [0.0]]

CRIM,ZN,INDUS,CHAS,NOX,RM,AGE,DIS,RAD,TAX,PTRATIO,B,LSTAT,MEDV =     tf.decode_csv(
                        csv_row, record_defaults=record_defaults)

# Turn the features back into a tensor.
features =    tf.pack([CRIM,ZN,INDUS,CHAS,NOX,RM,AGE,DIS,RAD,TAX,PTRATIO,B,LSTAT,MEDV])

#variable which we need to fill when we are ready to comput the graph
x=tf.placeholder(dtype=features.dtype)
y=tf.placeholder(dtype=MEDV.dtype)

W = tf.Variable(tf.random_normal([1]), name='weight')
b = tf.Variable(tf.random_normal([1]), name='bias')
y_pred = tf.add(tf.mul(x, W), b)


#loss function will measure the distance between our observations and    predictions
#and average over them.Here housing data have 506 instances so divide by 506.
error=tf.reduce_sum((y-y_pred)**2/506)


learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(error)

#create the session to use the graph with tf.Session() as sess:

  sess.run(tf.initialize_all_variables())

  coord = tf.train.Coordinator()
  threads = tf.train.start_queue_runners(coord=coord)

  x_data =np.array(sess.run(features))
  y_data =np.array(sess.run(MEDV))

  #gradient descent loop for 10 iteration
  for _ in range(10):
      sess.run([features,MEDV])

      #do gradient descent
      _,loss_val=sess.run([optimizer,error],feed_dict={x:x_data,y:y_data})

      print _,loss_val


coord.request_stop()
coord.join(threads)