In [1]:

    

# First you need to add library into your Databricks cluster
# Right click on Shared folder and hit "Create Library", then use PyPi as source and "tensorflow" as library name
import tensorflow as tf


    

In [2]:

    

tf.__version__


    

In [3]:

    

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse

# Import data
from tensorflow.examples.tutorials.mnist import input_data


    

In [4]:

    

#Load data 
mnist = input_data.read_data_sets('/tmp/data', one_hot=True)


    

In [5]:

    

#Define model
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.matmul(x, W) + b


    

In [6]:

    

#Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y, labels=y_))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)


    

In [7]:

    

#Train the model using small batches
sess = tf.InteractiveSession()

tf.global_variables_initializer().run()
for _ in range(1000):
  batch_xs, batch_ys = mnist.train.next_batch(100)
  sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})


    

In [8]:

    

#Predict the test data and print out accuracy
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={x: mnist.test.images,
                                    y_: mnist.test.labels}))


    

In [9]: