alexanderholt

from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.utils import np_utils
from keras.datasets import mnist

# 2. Load pre-shuffled MNIST data into train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()

# 3. Preprocess input data

alexanderholt

# create Y_predictions, in this case linear regression
Y_predictions = tf.add(b, tf.multiply(w,X))

squares = tf.square(Y - Y_predictions)

loss = tf.reduce_mean(squares, name='loss')

#gradiaent descent. pass learning rate as .01
optimizer = tf.train.GradientDescentOptimizer(0.01).minimize(loss=loss)

alexanderholt

# create placeholder tensors
x = tf.placeholder(tf.float32, name = 'x')
y = tf.placeholder(tf.float32, name = 'y')
# create Variable tensors

w = tf.Variable(0.0, name='w')
b = tf.Variable(0.0, name='b')
import tensorflow as tf
a_list = [1, 2, 3, 4, 5]
tf.reset_default_graph

alexanderholt

import tensorflow as tf
tf.reset_default_graph()

a = tf.constant(2, name='x')
b = tf.constant(3, name='y')
add_op = tf.add(a, b, name='add')
with tf.Session() as sess:
    # add this line to use TensorBoard.
    writer = tf.summary.FileWriter('./graphs', sess.graph)
    print(sess.run(add_op))

alexanderholt

# Creates a graph.

x = 2
y = 3
with tf.device('/cpu:1'):
    add_op = tf.add(x, y,)
    mul_op = tf.multiply(x, y)
    pow_op = tf.pow(add_op, mul_op)

with tf.device('/cpu:2'):

alexanderholt

# Now condense this a little bit

a = tf.add(4, 6)
b = tf.multiply(2, 10)
c = tf.subtract(b, 5)

with tf.Session() as sess:
    added = sess.run([a, b, c])
    print(added)

alexanderholt

# How to get the value of a?
# Create a session, assign it to variable sess so we can call it later
# Within the session, evaluate the graph to fetch the value of a

a = tf.add(4, 6)
sess = tf.Session()

print(sess.run(a))

sess.close()

alexanderholt

# How to get the value of a?
# Create a session, assign it to variable sess so we can call it later
# Within the session, evaluate the graph to fetch the value of a

a = tf.add(4, 6)
sess = tf.Session()

print(sess.run(a))

sess.close()

alexanderholt

data['is_recipe'] = data['title'].fillna('').str.contains('recipe')

alexanderholt

%%time 
#This took me about 5 minutes

# Import the built-in logging module and configure it so that Word2Vec 
# creates nice output messages
import logging
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',\
    level=logging.INFO)

# Set values for various parameters