def deep_test():
sess = tf.Session()
start_dim = 50000
x = tf.placeholder("float", [None, start_dim])
autoencoder = create(
x, [500]
) # Dimensionality of the hidden layers. To start with, only use 1 hidden layer.
tokens, vects, norm_tweets = convertTweetsToVec('all', start_dim)
tweets_dev, targets_dev, labels_dev = readTweetsOfficial(
tokenize_tweets.FILEDEV, 'windows-1252', 2)
vects_dev, norm_tweets_dev = tokenize_tweets.convertTweetsOfficialToVec(
start_dim, tokens, tweets_dev)
devbatch = []
for v in vects_dev:
devbatch.append(v)
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Restore variables from disk.
saver.restore(sess, "model.ckpt")
print("Model restored.")
decoded = sess.run(autoencoder['decoded'],
feed_dict={x: devbatch}) # apply to dev
encoded = sess.run(autoencoder['encoded'],
feed_dict={x: devbatch}) # apply to dev
sampnr = 12 # which ones of the dev samples to display for sanity check
print("\noriginal", labels_dev[sampnr],
norm_tweets_dev[sampnr]) # print "\noriginal", norm_tweets[2]
print(vects_dev[sampnr])
dec_tweet = []
n = 0
for r in decoded[sampnr]: # display first result
if r > 0.1:
dec_tweet.append(tokens[n])
n += 1
print(" cost", sess.run(autoencoder['cost'], feed_dict={x: devbatch}))
#print i, " original", batch[0]
print(
" encoded",
encoded[sampnr]) # latent representation of input, feed this to SVM(s)
print(" decoded", decoded[sampnr])
print(" decoded bow", dec_tweet)
def extractFeaturesAutoencoder(autoencodermodel, tweets_train, targets_train, labels_train, tweets_dev, targets_dev, labels_dev,
cross_features='false', usephrasemodel=False):
sess = tf.Session()
start_dim = 50000
x = tf.placeholder("float", [None, start_dim])
autoencoder = create(x, [100]) # Dimensionality of the hidden layers. To start with, only use 1 hidden layer.
tokens = readToks2(start_dim, usephrasemodel)
# read dev data and convert to vectors
#tweets_train, targets_train, labels_train = readTweetsOfficial(tokenize_tweets.FILETRAIN, 'windows-1252', 2)
vects_train,norm_tweets_train = tokenize_tweets.convertTweetsOfficialToVec(start_dim, tokens, tweets_train, filtering=True)
vects_train_targets, norm_train_targets = tokenize_tweets.convertTweetsOfficialToVec(start_dim, tokens, targets_train) # optimise runtime with more code later
# read dev data and convert to vectors
#tweets_dev, targets_dev, labels_dev = readTweetsOfficial(tokenize_tweets.FILEDEV, 'windows-1252', 2)
vects_dev,norm_tweets_dev = tokenize_tweets.convertTweetsOfficialToVec(start_dim, tokens, tweets_dev, filtering=True)
vects_dev_targets, norm_dev_targets = tokenize_tweets.convertTweetsOfficialToVec(start_dim, tokens, targets_dev)
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Restore variables from disk.
saver.restore(sess, autoencodermodel)
print("Model restored.")
# apply autoencoder to train and dev data
encoded_train = sess.run(autoencoder['encoded'], feed_dict={x: vects_train}) # apply to tweets
encoded_train_target = sess.run(autoencoder['encoded'], feed_dict={x: vects_train_targets}) # apply to target
encoded_dev = sess.run(autoencoder['encoded'], feed_dict={x: vects_dev}) # apply to tweets
encoded_dev_target = sess.run(autoencoder['encoded'], feed_dict={x: vects_dev_targets}) # apply to target
# decoder is just for sanity check, we don't really need that
#decoded_dev = sess.run(autoencoder['decoded'], feed_dict={x: vects_dev}) # apply to tweets
#decoded_dev_target = sess.run(autoencoder['decoded'], feed_dict={x: vects_dev_targets}) # apply to target
print("cost train tweets", sess.run(autoencoder['cost'], feed_dict={x: vects_train}))
print("cost train target", sess.run(autoencoder['cost'], feed_dict={x: vects_train_targets}))
print("cost dev tweets", sess.run(autoencoder['cost'], feed_dict={x: vects_dev}))
print("cost dev target", sess.run(autoencoder['cost'], feed_dict={x: vects_dev_targets}))
features_train = []
features_dev = []
if cross_features == "true":
for i, enc in enumerate(encoded_train_target):
features_train_i = []
for v in np.outer(encoded_train[i], encoded_train_target[i]):
features_train_i.extend(v)
features_train.append(features_train_i)
for i, enc in enumerate(encoded_dev_target):
features_dev_i = []
for v in np.outer(encoded_dev[i], encoded_dev_target[i]):
features_dev_i.extend(v)
features_dev.append(features_dev_i)
elif cross_features == "added":
for i, enc in enumerate(encoded_train_target):
features_train.append(np.append(encoded_train[i], enc))
for i, enc in enumerate(encoded_dev_target):
features_dev.append(np.append(encoded_dev[i], enc))
else:
features_train = encoded_train
features_dev = encoded_dev
print("Features extracted!")
return features_train, labels_train, features_dev, labels_dev
def extractFeaturesAutoencoder(autoencodermodel,
tweets_train,
targets_train,
labels_train,
tweets_dev,
targets_dev,
labels_dev,
cross_features='false',
usephrasemodel=False):
sess = tf.Session()
start_dim = 50000
x = tf.placeholder("float", [None, start_dim])
autoencoder = create(
x, [100]
) # Dimensionality of the hidden layers. To start with, only use 1 hidden layer.
tokens = readToks2(start_dim, usephrasemodel)
# read dev data and convert to vectors
#tweets_train, targets_train, labels_train = readTweetsOfficial(tokenize_tweets.FILETRAIN, 'windows-1252', 2)
vects_train, norm_tweets_train = tokenize_tweets.convertTweetsOfficialToVec(
start_dim, tokens, tweets_train, filtering=True)
vects_train_targets, norm_train_targets = tokenize_tweets.convertTweetsOfficialToVec(
start_dim, tokens,
targets_train) # optimise runtime with more code later
# read dev data and convert to vectors
#tweets_dev, targets_dev, labels_dev = readTweetsOfficial(tokenize_tweets.FILEDEV, 'windows-1252', 2)
vects_dev, norm_tweets_dev = tokenize_tweets.convertTweetsOfficialToVec(
start_dim, tokens, tweets_dev, filtering=True)
vects_dev_targets, norm_dev_targets = tokenize_tweets.convertTweetsOfficialToVec(
start_dim, tokens, targets_dev)
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Restore variables from disk.
saver.restore(sess, autoencodermodel)
print("Model restored.")
# apply autoencoder to train and dev data
encoded_train = sess.run(autoencoder['encoded'],
feed_dict={x: vects_train}) # apply to tweets
encoded_train_target = sess.run(autoencoder['encoded'],
feed_dict={x: vects_train_targets
}) # apply to target
encoded_dev = sess.run(autoencoder['encoded'],
feed_dict={x: vects_dev}) # apply to tweets
encoded_dev_target = sess.run(autoencoder['encoded'],
feed_dict={x: vects_dev_targets
}) # apply to target
# decoder is just for sanity check, we don't really need that
#decoded_dev = sess.run(autoencoder['decoded'], feed_dict={x: vects_dev}) # apply to tweets
#decoded_dev_target = sess.run(autoencoder['decoded'], feed_dict={x: vects_dev_targets}) # apply to target
print("cost train tweets",
sess.run(autoencoder['cost'], feed_dict={x: vects_train}))
print("cost train target",
sess.run(autoencoder['cost'], feed_dict={x: vects_train_targets}))
print("cost dev tweets",
sess.run(autoencoder['cost'], feed_dict={x: vects_dev}))
print("cost dev target",
sess.run(autoencoder['cost'], feed_dict={x: vects_dev_targets}))
features_train = []
features_dev = []
if cross_features == "true":
for i, enc in enumerate(encoded_train_target):
features_train_i = []
for v in np.outer(encoded_train[i], encoded_train_target[i]):
features_train_i.extend(v)
features_train.append(features_train_i)
for i, enc in enumerate(encoded_dev_target):
features_dev_i = []
for v in np.outer(encoded_dev[i], encoded_dev_target[i]):
features_dev_i.extend(v)
features_dev.append(features_dev_i)
elif cross_features == "added":
for i, enc in enumerate(encoded_train_target):
features_train.append(np.append(encoded_train[i], enc))
for i, enc in enumerate(encoded_dev_target):
features_dev.append(np.append(encoded_dev[i], enc))
else:
features_train = encoded_train
features_dev = encoded_dev
print("Features extracted!")
return features_train, labels_train, features_dev, labels_dev
def deep(modelname, layers, phrasem=True, useDev=True):
sess = tf.Session()
#load and convert tweets
tokens, vects, norm_tweets = convertTweetsToVec('all',
50000,
phrasemodel=phrasem)
start_dim = 50000 #tokens.__sizeof__() # 129887 tokens without singletons. Dimensionality of input. keep as big as possible, but throw singletons away.
x = tf.placeholder("float", [None, start_dim])
print("Creating autoencoder")
autoencoder = create(
x, layers
) # Dimensionality of the hidden layers. To start with, only use 1 hidden layer.
print("Creating Adam")
train_step = tf.train.AdamOptimizer(0.1).minimize(autoencoder['cost'])
print("Initialising all variables")
init = tf.initialize_all_variables()
sess.run(init)
print("Converting official training data to vectors")
tweets_train, targets_train, labels_train = readTweetsOfficial(
tokenize_tweets.FILETRAIN)
tweets_trump, targets_trump, labels_trump = readTweetsOfficial(
tokenize_tweets.FILETRUMP, 'utf-8', 1)
vects_train, norm_tweets_train = tokenize_tweets.convertTweetsOfficialToVec(
start_dim, tokens, tweets_train, filtering=True)
vects_trump, norm_tweets_trump = tokenize_tweets.convertTweetsOfficialToVec(
start_dim, tokens, tweets_trump, filtering=True)
for v in vects_train:
vects.append(v)
for v in vects_trump:
vects.append(v)
tweets_dev, targets_dev, labels_dev = readTweetsOfficial(
tokenize_tweets.FILEDEV)
vects_dev, norm_tweets_dev = tokenize_tweets.convertTweetsOfficialToVec(
start_dim, tokens, tweets_dev, filtering=True)
devbatch = []
if useDev == False:
for v in vects_dev:
devbatch.append(v)
else:
for v in vects_dev:
vects.append(v)
tweets_test, targets_test, labels_test = readTweetsOfficial(
tokenize_tweets.FILETEST)
vects_test, norm_tweets_test = tokenize_tweets.convertTweetsOfficialToVec(
start_dim, tokens, tweets_test, filtering=True)
for v in vects_test:
devbatch.append(v)
# start training
sampnr = 12 # which ones of the dev samples to display for sanity check
print("\noriginal", labels_dev[sampnr],
norm_tweets_dev[sampnr]) # print "\noriginal", norm_tweets[2]
print(vects[sampnr])
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
cost = 1.0
# do 1000 training steps
#for i in range(2000):
i = 0
while cost > 0.01:
# make a batch of 100:
batch = []
for j in range(500):
num = random.randint(0, len(vects) - 1)
batch.append(vects[num])
sess.run(train_step, feed_dict={x: np.array(batch)})
if i % 100 == 0:
decoded = sess.run(autoencoder['decoded'],
feed_dict={x: devbatch}) # apply to dev
encoded = sess.run(autoencoder['encoded'],
feed_dict={x: devbatch}) # apply to dev
#dec_tweet = []
#n = 0
#for r in decoded[sampnr]: # display first result
# if r > 0.1:
# dec_tweet.append(tokens[n])
# n+=1
cost = sess.run(autoencoder['cost'], feed_dict={x: devbatch})
print(i, " cost", cost)
#print i, " original", batch[0]
#print i, " encoded", encoded[sampnr] # latent representation of input, feed this to SVM(s)
print(i, " decoded", decoded[sampnr])
#print i, " decoded bow", dec_tweet
save_path = saver.save(
sess, modelname.replace(".ckpt", "_it" + str(i) + ".ckpt"))
print("Model saved in file: %s" % save_path)
i += 1
