Skip to content

Instantly share code, notes, and snippets.

@csetzkorn
Last active September 5, 2018 12:39
Show Gist options
  • Save csetzkorn/7b134cd25ccf08c508aeb002ddf699a9 to your computer and use it in GitHub Desktop.
Save csetzkorn/7b134cd25ccf08c508aeb002ddf699a9 to your computer and use it in GitHub Desktop.
simple text classification example using keras and word embedding
from numpy import array
from keras.preprocessing.text import one_hot
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers.embeddings import Embedding
# see also: https://machinelearningmastery.com/use-word-embedding-layers-deep-learning-keras/
# define documents
docs = ['Well done!',
'Good work',
'Great effort',
'nice work',
'Excellent!',
'Weak',
'Poor effort!',
'not good',
'poor work',
'Could have done better.']
# define class labels
labels = array([1,1,1,1,1,0,0,0,0,0])
# integer encode the documents
vocab_size = 50
encoded_docs = [one_hot(d, vocab_size) for d in docs]
print(encoded_docs)
# pad documents to a max length of 4 words
max_length = 4
padded_docs = pad_sequences(encoded_docs, maxlen=max_length, padding='post')
print(padded_docs)
# define the model
model = Sequential()
model.add(Embedding(vocab_size, 8, input_length=max_length))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
# compile the model
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])
# summarize the model
print(model.summary())
# fit the model
model.fit(padded_docs, labels, epochs=50, verbose=0)
# evaluate the model
loss, accuracy = model.evaluate(padded_docs, labels, verbose=0)
print('Accuracy: %f' % (accuracy*100))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment