explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix deep learning example code

Browse Source
This commit is contained in:
Matthew Honnibal 2016-10-20 21:32:26 +02:00
parent 5ec32f5d97
commit 1ae3bde58f
1 changed files with 16 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
examples/deep_learning_keras.py
View File

@ -7,6 +7,7 @@ import cytoolz
import numpy import numpy
from keras.models import Sequential, model_from_json from keras.models import Sequential, model_from_json
from keras.layers import LSTM, Dense, Embedding, Dropout, Bidirectional from keras.layers import LSTM, Dense, Embedding, Dropout, Bidirectional
from keras.layers import TimeDistributed
from keras.optimizers import Adam from keras.optimizers import Adam
import cPickle as pickle import cPickle as pickle
@ -48,10 +49,16 @@ class SentimentAnalyser(object):
def get_features(docs, max_length): def get_features(docs, max_length):
Xs = numpy.zeros((len(list(docs)), max_length), dtype='int32') docs = list(docs)
Xs = numpy.zeros((len(docs), max_length), dtype='int32')
for i, doc in enumerate(docs): for i, doc in enumerate(docs):
for j, token in enumerate(doc[:max_length]): j = 0
Xs[i, j] = token.rank if token.has_vector else 0 for token in doc:
if token.has_vector and not token.is_punct and not token.is_space:
Xs[i, j] = token.rank + 1
j += 1
if j >= max_length:
break
return Xs return Xs
@ -75,9 +82,12 @@ def compile_lstm(embeddings, shape, settings):
embeddings.shape[1], embeddings.shape[1],
input_length=shape['max_length'], input_length=shape['max_length'],
trainable=False, trainable=False,
weights=[embeddings] weights=[embeddings],
mask_zero=True
) )
) )
model.add(TimeDistributed(Dense(shape['nr_hidden'] * 2)))
model.add(Dropout(settings['dropout']))
model.add(Bidirectional(LSTM(shape['nr_hidden']))) model.add(Bidirectional(LSTM(shape['nr_hidden'])))
model.add(Dropout(settings['dropout'])) model.add(Dropout(settings['dropout']))
model.add(Dense(shape['nr_class'], activation='sigmoid')) model.add(Dense(shape['nr_class'], activation='sigmoid'))
@ -87,11 +97,11 @@ def compile_lstm(embeddings, shape, settings):
def get_embeddings(vocab): def get_embeddings(vocab):
max_rank = max(lex.rank for lex in vocab if lex.has_vector) max_rank = max(lex.rank+1 for lex in vocab if lex.has_vector)
vectors = numpy.ndarray((max_rank+1, vocab.vectors_length), dtype='float32') vectors = numpy.ndarray((max_rank+1, vocab.vectors_length), dtype='float32')
for lex in vocab: for lex in vocab:
if lex.has_vector: if lex.has_vector:
vectors[lex.rank] = lex.vector vectors[lex.rank + 1] = lex.vector
return vectors return vectors