explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update Keras deep learning tutorial

Browse Source
This commit is contained in:
Matthew Honnibal 2016-10-19 19:37:09 +02:00
parent f60cefc048
commit ca89fd0919
1 changed files with 8 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
examples/deep_learning_keras.py
View File

@ -14,7 +14,7 @@ class SentimentAnalyser(object):
def __call__(self, doc): def __call__(self, doc):
X = get_features([doc], self.max_length) X = get_features([doc], self.max_length)
y = self._keras_model.predict(X) y = self._model.predict(X)
self.set_sentiment(doc, y) self.set_sentiment(doc, y)
def pipe(self, docs, batch_size=1000, n_threads=2): def pipe(self, docs, batch_size=1000, n_threads=2):
@ -28,6 +28,13 @@ class SentimentAnalyser(object):
doc.user_data['sentiment'] = y doc.user_data['sentiment'] = y
def get_features(docs, max_length):
Xs = numpy.zeros(len(docs), max_length, dtype='int32')
for i, doc in enumerate(minibatch):
for j, token in enumerate(doc[:max_length]):
Xs[i, j] = token.rank if token.has_vector else 0
return Xs
def compile_lstm(embeddings, shape, settings, optimizer): def compile_lstm(embeddings, shape, settings, optimizer):
model = Sequential() model = Sequential()
model.add( model.add(
@ -59,14 +66,6 @@ def get_embeddings(vocab):
return vectors return vectors
def get_features(docs, max_length):
Xs = numpy.zeros(len(docs), max_length, dtype='int32')
for i, doc in enumerate(minibatch):
for j, token in enumerate(doc[:max_length]):
Xs[i, j] = token.rank if token.has_vector else 0
return Xs
def train(train_texts, train_labels, dev_texts, dev_labels, def train(train_texts, train_labels, dev_texts, dev_labels,
lstm_shape, lstm_settings, lstm_optimizer, batch_size=100, nb_epoch=5): lstm_shape, lstm_settings, lstm_optimizer, batch_size=100, nb_epoch=5):
nlp = spacy.load('en', parser=False, tagger=False, entity=False) nlp = spacy.load('en', parser=False, tagger=False, entity=False)