Created
August 1, 2019 12:32
-
-
Save sismetanin/836057bde8090f2e00e6c07066ef65d8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def getEmbeddings(file): | |
embeddingsIndex = {} | |
dim = 0 | |
with io.open(file, encoding="utf8") as f: | |
for line in f: | |
values = line.split() | |
word = values[0] | |
embeddingVector = np.asarray(values[1:], dtype='float32') | |
embeddingsIndex[word] = embeddingVector | |
dim = len(embeddingVector) | |
return embeddingsIndex, dim | |
def getEmbeddingMatrix(wordIndex, embeddings, dim): | |
embeddingMatrix = np.zeros((len(wordIndex) + 1, dim)) | |
for word, i in wordIndex.items(): | |
embeddingMatrix[i] = embeddings.get(word) | |
return embeddingMatrix | |
from keras.preprocessing.text import Tokenizer | |
embeddings, dim = getEmbeddings('emosense.300d.txt') | |
tokenizer = Tokenizer(filters='') | |
tokenizer.fit_on_texts([' '.join(list(embeddings.keys()))]) | |
wordIndex = tokenizer.word_index | |
print("Found %s unique tokens." % len(wordIndex)) | |
embeddings_matrix = getEmbeddingMatrix(wordIndex, embeddings, dim) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment