def __init__(self, alphabet_encoding):
self.alphabet_encoding = alphabet_encoding
#self.test_words = ["cat", "feline", "car", "truck", "tuck"]
#self.test_words = ['cat', 'CAT', 'egg', 'eggplant', 'brontosaurus']
self.test_words = ['pokemon', 'bigger', 'better', 'faster', 'stronger']
_encoded_test_words = map(self._encode, self.test_words)
self.data_provider = PaddedSequenceMinibatchProvider(
X=_encoded_test_words,
padding=self.alphabet_encoding['PADDING'],
batch_size=len(_encoded_test_words),
shuffle=False)
class ModelEvaluator(object):
def __init__(self, alphabet_encoding):
self.alphabet_encoding = alphabet_encoding
#self.test_words = ["cat", "feline", "car", "truck", "tuck"]
#self.test_words = ['cat', 'CAT', 'egg', 'eggplant', 'brontosaurus']
self.test_words = ['pokemon', 'bigger', 'better', 'faster', 'stronger']
_encoded_test_words = map(self._encode, self.test_words)
self.data_provider = PaddedSequenceMinibatchProvider(
X=_encoded_test_words,
padding=self.alphabet_encoding['PADDING'],
batch_size=len(_encoded_test_words),
shuffle=False)
def _encode(self, word):
encoded_word = [self.alphabet_encoding[c] for c in word]
encoded_word = [self.alphabet_encoding['START']] + encoded_word + [self.alphabet_encoding['END']]
return encoded_word
def evaluate(self, model):
X, meta = self.data_provider.next_batch()
Y_hat, meta, _ = model.fprop(X, meta=meta, num_layers=-1, return_state=True)
Y_hat, _ = meta['space_above'].transform(Y_hat, ['b', 'dwf'])
# print Y_hat
# compute cosine distance between rows of Y
Y_hat_norms = np.sqrt(np.sum(Y_hat**2, axis=1, keepdims=True))
distances = np.dot(Y_hat, Y_hat.T) / (Y_hat_norms * Y_hat_norms.T)
print self.test_words
print distances
def __init__(self, alphabet_encoding):
self.alphabet_encoding = alphabet_encoding
#self.test_words = ["cat", "feline", "car", "truck", "tuck"]
#self.test_words = ['cat', 'CAT', 'egg', 'eggplant', 'brontosaurus']
self.test_words = ['pokemon', 'bigger', 'better', 'faster', 'stronger']
_encoded_test_words = map(self._encode, self.test_words)
self.data_provider = PaddedSequenceMinibatchProvider(
X=_encoded_test_words,
padding=self.alphabet_encoding['PADDING'],
batch_size=len(_encoded_test_words),
shuffle=False)
class ModelEvaluator(object):
def __init__(self, alphabet_encoding):
self.alphabet_encoding = alphabet_encoding
#self.test_words = ["cat", "feline", "car", "truck", "tuck"]
#self.test_words = ['cat', 'CAT', 'egg', 'eggplant', 'brontosaurus']
self.test_words = ['pokemon', 'bigger', 'better', 'faster', 'stronger']
_encoded_test_words = map(self._encode, self.test_words)
self.data_provider = PaddedSequenceMinibatchProvider(
X=_encoded_test_words,
padding=self.alphabet_encoding['PADDING'],
batch_size=len(_encoded_test_words),
shuffle=False)
def _encode(self, word):
encoded_word = [self.alphabet_encoding[c] for c in word]
encoded_word = [self.alphabet_encoding['START']
] + encoded_word + [self.alphabet_encoding['END']]
return encoded_word
def evaluate(self, model):
X, meta = self.data_provider.next_batch()
Y_hat, meta, _ = model.fprop(X,
meta=meta,
num_layers=-1,
return_state=True)
Y_hat, _ = meta['space_above'].transform(Y_hat, ['b', 'dwf'])
# print Y_hat
# compute cosine distance between rows of Y
Y_hat_norms = np.sqrt(np.sum(Y_hat**2, axis=1, keepdims=True))
distances = np.dot(Y_hat, Y_hat.T) / (Y_hat_norms * Y_hat_norms.T)
print self.test_words
print distances
def load_json(file_name):
with open(file_name) as f:
return json.loads(f.read())
if __name__ == "__main__":
np.set_printoptions(linewidth=100)
data = load_json(
os.path.join(os.environ['DATA'], "words", "words.encoded.json"))
alphabet = load_json(
os.path.join(os.environ['DATA'], "words",
"words.alphabet.encoding.json"))
train_data_provider = PaddedSequenceMinibatchProvider(
X=data, padding=alphabet['PADDING'], batch_size=100)
embedding_dimension = 8
vocabulary_size = len(alphabet)
n_feature_maps = 8
kernel_width = 5
pooling_size = 2
n_epochs = 1
model = CSM(layers=[
WordEmbedding(dimension=embedding_dimension,
vocabulary_size=len(alphabet)),
SentenceConvolution(n_feature_maps=n_feature_maps,
kernel_width=kernel_width,
n_channels=1,
