def __init__(self,
embed_file,
dicts,
dropout=0.5,
gpu=True,
embed_size=100):
super(BaseModel, self).__init__()
self.gpu = gpu
self.embed_size = embed_size
# self.embed_drop = nn.Dropout(p=dropout)
#make embedding layer
if embed_file:
print("loading pretrained embeddings...")
W = torch.Tensor(extract_wvs.load_embeddings(embed_file))
print("Size of embedding matrix")
print(W.size())
self.embed = nn.Embedding(W.size()[0], W.size()[1])
self.embed.weight.data = W.clone()
else:
#add 2 to include UNK and PAD
# vocab_size = len(dicts[0])
# print("Vocab size: " + str(vocab_size))
vocab_size = 10 # TEMP
self.embed = nn.Embedding(vocab_size + 2, embed_size)
def __init__(self,
Y,
embed_file,
dicts,
lmbda=0,
dropout=0.5,
gpu=True,
embed_size=100):
super(BaseModel, self).__init__()
torch.manual_seed(1337)
self.gpu = gpu
self.Y = Y
self.embed_size = embed_size
self.embed_drop = nn.Dropout(p=dropout)
self.lmbda = lmbda
#make embedding layer
if embed_file:
print("loading pretrained embeddings...")
el, ind = extract_wvs.load_embeddings(embed_file)
assert ind == dicts[
'w2ind'] #assert that the index of the pretrained embeddings file aligns *exactly* with that used to embed the text
W = torch.Tensor(el)
self.embed = nn.Embedding(W.size()[0], W.size()[1], padding_idx=0)
self.embed.weight.data = W.clone()
else:
#add 2 to include UNK and PAD
vocab_size = len(dicts['ind2w'])
self.embed = nn.Embedding(vocab_size + 2,
embed_size,
padding_idx=0)
def __init__(self,
Y,
embed_file,
dicts,
lmbda=0,
dropout=0.5,
gpu=True,
embed_size=100):
super(BaseModel, self).__init__()
self.gpu = gpu
self.Y = Y
self.embed_size = embed_size
self.embed_drop = nn.Dropout(p=dropout)
self.lmbda = lmbda
#make embedding layer
if embed_file:
print("loading pretrained embeddings...")
W = torch.Tensor(extract_wvs.load_embeddings(embed_file))
self.embed = nn.Embedding(W.size()[0], W.size()[1])
self.embed.weight.data = W.clone()
else:
#add 2 to include UNK and PAD
vocab_size = len(dicts[0])
self.embed = nn.Embedding(vocab_size + 2, embed_size)
def __init__(self, embed_file, dicts, embed_size=100):
super(BaseModel, self).__init__()
self.embed_size = embed_size
#make embedding layer
if embed_file:
print("loading pretrained embeddings...")
W = torch.Tensor(extract_wvs.load_embeddings(embed_file))
print("Size of embedding matrix")
print(W.size())
self.embed = nn.Embedding(W.size()[0], W.size()[1])
self.embed.weight.data = W.clone()
self.embed.weight.requires_grad = True # Likely not needed
else:
vocab_size = len(dicts[0])
self.embed = nn.Embedding(
vocab_size + 2, embed_size) #add 2 to include UNK and PAD
# Set parameters:
maxlen = 200
embedding_dims = 200
nb_filter = 500
filter_length = 4
batch_size = 8
nb_epoch = 10
nb_labels = 50
train_data_path = "../mimicdata/mimic3/train_50.csv"
dev_data_path = "../mimicdata/mimic3/dev_50.csv"
test_data_path = "../mimicdata/mimic3/test_50.csv"
vocab = "../mimicdata/mimic3/vocab.csv"
embed_file = "../mimicdata/mimic3/processed_full.embed"
dicts = datasets.load_lookups(train_data_path, vocab, Y=nb_labels)
vocab_size = len(dicts[0])
embed_weight = extract_wvs.load_embeddings(embed_file)
# Load data
print('Loading data...')
def slim_data_generator(data_path):
while 1:
for batch_idx, tup in enumerate(
datasets.data_generator(data_path,
dicts,
batch_size=batch_size,
num_labels=nb_labels)):
X, y, _, code_set, descs = tup
X = sequence.pad_sequences(X, maxlen=maxlen)
yield X, y
