def __init__(self, opts, vocab, char_vocab, label_vocab):
super(Char_CNN, self).__init__()
random.seed(opts.seed)
torch.manual_seed(opts.seed)
torch.cuda.manual_seed(opts.seed)
# embedding parameters
self.embed_dim = opts.embed_size
self.char_embed_dim = opts.char_embed_size
self.vocab_size = vocab.m_size
self.char_num = char_vocab.m_size
self.pre_embed_path = opts.pre_embed_path
self.str2idx = vocab.str2idx
self.char_str2idx = char_vocab.str2idx
self.embed_uniform_init = opts.embed_uniform_init
# network parameters
self.stride = opts.stride
self.kernel_size = opts.kernel_size
self.kernel_num = opts.kernel_num
self.label_num = label_vocab.m_size
self.embed_dropout = opts.embed_dropout
self.fc_dropout = opts.fc_dropout
# gpu option
self.use_cuda = opts.use_cuda
# embeddings: word level and char level
self.word_embeddings = nn.Embedding(self.vocab_size, self.embed_dim)
self.char_embeddings = nn.Embedding(self.char_num, self.char_embed_dim)
if opts.pre_embed_path != '':
embedding = Embedding.load_predtrained_emb_zero(
self.pre_embed_path, self.str2idx)
self.word_embeddings.weight.data.copy_(embedding)
else:
nn.init.uniform_(self.word_embeddings.weight.data,
-self.embed_uniform_init, self.embed_uniform_init)
nn.init.uniform_(self.char_embeddings.weight.data,
-self.embed_uniform_init, self.embed_uniform_init)
word_char_embed_dim = self.embed_dim + len(
self.kernel_size) * self.kernel_num
self.word_char_convs = nn.ModuleList([
nn.Conv2d(1,
self.kernel_num, (K, word_char_embed_dim),
stride=self.stride,
padding=(K // 2, 0)) for K in self.kernel_size
])
self.char_convs = nn.ModuleList([
nn.Conv2d(1,
self.kernel_num, (K, self.char_embed_dim),
stride=self.stride,
padding=(K // 2, 0)) for K in self.kernel_size
])
infea = len(self.kernel_size) * self.kernel_num
self.linear1 = nn.Linear(infea, infea // 2)
self.linear2 = nn.Linear(infea // 2, self.label_num)
self.embed_dropout = nn.Dropout(self.embed_dropout)
self.fc_dropout = nn.Dropout(self.fc_dropout)
product_sentences_prior = order_products_prior.sort_values([
'order_id', 'add_to_cart_order'
]).groupby('order_id').apply(lambda order: order['product_id'].tolist())
product_sentences = product_sentences_prior.append(
product_sentences_train).values
return product_sentences
if __name__ == '__main__':
print('Generating sentences...')
product_sentences = gen_product_sentences()
print('Generating product_vector features...')
embedding = Embedding(product_sentences)
embedding.word_to_vector(size=100, window=5, min_count=2)
embedding.reduce_dimension(n_components=2)
product_vector_feat = embedding.return_dataframe(name='product_id')
product_vector_feat['product_id'] = product_vector_feat[
'product_id'].astype(np.int)
product_vector_feat['product_id_vector_1'] = product_vector_feat[
'product_id_vector_1'].astype(np.float)
product_vector_feat['product_id_vector_2'] = product_vector_feat[
'product_id_vector_1'].astype(np.float)
product_vector_feat.set_index('product_id', inplace=True)
pickle_dump(product_vector_feat,
'{}/product_vector_feat.pkl'.format(config.feat_folder))
print('Done - product_vector features')