from typing import Set, Dict, List
import random
import numpy as np
import os
import pickle
from qanta.util.io import safe_open
from qanta.config import conf
from qanta import logging
log = logging.get(__name__)
def create_embeddings(vocab: Set[str], expand_glove=False, mask_zero=False):
"""
Create embeddings
:param vocab: words in the vocabulary
:param expand_glove: Whether or not to expand embeddings past pre-trained ones
:param mask_zero: if True, then 0 is reserved as a sequence length mask (distinct from UNK)
:return:
"""
embeddings = []
embedding_lookup = {}
with open(conf['word_embeddings']) as f:
i = 0
line_number = 0
n_bad_embeddings = 0
if mask_zero:
emb = np.zeros((conf['embedding_dimension']))
embeddings.append(emb)
import time
import pickle
import numpy as np
from qanta import logging
from qanta.guesser.util import gen_util
from qanta.util.io import safe_open
from qanta.guesser.classify.learn_classifiers import evaluate, compute_vectors
from qanta.guesser.util.adagrad import Adagrad
from qanta.guesser.util.functions import relu, drelu
from qanta.util.constants import (DEEP_WE_TARGET, DEEP_DAN_PARAMS_TARGET, DEEP_TRAIN_TARGET,
DEEP_DEV_TARGET, DEEP_DAN_TRAIN_OUTPUT, DEEP_DAN_DEV_OUTPUT)
log = logging.get(__name__)
def objective_and_grad(data, params, d, len_voc, word_drop=0.3, rho=1e-5):
params = gen_util.unroll_params(params, d, len_voc, deep=3)
(W, b, W2, b2, W3, b3, L) = params
grads = gen_util.init_grads(d, len_voc, deep=3)
error_sum = 0.0
for qs, ans in data:
# answer vector
comp = L[:, ans[0]].reshape((d, 1))
history = []
for dist in qs:
sent = qs[dist]
