def load(self, model_dir): self._model_dir = model_dir self._paramsfile = os.path.join(self._model_dir, 'params.py') self._params = utils.load_param_file(self._paramsfile) self._num_before = utils.get_dict_value(self._params, "num_words_before") self._num_after = utils.get_dict_value(self._params, "num_words_after") ckpt = os.path.join(utils.get_dict_value(self._params,'output_location'), utils.get_dict_value(self._params, 'model_name') + '.ckpt') vocab_file = os.path.join(utils.get_dict_value(self._params, 'output_location'), 'vocab.pkl') self._e = Evaluator.load2(ckpt) self._i = TextIndexer.from_file(vocab_file) self._keywords = self._params['keywords'] self._id_to_word = self._params['id_to_keyword']
def load(self, model_dir): self._model_dir = model_dir self._paramsfile = os.path.join(self._model_dir, 'params.py') self._params = utils.load_param_file(self._paramsfile) self._num_before = utils.get_dict_value(self._params, "num_words_before") self._num_after = utils.get_dict_value(self._params, "num_words_after") ckpt = os.path.join(utils.get_dict_value(self._params,'output_location'), utils.get_dict_value(self._params, 'model_name') + '.ckpt') vocab_file = os.path.join(utils.get_dict_value(self._params, 'output_location'), 'vocab.pkl') self._e = Evaluator.load2(ckpt) self._i = TextIndexer.from_file(vocab_file) with open(os.path.join( utils.get_dict_value(self._params, 'output_location'), 'keywords.pkl'), 'rb') as f: keywords = pickle.load(f) self._params['keywords'] = keywords self._keywords = self._params['keywords'] self._keyword_map, self._keyword_list = gen_keywords(self._params)
def eval(params,
save_accuracy_file=True,
batch_size=5000,
num_batches=20,
topn=1,
verbose=True):
num_before = utils.get_dict_value(params, "num_words_before")
num_after = utils.get_dict_value(params, "num_words_after")
ckpt = os.path.join(utils.get_dict_value(params,'output_location'),
utils.get_dict_value(params, 'model_name') + '.ckpt')
accuracy_file = os.path.join(utils.get_dict_value(params,'output_location'),
'accuracy.txt')
vocab_file = os.path.join(utils.get_dict_value(params, 'output_location'), 'vocab.pkl')
keywords_file = os.path.join(utils.get_dict_value(params, 'output_location'), 'keywords.pkl')
e = Evaluator.load2(ckpt)
i = TextIndexer.from_file(vocab_file)
#test_sentence = "<S> ___ quick brown fox jumped over the lazy dog"
test_sentence = "<S> ___ is no way to know whether it will work"
#test_sentence = "<S> ___ house is on fire"
# test_sentence = "<S> ___ in your best interest to lie"
# test_sentence = "<S> ___ yours and I cannot touch it"
#test_sentence = "<S> I ate a ___ and an apple"
#test_sentence = "<S> I have to take ___ life away"
# test_sentence = "<S> ___ may and it is raining"
#test_sentence = "<S> This will take ___ before it will actually work"
#test_sentence = "<S> this is probably bigger ___ that"
# test_sentence = "<S> ___ is no place like home"
#test_sentence = "I have ___ of money"
#test_sentence = "<S> I think I ___ have it"
test_sentence = "<S> don 't forget to get orange , banana , and ___ ."
# test_sentence = "<S> in the heat ___ the night"
# test_sentence = "<S> in the river , ___ the boat"
# test_sentence = "<S> nothing can be ___ from the truth"
# test_sentence = "<S> the ___ knot will unwind"
# test_sentence = "<S> if you keep playing, you will ___ ."
test_sentence = "<s> I ate a ___ of oranges ."
# test_sentence = "<s> I ate a ___ and oranges ."
# test_sentence = "<s> I live in a ___ ."
# test_sentence = "<s> I ate a ___ of oranges ."
test_sentence = "<s> I ate a ___ and oranges ."
test_sentence = "<s> I live in a ___ ."
test_sentence = "<s> I have seen it on him , and can ___ to it ."
test_sentence = "<s> the thieves ___ the library and got very little for their pains ."
# input data
with open('/mnt/work/NeuralRewriting/eval/small_eval_data.json') as f:
data = json.load(f)
with open(keywords_file, 'rb') as f:
k = pickle.load(f)
unk_list = []
for q in data:
query_word = q['query_word']
orig_sent = q['orig_sent']
options = q['options']
orig_sent = orig_sent.replace(query_word, "___")
orig_sent = "<s> " + orig_sent
test_sentence = orig_sent.lower()
split_sentence = list(split_sentence_for_eval(test_sentence.split(), ["___"], num_before, num_after))
# print(split_sentence[0][0])
_, sentence, _, _ = i.index_wordlist(split_sentence[0][0])
bef = time()
r = e.eval({'sentence': [sentence]}, {'sm_decision'})
aft = time()
sm = r[0][0]
for o in options:
synonym = o['synonym']
if synonym not in k:
score = -1000
unk_list += [synonym]
else:
score = math.log(sm[k.index(synonym)])
o['clmtV1'] = score
print(score)
# save output
with open('/mnt/work/NeuralRewriting/eval/small_eval_data_out.json','w') as f:
json.dump(data,f)
from framework.evaluator import Evaluator
import framework.utils.common as utils
from framework.trainer import Trainer
import framework.subgraph.losses as losses
import logging
import sys
import os
from framework.utils.data.text_indexer import TextIndexer
import tensorflow as tf
sentences = ['Jimenez reported from San Jose Costa Rica ; Associated Press',
"We went to the store and I bought a banana",
"This is the cat that walked over the mat .",
"<pad> <pad> In this case I think the problem is"]
e = Evaluator.load2("outputv0.ckpt")
i = TextIndexer.from_file('vocab.pkl')
for sentence in sentences:
# for j in range(5):
# sentence = '<pad> ' + sentence + " <pad>"
_,indexed,_,_ = i.index_wordlist(sentence.split())
r = e.eval({'sentence': [indexed]}, {'sm_decision'})
print(sentence)
print(r)
from urllib.parse import urlparse
from http.server import BaseHTTPRequestHandler, HTTPServer
run_server = True
paramsfile = "params.py"
data_base_dir = ""
http_port = 8080
params = utils.load_param_file(paramsfile)
vocab_file = os.path.join(utils.get_dict_value(params,'output_location'), 'vocab.pkl')
ckpt = os.path.join(utils.get_dict_value(params,'output_location'),
utils.get_dict_value(params, 'model_name') + '.ckpt')
print(ckpt)
e = Evaluator.load2(ckpt)
i = TextIndexer.from_file(vocab_file)
num_before = utils.get_dict_value(params, "num_words_before")
num_after = utils.get_dict_value(params, "num_words_after")
pad_tok = utils.get_dict_value(params, "pad_tok", '<pad>')
def split_sentence_for_eval(sentence, keywords, num_before, num_after):
result = data.gen_data(sentence, keywords, num_before=num_before, num_after=num_after,
ignore_negative_data=True, add_redundant_keyword_data=False)
return result
def merge_sentence(sentence, num_before, num_after, mid_word):
before = sentence[:num_before]
after = sentence[num_after:]
rlist = (before + [mid_word] + after)
def eval(params,
save_accuracy_file=True,
batch_size=5000,
num_batches=20,
topn=1,
verbose=True):
num_before = utils.get_dict_value(params, "num_words_before")
num_after = utils.get_dict_value(params, "num_words_after")
ckpt = os.path.join(utils.get_dict_value(params,'output_location'),
utils.get_dict_value(params, 'model_name') + '.ckpt')
accuracy_file = os.path.join(utils.get_dict_value(params,'output_location'),
'accuracy.txt')
keywords = params['keywords']
rkeywords = params['id_to_keyword']
vocab_file = os.path.join(utils.get_dict_value(params, 'output_location'), 'vocab.pkl')
e = Evaluator.load2(ckpt)
i = TextIndexer.from_file(vocab_file)
e.dump_variable_sizes()
exit(0)
test_sentence = "it is better to die happy then to live miserably"
# test_sentence = "there going two make a turkey today"
# test_sentence = "they 're going two make a turkey today"
test_sentence = "to big to fail my ass !"
# test_sentence = "two big is not bad"
# test_sentence = "<S> two big fishes in the same bucket"
# test_sentence = "<S> there are two fishes in the same bucket ."
# test_sentence = "<S> there are too fishes in the same bucket ."
#test_sentence = "<S> I had two fishes for dinner"
test_sentence = "<S> its raining men . hallelujah !"
# test_sentence = "it 's head is too big"
#test_sentence = "if it 's not one than it 's true"
#test_sentence = "i would except it , but i don 't think it 's true"
print("HELLO")
print(keywords)
split_sentence = list(split_sentence_for_eval(test_sentence.split(), keywords, num_before, num_after))
print(split_sentence)
for j in range(len(split_sentence)):
print(split_sentence[j][0])
_, sentence, _, _ = i.index_wordlist(split_sentence[j][0])
bef = time()
r = e.eval({'sentence': [sentence]}, {'sm_decision'})
aft = time()
#print(r[0][0])
sm = r[0][0]
am = np.argmax(sm)
#print(am)
k = rkeywords
if am == 0:
print("DO NOTHING")
else:
print(k[am - 1])
k = [''] + k
sm, k = zip(*sorted(zip(sm, k), reverse=True))
# print(k)
for q,(x,y) in enumerate(zip(sm,k)):
if q > 10:
break
print("%0.4f %s" %(x,y))
print(test_sentence)
print("EVAL TIME = %s"%(aft-bef))