def main(sentences,
wordfile: str,
weightfile: str,
weightpara: float = 1e-3,
rmpc: int = 1):
# load word vectors
(words, We) = data_io.getWordmap(wordfile)
# load word weights
word2weight = data_io.getWordWeight(
weightfile,
weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(
words, word2weight) # weight4ind[i] is the weight for the i-th word
# load sentences
x, m, _ = data_io.sentences2idx(
sentences, words
) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
w = data_io.seq2weight(x, m, weight4ind) # get word weights
# set parameters
params = params.params()
params.rmpc = rmpc
# get SIF embedding
embedding = SIF_embedding.SIF_embedding(
We, x, w, params) # embedding[i,:] is the embedding for sentence i
def SIFDocEmbedding(w2vdict, weighttxt, txtfile):
weightpara = 1e-3 # the parameter in the SIF weighting scheme, usually in the range [3e-5, 3e-3]
(words, We) = getWordMap(w2vdict)
word2weight = data_io.getWordWeight(
weighttxt, word2weight_pickle_file,
weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(
words, word2weight) # weight4ind[i] is the weight for the i-th word
DocVectorDict = {}
DocSentVecDict = {}
docNum = 0
with open(txtfile, 'r') as reader:
txt = reader.readlines()
reader.close()
for doc in txt:
doc = doc.strip()
sentEm = SIFSentEmbedding(weighttxt,
doc,
words,
We,
weight4ind,
weightpara=1e-3,
paramm=1)
DocSentVecDict[docNum] = sentEm
docVector = (np.sum(sentEm, axis=1)) / (sentEm.shape[0])
DocVectorDict[docNum] = docVector
docNum += 1
return DocVectorDict, DocSentVecDict, We
def load_embeddings(wordfile, weightfile, weightpara=5e-4, word2vec=False):
if word2vec:
(words, We) = getWordmapWord2Vec(wordfile)
else:
(words, We) = data_io.getWordmap(wordfile)
word2weight = data_io.getWordWeight(
weightfile,
weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(
words, word2weight) # weight4ind[i] is the weight for the i-th word
return words, We, weight4ind
def get_embs(sentences, params):
# load word vectors
(words, We) = data_io.getWordmap(wordfile)
# load word weights
word2weight = data_io.getWordWeight(weightfile, weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(words, word2weight) # weight4ind[i] is the weight for the i-th word
# load sentences
x, m = data_io.sentences2idx(sentences, words) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
w = data_io.seq2weight(x, m, weight4ind) # get word weights
# get SIF embedding
embedding = SIF_embedding.SIF_embedding(We, x, w, params) # embedding[i,:] is the embedding for sentence i
return embedding
def __init__(self):
self.weightfile = config.url_enwiki
self.weightpara = 1e-3
print("Getting embeddings from the Glove pickles")
with open(config.url_glove_pickle_we_1, "rb") as file:
We_1 = pickle.load(file)
with open(config.url_glove_pickle_words_1, "rb") as file:
words_1 = pickle.load(file)
with open(config.url_glove_pickle_we_2, "rb") as file:
We_2 = pickle.load(file)
with open(config.url_glove_pickle_words_2, "rb") as file:
words_2 = pickle.load(file)
with open(config.url_glove_pickle_we_3, "rb") as file:
We_3 = pickle.load(file)
with open(config.url_glove_pickle_words_3, "rb") as file:
words_3 = pickle.load(file)
self.We = []
self.We.extend(We_1)
self.We.extend(We_2)
self.We.extend(We_3)
self.words = {}
self.words.update(words_1)
self.words.update(words_2)
self.words.update(words_3)
with open(config.url_snli_pc1, "rb") as file:
self.snli_pc_1 = pickle.load(file)
with open(config.url_snli_pc2, "rb") as file:
self.snli_pc_2 = pickle.load(file)
print("Successfully got the embeddings from the pickle")
self.word2weight = data_io.getWordWeight(
self.weightfile, self.weightpara
) # word2weight['str'] is the weight for the word 'str'
self.weight4ind = data_io.getWeight(
self.words,
self.word2weight) # weight4ind[i] is the weight for the i-th word
def get_sif(dataset):
wordfile = '../data/glove.6B.50d.txt' # word vector file, can be downloaded from GloVe website
weightfile = '../auxiliary_data/enwiki_vocab_min200.txt' # each line is a word and its frequency
weightpara = 2.7e-4 # the parameter in the SIF weighting scheme, usually in the range [3e-5, 3e-3]
rmpc = 0 # number of principal components to remove in SIF weighting scheme
# load word vectors
(words, We) = data_io.getWordmap(wordfile)
# load word weights
word2weight = data_io.getWordWeight(
weightfile,
weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(
words, word2weight) # weight4ind[i] is the weight for the i-th word
param = params.params()
param.rmpc = rmpc
sentence_embedding_all = get_sentences_embedding(dataset, words,
weight4ind, param, We)
# sentence_embedding_all = turn2std(sentence_embedding_all) # 将矩阵转换为标准矩阵
return sentence_embedding_all
def main(word_embeddings_path, word_weight_path, out_dir):
wordfile = word_embeddings_path
weightfile = word_weight_path
weightparas = [1e-2, 1e-3, 1e-4]
(words, We) = getWordmap(wordfile)
vector_file = open(os.path.join(out_dir, "vectors"), "w")
pickle.dump(We, vector_file)
words_file = open(os.path.join(out_dir, "words"), "w")
pickle.dump(words, words_file)
for weightpara in weightparas:
print("calculating word2weight with a = {}.".format(weightpara))
word2weight = data_io.getWordWeight(weightfile, weightpara)
print("calculating weight4ind with a = {}.".format(weightpara))
weight4ind = data_io.getWeight(words, word2weight)
weight4ind_file = open(
os.path.join(out_dir,
"weight4ind_weightpara_%.E" % Decimal(weightpara)),
'w')
pickle.dump(weight4ind, weight4ind_file)
def sif_embedding(sen):
import sys
#sys.path.append("../src")
#sys.path.append("../data")
import data_io, params, SIF_embedding
import params
import SIF_embedding
# input
wordfile = 'data/dic_files.txt' # word vector file, can be downloaded from GloVe website
weightfile = 'data/dic_freq.txt' # each line is a word and its frequency
weightpara = 1e-3 # the parameter in the SIF weighting scheme, usually in the range [3e-5, 3e-3]
rmpc = 1 # number of principal components to remove in SIF weighting scheme
# sentences = ['这是一个例句', '这是一个更长一些的例句']
# sentences = ['昨天天气不错', '这是一个更长一些的例句']
sentences = sen
# sentences = ['this is an example sentence', 'this is another sentence that is slightly longer']
# load word vectors
(words, We) = data_io.getWordmap(wordfile)
# print(words,We) #单词，和词向量
# load word weights
word2weight = data_io.getWordWeight(
weightfile,
weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(
words, word2weight) # weight4ind[i] is the weight for the i-th word
# load sentences
# x, m, _ = data_io.sentences2idx(sentences, words) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
x, m = data_io.sentences2idx(
sentences, words
) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
# print(x,m)
w = data_io.seq2weight(x, m, weight4ind) # get word weights
# print('word weight:',w)
# set parameters
# params = params.params()
params = params.params_all() # name 'params' is not defined
params.rmpc = rmpc
# get SIF embedding
embedding = SIF_embedding.SIF_embedding(
We, x, w, params) # embedding[i,:] is the embedding for sentence i
return embedding
def vectorize_sif(filename):
class params(object):
def __init__(self):
self.LW = 1e-5
self.LC = 1e-5
self.eta = 0.05
def __str__(self):
t = "LW", self.LW, ", LC", self.LC, ", eta", self.eta
t = map(str, t)
return ' '.join(t)
# input
wordfile = 'glove.6B.100d.txt' # word vector file, can be downloaded from GloVe website
weightfile = 'enwiki_vocab_min200.txt' # each line is a word and its frequency
weightpara = 1e-3 # the parameter in the SIF weighting scheme, usually in the range [3e-5, 3e-3]
rmpc = 1 # number of principal components to remove in SIF weighting scheme
#sentiment_file = '../data/sentiment-test' # sentiment data file
#cleanfile = "2/D1026-A.M.100.E.10.segs.cl"
#sentiment_file = '../data/clean-5.txt'
# load word vectors
(words, We) = data_io.getWordmap(wordfile)
# load word weights
word2weight = data_io.getWordWeight(
weightfile,
weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(
words, word2weight) # weight4ind[i] is the weight for the i-th word
# load sentences (here use sentiment data as an example)
#x, m, _ = data_io.sentiment2idx(sentiment_file, words) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
x, m = data_io.sentiment2idx(filename, words)
w = data_io.seq2weight(x, m, weight4ind) # get word weights
# parameters
params = params()
#params = params.params()
params.rmpc = rmpc
# get SIF embedding
embedding = SIF_embedding_lib.SIF_embedding(
We, x, w, params) # embedding[i,:] is the embedding for sentence i
return embedding
def load_model():
wordfile = "glove path (glove.840B.300d.txt file)" # you can download glove from https://www.kaggle.com/takuok/glove840b300dtxt
weightfile = artifact_path + '/SIF/enwiki_vocab_min200.txt' # each line is a word and its frequency
weightpara = 1e-3 # the parameter in the SIF weighting scheme, usually in the range [3e-5, 3e-3]
rmpc = 1 # number of principal components to remove in SIF weighting scheme
(words, We) = data_io.getWordmap(wordfile)
a = list(words.keys())
for i, v in enumerate(a):
words[v.decode("utf-8")] = words.pop(v)
# load word weights
word2weight = data_io.getWordWeight(
weightfile,
weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(
words, word2weight) # weight4ind[i] is the weight for the i-th word
return (words, weight4ind, rmpc, We)
def load_embed(wordfile, weightfile, weightpara=1e-3, param=None, rmpc=0):
'''
wordfile: : location of embedding data (e.g., glove embedings)
weightfile: : location of TF data for words
weightpara: : the parameter in the SIF weighting scheme, usually in range [3e-5, 3e-3]
rmpc: : number of principal components to remove in SIF weighting scheme
'''
# input
wordfile = '/home/francisco/GitHub/SIF/data/glove.840B.300d.txt' # word vector file, can be downloaded from GloVe website
weightfile = '/home/francisco/GitHub/SIF/auxiliary_data/enwiki_vocab_min200.txt' # each line is a word and its frequency
# load word vectors
(words, Weights) = data_io.getWordmap(wordfile)
# load word weights
word2weight = data_io.getWordWeight(weightfile, weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(words, word2weight) # weight4ind[i] is the weight for the i-th word
# set parameters
param.rmpc = rmpc
return Weights, words, word2weight, weight4ind
def get_sent_vec(sentences):
import params
# 详见data_io.py
(words, We) = data_io.getWordmap(wordfile)
# 详见data_io.py
word2weight = data_io.getWordWeight(weightfile, weightpara)
weight4ind = data_io.getWeight(words, word2weight)
# 详见data_io.py
x, m = data_io.sentences2idx(sentences, words)
w = data_io.seq2weight(x, m, weight4ind)
# 参数设置
params = params.params()
params.rmpc = rmpc
# 调用SIF核心算法计算句向量，详见SIF_core
embedding = SIF_core.SIF_embedding(We, x, w, params)
get_sent_vec = {}
for i in range(len(embedding)):
get_sent_vec[sentences[i]] = embedding[i]
return get_sent_vec
wordfiles = [ #'../data/paragram_sl999_small.txt', # need to download it from John Wieting's github (https://github.com/jwieting/iclr2016)
'/Users/sherryruan/data/glove/glove.6B/glove.6B.300d.txt' # need to download it first
]
weightfile = '../auxiliary_data/enwiki_vocab_min200.txt'
weightparas = [-1, 1e-3] #[-1,1e-1,1e-2,1e-3,1e-4]
rmpcs = [0, 1] # [0,1,2]
params = params.params()
parr4para = {}
sarr4para = {}
for wordfile in wordfiles:
(words, We) = data_io.getWordmap(wordfile)
for weightpara in weightparas:
word2weight = data_io.getWordWeight(weightfile, weightpara)
weight4ind = data_io.getWeight(words, word2weight)
for rmpc in rmpcs:
print('word vectors loaded from %s' % wordfile)
print('word weights computed from %s using parameter a=%f' %
(weightfile, weightpara))
params.rmpc = rmpc
print('remove the first %d principal components' % rmpc)
## eval just one example dataset
parr, sarr = eval.sim_evaluate_one(
We, words, weight4ind, sim_algo.weighted_average_sim_rmpc,
params)
## eval all datasets; need to obtained datasets from John Wieting (https://github.com/jwieting/iclr2016)
# parr, sarr = eval.sim_evaluate_all(We, words, weight4ind, sim_algo.weighted_average_sim_rmpc, params)
paras = (wordfile, weightfile, weightpara, rmpc)
parr4para[paras] = parr
sarr4para[paras] = sarr
def run():
parser = ArgumentParser()
parser.add_argument(
"--dataset_path",
type=str,
default="",
help="Path or url of the dataset. If empty download from S3.")
parser.add_argument("--dataset_cache",
type=str,
default='./dataset_cache',
help="Path or url of the dataset cache")
parser.add_argument("--model",
type=str,
default="gpt",
help="Model type (gpt or gpt2)")
parser.add_argument("--model_checkpoint",
type=str,
default="",
help="Path, url or short name of the model")
parser.add_argument(
"--max_history",
type=int,
default=2,
help="Number of previous utterances to keep in history")
parser.add_argument("--device",
type=str,
default="cuda" if torch.cuda.is_available() else "cpu",
help="Device (cuda or cpu)")
parser.add_argument("--no_sample",
action='store_true',
help="Set to use greedy decoding instead of sampling")
parser.add_argument("--max_length",
type=int,
default=20,
help="Maximum length of the output utterances")
parser.add_argument("--min_length",
type=int,
default=1,
help="Minimum length of the output utterances")
parser.add_argument("--seed", type=int, default=42, help="Seed")
parser.add_argument("--temperature",
type=int,
default=0.7,
help="Sampling softmax temperature")
parser.add_argument(
"--top_k",
type=int,
default=0,
help="Filter top-k tokens before sampling (<=0: no filtering)")
parser.add_argument(
"--top_p",
type=float,
default=0.9,
help="Nucleus filtering (top-p) before sampling (<=0.0: no filtering)")
args = parser.parse_args()
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__file__)
logger.info(pformat(args))
if args.model_checkpoint == "":
args.model_checkpoint = download_pretrained_model()
random.seed(args.seed)
torch.random.manual_seed(args.seed)
torch.cuda.manual_seed(args.seed)
logger.info("Get pretrained model and tokenizer")
tokenizer_class = GPT2Tokenizer if "gpt2" == args.model else OpenAIGPTTokenizer
tokenizer = tokenizer_class.from_pretrained(args.model_checkpoint)
model_class = GPT2LMHeadModel if "gpt2" == args.model else OpenAIGPTLMHeadModel
model = model_class.from_pretrained(args.model_checkpoint)
model.to(args.device)
add_special_tokens_(model, tokenizer)
logger.info("Sample a personality")
#personalities = get_dataset_personalities(tokenizer, args.dataset_path, args.dataset_cache)
#personality = random.choice(personalities)
#logger.info("Selected personality: %s", tokenizer.decode(chain(*personality)))
wordfile = './data/truncate.txt' # word vector file, can be downloaded from GloVe website
weightfile = './auxiliary_data/enwiki_vocab_min200.txt' # each line is a word and its frequency
weightpara = 1e-3 # the parameter in the SIF weighting scheme, usually in the range [3e-5, 3e-3]
# load word vectors
(words, We) = data_io.getWordmap(wordfile)
# load word weights
word2weight = data_io.getWordWeight(
weightfile,
weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(
words, word2weight) # weight4ind[i] is the weight for the i-th word
p = 0
start_time = time.time()
with open('data_volunteers.json') as json_file:
json_data = json.load(json_file)
for i in json_data:
p += 1
#if p <1100:
# continue
history = []
personality = []
query_set = []
json_dialog = i["dialog"]
json_bot = i["bot_profile"]
for j in json_bot:
personality.append(tokenizer.encode(j))
#logger.info("Selected personality: %s", tokenizer.decode(chain(*personality)))
persona = tokenizer.decode(chain(*personality))
row = {"Personality": persona}
text = []
for j in json_dialog:
if j["sender_class"] == "Human":
json_text = j["text"]
raw_text = json_text
check = tokenizer.decode(tokenizer.encode(raw_text),
skip_special_tokens=True)
if check == "":
history.append(tokenizer.encode(raw_text))
with torch.no_grad():
out_ids = normal_sample_sequence(
personality, history, tokenizer, model, args)
# history.append(out_ids)
history = history[-(2 * args.max_history + 1):]
out_text = tokenizer.decode(out_ids,
skip_special_tokens=True)
text.append({
"evaluation_score": j["evaluation_score"],
"id": j["id"],
"sender": j["sender"],
"sender_class": j["sender_class"],
"text": raw_text,
"generated_text": out_text
})
continue
history.append(tokenizer.encode(raw_text))
with torch.no_grad():
out_ids = sample_sequence(personality, history,
tokenizer, model, args,
words, weight4ind, We)
# history.append(out_ids)
history = history[-(2 * args.max_history + 1):]
out_text = tokenizer.decode(out_ids,
skip_special_tokens=True)
text.append({
"evaluation_score": j["evaluation_score"],
"id": j["id"],
"sender": j["sender"],
"sender_class": j["sender_class"],
"text": raw_text,
"generated_text": out_text
})
else:
json_text = j["text"]
raw_text = json_text
history.append(tokenizer.encode(raw_text))
text.append({
"evaluation_score": j["evaluation_score"],
"id": j["id"],
"sender": j["sender"],
"sender_class": j["sender_class"],
"text": raw_text
})
row["dialog"] = text
query_set.append(row)
#print(query_set)
with open('./sif_set/sif' + str(p) + '.json',
'w',
encoding='utf-8') as make_file:
json.dump(query_set, make_file)
if not p % 10:
print(
str(p * 100 / 1111) + '%, ' +
str(time.time() - start_time) + 'sec')
'''
def get_embedding(self, sentences, language='Chinese', weightpara=1e-3):
"""
This function return the embeddings for all sentences in the input parameter: sentences
sentences is a list of sentencs need for SIF embeddings
"""
if language == 'Chinese':
# word vector file
# For model2：
# wordfile =
# For model1：
# wordfile='../models/wiki_news_word_vector_small2.txt'
# word frequency file
# weightfile =
words = self.words_chi
word2weight = self.word2weight_chi
We = self.We_chi
else:
# for english use:
# wordfile =
# wordfile='../models/glove.840B.300d.txt'
# weightfile =
# weightpara = 1e-5
# weightpara = 1e-3 # the parameter in the SIF weighting scheme, usually in the range [3e-5, 3e-3]
words = self.words_eng
word2weight = self.word2weight_eng
We = self.We_eng
rmpc = 1 # number of principal components to remove in SIF weighting scheme
weight4ind = data_io.getWeight(words, word2weight)
print('weight4ind finished ')
# load sentences
if language == 'Chinese':
x, m = data_io.sentences2idx_c(sentences, words)
else:
x, m = data_io.sentences2idx(sentences, words)
# print (x.shape) # (句子的数量，最长的句子的单词的数量)
# print (m.shape) # (句子的数量，最长的句子的单词的数量)
print('sentences2idx finished ')
w = data_io.seq2weight(x, m, weight4ind) # get word weights
print('seq2weight finished ')
# set parameters
param = params.params()
param.rmpc = rmpc
# get SIF embedding
"""
return 所有需要计算similarity的title，全文，句子的embedding。
paper 里面用的是TruncatedSVD，project 要求我们用PCA方法decomposite
"""
print('embedding start ')
embedding = SIF_embedding.SIF_embedding(
We, x, w, param,
method='PCA') # embedding[i,:] is the embedding for sentence i
print('embedding finished ')
print(embedding.shape)
return embedding
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-d',
'--dataname',
default='t6',
help='dataset name',
choices=['t6', 't26', '2C'])
parser.add_argument('-c',
'--classifiername',
default='RF',
help='which classifier to use',
choices=['GaussianNB', 'RF', 'SVM', 'KNN'])
args = parser.parse_args()
data_name = args.dataname # t6 or t26, 2C, 4C
clf_name = args.classifiername # classfier
# Original SIF paper used glove.840B.300d, we use the ones that were trained on twitter.
embed_dims = [100] # can add 25, 50, 200 dimension if needed
wordfile_list = [
'../data/glove.twitter.27B.{}d.txt'.format(dim) for dim in embed_dims
]
# each line is a word and its frequency
weightfile = 'SIF-master/auxiliary_data/enwiki_vocab_min200.txt'
# the parameter in the SIF weighting scheme, usually in the range [3e-5, 3e-3]
weightpara = 1e-3
# number of principal components to remove in SIF weighting scheme
rmpc = 1
for wordfile, dim in zip(wordfile_list, embed_dims):
# load word vectors
(words, We) = data_io.getWordmap(wordfile)
# load word weights
# word2weight['str'] is the weight for the word 'str'
word2weight = data_io.getWordWeight(weightfile, weightpara)
# weight4ind[i] is the weight for the i-th word
weight4ind = data_io.getWeight(words, word2weight)
data_path = "../data/"
if data_name == "t6":
file_path = data_path + "CrisisLexT6_cleaned/"
disasters = [
"sandy", "queensland", "boston", "west_texas", "oklahoma",
"alberta"
]
test_list = [
"{}_glove_token.csv.unique.csv".format(disaster)
for disaster in disasters
]
train_list = [
"{}_training.csv".format(disaster) for disaster in disasters
]
if data_name == "t26":
file_path = data_path + "CrisisLexT26_cleaned/"
disasters = [
"2012_Colorado_wildfires", "2013_Queensland_floods",
"2013_Boston_bombings", "2013_West_Texas_explosion",
"2013_Alberta_floods", "2013_Colorado_floods",
"2013_NY_train_crash"
]
test_list = [
"{}-tweets_labeled.csv.unique.csv".format(disaster)
for disaster in disasters
]
train_list = [
"{}_training.csv".format(disaster) for disaster in disasters
]
if data_name == "2C":
file_path = data_path + "2CTweets_cleaned/"
disasters = [
"Memphis", "Seattle", "NYC", "Chicago", "SanFrancisco",
"Boston", "Brisbane", "Dublin", "London", "Sydney"
]
test_list = [
"{}2C.csv.token.csv.unique.csv".format(disaster)
for disaster in disasters
]
train_list = [
"{}2C_training.csv".format(disaster) for disaster in disasters
]
accu_list = []
roc_list = []
precision_list = []
recall_list = []
f1_list = []
for train, test in zip(train_list, test_list):
train_file = os.path.join(file_path, train)
test_file = os.path.join(file_path, test)
xtrain, ytrain = load_data(data_name, train_file)
xtest, ytest = load_data(data_name, test_file)
# load train
# xtrain_windx is the array of word indices, m_train is the binary mask indicating whether there is a word in that location
xtrain_windx, m_train = data_io.sentences2idx(xtrain, words)
w_train = data_io.seq2weight(xtrain_windx, m_train,
weight4ind) # get word weights
# set parameters
paramss = params.params()
paramss.rmpc = rmpc
# get SIF embedding
train_embed = SIF_embedding.SIF_embedding(
We, xtrain_windx, w_train,
paramss) # embedding[i,:] is the embedding for sentence i
# load target
# xtest_windx is the array of word indices, m_test is the binary mask indicating whether there is a word in that location
xtest_windx, m_test = data_io.sentences2idx(xtest, words)
# get word weights
w_test = data_io.seq2weight(xtest_windx, m_test, weight4ind)
# set parameters
paramsss = params.params()
paramsss.rmpc = rmpc
# get SIF embedding
test_embed = SIF_embedding.SIF_embedding(
We, xtest_windx, w_test,
paramsss) # embedding[i,:] is the embedding for sentence i
print(test)
accu, roc, precision, recall, f1 = run_classifier(
train_embed, ytrain, test_embed, ytest, clf_name, 100)
accu_list.append(accu)
roc_list.append(roc)
precision_list.append(precision)
recall_list.append(recall)
f1_list.append(f1)
print("{}_SIF_{}_LOO_accuracy {}".format(data_name,
clf_name + str(dim),
accu_list))
print("{}_SIF_{}_LOO_roc {}".format(data_name, clf_name + str(dim),
roc_list))
print("{}_SIF_{}_LOO_precision {}".format(data_name,
clf_name + str(dim),
precision_list))
print("{}_SIF_{}_LOO_recall {}".format(data_name, clf_name + str(dim),
recall_list))
print("{}_SIF_{}_LOO_f1 {}".format(data_name, clf_name + str(dim),
f1_list))
print(
"{0}_SIF_LOO_{1} {2:.4f} + {3:.4f} {4:.4f} + {5:.4f} {6:.4f} + {7:.4f} {8:.4f} + {9:.4f} {10:.4f} + {11:.4f}"
.format(data_name, clf_name + str(dim), np.mean(accu_list),
np.std(accu_list), np.mean(roc_list), np.std(roc_list),
np.mean(f1_list), np.std(f1_list), np.mean(precision_list),
np.std(precision_list), np.mean(recall_list),
np.std(recall_list)))
def SIF_master(segfile, cleanfile, directory, summ_ind):
print "segfile: ", segfile
print "clean file: ", cleanfile
#cleanfile = cleanfile+".ls"
class params(object):
def __init__(self):
self.LW = 1e-5
self.LC = 1e-5
self.eta = 0.05
def __str__(self):
t = "LW", self.LW, ", LC", self.LC, ", eta", self.eta
t = map(str, t)
return ' '.join(t)
# input
wordfile = 'glove.6B.100d.txt' # word vector file, can be downloaded from GloVe website
weightfile = 'enwiki_vocab_min200.txt' # each line is a word and its frequency
weightpara = 1e-3 # the parameter in the SIF weighting scheme, usually in the range [3e-5, 3e-3]
rmpc = 1 # number of principal components to remove in SIF weighting scheme
#sentiment_file = '../data/sentiment-test' # sentiment data file
#cleanfile = "2/D1026-A.M.100.E.10.segs.cl"
#sentiment_file = '../data/clean-5.txt'
# load word vectors
(words, We) = data_io.getWordmap(wordfile)
# load word weights
word2weight = data_io.getWordWeight(
weightfile,
weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(
words, word2weight) # weight4ind[i] is the weight for the i-th word
# load sentences (here use sentiment data as an example)
#x, m, _ = data_io.sentiment2idx(sentiment_file, words) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
x, m = data_io.sentiment2idx(cleanfile, words)
w = data_io.seq2weight(x, m, weight4ind) # get word weights
# parameters
params = params()
#params = params.params()
params.rmpc = rmpc
# get SIF embedding
embedding = SIF_embedding_lib.SIF_embedding(
We, x, w, params) # embedding[i,:] is the embedding for sentence i
#segfile = segfile+".segs"
f = open(segfile).readlines()
indexes = []
matches = []
for item in f:
ind = item.rfind("&")
indexes.append(item[:ind + 1])
if len(indexes) == len(embedding):
for ind in range(0, len(indexes)):
lines = indexes[ind] + str(list(embedding[ind]))
matches.append(lines)
else:
print "length doesn't match!! Check if there is empty line!!"
#fname = directory +'/'+str(summ_ind)+ '/' + getRealName(segfile) + '.ls'
#fname = directory +'/'+str(summ_ind)+ '/' + segfile + '.ls'
fname = directory + '/' + str(summ_ind) + '/' + getRealName(segfile)
print fname
with open(fname + ".ls", "w") as file:
for item in matches:
file.write(item + "\n")
return embedding
# srcsent = ['Pada mulanya, waktu Allah mulai menciptakan alam semesta']
# tgtsent = ['God saw the light, and saw that it was good. God divided the light from the darkness.']
# params = params.params()
weightpara = 1e-3
rmpc = 1
# def srcEmbedding(srcWordFilePath, srcsent):
src_model_300 = gensim.models.KeyedVectors.load_word2vec_format(
srcWordFilePath, binary=False)
srcwords = {}
for index, word in enumerate(src_model_300.wv.index2entity):
srcwords[word] = index
srcWe = src_model_300.wv.vectors
srcword2weight = data_io.getWordWeight(src_model_300.wv.vocab, weightpara)
srcweight4ind = data_io.getWeight(srcwords, srcword2weight)
srcx, srcm = data_io.sentences2idx(srcsent, srcwords)
srcw = data_io.seq2weight(srcx, srcm, srcweight4ind)
srcparams = params.params()
srcparams.rmpc = rmpc
srcEmbedding = SIF_embedding.SIF_embedding(srcWe, srcx, srcw, srcparams)
# return embedding
# def tgtEmbedding(tgtWordFilePath, tgtsent):
tgtmodel_300 = gensim.models.KeyedVectors.load_word2vec_format(tgtWordFilePath,
binary=False)
tgtwords = {}
for index, word in enumerate(tgtmodel_300.wv.index2entity):
tgtwords[word] = index
tgtWe = tgtmodel_300.wv.vectors
tgtword2weight = data_io.getWordWeight(tgtmodel_300.wv.vocab, weightpara)
wordfile = '../models/glove_full_grams_sg_300_wiki.txt'
weightfile = '../AraSIF_word_counts/arwiki_vocab_min200.txt' # each line is a word and its frequency
weightpara = 1e-3 # the parameter in the SIF weighting scheme, usually in the range [3e-5, 3e-3]
rmpc = 1 # number of principal components to remove in SIF weighting scheme
# load word vectors
print("Reading embedding matrix. Hang on! this will take a while ...")
(glove_words, We) = data_io.getWordmap(wordfile)
print("shape of Word embedding is: " + str(We.shape))
# load word weights
word2weight = data_io.getWordWeight(
weightfile,
weightpara) # word2weight['str'] is the weight for the word 'str'
weight4ind = data_io.getWeight(
glove_words, word2weight) # weight4ind[i] is the weight for the i-th word
# set parameters
params = params.params()
params.rmpc = rmpc
# load sentences
print("reading the input sentences now & converting to indices .. \n")
sample_sents = read_NMT_data.read_data(sample_ara)
# AraSIF embedding for sample sentences
print("computing AraSIF embedding now ...\n")
# x is the array of word indices, m is the binary mask indicating whether there is a word in that location
x, m = data_io.sentences2idx(sample_sents, glove_words)
w = data_io.seq2weight(x, m, weight4ind) # get word weights
line = line.strip()
line = line.split(':')[1]
sentences.append(line)
glove_word2vector_path = './chinese_data_douban_cropus_vectors.txt' # word vector file, can be downloaded from GloVe website
word_freauency_path = './douban_cropus_vocab.txt' # each line is a word and its frequency
weightpara = 1e-3
rmpc = 1
# load word vectors
(Word2Indx, Word2vector) = data_io.getWordmap(glove_word2vector_path)
# load word weights
word2weight = data_io.getWordWeight(
word_freauency_path,
weightpara) # word2weight['str'] is the weight for the word 'str'
Index2Weight = data_io.getWeight(
Word2Indx, word2weight) # weight4ind[i] is the weight for the i-th word
word_idx_seq_of_sentence, mask = data_io.sentences2idx(
sentences, Word2Indx
) # x is the array of word indices, m is the binary mask indicating whether there is a word in that location
word_weight_of_sentence = data_io.seq2weight(word_idx_seq_of_sentence, mask,
Index2Weight) # get word weights
# set parameters
params = params.params()
params.rmpc = rmpc
embedding = SIF_embedding.SIF_embedding(Word2vector, word_idx_seq_of_sentence,
word_weight_of_sentence, params)
np.save("douban_sentence2vector.npy", embedding)