khuangaf

# compute average hit rate for all users
def precision_at_k(predictions, k):
    '''
    Return the average ndcg for each users
    args:
        predictions: np.array user-item predictions
    returns:
        hit_rate: float, computed hit rate
    '''

khuangaf

# compute average hit rate for all users
def precision_at_k(predictions, k):
    '''
    Return the average ndcg for each users
    args:
        predictions: np.array user-item predictions
    returns:
        hit_rate: float, computed hit rate
    '''

khuangaf

class CustomBERTModel(BertPreTrainedModel):

    def __init__(self, config, num_class):
        super(CustomBERTModel, self).__init__(config)
        self.bert = BertModel(config)
        self.linear = nn.Linear(config.hidden_size, num_class)

model = CustomBERTModel.from_pretrained('bert-base-uncased',num_class=10)

khuangaf

model = BertModel.from_pretrained('bert-base-uncased')

khuangaf

all_doc_tokens=['SEP']
orig_to_tok_index=[]
for (i, word) in enumerate(words):
    orig_to_tok_index.append(len(all_doc_tokens))
    sub_tokens = tokenizer.tokenize(token)
    all_doc_tokens.extend(sub_tokens)

khuangaf

tokenizer.convert_tokens_to_ids(tokens)

khuangaf

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
tokens = tokenizer.tokenize('Learn Hugging Face Transformers & BERT with PyTorch in 5 Minutes')
tokens = ['[CLS]'] + tokens + ['[SEP]']

khuangaf

# infer the topic distribution of the second corpus.
lda[common_corpus[1]]
'''
output
[(0, 0.014287902),
 (1, 0.014287437),
 (2, 0.014287902),
 (3, 0.014285716),
 (4, 0.014285716),
 (5, 0.014285714),

khuangaf

from gensim.test.utils import common_texts
from gensim.corpora.dictionary import Dictionary
from gensim.models import LdaModel

# Create a corpus from a list of texts
common_dictionary = Dictionary(common_texts)
common_corpus = [common_dictionary.doc2bow(text) for text in common_texts]

# Train the model on the corpus.
lda = LdaModel(common_corpus, num_topics=10)

khuangaf

from gensim.test.utils import common_texts
from gensim.corpora.dictionary import Dictionary
from gensim.models import LdaModel

# Create a corpus from a list of texts
common_dictionary = Dictionary(common_texts)
common_corpus = [common_dictionary.doc2bow(text) for text in common_texts]

# Train the model on the corpus.
lda = LdaModel(common_corpus, num_topics=10)