Spaces:
Sleeping
Sleeping
import string | |
import torch | |
import numpy as np | |
from nltk.corpus import stopwords | |
stop_words = set(stopwords.words('english')) | |
import torch.nn as nn | |
import pickle | |
from transformers import BertTokenizer, BertModel, DistilBertTokenizer, DistilBertModel | |
from sklearn.linear_model import LogisticRegression | |
EMBEDDING_DIM = 64 | |
VOCAB_SIZE = 203310 | |
embedding_matrix = np.zeros((VOCAB_SIZE, EMBEDDING_DIM)) | |
embedding_layer = torch.nn.Embedding.from_pretrained(torch.FloatTensor(embedding_matrix)) | |
with open('lstm/vocab_to_int.txt', 'rb') as f: | |
vocab_to_int = pickle.load(f) | |
class LSTMClassifier(nn.Module): | |
def __init__(self, embedding_dim: int, hidden_size: int = 32) -> None: | |
super().__init__() | |
self.embedding_dim = embedding_dim # создаем эмбединг сайз | |
self.hidden_size = hidden_size # создаем хидден сайз | |
self.embedding = embedding_layer # создаем слои модели | |
self.lstm = nn.LSTM( | |
input_size=self.embedding_dim, | |
hidden_size=self.hidden_size, | |
batch_first=True | |
) | |
self.clf = nn.Linear(self.hidden_size, 1) | |
def forward(self, x): | |
embedding = self.embedding(x) | |
_, (h_n, _) = self.lstm(embedding) | |
out = self.clf(h_n.squeeze()) | |
return out | |
def data_preprocessing(text: str) -> str: | |
text = text.lower() | |
text = ''.join([c for c in text if c not in string.punctuation])# Remove punctuation | |
text = [word for word in text.split() if word not in stop_words] | |
text = ' '.join(text) | |
return text | |
def padding(review_int: list, seq_len: int) -> np.array: | |
features = np.zeros((len(review_int), seq_len), dtype = int) | |
for i, review in enumerate(review_int): | |
if len(review) <= seq_len: | |
zeros = list(np.zeros(seq_len - len(review))) | |
new = zeros + review | |
else: | |
new = review[: seq_len] | |
features[i, :] = np.array(new) | |
return features | |
def preprocess_single_string(input_string: str, seq_len: int, vocab_to_int: dict = vocab_to_int) -> list: | |
preprocessed_string = data_preprocessing(input_string) | |
result_list = [] | |
for word in preprocessed_string.split(): | |
try: | |
result_list.append(vocab_to_int[word]) | |
except KeyError as e: | |
print(f'{e}: not in dictionary!') | |
result_padded = padding([result_list], seq_len)[0] | |
return torch.tensor(result_padded) | |