Upload 7 files

biLSTM1.py

@@ -0,0 +1,50 @@
+import torch
+import torch.nn as nn
+import torchutils as tu
+
+
+
+class biLSTM(nn.Module):
+    """
+    The LSTM model that will be used to perform Sentiment analysis.
+    """
+    
+    def __init__(self, 
+                # объем словаря, с которым мы работаем, размер входа для слоя Embedding
+                vocab_size: int, 
+                # размер выходного эмбеддинга каждый элемент последовательности
+                # будет описан вектором такой размерности
+                embedding_dim: int, 
+                # размерность hidden state LSTM слоя
+                hidden_dim: int,
+                # число слоев в LSTM
+                n_layers: int,                
+                drop_prob=0.5,
+                seq_len = 128) -> None:
+        
+        super().__init__()
+        self.hidden_dim = hidden_dim
+        self.n_layers = n_layers
+        self.seq_len = seq_len
+        self.embedding = nn.Embedding(vocab_size, embedding_dim)
+        self.lstm = nn.LSTM(embedding_dim, 
+                            hidden_dim, 
+                            n_layers, 
+                            dropout=drop_prob, 
+                            batch_first=True,
+                            bidirectional=True
+                            )
+        
+        self.do = nn.Dropout()
+        
+        self.fc1 = nn.Linear(2*hidden_dim * self.seq_len, 256)
+        self.fc2 = nn.Linear(256, 1)
+        self.sigmoid = nn.Sigmoid()
+        
+    def forward(self, x):
+        embeds = self.embedding(x)
+        lstm_out, _ = self.lstm(embeds)  
+        out = self.fc2(torch.tanh(self.do(self.fc1(lstm_out.flatten(1)))))
+        sig_out = self.sigmoid(out)
+        
+        return sig_out

biLSTM_model_do_05_lr001_best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2637ba70306b15159cd0b6fa890c2277390edc5ea93cdc63e580a4dd9ed92a6d
+size 19147847

history_do_05_lr001_best.txt

@@ -0,0 +1 @@
+{'train_losses': [0.5731778456687927, 0.4595582458972931, 0.3687778123021126, 0.35563799259662626, 0.3177712473154068, 0.29712616628408434, 0.2833286724328995, 0.2641707232952118, 0.25079714640378953], 'valid_losses': [0.5975278757321529, 0.5386148532613729, 0.5021108987812812, 0.5125980156545455, 0.4879682982961337, 0.5328947740296522, 0.4984460395211593, 0.5014419947297145, 0.4964689599015774], 'train_metric': [0.687675, 0.794925, 0.843925, 0.85195, 0.870875, 0.8851, 0.890425, 0.898875, 0.9035], 'valid_metric': [0.7419871794871795, 0.8210136217948718, 0.8392427884615384, 0.8481570512820513, 0.8505608974358975, 0.8615785256410257, 0.860176282051282, 0.858573717948718, 0.8645833333333334]}

logistic_regression_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d021f47f5848ca4112983aaa05ee2f2165b420fa21fa91b52af23563cfd3458b
+size 1669478

lstm_preprocessing.py

@@ -0,0 +1,78 @@
+import re
+import string
+import numpy as np
+import torch
+
+from nltk.corpus import stopwords
+stop_words = set(stopwords.words('english'))
+
+def data_preprocessing(text: str) -> str:
+    """preprocessing string: lowercase, removing html-tags, punctuation and stopwords
+
+    Args:
+        text (str): input string for preprocessing
+
+    Returns:
+        str: preprocessed string
+    """    
+
+    text = text.lower()
+    text = re.sub('<.*?>', '', text) # Remove html tags
+    text = re.sub(r'@\w+', " ", text) # Remove usernames
+    text = re.sub(r'#\w+', " ", text) #Remove hash tags
+    text = re.sub(r'\d+', " ", text) #Remove digits
+    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 get_words_by_freq(sorted_words: list, n: int = 10) -> list:
+    return list(filter(lambda x: x[1] > n, sorted_words))
+
+def padding(review_int: list, seq_len: int) -> np.array:
+    """Make left-sided padding for input list of tokens
+
+    Args:
+        review_int (list): input list of tokens
+        seq_len (int): max length of sequence, it len(review_int[i]) > seq_len it will be trimmed, else it will be padded by zeros
+
+    Returns:
+        np.array: padded sequences
+    """    
+    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,
+    ) -> torch.tensor:
+    """Function for all preprocessing steps on a single string
+
+    Args:
+        input_string (str): input single string for preprocessing
+        seq_len (int): max length of sequence, it len(review_int[i]) > seq_len it will be trimmed, else it will be padded by zeros
+        vocab_to_int (dict, optional): word corpus {'word' : int index}. Defaults to vocab_to_int.
+
+    Returns:
+        list: preprocessed string
+    """    
+
+    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)

tfidf_vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a578ab761a1e2b767ae846945b2ee5c59d2d1b34a14d2fba922ddcc110c2883
+size 6834168