Update functions_preprocess.py

functions_preprocess.py

@@ -13,7 +13,10 @@ from nltk.corpus import stopwords
 from nltk.stem import WordNetLemmatizer
 from nltk.tokenize import word_tokenize
 from nltk.corpus import wordnet
-
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torch.nn.functional as F
 
 def download_if_non_existent(res_path, res_name):
   try:
@@ -112,4 +115,20 @@ def training_data(dataset_1, dataset_2, dataset_3):
   X_test = np.array(X_test)
   X_train = np.array(X_train)
 
-  return X_train, y_train, X_test, y_test
+  return X_train, y_train, X_test, y_test
+
+class CNN(nn.Module):
+    def __init__(self, vocab_size, embed_size, n_filters, filter_sizes, dropout, num_classes):
+        super(CNN, self).__init__()
+        self.embedding = nn.Embedding(vocab_size, embed_size)
+        self.convs = nn.ModuleList([nn.Conv2d(in_channels=1, out_channels=n_filters, kernel_size=(fs, embed_size)) for fs in filter_sizes])
+        self.dropout = nn.Dropout(dropout)
+        self.fc1 = nn.Linear(len(filter_sizes) * n_filters, num_classes)
+
+    def forward(self, text):
+        embedded = self.embedding(text)
+        embedded = embedded.unsqueeze(1)
+        conved = [F.leaky_relu(conv(embedded)).squeeze(3) for conv in self.convs]
+        pooled = [F.max_pool1d(conv, conv.shape[2]).squeeze(2) for conv in conved]
+        cat = self.dropout(torch.cat(pooled, dim=1))
+        return self.fc1(cat)