Upload 8 files

Generating BERT embeddings.py

@@ -0,0 +1,41 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# # Generating BERT embeddings from the scratch
+
+# In[1]:
+
+
+import pandas as pd
+from transformers import BertTokenizer, BertModel
+import torch
+
+# Reading the main data as CSV file into a pandas DataFrame.
+df = pd.read_csv('/users/deniz.bilgin/Deep Learning/socialmedia-disaster-tweets-DFE.csv', encoding='UTF-8')
+
+#loading the pre-trained BERT model and its tokenizer.
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+model = BertModel.from_pretrained('bert-base-uncased')
+
+# def function to create BERT embeddings for a given text.
+def generate_bert_embeddings(text):
+    # First, tokenizing the tweets in text column.
+    input_ids = torch.tensor(tokenizer.encode(text, add_special_tokens=True))
+    # Generating BERT embeddings
+    with torch.no_grad():
+        last_hidden_states = model(input_ids.unsqueeze(0))[0]  #applying the Bert model on tokenized text.
+    embeddings = torch.mean(last_hidden_states, dim=1) #calculating the mean of the embeddings for all the tokens in the text to generate a single embedding for the entire text.
+    return embeddings.numpy() # converting the tensor that contains the embeddings to a numpy array.
+
+#applying the embeddings to every tweet in text data in the dataframe.
+df['embeddings'] = df['text'].apply(generate_bert_embeddings)
+
+# Saving the embeddings to a CSV file.
+df.to_csv('bert_embeddings_tweets.csv', index=False)
+
+
+# In[ ]:
+
+
+
+

keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daed174a86fe7f24fcc14975d18f6a3832e62fdefe464088ace51f807a546915
+size 7484

saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b84f3cbf9148af39271d1cca87dc338c574ebf4999724456a59a7f9bf87d440
+size 81866

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}