pcuenca/alzheimer

Early Detection of Alzheimer Disease using NLP & Deep Learning

alzheimer's Issues

Access to data

This may not be very related to this repository but can I ask how did you get access to the datasets? I tried all different ways and I failed to contact them. Can you point me in the right direction on accessing the data?

Cannot find '*_cookie_simb_off.csv' for BERT training.

Hi, thanks for your sharing this great works. I've come across an issue that I cannot find the file 'train_cookie_simb_off.csv' and 'test_cookie_simb_off.csv' mentioned in Cookie_Bert*.py.
I guess the df['text'] content is like the sentences_clean or clean in pitt-cookie-complete.csv, but when I run the line train_dataset = BERTDataset("Cookie_Text_for_finetuning.txt", tokenizer, seq_len=max_seq_length, corpus_lines=None, on_memory=True) in Cookie_Bert_Lm_finetuning.py, it got IndexError: list index out of range at the line if self.all_docs[-1] != doc: ... of BERTDataset .
I'm confused about the format of df['text'] content, could you share it again?

Want to find metrics scores for ULMFiT model using this code

Hi! I am referring to this code for Alzheimer's detection, but can't seem to find a way to get the precision , recall and F1 score to see the performance of this model on my data. Can someone help?