# -*- coding: utf-8 -*-

"""Untitled39.ipynb

Automatically generated by Colab.

Original file is located at

    https://colab.research.google.com/drive/1pcHOb70S4TwkxIKgrNTFfLdc71vMgOKg

"""

import torch

import time

import evaluate

import pandas as pd

import numpy as np

from transformers import DataCollatorForSeq2Seq

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

from transformers import Seq2SeqTrainingArguments, DataCollatorForSeq2Seq, Seq2SeqTrainer

#from datasets import load_dataset

from google.colab import drive

drive.mount('/content/drive')

import os

folder_path = '/content/drive/My Drive/nosocomial/hapi'

os.chdir(folder_path)

print("Current Directory:", os.getcwd())

hapi_trainLabels = pd.read_csv('train.labels.csv')

hapi_trainChronologies=pd.read_csv('train.chronologies.csv')

hapi_trainLabels=pd.read_csv('train.labels.csv')

hapi_develAdmittimes=pd.read_csv('devel.admittimes.csv')

hapi_develChronologies=pd.read_csv('devel.chronologies.csv')

hapi_develLabels=pd.read_csv('devel.labels.csv')

hapi_negativeLabels=pd.read_csv('negative_labels.csv')

hapi_testAdmittimes=pd.read_csv('test.admittimes.csv')

hapi_testchronologies=pd.read_csv('test.chronologies.csv')

hapi_testLabels =pd.read_csv('test.labels.csv')

hapi_testChronologies =pd.read_csv('test.chronologies.csv')

hapi_testLabels =pd.read_csv('test.labels.csv')

haki_trainLabels = pd.read_csv('train.labels.csv')

haki_trainChronologies=pd.read_csv('train.chronologies.csv')

haki_trainLabels=pd.read_csv('train.labels.csv')

haki_develAdmittimes=pd.read_csv('devel.admittimes.csv')

haki_develChronologies=pd.read_csv('devel.chronologies.csv')

haki_develLabels=pd.read_csv('devel.labels.csv')

haki_negativeLabels=pd.read_csv('negative_labels.csv')

haki_testAdmittimes=pd.read_csv('test.admittimes.csv')

haki_testchronologies=pd.read_csv('test.chronologies.csv')

haki_testLabels =pd.read_csv('test.labels.csv')

haki_testChronologies =pd.read_csv('test.chronologies.csv')

haki_testLabels =pd.read_csv('test.labels.csv')

haa_trainLabels = pd.read_csv('train.labels.csv')

haa_trainChronologies=pd.read_csv('train.chronologies.csv')

haa_develAdmittimes=pd.read_csv('devel.admittimes.csv')

haa_develChronologies=pd.read_csv('devel.chronologies.csv')

haa_develLabels=pd.read_csv('devel.labels.csv')

haa_negativeLabels=pd.read_csv('negative_labels.csv')

haa_testAdmittimes=pd.read_csv('test.admittimes.csv')

haa_testchronologies=pd.read_csv('test.chronologies.csv')

haa_testLabels =pd.read_csv('test.labels.csv')

haa_testChronologies =pd.read_csv('test.chronologies.csv')

haa_testLabels =pd.read_csv('test.labels.csv')

"""####  HAA    C0002871 (Anemia)   anemia, anaemia, HAA    WHO[19]"""

haa_trainChronologies.head()

haa_trainChronologies.head()

haa_develAdmittimes.head()

haa_develChronologies.head()