farm_beir_imports_dataset.py

## import relevant packages
import pandas as pd
import numpy as np
import random


import ast
from typing import List, Union, Dict, Optional
import logging

import torch
from transformers import AutoTokenizer, AutoModel
from farm.infer import Inferencer


from beir import util, LoggingHandler
from beir.datasets.data_loader import GenericDataLoader
from beir.retrieval.evaluation import EvaluateRetrieval
from beir.retrieval.search.dense import DenseRetrievalExactSearch as DRES

import logging
import pathlib, os
logging.basicConfig()
logging.getLogger(__name__).setLevel(logging.INFO)


## Load TREC COVID dataset 
dataset = "trec-covid"
url = "https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/{}.zip".format(dataset)
data_path = util.download_and_unzip(url, "datasets")
corpus, queries, qrels = GenericDataLoader(data_folder=data_path).load(split="test")