Script for downloading data of the GLUE benchmark (gluebenchmark.com)

download_glue_data.py

''' Script for downloading all GLUE data.

Note: for legal reasons, we are unable to host MRPC.
You can either use the version hosted by the SentEval team, which is already tokenized, 
or you can download the original data from (https://download.microsoft.com/download/D/4/6/D46FF87A-F6B9-4252-AA8B-3604ED519838/MSRParaphraseCorpus.msi) and extract the data from it manually.
For Windows users, you can run the .msi file. For Mac and Linux users, consider an external library such as 'cabextract' (see below for an example).
You should then rename and place specific files in a folder (see below for an example).

mkdir MRPC
cabextract MSRParaphraseCorpus.msi -d MRPC
cat MRPC/_2DEC3DBE877E4DB192D17C0256E90F1D | tr -d $'\r' > MRPC/msr_paraphrase_train.txt
cat MRPC/_D7B391F9EAFF4B1B8BCE8F21B20B1B61 | tr -d $'\r' > MRPC/msr_paraphrase_test.txt
rm MRPC/_*
rm MSRParaphraseCorpus.msi

1/30/19: It looks like SentEval is no longer hosting their extracted and tokenized MRPC data, so you'll need to download the data from the original source for now.
2/11/19: It looks like SentEval actually *is* hosting the extracted data. Hooray!
'''

import os
import sys
import shutil
import argparse
import tempfile
import urllib.request
import zipfile

TASKS = ["CoLA", "SST", "MRPC", "QQP", "STS", "MNLI", "QNLI", "RTE", "WNLI", "diagnostic"]
TASK2PATH = {"CoLA":'https://dl.fbaipublicfiles.com/glue/data/CoLA.zip',
             "SST":'https://dl.fbaipublicfiles.com/glue/data/SST-2.zip',
             "QQP":'https://dl.fbaipublicfiles.com/glue/data/QQP-clean.zip',
             "STS":'https://dl.fbaipublicfiles.com/glue/data/STS-B.zip',
             "MNLI":'https://dl.fbaipublicfiles.com/glue/data/MNLI.zip',
             "QNLI":'https://dl.fbaipublicfiles.com/glue/data/QNLIv2.zip',
             "RTE":'https://dl.fbaipublicfiles.com/glue/data/RTE.zip',
             "WNLI":'https://dl.fbaipublicfiles.com/glue/data/WNLI.zip',
             "diagnostic":'https://dl.fbaipublicfiles.com/glue/data/AX.tsv'}

MRPC_TRAIN = 'https://dl.fbaipublicfiles.com/senteval/senteval_data/msr_paraphrase_train.txt'
MRPC_TEST = 'https://dl.fbaipublicfiles.com/senteval/senteval_data/msr_paraphrase_test.txt'

def download_and_extract(task, data_dir):
    print("Downloading and extracting %s..." % task)
    if task == "MNLI":
        print("\tNote (12/10/20): This script no longer downloads SNLI. You will need to manually download and format the data to use SNLI.")
    data_file = "%s.zip" % task
    urllib.request.urlretrieve(TASK2PATH[task], data_file)
    with zipfile.ZipFile(data_file) as zip_ref:
        zip_ref.extractall(data_dir)
    os.remove(data_file)
    print("\tCompleted!")

def format_mrpc(data_dir, path_to_data):
    print("Processing MRPC...")
    mrpc_dir = os.path.join(data_dir, "MRPC")
    if not os.path.isdir(mrpc_dir):
        os.mkdir(mrpc_dir)
    if path_to_data:
        mrpc_train_file = os.path.join(path_to_data, "msr_paraphrase_train.txt")
        mrpc_test_file = os.path.join(path_to_data, "msr_paraphrase_test.txt")
    else:
        try:
            mrpc_train_file = os.path.join(mrpc_dir, "msr_paraphrase_train.txt")
            mrpc_test_file = os.path.join(mrpc_dir, "msr_paraphrase_test.txt")
            URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file)
            URLLIB.urlretrieve(MRPC_TEST, mrpc_test_file)
        except urllib.error.HTTPError:
            print("Error downloading MRPC")
            return
    assert os.path.isfile(mrpc_train_file), "Train data not found at %s" % mrpc_train_file
    assert os.path.isfile(mrpc_test_file), "Test data not found at %s" % mrpc_test_file

    with io.open(mrpc_test_file, encoding='utf-8') as data_fh, \
            io.open(os.path.join(mrpc_dir, "test.tsv"), 'w', encoding='utf-8') as test_fh:
        header = data_fh.readline()
        test_fh.write("index\t#1 ID\t#2 ID\t#1 String\t#2 String\n")
        for idx, row in enumerate(data_fh):
            label, id1, id2, s1, s2 = row.strip().split('\t')
            test_fh.write("%d\t%s\t%s\t%s\t%s\n" % (idx, id1, id2, s1, s2))

    try:
        URLLIB.urlretrieve(TASK2PATH["MRPC"], os.path.join(mrpc_dir, "dev_ids.tsv"))
    except KeyError or urllib.error.HTTPError:
        print("\tError downloading standard development IDs for MRPC. You will need to manually split your data.")
        return

    dev_ids = []
    with io.open(os.path.join(mrpc_dir, "dev_ids.tsv"), encoding='utf-8') as ids_fh:
        for row in ids_fh:
            dev_ids.append(row.strip().split('\t'))

    with io.open(mrpc_train_file, encoding='utf-8') as data_fh, \
         io.open(os.path.join(mrpc_dir, "train.tsv"), 'w', encoding='utf-8') as train_fh, \
         io.open(os.path.join(mrpc_dir, "dev.tsv"), 'w', encoding='utf-8') as dev_fh:
        header = data_fh.readline()
        train_fh.write(header)
        dev_fh.write(header)
        for row in data_fh:
            label, id1, id2, s1, s2 = row.strip().split('\t')
            if [id1, id2] in dev_ids:
                dev_fh.write("%s\t%s\t%s\t%s\t%s\n" % (label, id1, id2, s1, s2))
            else:
                train_fh.write("%s\t%s\t%s\t%s\t%s\n" % (label, id1, id2, s1, s2))
                
    print("\tCompleted!")
    
def download_diagnostic(data_dir):
    print("Downloading and extracting diagnostic...")
    if not os.path.isdir(os.path.join(data_dir, "diagnostic")):
        os.mkdir(os.path.join(data_dir, "diagnostic"))
    data_file = os.path.join(data_dir, "diagnostic", "diagnostic.tsv")
    urllib.request.urlretrieve(TASK2PATH["diagnostic"], data_file)
    print("\tCompleted!")
    return

def get_tasks(task_names):
    task_names = task_names.split(',')
    if "all" in task_names:
        tasks = TASKS
    else:
        tasks = []
        for task_name in task_names:
            assert task_name in TASKS, "Task %s not found!" % task_name
            tasks.append(task_name)
    return tasks

def main(arguments):
    parser = argparse.ArgumentParser()
    parser.add_argument('--data_dir', help='directory to save data to', type=str, default='glue_data')
    parser.add_argument('--tasks', help='tasks to download data for as a comma separated string',
                        type=str, default='all')
    parser.add_argument('--path_to_mrpc', help='path to directory containing extracted MRPC data, msr_paraphrase_train.txt and msr_paraphrase_text.txt',
                        type=str, default='')
    args = parser.parse_args(arguments)

    if not os.path.isdir(args.data_dir):
        os.mkdir(args.data_dir)
    tasks = get_tasks(args.tasks)

    for task in tasks:
        if task == 'MRPC':
            format_mrpc(args.data_dir, args.path_to_mrpc)
        elif task == 'diagnostic':
            download_diagnostic(args.data_dir)
        else:
            download_and_extract(task, args.data_dir)


if __name__ == '__main__':
    sys.exit(main(sys.argv[1:]))

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

It works for me. Thanks a lot!

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

Thanks!@stevenwjy

Traceback (most recent call last):
File "E:/BERT/YYBert-master/download_glue_data.py", line 150, in
sys.exit(main(sys.argv[1:]))
File "E:/BERT/YYBert-master/download_glue_data.py", line 142, in main
format_mrpc(args.data_dir, args.path_to_mrpc)
File "E:/BERT/YYBert-master/download_glue_data.py", line 65, in format_mrpc
URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file)
AttributeError: 'NoneType' object has no attribute 'urlretrieve'

How to fix it....

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

Worked for me! Thanks. Why isn't the URLLIB declared? @W4ngatang

Dear all , I get the following error when attempting to download the data Downloading and extracting CoLA...
Traceback (most recent call last):
File "/mnt/784C5F3A4C5EF1FC/PROJECTS/MSC/reformer-pytorch/dev/download_glue_data.py", line 141, in
sys.exit(main(sys.argv[1:]))
File "/mnt/784C5F3A4C5EF1FC/PROJECTS/MSC/reformer-pytorch/dev/download_glue_data.py", line 137, in main
download_and_extract(task, args.data_dir)
File "/mnt/784C5F3A4C5EF1FC/PROJECTS/MSC/reformer-pytorch/dev/download_glue_data.py", line 47, in download_and_extract
urllib.request.urlretrieve(TASK2PATH[task], data_file)
File "/usr/lib/python3.6/urllib/request.py", line 248, in urlretrieve
with contextlib.closing(urlopen(url, data)) as fp:
File "/usr/lib/python3.6/urllib/request.py", line 223, in urlopen
return opener.open(url, data, timeout)
File "/usr/lib/python3.6/urllib/request.py", line 532, in open
response = meth(req, response)
File "/usr/lib/python3.6/urllib/request.py", line 642, in http_response
'http', request, response, code, msg, hdrs)
File "/usr/lib/python3.6/urllib/request.py", line 570, in error
return self._call_chain(*args)
File "/usr/lib/python3.6/urllib/request.py", line 504, in _call_chain
result = func(*args)
File "/usr/lib/python3.6/urllib/request.py", line 650, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 403: Forbidden

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

It works for me. Thanks a lot!

Works for me, thanks a lot.

import io
URLLIB = urllib.request
'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

Here is fixed script in case anyone else needs it: https://gist.github.com/vlasenkoalexey/fef1601580f269eca73bf26a198595f3

Here is fixed script in case anyone else needs it: https://gist.github.com/vlasenkoalexey/fef1601580f269eca73bf26a198595f3

Cool, this script works perfectly. Thanks.

Here is fixed script in case anyone else needs it: https://gist.github.com/vlasenkoalexey/fef1601580f269eca73bf26a198595f3

thx

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

fine!

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

Thanks!

"QQP":'https://dl.fbaipublicfiles.com/glue/data/STS-B.zip',
"STS":'https://dl.fbaipublicfiles.com/glue/data/QQP-clean.zip'
The urls of the two datasets are reversed.

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

Thanks!@stevenwjy

Thanks!

"QQP":'https://dl.fbaipublicfiles.com/glue/data/STS-B.zip',
"STS":'https://dl.fbaipublicfiles.com/glue/data/QQP-clean.zip'
The urls of the two datasets are reversed.

Yeas, you are right. Thanks!

I'm getting the following warning:

Downloading and extracting MNLI...
	Note (12/10/20): This script no longer downloads SNLI. You will need to manually download and format the data to use SNLI.

Here is the script with all the fixes so far

I am getting the following error when trying to download MRPC files for BERT classifier:

Processing MRPC...
	Error downloading standard development IDs for MRPC. You will need to manually split your data.
***** Task data directory: glue_data/MRPC *****
msr_paraphrase_test.txt  msr_paraphrase_train.txt  test.tsv
***** Model output directory: gs://capstone-testing/bert-tfhub/models/MRPC *****

What is the best method to resolve this?

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH

Thanks a lot! It works for me, too

I'm getting the following warning:

Downloading and extracting MNLI...
	Note (12/10/20): This script no longer downloads SNLI. You will need to manually download and format the data to use SNLI.

+1

I'm getting the following warning:

Downloading and extracting MNLI...
	Note (12/10/20): This script no longer downloads SNLI. You will need to manually download and format the data to use SNLI.

+1

You should download the SNLI dataset manually, by https://nlp.stanford.edu/projects/snli/snli_1.0.zip

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

Thanks

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

Thanks for saving some time for all of us :)

https://gist.github.com/vlasenkoalexey/fef1601580f269eca73bf26a198595f3

THx!

Here is fixed script in case anyone else needs it: https://gist.github.com/vlasenkoalexey/fef1601580f269eca73bf26a198595f3

Nice! Worked for me.

It works for me. Thanks a lot!!

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the dict (creds to @laouerTASK2PATH)

thanks a lot!

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

it really works!

Got a NameError 'URLLIB' is not defined here:
Traceback (most recent call last): File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 150, in <module> sys.exit(main(sys.argv[1:])) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 142, in main format_mrpc(args.data_dir, args.path_to_mrpc) File "C:\Users\cpeng4\Downloads\download_glue_data\download_glue_data.py", line 65, in format_mrpc URLLIB.urlretrieve(MRPC_TRAIN, mrpc_train_file) NameError: name 'URLLIB' is not defined

I managed to get the MRPC donwload completed by adding the following three lines:

• import io
• URLLIB = urllib.request
• 'MRPC':'https://raw.githubusercontent.com/MegEngine/Models/master/official/nlp/bert/glue_data/MRPC/dev_ids.tsv' inside the TASK2PATH dict (creds to @laouer)

tanks a lot!!