File size: 1,556 Bytes
ee9e25e 513e813 ee9e25e 513e813 83a34f0 513e813 83a34f0 c32735e 30fa96a c32735e 30fa96a c32735e ee9e25e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 |
import unittest
from details_data_processor import DetailsDataProcessor
import pandas as pd
import requests
import os
class TestDetailsDataProcessor(unittest.TestCase):
def setUp(self):
self.processor = DetailsDataProcessor()
# check that the result is a pandas dataframe
def test_process_data(self):
pass
# data = self.processor.data
# self.assertIsInstance(data, pd.DataFrame)
def test_download_file(self):
DetailsDataProcessor.download_file('https://www.google.com', 'test.html')
self.assertTrue(os.path.exists('test.html'))
os.remove('test.html')
def test_generate_url(self):
results_file_path = "64bits/LexPodLM-13B/results_2023-07-25T13:41:51.227672.json"
expected_url = 'https://huggingface.co/datasets/open-llm-leaderboard/details/resolve/main/64bits/LexPodLM-13B/details_harness%7ChendrycksTest-moral_scenarios%7C5_2023-07-25T13%3A41%3A51.227672.json'
constructed_url = self.processor.generate_url(results_file_path)
self.assertEqual(expected_url, constructed_url)
def test_pipeline(self):
df = self.processor.pipeline()
print(100 * "****")
print(df)
self.assertIsInstance(df, pd.DataFrame)
def test_find_files(self):
directory = 'results'
pattern = 'results*.json'
files = self.processor._find_files(directory, pattern)
# breakpoint()
# print(files)
self.assertIsInstance(files, list)
if __name__ == '__main__':
unittest.main() |