# Imports
from datasets import load_dataset
import pandas as pd
import numpy as np
from tqdm import tqdm
tqdm.pandas()

# Load the English STSB dataset
stsb_dataset = load_dataset('stsb_multi_mt', 'en')
stsb_train = pd.DataFrame(stsb_dataset['train'])
stsb_test = pd.DataFrame(stsb_dataset['test'])

# Check loaded data
print(stsb_train.shape, stsb_test.shape)
stsb_test.head()