Shorten corpuses to avoid heap overflow

with open('/Users/manuelsegimonplana/Documents/Current Courses/Not Completed Homework/DS - Project/group7/src/main/java/resources/english.txt', 'r') as file:

    lines = file.readlines()

# Remove lines with less than 4 words

lines = [line for line in lines if len(line.split()) >= 4]

# Shuffle the lines

random.shuffle(lines)

# Optionally, you can write the cleaned lines back to a file

with open('src/main/java/resources/brown.txt', 'a') as file:

    file.writelines(lines[:450000]) # Last working number: 500000

    file.writelines(lines[:10000])