def word_to_keep(word, freq):
    """ return true if word has a length of 5 to 9, a distinct number
        of characters of at least four, and a frequency of more than 2000000.
    """
    return 5 <= len(word) <= 9 and \
        len(set(word)) >= 4 and \
        freq > 2000000
		
# File download from https://www.kaggle.com/datasets/rtatman/english-word-frequency
input_filename = "unigram_freq.csv"
output_filename = "hangman_words.txt"

outfile = open(output_filename, 'w')    
with open(input_filename, 'r') as infile:
    first_line = infile.readline()  # throw away the heading line (line #1)
    for line in infile:
        # Remove leading/trailing whitespace and check if not empty
        line = line.strip()
        word, freq = line.split(',')
        freq = int(freq)
        
        if word_to_keep(word, freq):
            outfile.write(word+'\n')
outfile.close()