Created
July 28, 2016 15:43
-
-
Save msszczep/a77c9361b9dfff6f8f57bf772ef5c2a4 to your computer and use it in GitHub Desktop.
Python script to filter "memorable" words from MRC Psycholinguistic Database
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from itertools import product | |
| final_answer = set() | |
| for a in open('mrc2.dct'): | |
| cols = a.split(' ', 1) | |
| b = list(cols[0]) | |
| c = int(b[28] + b[29] + b[30]) # concreteness rating | |
| i = int(b[31] + b[32] + b[33]) # imagery rating | |
| f = int(b[25] + b[26] + b[27]) # familiarity rating | |
| m1 = int(b[34] + b[35] + b[36]) # meaningfulness rating #1 | |
| m2 = int(b[37] + b[38] + b[39]) # meaningfulness rating #2 | |
| try: | |
| word = cols[1][:-1].split(' ')[4].split('|')[0] | |
| except: | |
| word = '' | |
| if (f > 400 or i > 400 or m1 > 400 or m2 > 400) and word != '': | |
| final_answer.add(word) | |
| z = sorted(final_answer) | |
| k = 0 | |
| for n in product(range(1,7), repeat=5): | |
| print "".join(map(lambda x: str(x), n)), z[k] | |
| k = k + 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment