Added Czech wordlists, reduced English wordlist sizes

Author: veproza

data-scripts/build_frequency_lists.py

@@ -29,12 +29,14 @@ def usage():
 
 # maps dict name to num words. None value means "include all words"
 DICTIONARIES = dict(
-    us_tv_and_film    = 30000,
+    us_tv_and_film    = 15000,
     english_wikipedia = 30000,
-    passwords         = 30000,
+    passwords         = 15000,
     surnames          = 10000,
     male_names        = None,
     female_names      = None,
+    cs_passwords      = 15000,
+    cs_tv_film_no_dia = 15000,
 )
 
 # returns {list_name: {token: rank}}, as tokens and ranks occur in each file.