From a12a2f4385063447e458c63ca3654be6bd5decf0 Mon Sep 17 00:00:00 2001
From: Grail Finder <wohilas@gmail.com>
Date: Thu, 19 Jun 2025 06:17:39 +0300
Subject: [PATCH] Enha: set how common words are

---
 adjectives.txt => adjectives_5.txt | 0
 main.py                            | 7 ++++---
 nouns.txt => nouns_5.txt           | 0
 3 files changed, 4 insertions(+), 3 deletions(-)
 rename adjectives.txt => adjectives_5.txt (100%)
 rename nouns.txt => nouns_5.txt (100%)

diff --git a/adjectives.txt b/adjectives_5.txt
similarity index 100%
rename from adjectives.txt
rename to adjectives_5.txt
diff --git a/main.py b/main.py
index c255fcc..83470d8 100644
--- a/main.py
+++ b/main.py
@@ -5,6 +5,7 @@ from collections import defaultdict
 
 NPATH = os.environ["NLTK_DATA"]
 COMMON_WORDS = {}
+HOW_COMMON = 10
 
 def load_data():
     nltk.download('brown', download_dir=NPATH)
@@ -14,7 +15,7 @@ def load_data():
     freq_dist = nltk.FreqDist(word.lower() for word in brown.words())
     # Create a set of common words (adjust threshold as needed)
     global COMMON_WORDS
-    COMMON_WORDS = {word for word, count in freq_dist.items() if count >= 5}
+    COMMON_WORDS = {word for word, count in freq_dist.items() if count >= HOW_COMMON}
 
 def is_common(word):
     # Check if word exists in Brown Corpus with minimal frequency
@@ -62,5 +63,5 @@ def writefile(fname, data):
 if __name__ == "__main__":
     load_data()
     nouns, adjectives = get_words()
-    writefile("nouns.txt", nouns)
-    writefile("adjectives.txt", adjectives)
+    writefile(f"nouns_{HOW_COMMON}.txt", nouns)
+    writefile(f"adjectives_{HOW_COMMON}.txt", adjectives)
diff --git a/nouns.txt b/nouns_5.txt
similarity index 100%
rename from nouns.txt
rename to nouns_5.txt