From f6467ac9ee80a84e60a6a0abc4e0515ddfba430d Mon Sep 17 00:00:00 2001
From: imLogM <qiyu.logm@qq.com>
Date: Tue, 18 Jun 2019 18:28:22 +0800
Subject: [PATCH] correct IDF formula in "compute_idf.py"

The compute of IDF in "compute_idf.py" is wrong, now correct it.
---
 Utils/compute_idf.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/Utils/compute_idf.py b/Utils/compute_idf.py
index ec3bb9c..c2cce81 100644
--- a/Utils/compute_idf.py
+++ b/Utils/compute_idf.py
@@ -29,8 +29,9 @@ def load_corpus(self):
     def com_idf(self,word):
         n = 0
         for _,line in enumerate(self.corpus_data):
-           n+=line.count(word)
-        idf=math.log(1.0*self.N/n+1)
+           if line.find(word) != -1:
+                n += 1
+        idf=math.log(1.0*self.N/(n+1))
         return {word:idf}
 
     def parts(self):