diff --git a/ml/InverseIndex.py b/ml/InverseIndex.py
new file mode 100644
index 0000000..e756cd8
--- /dev/null
+++ b/ml/InverseIndex.py
@@ -0,0 +1,26 @@
+#encoding=utf-8
+import jieba
+import json
+import sys
+
+reload(sys)
+sys.setdefaultencoding('utf-8')
+
+
+file = open('../news_spider/title.json')
+worddict = dict()
+count=0
+while True:
+	line = file.readline()
+	if not line:
+		break
+	data = json.loads(line)
+	seg_list = list(jieba.cut(data['title'], cut_all=True))
+	count+=1
+	for w in seg_list:
+		if w not in worddict:
+			worddict[w] = []	
+		worddict[w].append(count)
+
+for i in worddict:
+	print i