Generates top k tags in database

nishnik · Apr 11, 2016 · 76508ef · 76508ef
1 parent 7e4571e
commit 76508ef
Showing 1 changed file with 18 additions and 0 deletions.
diff --git a/scripts/top_k_tags.py b/scripts/top_k_tags.py
@@ -0,0 +1,18 @@
+import json, collections
+
+with open('clean.json') as data_file:
+    a = json.load(data_file)# type(data)=dict
+
+c = []
+total = 0
+for i in a:
+	for j in a[i]:
+		c.append(j)
+	total = total + len(a[i])
+counts = collections.Counter(c)
+
+
+
+n = 5000
+for word, count in counts.most_common(n):
+    print("{0}".format(word))