머신러닝스터디/2016/2016 07 30: Difference between revisions

Latest revision as of 00:44, 27 March 2026

머신러닝스터디/2016 머신러닝스터디/2016/목차

내용

sklearn의 k-means
tensorflow로 k-means algorithm 구현하기

코드

sklearn

from sklearn import cluster

clst = cluster.KMeans()
clst.fit([[0],[1],[2],[3], [1000], [1004], [1010], [2000], [100000], [12345], [23456], [66666]])
clst.predict([[11], [3000], [99999]])

# result 
# array([5, 6, 1], dtype=int32)

tensorflow

unsorted_segment_sum

@@ Line 6: / Line 6: @@
 === 코드 ===
-==== sklearn의 k-means ====
+==== sklearn ====
   from sklearn import cluster
   clst = cluster.KMeans()
-  clst.fit([[0],[1],[2],[3], [1000], [1004], [1010], [2000], [100000], [12345], [23456], [66666]])
+  clst.fit(&#91;&#91;0&#93;,&#91;1&#93;,&#91;2&#93;,&#91;3&#93;, &#91;1000&#93;, &#91;1004&#93;, &#91;1010&#93;, &#91;2000&#93;, &#91;100000&#93;, &#91;12345&#93;, &#91;23456&#93;, &#91;66666&#93;&#93;)
-  clst.predict([[11], [3000], [99999]])
+  clst.predict(&#91;&#91;11&#93;, &#91;3000&#93;, &#91;99999&#93;&#93;)
   # result
-  # array([5, 6, 1], dtype=int32)
+  # array(&#91;5, 6, 1&#93;, dtype=int32)
+=== tensorflow ===
+* [https://www.tensorflow.org/versions/r0.10/api_docs/python/math_ops.html#unsorted_segment_sum unsorted_segment_sum]
 == 다음 시간에는 ==