From efd932618270d2b3c518bdb0e5ce34932b82e9a0 Mon Sep 17 00:00:00 2001 From: Yuhao Yang Date: Sun, 5 Jun 2016 13:39:29 -0700 Subject: [PATCH] update readme --- README.md | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 22b33b0..7dc615a 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -# SparseSpark +# SparseML Yuhao Yang (yuhao.yang@intel.com)

@@ -22,15 +22,12 @@ in the context of sparse data support on Spark MLlib. ## Usage: The class/function signature remains the same as in Spark MLlib. Please refer to the examples folder -## Benchmark - -Thought the concrete performance improvements depends on the sparsity of the dataset. The algorithms +## Performance: +Although the concrete performance improvements depends on the sparsity of the dataset. The algorithms in SparseSpark generally significantly reduce the time and memory consumption compared with the original Spark implementation. -Some examples: - ## Accuracy -The optimization does not affect the accuracy. It yields the same result with the original Spark version, -yet with much less resources. \ No newline at end of file +The optimization does not affect the accuracy. It yields the same result with the Spark version, +yet with less computation resources. \ No newline at end of file