From 007da1a9dc3bb912da841cc0f5832a4fa28e6d9d Mon Sep 17 00:00:00 2001
From: Joshi <rekhajoshm@gmail.com>
Date: Wed, 6 Jan 2016 10:48:14 -0800
Subject: [PATCH] [SPARK-11531][ML] SparseVector error Msg
PySpark SparseVector should have "Found duplicate indices" error message
Author: Joshi <rekhajoshm@gmail.com>
Author: Rekha Joshi <rekhajoshm@gmail.com>
Closes #9525 from rekhajoshm/SPARK-11531.
---
python/pyspark/mllib/linalg/__init__.py | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/python/pyspark/mllib/linalg/__init__.py b/python/pyspark/mllib/linalg/__init__.py
index ae9ce58450..131b855bf9 100644
--- a/python/pyspark/mllib/linalg/__init__.py
+++ b/python/pyspark/mllib/linalg/__init__.py
@@ -528,7 +528,9 @@ class SparseVector(Vector):
assert len(self.indices) == len(self.values), "index and value arrays not same length"
for i in xrange(len(self.indices) - 1):
if self.indices[i] >= self.indices[i + 1]:
- raise TypeError("indices array must be sorted")
+ raise TypeError(
+ "Indices %s and %s are not strictly increasing"
+ % (self.indices[i], self.indices[i + 1]))
def numNonzeros(self):
"""
--
GitLab