From dc413138995b45a7a957acae007dc11622110310 Mon Sep 17 00:00:00 2001 From: Reynold Xin Date: Thu, 18 Jun 2015 18:41:15 -0700 Subject: [SPARK-8218][SQL] Binary log math function update. Some minor updates based on after merging #6725. Author: Reynold Xin Closes #6871 from rxin/log and squashes the following commits: ab51542 [Reynold Xin] Use JVM log 76fc8de [Reynold Xin] Fixed arg. a7c1522 [Reynold Xin] [SPARK-8218][SQL] Binary log math function update. --- python/pyspark/sql/functions.py | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'python/pyspark') diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py index 177fc196e0..acdb01d3d3 100644 --- a/python/pyspark/sql/functions.py +++ b/python/pyspark/sql/functions.py @@ -404,18 +404,23 @@ def when(condition, value): return Column(jc) -@since(1.4) -def log(col, base=math.e): +@since(1.5) +def log(arg1, arg2=None): """Returns the first argument-based logarithm of the second argument. - >>> df.select(log(df.age, 10.0).alias('ten')).map(lambda l: str(l.ten)[:7]).collect() + If there is only one argument, then this takes the natural logarithm of the argument. + + >>> df.select(log(10.0, df.age).alias('ten')).map(lambda l: str(l.ten)[:7]).collect() ['0.30102', '0.69897'] >>> df.select(log(df.age).alias('e')).map(lambda l: str(l.e)[:7]).collect() ['0.69314', '1.60943'] """ sc = SparkContext._active_spark_context - jc = sc._jvm.functions.log(base, _to_java_column(col)) + if arg2 is None: + jc = sc._jvm.functions.log(_to_java_column(arg1)) + else: + jc = sc._jvm.functions.log(arg1, _to_java_column(arg2)) return Column(jc) -- cgit v1.2.3