diff options
author | Reynold Xin <rxin@databricks.com> | 2015-11-03 16:27:56 -0800 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2015-11-03 16:27:56 -0800 |
commit | 5051262d4ca6a2c529c9b1ba86d54cce60a7af17 (patch) | |
tree | f7c89be1ccc400a803aaa136926b84405a7e43e1 /python/pyspark/sql | |
parent | 53e9cee3e4e845d1f875c487215c0f22503347b1 (diff) | |
download | spark-5051262d4ca6a2c529c9b1ba86d54cce60a7af17.tar.gz spark-5051262d4ca6a2c529c9b1ba86d54cce60a7af17.tar.bz2 spark-5051262d4ca6a2c529c9b1ba86d54cce60a7af17.zip |
[SPARK-11489][SQL] Only include common first order statistics in GroupedData
We added a bunch of higher order statistics such as skewness and kurtosis to GroupedData. I don't think they are common enough to justify being listed, since users can always use the normal statistics aggregate functions.
That is to say, after this change, we won't support
```scala
df.groupBy("key").kurtosis("colA", "colB")
```
However, we will still support
```scala
df.groupBy("key").agg(kurtosis(col("colA")), kurtosis(col("colB")))
```
Author: Reynold Xin <rxin@databricks.com>
Closes #9446 from rxin/SPARK-11489.
Diffstat (limited to 'python/pyspark/sql')
-rw-r--r-- | python/pyspark/sql/group.py | 88 |
1 files changed, 0 insertions, 88 deletions
diff --git a/python/pyspark/sql/group.py b/python/pyspark/sql/group.py index 946b53e71c..71c0bccc5e 100644 --- a/python/pyspark/sql/group.py +++ b/python/pyspark/sql/group.py @@ -167,94 +167,6 @@ class GroupedData(object): [Row(sum(age)=7, sum(height)=165)] """ - @df_varargs_api - @since(1.6) - def stddev(self, *cols): - """Compute the sample standard deviation for each numeric columns for each group. - - :param cols: list of column names (string). Non-numeric columns are ignored. - - >>> df3.groupBy().stddev('age', 'height').collect() - [Row(STDDEV(age)=2.12..., STDDEV(height)=3.53...)] - """ - - @df_varargs_api - @since(1.6) - def stddev_samp(self, *cols): - """Compute the sample standard deviation for each numeric columns for each group. - - :param cols: list of column names (string). Non-numeric columns are ignored. - - >>> df3.groupBy().stddev_samp('age', 'height').collect() - [Row(STDDEV_SAMP(age)=2.12..., STDDEV_SAMP(height)=3.53...)] - """ - - @df_varargs_api - @since(1.6) - def stddev_pop(self, *cols): - """Compute the population standard deviation for each numeric columns for each group. - - :param cols: list of column names (string). Non-numeric columns are ignored. - - >>> df3.groupBy().stddev_pop('age', 'height').collect() - [Row(STDDEV_POP(age)=1.5, STDDEV_POP(height)=2.5)] - """ - - @df_varargs_api - @since(1.6) - def variance(self, *cols): - """Compute the sample variance for each numeric columns for each group. - - :param cols: list of column names (string). Non-numeric columns are ignored. - - >>> df3.groupBy().variance('age', 'height').collect() - [Row(VARIANCE(age)=2.25, VARIANCE(height)=6.25)] - """ - - @df_varargs_api - @since(1.6) - def var_pop(self, *cols): - """Compute the sample variance for each numeric columns for each group. - - :param cols: list of column names (string). Non-numeric columns are ignored. - - >>> df3.groupBy().var_pop('age', 'height').collect() - [Row(VAR_POP(age)=2.25, VAR_POP(height)=6.25)] - """ - - @df_varargs_api - @since(1.6) - def var_samp(self, *cols): - """Compute the sample variance for each numeric columns for each group. - - :param cols: list of column names (string). Non-numeric columns are ignored. - - >>> df3.groupBy().var_samp('age', 'height').collect() - [Row(VAR_SAMP(age)=4.5, VAR_SAMP(height)=12.5)] - """ - - @df_varargs_api - @since(1.6) - def skewness(self, *cols): - """Compute the skewness for each numeric columns for each group. - - :param cols: list of column names (string). Non-numeric columns are ignored. - - >>> df3.groupBy().skewness('age', 'height').collect() - [Row(SKEWNESS(age)=0.0, SKEWNESS(height)=0.0)] - """ - - @df_varargs_api - @since(1.6) - def kurtosis(self, *cols): - """Compute the kurtosis for each numeric columns for each group. - - :param cols: list of column names (string). Non-numeric columns are ignored. - - >>> df3.groupBy().kurtosis('age', 'height').collect() - [Row(KURTOSIS(age)=-2.0, KURTOSIS(height)=-2.0)] - """ - def _test(): import doctest |