[SPARK-11467][SQL] add Python API for stddev/variance

Add Python API for stddev/stddev_pop/stddev_samp/variance/var_pop/var_samp/skewness/kurtosis

Author: Davies Liu <davies@databricks.com>

Closes #9424 from davies/py_var.

1 files changed, 88 insertions, 0 deletions

diff --git a/python/pyspark/sql/group.py b/python/pyspark/sql/group.py
index 71c0bccc5e..946b53e71c 100644
--- a/python/pyspark/sql/group.py
+++ b/python/pyspark/sql/group.py
@@ -167,6 +167,94 @@ 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