Add NDFrame.median() aggregation

eland/ndframe.py

@@ -252,11 +252,95 @@ class NDFrame(ABC):
         return self._query_compiler.min(numeric_only=numeric_only)
 
     def var(self, numeric_only=True):
+        """
+        Return variance for each numeric column
+
+        Returns
+        -------
+        pandas.Series
+            The value of the variance for each numeric column
+
+        See Also
+        --------
+        :pandas_api_docs:`pandas.DataFrame.var`
+
+        Examples
+        --------
+        >>> df = ed.DataFrame('localhost', 'flights')
+        >>> df.var() # doctest: +SKIP
+        AvgTicketPrice        7.096185e+04
+        Cancelled             1.119831e-01
+        DistanceKilometers    2.096049e+07
+        DistanceMiles         8.092892e+06
+        FlightDelay           1.880825e-01
+        FlightDelayMin        9.359209e+03
+        FlightTimeHour        3.112545e+01
+        FlightTimeMin         1.120516e+05
+        dayOfWeek             3.761135e+00
+        dtype: float64
+        """
         return self._query_compiler.var(numeric_only=numeric_only)
 
     def std(self, numeric_only=True):
+        """
+        Return standard deviation for each numeric column
+
+        Returns
+        -------
+        pandas.Series
+            The value of the standard deviation for each numeric column
+
+        See Also
+        --------
+        :pandas_api_docs:`pandas.DataFrame.std`
+
+        Examples
+        --------
+        >>> df = ed.DataFrame('localhost', 'flights')
+        >>> df.std() # doctest: +SKIP
+        AvgTicketPrice         266.386661
+        Cancelled                0.334639
+        DistanceKilometers    4578.263193
+        DistanceMiles         2844.800855
+        FlightDelay              0.433685
+        FlightDelayMin          96.743006
+        FlightTimeHour           5.579019
+        FlightTimeMin          334.741135
+        dayOfWeek                1.939365
+        dtype: float64
+        """
         return self._query_compiler.std(numeric_only=numeric_only)
 
+    def median(self, numeric_only=True):
+        """
+        Return the median value for each numeric column
+
+        Returns
+        -------
+        pandas.Series
+            median value for each numeric column
+
+        See Also
+        --------
+        :pandas_api_docs:`pandas.DataFrame.median`
+
+        Examples
+        --------
+        >>> df = ed.DataFrame('localhost', 'flights')
+        >>> df.median() # doctest: +SKIP
+        AvgTicketPrice         640.387285
+        Cancelled                0.000000
+        DistanceKilometers    7612.072403
+        DistanceMiles         4729.922470
+        FlightDelay              0.000000
+        FlightDelayMin           0.000000
+        FlightTimeHour           8.383113
+        FlightTimeMin          503.148975
+        dayOfWeek                3.000000
+        dtype: float64
+        """
+        return self._query_compiler.median(numeric_only=numeric_only)
+
     def max(self, numeric_only=True):
         """
         Return the maximum value for each numeric column

eland/operations.py

@@ -135,6 +135,11 @@ class Operations:
             numeric_only=numeric_only,
         )
 
+    def median(self, query_compiler, numeric_only=True):
+        return self._metric_aggs(
+            query_compiler, ("percentiles", "50.0"), numeric_only=numeric_only
+        )
+
     def sum(self, query_compiler, numeric_only=True):
         return self._metric_aggs(query_compiler, "sum", numeric_only=numeric_only)
 
@@ -275,9 +280,14 @@ class Operations:
                         )
                 else:
                     if isinstance(func, tuple):
-                        results[field] = response["aggregations"][
-                            func[0] + "_" + field
-                        ][func[1]]
+                        if func[0] == "percentiles":
+                            results[field] = response["aggregations"][
+                                "percentiles_" + field
+                            ]["values"]["50.0"]
+                        else:
+                            results[field] = response["aggregations"][
+                                func[0] + "_" + field
+                            ][func[1]]
                     else:
                         results[field] = response["aggregations"][field]["value"]
 

eland/query_compiler.py

@@ -469,6 +469,9 @@ class QueryCompiler:
     def std(self, numeric_only=None):
         return self._operations.std(self, numeric_only=numeric_only)
 
+    def median(self, numeric_only=None):
+        return self._operations.median(self, numeric_only=numeric_only)
+
     def sum(self, numeric_only=None):
         return self._operations.sum(self, numeric_only=numeric_only)
 

eland/tests/dataframe/test_metrics_pytest.py

@@ -12,16 +12,16 @@
 #      See the License for the specific language governing permissions and
 #      limitations under the License.
 
-# File called _pytest for PyCharm compatability
+# File called _pytest for PyCharm compatibility
 
-from pandas.util.testing import assert_series_equal, assert_almost_equal
+from pandas.testing import assert_series_equal
 
 from eland.tests.common import TestData
 
 
 class TestDataFrameMetrics(TestData):
     funcs = ["max", "min", "mean", "sum"]
-    extended_funcs = ["var", "std"]
+    extended_funcs = ["var", "std", "median"]
 
     def test_flights_metrics(self):
         pd_flights = self.pd_flights()
@@ -41,7 +41,7 @@ class TestDataFrameMetrics(TestData):
             pd_metric = getattr(pd_flights, func)(numeric_only=True)
             ed_metric = getattr(ed_flights, func)(numeric_only=True)
 
-            assert_almost_equal(pd_metric, ed_metric, check_less_precise=True)
+            assert_series_equal(pd_metric, ed_metric, check_less_precise=True)
 
     def test_ecommerce_selected_non_numeric_source_fields(self):
         # None of these are numeric