Closes issue pandas-dev#10174. Added 'interpolation' keyword in Dataframe.quantile and Series.quantile

Author: mayankasthana

pandas/core/frame.py

@@ -4468,7 +4468,7 @@ def mode(self, axis=0, numeric_only=False):
         f = lambda s: s.mode()
         return data.apply(f, axis=axis)
 
-    def quantile(self, q=0.5, axis=0, numeric_only=True):
+    def quantile(self, q=0.5, axis=0, numeric_only=True, interpolation='linear'):
         """
         Return values at the given quantile over requested axis, a la
         numpy.percentile.
@@ -4479,6 +4479,14 @@ def quantile(self, q=0.5, axis=0, numeric_only=True):
             0 <= q <= 1, the quantile(s) to compute
         axis : {0, 1}
             0 for row-wise, 1 for column-wise
+        interpolation : {‘linear’, ‘lower’, ‘higher’, ‘midpoint’, ‘nearest’}
+            Specifies the interpolation method to use, when the desired quantile lies between two data points i and j:
+                linear: i + (j - i) * fraction, where fraction is the fractional part of the index surrounded by i and j.
+                lower: i.
+                higher: j.
+                nearest: i or j whichever is nearest.
+                midpoint: (i + j) / 2.
+
 
         Returns
         -------
@@ -4512,7 +4520,7 @@ def quantile(self, q=0.5, axis=0, numeric_only=True):
         else:
             squeeze = False
 
-        def f(arr, per):
+        def f(arr, per,interpolation):
             if arr._is_datelike_mixed_type:
                 values = _values_from_object(arr).view('i8')
             else:
@@ -4521,7 +4529,7 @@ def f(arr, per):
             if len(values) == 0:
                 return NA
             else:
-                return _quantile(values, per)
+                return _quantile(values, per, interpolation=interpolation)
 
         data = self._get_numeric_data() if numeric_only else self
         if axis == 1:
@@ -4532,7 +4540,7 @@ def f(arr, per):
         is_dt_col = data.dtypes.map(com.is_datetime64_dtype)
         is_dt_col = is_dt_col[is_dt_col].index
 
-        quantiles = [[f(vals, x) for x in per]
+        quantiles = [[f(vals, x, interpolation) for x in per]
                      for (_, vals) in data.iteritems()]
         result = DataFrame(quantiles, index=data._info_axis, columns=q).T
         if len(is_dt_col) > 0:

pandas/core/series.py

@@ -1216,15 +1216,21 @@ def round(self, decimals=0, out=None):
 
         return result
 
-    def quantile(self, q=0.5):
+    def quantile(self, q=0.5, interpolation='linear'):
         """
         Return value at the given quantile, a la numpy.percentile.
 
         Parameters
         ----------
         q : float or array-like, default 0.5 (50% quantile)
             0 <= q <= 1, the quantile(s) to compute
-
+        interpolation : {‘linear’, ‘lower’, ‘higher’, ‘midpoint’, ‘nearest’}
+            Specifies the interpolation method to use, when the desired quantile lies between two data points i and j:
+                linear: i + (j - i) * fraction, where fraction is the fractional part of the index surrounded by i and j.
+                lower: i.
+                higher: j.
+                nearest: i or j whichever is nearest.
+                midpoint: (i + j) / 2.
         Returns
         -------
         quantile : float or Series
@@ -1245,14 +1251,14 @@ def quantile(self, q=0.5):
         """
         valid = self.dropna()
 
-        def multi(values, qs):
+        def multi(values, qs, interpolation):
             if com.is_list_like(qs):
-                return Series([_quantile(values, x*100)
+                return Series([_quantile(values, x*100, interpolation=interpolation)
                                for x in qs], index=qs)
             else:
-                return _quantile(values, qs*100)
+                return _quantile(values, qs*100, interpolation=interpolation)
 
-        return self._maybe_box(lambda values: multi(values, q), dropna=True)
+        return self._maybe_box(lambda values: multi(values, q, interpolation), dropna=True)
 
     def ptp(self, axis=None, out=None):
         return _values_from_object(self).ptp(axis, out)