Optimization for heatmap aggregation with pandas

holoviews/core/data/__init__.py

@@ -17,11 +17,13 @@
 from .ndelement import NdElementInterface
 
 datatypes = ['array', 'dictionary', 'grid', 'ndelement']
+DF_INTERFACES = []
 
 try:
     import pandas as pd # noqa (Availability import)
     from .pandas import PandasInterface
     datatypes = ['array', 'dataframe', 'dictionary', 'grid', 'ndelement']
+    DF_INTERFACES.append(PandasInterface)
     DFColumns = PandasInterface
 except ImportError:
     pass
@@ -49,6 +51,7 @@
 try:
     from .dask import DaskInterface
     datatypes.append('dask')
+    DF_INTERFACES.append(DaskInterface)
 except ImportError:
     pass
 

holoviews/element/util.py

@@ -4,6 +4,7 @@
 import numpy as np
 
 from ..core import Dataset, OrderedDict
+from ..core.data import DF_INTERFACES
 from ..core.operation import ElementOperation
 from ..core.util import (pd, is_nan, sort_topologically,
                          cartesian_product, is_cyclic, one_to_one)
@@ -134,7 +135,11 @@ def _aggregate_dataset(self, obj, xcoords, ycoords):
         dtype = 'dataframe' if pd else 'dictionary'
         dense_data = Dataset(data, kdims=obj.kdims, vdims=obj.vdims, datatype=[dtype])
         concat_data = obj.interface.concatenate([dense_data, obj], datatype=[dtype])
-        agg = concat_data.reindex([xdim, ydim], vdims).aggregate([xdim, ydim], reduce_fn)
+        reindexed = concat_data.reindex([xdim, ydim], vdims)
+        if reindexed.interface in DF_INTERFACES:
+            agg = reindexed.clone(reindexed.data.groupby([xdim, ydim]).first().reset_index())
+        else:
+            agg = reindexed.aggregate([xdim, ydim], reduce_fn)
 
         # Convert data to a gridded dataset
         grid_data = {xdim: xcoords, ydim: ycoords}

holoviews/operation/datashader.py

@@ -20,12 +20,12 @@
 
 from ..core import (ElementOperation, Element, Dimension, NdOverlay,
                     Overlay, CompositeOverlay, Dataset)
-from ..core.data import ArrayInterface, PandasInterface, DaskInterface
+from ..core.data import (ArrayInterface, PandasInterface, DaskInterface,
+                         DF_INTERFACES)
 from ..core.util import get_param_values, basestring
 from ..element import GridImage, Image, Path, Curve, Contours, RGB
 from ..streams import RangeXY
 
-DF_INTERFACES = [PandasInterface, DaskInterface]
 
 @dispatch(Element)
 def discover(dataset):