Added operation_kwargs Histogram property (#3921)

* Added private _operation_kwargs Histogram property. For Histogram elements created using the histogram operation, this holds a dict of operation kwargs that can be used to recreate the histogram from the same dataset.  Or None, if the Histogram was created directly using the Histogram constructor.

holoviews/element/chart.py

@@ -1,5 +1,5 @@
 import numpy as np
-
+import copy
 import param
 
 from ..core import util
@@ -182,6 +182,8 @@ def __init__(self, data, edges=None, **params):
         elif isinstance(data, tuple) and len(data) == 2 and len(data[0])+1 == len(data[1]):
             data = data[::-1]
 
+        self._operation_kwargs = params.pop('_operation_kwargs', None)
+
         dataset = params.pop("dataset", None)
         super(Histogram, self).__init__(data, **params)
 
@@ -204,6 +206,7 @@ def clone(self, data=None, shared_data=True, new_type=None, *args, **overrides):
             data=data,
             shared_data=shared_data,
             new_type=new_type,
+            _operation_kwargs=copy.deepcopy(self._operation_kwargs),
             *args,
             **overrides
         )

holoviews/operation/element.py

@@ -655,6 +655,18 @@ def _process(self, element, key=None):
             hist = np.cumsum(hist)
             if self.p.normed in (True, 'integral'):
                 hist *= edges[1]-edges[0]
+
+        # Save off the kwargs needed to reproduce this Histogram later.
+        # We remove the properties that are used as instructions for how to
+        # calculate the bins, and replace those with the explicit list of bin
+        # edges.  This way, not only can we regenerate this exact histogram
+        # from the same data set, but we can also generate a histogram using
+        # a different dataset that will share the exact same bins.
+        exclusions = {'log', 'bin_range', 'num_bins'}
+        params['_operation_kwargs'] = {
+            k: v for k, v in self.p.items() if k not in exclusions
+        }
+        params['_operation_kwargs']['bins'] = list(edges)
         return Histogram((edges, hist), kdims=[element.get_dimension(selected_dim)],
                          label=element.label, dataset=element.dataset, **params)
 

holoviews/tests/operation/testoperation.py

@@ -147,9 +147,49 @@ def test_points_histogram(self):
                          vdims=('x_frequency', 'Frequency'))
         self.assertEqual(op_hist, hist)
 
+    def test_histogram_operation_kwargs(self):
+        points = Points([float(j) for i in range(10) for j in [i] * (2 * i)])
+        op_hist = histogram(
+            points,
+            dimension='y',
+            normed=False,
+            num_bins=10,
+            bin_range=[0, 10],
+        )
+
+        hist = Histogram((
+            [0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0],
+            [0, 2, 4, 6, 8, 10, 12, 14, 16, 18]
+        ), vdims=('y_count', 'Count'), kdims='y')
+
+        # Check histogram
+        self.assertEqual(op_hist, hist)
+
+        # Check operation kwargs for histogram generated with operation
+        self.assertEqual(
+            op_hist._operation_kwargs,
+            {'dimension': 'y',
+             'normed': False,
+             'dynamic': False,
+             'bins': [0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0]}
+        )
+
+        # Test that operation_kwargs is preserved through clone
+        self.assertEqual(
+            op_hist.clone()._operation_kwargs,
+            {'dimension': 'y',
+             'normed': False,
+             'dynamic': False,
+             'bins': [0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0]}
+        )
+
+        # Check that operation kwargs is None for histogram generated directly
+        # from the Histogram constructor
+        self.assertIsNone(hist._operation_kwargs)
+
     @da_skip
     def test_dataset_histogram_dask(self):
-        import dask.array as da 
+        import dask.array as da
         ds = Dataset((da.from_array(np.array(range(10), dtype='f'), chunks=(3)),),
                      ['x'], datatype=['dask'])
         op_hist = histogram(ds, num_bins=3)
@@ -161,7 +201,7 @@ def test_dataset_histogram_dask(self):
 
     @da_skip
     def test_dataset_cumulative_histogram_dask(self):
-        import dask.array as da 
+        import dask.array as da
         ds = Dataset((da.from_array(np.array(range(10), dtype='f'), chunks=(3)),),
                      ['x'], datatype=['dask'])
         op_hist = histogram(ds, num_bins=3, cumulative=True)