Fix histogram operation on Ibis data (#5929)

holoviews/core/data/ibis.py

@@ -23,6 +23,11 @@ def ibis4():
     return ibis_version() >= Version("4.0")
 
 
+@lru_cache
+def ibis5():
+    return ibis_version() >= Version("5.0")
+
+
 class IbisInterface(Interface):
 
     types = ()
@@ -163,16 +168,16 @@ def histogram(cls, expr, bins, density=True, weights=None):
         else:
             # sort_by will be removed in Ibis 5.0
             hist_bins = binned.value_counts().sort_by('bucket').execute()
-
-        for b, v in zip(hist_bins['bucket'], hist_bins['count']):
+        metric_name = 'bucket_count' if ibis5() else 'count'
+        for b, v in zip(hist_bins['bucket'], hist_bins[metric_name]):
             if np.isnan(b):
                 continue
             hist[int(b)] = v
         if weights is not None:
             raise NotImplementedError("Weighted histograms currently "
                                       "not implemented for IbisInterface.")
         if density:
-            hist = hist/expr.count().execute()
+            hist = hist/expr.count().execute()/np.diff(bins)
         return hist, bins
 
     @classmethod

holoviews/operation/element.py

@@ -737,10 +737,16 @@ def _process(self, element, key=None):
 
         # Mask data
         if is_ibis_expr(data):
+            from ..core.data.ibis import ibis5
+
             mask = data.notnull()
             if self.p.nonzero:
                 mask = mask & (data != 0)
-            data = data.to_projection()
+            if ibis5():
+                data = data.as_table()
+            else:
+                # to_projection removed in ibis 5.0.0
+                data = data.to_projection()
             data = data[mask]
             no_data = not len(data.head(1).execute())
             data = data[dim.name]

holoviews/tests/conftest.py

@@ -1,3 +1,5 @@
+import pytest
+
 from panel.tests.conftest import server_cleanup, port, pytest_addoption, pytest_configure, optional_markers  # noqa
 
 
@@ -26,3 +28,15 @@ def pytest_collection_modifyitems(config, items):
     dask.config.set({"dataframe.convert-string": False})
 except Exception:
     pass
+
+
+@pytest.fixture
+def ibis_sqlite_backend():
+    try:
+        import ibis
+    except ImportError:
+        yield None
+    else:
+        ibis.set_backend('sqlite')
+        yield
+        ibis.set_backend(None)

holoviews/tests/operation/test_operation.py

@@ -10,6 +10,11 @@
 except ImportError:
     da = None
 
+try:
+    import ibis
+except ImportError:
+    ibis = None
+
 from holoviews import (HoloMap, NdOverlay, NdLayout, GridSpace, Image,
                        Contours, Polygons, Points, Histogram, Curve, Area,
                        QuadMesh, Dataset, renderer)
@@ -20,6 +25,7 @@
                                          interpolate_curve, decimate)
 
 da_skip = skipIf(da is None, "dask.array is not available")
+ibis_skip = skipIf(ibis is None, "ibis is not available")
 
 
 class OperationTests(ComparisonTestCase):
@@ -179,6 +185,43 @@ def test_dataset_weighted_histogram_dask(self):
         self.assertIsInstance(op_hist.data['y'], da.Array)
         self.assertEqual(op_hist, hist)
 
+    @ibis_skip
+    @pytest.mark.usefixtures('ibis_sqlite_backend')
+    def test_dataset_histogram_ibis(self):
+        df = pd.DataFrame(dict(x=np.arange(10)))
+        t = ibis.memtable(df, name='t')
+        ds = Dataset(t, vdims='x')
+        op_hist = histogram(ds, dimension='x', num_bins=3, normed=True)
+
+        hist = Histogram(([0, 3, 6, 9], [0.1, 0.1, 0.133333]),
+                         vdims=('x_frequency', 'Frequency'))
+        self.assertEqual(op_hist, hist)
+
+    @ibis_skip
+    @pytest.mark.usefixtures('ibis_sqlite_backend')
+    def test_dataset_cumulative_histogram_ibis(self):
+        df = pd.DataFrame(dict(x=np.arange(10)))
+        t = ibis.memtable(df, name='t')
+        ds = Dataset(t, vdims='x')
+        op_hist = histogram(ds, num_bins=3, cumulative=True, normed=True)
+
+        hist = Histogram(([0, 3, 6, 9], [0.3, 0.6, 1]),
+                         vdims=('x_frequency', 'Frequency'))
+        self.assertEqual(op_hist, hist)
+
+    @ibis_skip
+    @pytest.mark.usefixtures('ibis_sqlite_backend')
+    def test_dataset_histogram_explicit_bins_ibis(self):
+        df = pd.DataFrame(dict(x=np.arange(10)))
+        t = ibis.memtable(df, name='t')
+        ds = Dataset(t, vdims='x')
+        op_hist = histogram(ds, bins=[0, 1, 3], normed=False)
+
+        hist = Histogram(([0, 1, 3], [1, 3]),
+                         vdims=('x_count', 'Count'))
+        self.assertEqual(op_hist, hist)
+
+
     def test_points_histogram_bin_range(self):
         points = Points([float(i) for i in range(10)])
         op_hist = histogram(points, num_bins=3, bin_range=(0, 3), normed=True)