Remove Deprecated Sampling Options (#3816)

The `uniform_neighbor_sample` code is becoming increasingly difficult to maintain.  This PR removes all the options that were deprecated in the previous release, and also deprecates the `with_edge_properties` option, which will be replaced by returning whatever properties are in the graph in the next release.

This PR also resolves a FIXME by allowing `fanout_vals` to be a `cupy.ndarray`, `numpy.ndarray`, or `cudf.Series`.

Closes #3698

Authors:
  - Alex Barghi (https://github.com/alexbarghi-nv)

Approvers:
  - Brad Rees (https://github.com/BradReesWork)
  - Rick Ratzel (https://github.com/rlratzel)

URL: #3816

python/cugraph-pyg/cugraph_pyg/data/cugraph_store.py

@@ -367,6 +367,7 @@ def __construct_graph(
         -------
         A newly-constructed directed cugraph.MultiGraph object.
         """
+
         # Ensure the original dict is not modified.
         edge_info_cg = {}
 

python/cugraph-pyg/cugraph_pyg/tests/mg/test_mg_cugraph_sampler.py

@@ -33,14 +33,21 @@ def test_neighbor_sample(dask_client, basic_graph_1):
     F, G, N = basic_graph_1
     cugraph_store = CuGraphStore(F, G, N, multi_gpu=True)
 
+    batches = cudf.DataFrame(
+        {
+            "start": cudf.Series([0, 1, 2, 3, 4], dtype="int64"),
+            "batch": cudf.Series(cupy.zeros(5, dtype="int32")),
+        }
+    )
+
     sampling_results = (
         uniform_neighbor_sample(
             cugraph_store._subgraph(),
-            cudf.Series([0, 1, 2, 3, 4], dtype="int64"),
+            batches,
+            with_batch_ids=True,
             fanout_vals=[-1],
             with_replacement=False,
             with_edge_properties=True,
-            batch_id_list=cudf.Series(cupy.zeros(5, dtype="int32")),
             random_state=62,
             return_offsets=False,
             return_hops=True,
@@ -90,16 +97,23 @@ def test_neighbor_sample_multi_vertex(dask_client, multi_edge_multi_vertex_graph
     F, G, N = multi_edge_multi_vertex_graph_1
     cugraph_store = CuGraphStore(F, G, N, multi_gpu=True)
 
+    batches = cudf.DataFrame(
+        {
+            "start": cudf.Series([0, 1, 2, 3, 4], dtype="int64"),
+            "batches": cudf.Series(cupy.zeros(5, dtype="int32")),
+        }
+    )
+
     sampling_results = (
         uniform_neighbor_sample(
             cugraph_store._subgraph(),
-            cudf.Series([0, 1, 2, 3, 4], dtype="int64"),
+            batches,
             fanout_vals=[-1],
             with_replacement=False,
             with_edge_properties=True,
-            batch_id_list=cudf.Series(cupy.zeros(5, dtype="int32")),
             random_state=62,
             return_offsets=False,
+            with_batch_ids=True,
         )
         .sort_values(by=["sources", "destinations"])
         .compute()

python/cugraph-pyg/cugraph_pyg/tests/test_cugraph_sampler.py

@@ -31,13 +31,20 @@ def test_neighbor_sample(basic_graph_1):
     F, G, N = basic_graph_1
     cugraph_store = CuGraphStore(F, G, N)
 
+    batches = cudf.DataFrame(
+        {
+            "start": cudf.Series([0, 1, 2, 3, 4], dtype="int64"),
+            "batch": cudf.Series(cupy.zeros(5, dtype="int32")),
+        }
+    )
+
     sampling_results = uniform_neighbor_sample(
         cugraph_store._subgraph(),
-        cudf.Series([0, 1, 2, 3, 4], dtype="int64"),
+        batches,
         fanout_vals=[-1],
         with_replacement=False,
         with_edge_properties=True,
-        batch_id_list=cudf.Series(cupy.zeros(5, dtype="int32")),
+        with_batch_ids=True,
         random_state=62,
         return_offsets=False,
     ).sort_values(by=["sources", "destinations"])
@@ -82,15 +89,22 @@ def test_neighbor_sample_multi_vertex(multi_edge_multi_vertex_graph_1):
     F, G, N = multi_edge_multi_vertex_graph_1
     cugraph_store = CuGraphStore(F, G, N)
 
+    batches = cudf.DataFrame(
+        {
+            "start": cudf.Series([0, 1, 2, 3, 4], dtype="int64"),
+            "batch": cudf.Series(cupy.zeros(5, dtype="int32")),
+        }
+    )
+
     sampling_results = uniform_neighbor_sample(
         cugraph_store._subgraph(),
-        cudf.Series([0, 1, 2, 3, 4], dtype="int64"),
+        batches,
         fanout_vals=[-1],
         with_replacement=False,
         with_edge_properties=True,
-        batch_id_list=cudf.Series(cupy.zeros(5, dtype="int32")),
         random_state=62,
         return_offsets=False,
+        with_batch_ids=True,
     ).sort_values(by=["sources", "destinations"])
 
     out = _sampler_output_from_sampling_results(