Rename tests for alphabetical ordering

tests/tpch/dask_queries.py

@@ -3,7 +3,7 @@
 import dask.dataframe as dd
 
 
-def query_1(dataset_path, fs, scale):
+def query_01(dataset_path, fs, scale):
     VAR1 = datetime(1998, 9, 2)
     lineitem_ds = dd.read_parquet(dataset_path + "lineitem", filesystem=fs)
 
@@ -40,7 +40,7 @@ def query_1(dataset_path, fs, scale):
     return total.reset_index().sort_values(["l_returnflag", "l_linestatus"])
 
 
-def query_2(dataset_path, fs, scale):
+def query_02(dataset_path, fs, scale):
     var1 = 15
     var2 = "BRASS"
     var3 = "EUROPE"
@@ -109,7 +109,7 @@ def query_2(dataset_path, fs, scale):
     )
 
 
-def query_3(dataset_path, fs, scale):
+def query_03(dataset_path, fs, scale):
     var1 = datetime.strptime("1995-03-15", "%Y-%m-%d")
     var2 = "BUILDING"
 
@@ -138,7 +138,7 @@ def query_3(dataset_path, fs, scale):
     )
 
 
-def query_4(dataset_path, fs, scale):
+def query_04(dataset_path, fs, scale):
     date1 = datetime.strptime("1993-10-01", "%Y-%m-%d")
     date2 = datetime.strptime("1993-07-01", "%Y-%m-%d")
 
@@ -162,7 +162,7 @@ def query_4(dataset_path, fs, scale):
     return result_df
 
 
-def query_5(dataset_path, fs, scale):
+def query_05(dataset_path, fs, scale):
     date1 = datetime.strptime("1994-01-01", "%Y-%m-%d")
     date2 = datetime.strptime("1995-01-01", "%Y-%m-%d")
 
@@ -191,7 +191,7 @@ def query_5(dataset_path, fs, scale):
     return gb.reset_index().sort_values("revenue", ascending=False)
 
 
-def query_6(dataset_path, fs, scale):
+def query_06(dataset_path, fs, scale):
     date1 = datetime.strptime("1994-01-01", "%Y-%m-%d")
     date2 = datetime.strptime("1995-01-01", "%Y-%m-%d")
     var3 = 24
@@ -211,7 +211,7 @@ def query_6(dataset_path, fs, scale):
     return revenue.sum().to_frame("revenue")
 
 
-def query_7(dataset_path, fs, scale):
+def query_07(dataset_path, fs, scale):
     var1 = datetime.strptime("1995-01-01", "%Y-%m-%d")
     var2 = datetime.strptime("1997-01-01", "%Y-%m-%d")
 
@@ -306,7 +306,7 @@ def query_7(dataset_path, fs, scale):
     )
 
 
-def query_8(dataset_path, fs, scale):
+def query_08(dataset_path, fs, scale):
     var1 = datetime.strptime("1995-01-01", "%Y-%m-%d")
     var2 = datetime.strptime("1997-01-01", "%Y-%m-%d")
 
@@ -364,7 +364,7 @@ def query_8(dataset_path, fs, scale):
     return final.sort_values(by=["o_year"], ascending=[True])[["o_year", "mkt_share"]]
 
 
-def query_9(dataset_path, fs, scale):
+def query_09(dataset_path, fs, scale):
     """
     select
         nation,

tests/tpch/test_correctness.py

@@ -160,6 +160,6 @@ def test_dask_results(
 ):
     from . import dask_queries
 
-    func = getattr(dask_queries, f"query_{query}")
+    func = getattr(dask_queries, f"query_{query:02d}")
     result = func(dataset_path, None, scale).compute()
     verify_result(result, query, answers_path, s3_storage_options)

tests/tpch/test_dask.py

@@ -23,46 +23,46 @@ def dataset_path(local, scale):
 
 @pytest.mark.shuffle_p2p
 def test_query_1(client, dataset_path, fs, scale):
-    dask_queries.query_1(dataset_path, fs, scale).compute()
+    dask_queries.query_01(dataset_path, fs, scale).compute()
 
 
 @pytest.mark.shuffle_p2p
 def test_query_2(client, dataset_path, fs, scale):
-    dask_queries.query_2(dataset_path, fs, scale).compute()
+    dask_queries.query_02(dataset_path, fs, scale).compute()
 
 
 @pytest.mark.shuffle_p2p
 def test_query_3(client, dataset_path, fs, scale):
-    dask_queries.query_3(dataset_path, fs, scale).compute()
+    dask_queries.query_03(dataset_path, fs, scale).compute()
 
 
 @pytest.mark.shuffle_p2p
 def test_query_4(client, dataset_path, fs, scale):
-    dask_queries.query_4(dataset_path, fs, scale).compute()
+    dask_queries.query_04(dataset_path, fs, scale).compute()
 
 
 @pytest.mark.shuffle_p2p
 def test_query_5(client, dataset_path, fs, scale):
-    dask_queries.query_5(dataset_path, fs, scale).compute()
+    dask_queries.query_05(dataset_path, fs, scale).compute()
 
 
 def test_query_6(client, dataset_path, fs, scale):
-    dask_queries.query_6(dataset_path, fs, scale).compute()
+    dask_queries.query_06(dataset_path, fs, scale).compute()
 
 
 @pytest.mark.shuffle_p2p
 def test_query_7(client, dataset_path, fs, scale):
-    dask_queries.query_7(dataset_path, fs, scale).compute()
+    dask_queries.query_07(dataset_path, fs, scale).compute()
 
 
 @pytest.mark.shuffle_p2p
 def test_query_8(client, dataset_path, fs, scale):
-    dask_queries.query_8(dataset_path, fs, scale).compute()
+    dask_queries.query_08(dataset_path, fs, scale).compute()
 
 
 @pytest.mark.shuffle_p2p
 def test_query_9(client, dataset_path, fs, scale):
-    dask_queries.query_9(dataset_path, fs, scale).compute()
+    dask_queries.query_09(dataset_path, fs, scale).compute()
 
 
 @pytest.mark.shuffle_p2p

tests/tpch/test_optimization.py

@@ -36,14 +36,14 @@ def query(request):
 
 
 def test_optimization(query, dataset_path, fs, client, scale):
-    func = getattr(dask_queries, f"query_{query}")
+    func = getattr(dask_queries, f"query_{query:02d}")
     result = func(dataset_path, fs, scale)
     # We need to inject .repartition(npartitions=1) which .compute() does under the hood
     result.repartition(npartitions=1).optimize()
 
 
 def test_delay_computation_start(query, dataset_path, fs, client, scale):
-    func = getattr(dask_queries, f"query_{query}")
+    func = getattr(dask_queries, f"query_{query:02d}")
     result = func(dataset_path, fs, scale).optimize()
     # Client.compute unblocks as soon as update_graph finishes, i.e. graph is
     # submitted and parsed. This is the time until the dashboard kicks off