TST: merge high_memory mark with single_cpu (pandas-dev#46261)

Author: mroeschke

.circleci/config.yml

@@ -10,6 +10,7 @@ jobs:
       PYTEST_WORKERS: auto
       PATTERN: "not slow and not network and not clipboard and not arm_slow"
       PYTEST_TARGET: "pandas"
+      PANDAS_CI: "1"
     steps:
       - checkout
       - run: ci/setup_env.sh

azure-pipelines.yml

@@ -18,7 +18,7 @@ pr:
 variables:
   PYTEST_WORKERS: auto
   PYTEST_TARGET:  pandas
-  PATTERN: "not slow and not high_memory and not db and not network and not single_cpu"
+  PATTERN: "not slow and not db and not network and not single_cpu"
   PANDAS_CI: 1
 
 jobs:
@@ -48,7 +48,7 @@ jobs:
         pip install cython numpy python-dateutil pytz pytest pytest-xdist hypothesis pytest-azurepipelines && \
         python setup.py build_ext -q -j2 && \
         python -m pip install --no-build-isolation -e . && \
-        pytest -m 'not slow and not network and not clipboard' pandas --junitxml=test-data.xml"
+        pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml"
       displayName: 'Run 32-bit manylinux2014 Docker Build / Tests'
 
     - task: PublishTestResults@2

pandas/conftest.py

@@ -106,7 +106,6 @@ def pytest_collection_modifyitems(items, config):
     only_slow = config.getoption("--only-slow")
     skip_network = config.getoption("--skip-network")
     skip_db = config.getoption("--skip-db")
-    run_high_memory = config.getoption("--run-high-memory")
 
     marks = [
         (pytest.mark.slow, "slow", skip_slow, "--skip-slow"),
@@ -139,13 +138,6 @@ def pytest_collection_modifyitems(items, config):
         if only_slow and "slow" not in item.keywords:
             item.add_marker(pytest.mark.skip("skipping due to --only-slow"))
 
-        if "high_memory" in item.keywords and not run_high_memory:
-            item.add_marker(
-                pytest.mark.skip(
-                    "skipping high memory test since --run-high-memory was not set"
-                )
-            )
-
 
 # Hypothesis
 hypothesis.settings.register_profile(

pandas/tests/frame/methods/test_rank.py

@@ -328,7 +328,6 @@ def test_rank_pct_true(self, method, exp):
         tm.assert_frame_equal(result, expected)
 
     @pytest.mark.single_cpu
-    @pytest.mark.high_memory
     def test_pct_max_many_rows(self):
         # GH 18271
         df = DataFrame(

pandas/tests/io/parser/test_c_parser_only.py

@@ -17,7 +17,10 @@
 import numpy as np
 import pytest
 
-from pandas.compat import IS64
+from pandas.compat import (
+    IS64,
+    is_ci_environment,
+)
 from pandas.errors import ParserError
 import pandas.util._test_decorators as td
 
@@ -555,15 +558,16 @@ def test_read_tarfile(c_parser_only, csv_dir_path, tar_suffix):
         tm.assert_frame_equal(out, expected)
 
 
-@pytest.mark.high_memory
+@pytest.mark.single_cpu
+@pytest.mark.skipif(is_ci_environment(), reason="Too memory intensive for CI.")
 def test_bytes_exceed_2gb(c_parser_only):
     # see gh-16798
     #
     # Read from a "CSV" that has a column larger than 2GB.
     parser = c_parser_only
 
     if parser.low_memory:
-        pytest.skip("not a high_memory test")
+        pytest.skip("not a low_memory test")
 
     csv = StringIO("strings\n" + "\n".join(["x" * (1 << 20) for _ in range(2100)]))
     df = parser.read_csv(csv)

pandas/tests/series/methods/test_rank.py

@@ -476,7 +476,6 @@ def test_rank_first_pct(dtype, ser, exp):
 
 
 @pytest.mark.single_cpu
-@pytest.mark.high_memory
 def test_pct_max_many_rows():
     # GH 18271
     s = Series(np.arange(2**24 + 1))

pandas/tests/test_algos.py

@@ -1659,7 +1659,6 @@ def test_too_many_ndims(self):
             algos.rank(arr)
 
     @pytest.mark.single_cpu
-    @pytest.mark.high_memory
     def test_pct_max_many_rows(self):
         # GH 18271
         values = np.arange(2**24 + 1)

pyproject.toml

@@ -48,11 +48,10 @@ filterwarnings = [
 ]
 junit_family = "xunit2"
 markers = [
-  "single_cpu: mark a test that should run on a single cpu only",
+  "single_cpu: tests that should run on a single cpu only",
   "slow: mark a test as slow",
   "network: mark a test as network",
   "db: tests requiring a database (mysql or postgres)",
-  "high_memory: mark a test as a high-memory only",
   "clipboard: mark a pd.read_clipboard test",
   "arm_slow: mark a test as slow for arm64 architecture",
   "arraymanager: mark a test to run with ArrayManager enabled",