ARROW-6674: [Python] Fix or ignore the test warnings

python/pyarrow/tests/conftest.py

@@ -51,7 +51,9 @@
     'plasma',
     's3',
     'tensorflow',
-    'flight'
+    'flight',
+    'slow',
+    'requires_testing_data',
 ]
 
 
@@ -70,6 +72,8 @@
     's3': False,
     'tensorflow': False,
     'flight': False,
+    'slow': False,
+    'requires_testing_data': True,
 }
 
 try:
@@ -166,18 +170,6 @@ def bool_env(name, default=None):
                          action='store_true', default=default,
                          help=('Run only the {} test group'.format(group)))
 
-    parser.addoption('--runslow', action='store_true',
-                     default=False, help='run slow tests')
-
-
-def pytest_collection_modifyitems(config, items):
-    if not config.getoption('--runslow'):
-        skip_slow = pytest.mark.skip(reason='need --runslow option to run')
-
-        for item in items:
-            if 'slow' in item.keywords:
-                item.add_marker(skip_slow)
-
 
 def pytest_runtest_setup(item):
     only_set = False

python/pyarrow/tests/test_array.py

@@ -152,25 +152,25 @@ def test_to_pandas_zero_copy():
     arr = pa.array(range(10))
 
     for i in range(10):
-        np_arr = arr.to_pandas()
-        assert sys.getrefcount(np_arr) == 2
-        np_arr = None  # noqa
+        series = arr.to_pandas()
+        assert sys.getrefcount(series) == 2
+        series = None  # noqa
 
     assert sys.getrefcount(arr) == 2
 
     for i in range(10):
         arr = pa.array(range(10))
-        np_arr = arr.to_pandas()
+        series = arr.to_pandas()
         arr = None
         gc.collect()
 
         # Ensure base is still valid
 
         # Because of py.test's assert inspection magic, if you put getrefcount
         # on the line being examined, it will be 1 higher than you expect
-        base_refcount = sys.getrefcount(np_arr.base)
+        base_refcount = sys.getrefcount(series.values.base)
         assert base_refcount == 2
-        np_arr.sum()
+        series.sum()
 
 
 @pytest.mark.nopandas

python/pyarrow/tests/test_io.py

@@ -1191,7 +1191,7 @@ def test_compressed_recordbatch_stream(compression):
         else:
             raise
     writer = pa.RecordBatchStreamWriter(stream, table.schema)
-    writer.write_table(table, chunksize=3)
+    writer.write_table(table, max_chunksize=3)
     writer.close()
     stream.close()  # Flush data
     buf = raw.getvalue()

python/pyarrow/tests/test_parquet.py

@@ -2352,9 +2352,7 @@ def test_noncoerced_nanoseconds_written_without_exception(tempdir):
     # nanosecond timestamps by default
     n = 9
     df = pd.DataFrame({'x': range(n)},
-                      index=pd.DatetimeIndex(start='2017-01-01',
-                      freq='1n',
-                      periods=n))
+                      index=pd.date_range('2017-01-01', freq='1n', periods=n))
     tb = pa.Table.from_pandas(df)
 
     filename = tempdir / 'written.parquet'
@@ -3025,7 +3023,7 @@ def test_write_nested_zero_length_array_chunk_failure():
     # Each column is a ChunkedArray with 2 elements
     my_arrays = [pa.array(batch, type=pa.struct(cols)).flatten()
                  for batch in data]
-    my_batches = [pa.RecordBatch.from_arrays(batch, pa.schema(cols))
+    my_batches = [pa.RecordBatch.from_arrays(batch, schema=pa.schema(cols))
                   for batch in my_arrays]
     tbl = pa.Table.from_batches(my_batches, pa.schema(cols))
     _check_roundtrip(tbl)

python/pyarrow/tests/test_serialization.py

@@ -520,6 +520,8 @@ def deserializer(data):
     assert np.alltrue(new_x.view(np.ndarray) == np.zeros(3))
 
 
+@pytest.mark.filterwarnings(
+    "ignore:the matrix subclass:PendingDeprecationWarning")
 def test_numpy_matrix_serialization(tmpdir):
     class CustomType(object):
         def __init__(self, val):