DEPS: Bump optional dependencies (pandas-dev#47048)

Author: mroeschke

ci/deps/actions-38-minimum_versions.yaml

@@ -20,38 +20,37 @@ dependencies:
   - numpy=1.18.5
   - pytz=2020.1
 
-  # optional dependencies, markupsafe for jinja2
-  - beautifulsoup4=4.8.2
-  - blosc=1.20.1
-  - bottleneck=1.3.1
+  # optional dependencies
+  - beautifulsoup4=4.9.3
+  - blosc=1.21.0
+  - bottleneck=1.3.2
   - brotlipy=0.7.0
   - fastparquet=0.4.0
-  - fsspec=0.7.4
+  - fsspec=2021.05.0
   - html5lib=1.1
-  - hypothesis=5.5.3
-  - gcsfs=0.6.0
-  - jinja2=2.11
-  - lxml=4.5.0
-  - markupsafe=2.0.1
+  - hypothesis=6.13.0
+  - gcsfs=2021.05.0
+  - jinja2=3.0.0
+  - lxml=4.6.3
   - matplotlib=3.3.2
-  - numba=0.50.1
-  - numexpr=2.7.1
+  - numba=0.53.1
+  - numexpr=2.7.3
   - odfpy=1.4.1
-  - openpyxl=3.0.3
-  - pandas-gbq=0.14.0
-  - psycopg2=2.8.4
+  - openpyxl=3.0.7
+  - pandas-gbq=0.15.0
+  - psycopg2=2.8.6
   - pyarrow=1.0.1
-  - pymysql=0.10.1
-  - pyreadstat=1.1.0
+  - pymysql=1.0.2
+  - pyreadstat=1.1.2
   - pytables=3.6.1
   - python-snappy=0.6.0
-  - pyxlsb=1.0.6
-  - s3fs=0.4.0
-  - scipy=1.4.1
-  - sqlalchemy=1.4.0
-  - tabulate=0.8.7
-  - xarray=0.15.1
+  - pyxlsb=1.0.8
+  - s3fs=2021.05.0
+  - scipy=1.7.1
+  - sqlalchemy=1.4.16
+  - tabulate=0.8.9
+  - xarray=0.19.0
   - xlrd=2.0.1
-  - xlsxwriter=1.2.2
+  - xlsxwriter=1.4.3
   - xlwt=1.3.0
   - zstandard=0.15.2

doc/source/whatsnew/v1.5.0.rst

@@ -363,7 +363,50 @@ If installed, we now require:
 +=================+=================+==========+=========+
 | mypy (dev)      | 0.950           |          |    X    |
 +-----------------+-----------------+----------+---------+
-
+| beautifulsoup4  | 4.9.3           |          |    X    |
++-----------------+-----------------+----------+---------+
+| blosc           | 1.21.0          |          |    X    |
++-----------------+-----------------+----------+---------+
+| bottleneck      | 1.3.2           |          |    X    |
++-----------------+-----------------+----------+---------+
+| fsspec          | 2021.05.0       |          |    X    |
++-----------------+-----------------+----------+---------+
+| hypothesis      | 6.13.0          |          |    X    |
++-----------------+-----------------+----------+---------+
+| gcsfs           | 2021.05.0       |          |    X    |
++-----------------+-----------------+----------+---------+
+| jinja2          | 3.0.0           |          |    X    |
++-----------------+-----------------+----------+---------+
+| lxml            | 4.6.3           |          |    X    |
++-----------------+-----------------+----------+---------+
+| numba           | 0.53.1          |          |    X    |
++-----------------+-----------------+----------+---------+
+| numexpr         | 2.7.3           |          |    X    |
++-----------------+-----------------+----------+---------+
+| openpyxl        | 3.0.7           |          |    X    |
++-----------------+-----------------+----------+---------+
+| pandas-gbq      | 0.15.0          |          |    X    |
++-----------------+-----------------+----------+---------+
+| psycopg2        | 2.8.6           |          |    X    |
++-----------------+-----------------+----------+---------+
+| pymysql         | 1.0.2           |          |    X    |
++-----------------+-----------------+----------+---------+
+| pyreadstat      | 1.1.2           |          |    X    |
++-----------------+-----------------+----------+---------+
+| pyxlsb          | 1.0.8           |          |    X    |
++-----------------+-----------------+----------+---------+
+| s3fs            | 2021.05.0       |          |    X    |
++-----------------+-----------------+----------+---------+
+| scipy           | 1.7.1           |          |    X    |
++-----------------+-----------------+----------+---------+
+| sqlalchemy      | 1.4.16          |          |    X    |
++-----------------+-----------------+----------+---------+
+| tabulate        | 0.8.9           |          |    X    |
++-----------------+-----------------+----------+---------+
+| xarray          | 0.19.0          |          |    X    |
++-----------------+-----------------+----------+---------+
+| xlsxwriter      | 1.4.3           |          |    X    |
++-----------------+-----------------+----------+---------+
 
 For `optional libraries <https://pandas.pydata.org/docs/getting_started/install.html>`_ the general recommendation is to use the latest version.
 The following table lists the lowest version per library that is currently being tested throughout the development of pandas.

pandas/compat/_optional.py

@@ -10,40 +10,39 @@
 # Update install.rst when updating versions!
 
 VERSIONS = {
-    "bs4": "4.8.2",
-    "blosc": "1.20.1",
-    "bottleneck": "1.3.1",
+    "bs4": "4.9.3",
+    "blosc": "1.21.0",
+    "bottleneck": "1.3.2",
     "brotli": "0.7.0",
     "fastparquet": "0.4.0",
-    "fsspec": "0.7.4",
+    "fsspec": "2021.05.0",
     "html5lib": "1.1",
-    "hypothesis": "5.5.3",
-    "gcsfs": "0.6.0",
-    "jinja2": "2.11",
-    "lxml.etree": "4.5.0",
-    "markupsafe": "2.0.1",
+    "hypothesis": "6.13.0",
+    "gcsfs": "2021.05.0",
+    "jinja2": "3.0.0",
+    "lxml.etree": "4.6.3",
     "matplotlib": "3.3.2",
-    "numba": "0.50.1",
-    "numexpr": "2.7.1",
+    "numba": "0.53.1",
+    "numexpr": "2.7.3",
     "odfpy": "1.4.1",
-    "openpyxl": "3.0.3",
-    "pandas_gbq": "0.14.0",
-    "psycopg2": "2.8.4",  # (dt dec pq3 ext lo64)
-    "pymysql": "0.10.1",
+    "openpyxl": "3.0.7",
+    "pandas_gbq": "0.15.0",
+    "psycopg2": "2.8.6",  # (dt dec pq3 ext lo64)
+    "pymysql": "1.0.2",
     "pyarrow": "1.0.1",
-    "pyreadstat": "1.1.0",
+    "pyreadstat": "1.1.2",
     "pytest": "6.0",
-    "pyxlsb": "1.0.6",
-    "s3fs": "0.4.0",
-    "scipy": "1.4.1",
+    "pyxlsb": "1.0.8",
+    "s3fs": "2021.05.0",
+    "scipy": "1.7.1",
     "snappy": "0.6.0",
-    "sqlalchemy": "1.4.0",
+    "sqlalchemy": "1.4.16",
     "tables": "3.6.1",
-    "tabulate": "0.8.7",
-    "xarray": "0.15.1",
+    "tabulate": "0.8.9",
+    "xarray": "0.19.0",
     "xlrd": "2.0.1",
     "xlwt": "1.3.0",
-    "xlsxwriter": "1.2.2",
+    "xlsxwriter": "1.4.3",
     "zstandard": "0.15.2",
 }
 

pandas/tests/io/data/excel/high_surrogate.xlsx

@@ -1,12 +1,5 @@
 import pytest
 
-from pandas.compat._optional import (
-    get_version,
-    import_optional_dependency,
-)
-
-from pandas.util.version import Version
-
 pytestmark = [
     pytest.mark.filterwarnings(
         # Looks like tree.getiterator is deprecated in favor of tree.iter
@@ -25,11 +18,3 @@
         "ignore:.*In xlrd >= 2.0, only the xls format is supported:FutureWarning"
     ),
 ]
-
-
-if import_optional_dependency("xlrd", errors="ignore") is None:
-    xlrd_version = None
-else:
-    import xlrd
-
-    xlrd_version = Version(get_version(xlrd))

pandas/tests/io/excel/__init__.py

@@ -21,8 +21,6 @@
     Series,
 )
 import pandas._testing as tm
-from pandas.tests.io.excel import xlrd_version
-from pandas.util.version import Version
 
 read_ext_params = [".xls", ".xlsx", ".xlsm", ".xlsb", ".ods"]
 engine_params = [
@@ -69,12 +67,7 @@ def _is_valid_engine_ext_pair(engine, read_ext: str) -> bool:
         return False
     if read_ext == ".xlsb" and engine != "pyxlsb":
         return False
-    if (
-        engine == "xlrd"
-        and xlrd_version is not None
-        and xlrd_version >= Version("2")
-        and read_ext != ".xls"
-    ):
+    if engine == "xlrd" and read_ext != ".xls":
         return False
     return True
 
@@ -1527,18 +1520,6 @@ def test_excel_read_binary_via_read_excel(self, read_ext, engine):
         expected = pd.read_excel("test1" + read_ext, engine=engine)
         tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.skipif(
-        xlrd_version is not None and xlrd_version >= Version("2"),
-        reason="xlrd no longer supports xlsx",
-    )
-    def test_excel_high_surrogate(self):
-        # GH 23809
-        expected = DataFrame(["\udc88"], columns=["Column1"])
-
-        # should not produce a segmentation violation
-        actual = pd.read_excel("high_surrogate.xlsx", engine="xlrd")
-        tm.assert_frame_equal(expected, actual)
-
     @pytest.mark.parametrize("filename", ["df_empty.xlsx", "df_equals.xlsx"])
     def test_header_with_index_col(self, filename):
         # GH 33476

pandas/tests/io/excel/test_readers.py

@@ -21,7 +21,6 @@
     option_context,
 )
 import pandas._testing as tm
-from pandas.util.version import Version
 
 from pandas.io.excel import (
     ExcelFile,
@@ -1091,8 +1090,7 @@ def test_comment_empty_line(self, path):
         result = pd.read_excel(path, comment="#")
         tm.assert_frame_equal(result, expected)
 
-    def test_datetimes(self, path, request):
-        openpyxl = pytest.importorskip("openpyxl")
+    def test_datetimes(self, path):
         # Test writing and reading datetimes. For issue #9139. (xref #9185)
         datetimes = [
             datetime(2013, 1, 13, 1, 2, 3),
@@ -1110,16 +1108,6 @@ def test_datetimes(self, path, request):
 
         write_frame = DataFrame({"A": datetimes})
         write_frame.to_excel(path, "Sheet1")
-        if (path.endswith("xlsx") or path.endswith("xlsm")) and Version(
-            openpyxl.__version__
-        ) < Version("3.0.6"):
-            request.node.add_marker(
-                pytest.mark.xfail(
-                    reason="Defaults to openpyxl and fails with "
-                    "floating point error on datetimes; may be fixed on "
-                    "newer versions of openpyxl - GH #38644"
-                )
-            )
         read_frame = pd.read_excel(path, sheet_name="Sheet1", header=0)
 
         tm.assert_series_equal(write_frame["A"], read_frame["A"])

pandas/tests/io/excel/test_writers.py

@@ -6,8 +6,6 @@
 
 import pandas as pd
 import pandas._testing as tm
-from pandas.tests.io.excel import xlrd_version
-from pandas.util.version import Version
 
 from pandas.io.excel import ExcelFile
 from pandas.io.excel._base import inspect_excel_format
@@ -20,11 +18,7 @@
 )
 
 
-# error: Unsupported operand types for <= ("Version" and "None")
-if xlrd_version >= Version("2"):  # type: ignore[operator]
-    exts = [".xls"]
-else:
-    exts = [".xls", ".xlsx", ".xlsm"]
+exts = [".xls"]
 
 
 @pytest.fixture(params=exts)
@@ -77,19 +71,11 @@ def test_read_excel_warning_with_xlsx_file(datapath):
     path = datapath("io", "data", "excel", "test1.xlsx")
     has_openpyxl = import_optional_dependency("openpyxl", errors="ignore") is not None
     if not has_openpyxl:
-        if xlrd_version >= Version("2"):
-            with pytest.raises(
-                ValueError,
-                match="Your version of xlrd is ",
-            ):
-                pd.read_excel(path, "Sheet1", engine=None)
-        else:
-            with tm.assert_produces_warning(
-                FutureWarning,
-                raise_on_extra_warnings=False,
-                match="The xlrd engine is no longer maintained",
-            ):
-                pd.read_excel(path, "Sheet1", engine=None)
+        with pytest.raises(
+            ValueError,
+            match="Your version of xlrd is ",
+        ):
+            pd.read_excel(path, "Sheet1", engine=None)
     else:
         with tm.assert_produces_warning(None):
             pd.read_excel(path, "Sheet1", engine=None)

pandas/tests/io/excel/test_xlrd.py

@@ -188,7 +188,6 @@ def test_highlight_quantile(styler, kwargs):
     assert result == expected
 
 
-@pytest.mark.skipif(np.__version__[:4] in ["1.16", "1.17"], reason="Numpy Issue #14831")
 @pytest.mark.parametrize(
     "f,kwargs",
     [

pandas/tests/io/formats/style/test_highlight.py

@@ -3,8 +3,6 @@
 import numpy as np
 import pytest
 
-from pandas.compat._optional import VERSIONS
-
 from pandas import (
     DataFrame,
     date_range,
@@ -294,21 +292,7 @@ def test_stata_options(fsspectest):
 
 
 @td.skip_if_no("tabulate")
-def test_markdown_options(request, fsspectest):
-    import fsspec
-
-    # error: Library stubs not installed for "tabulate"
-    # (or incompatible with Python 3.8)
-    import tabulate  # type: ignore[import]
-
-    request.node.add_marker(
-        pytest.mark.xfail(
-            fsspec.__version__ == VERSIONS["fsspec"]
-            and tabulate.__version__ == VERSIONS["tabulate"],
-            reason="Fails on the min version build",
-            raises=FileNotFoundError,
-        )
-    )
+def test_markdown_options(fsspectest):
     df = DataFrame({"a": [0]})
     df.to_markdown("testmem://afile", storage_options={"test": "md_write"})
     assert fsspectest.test[0] == "md_write"

pandas/tests/io/test_fsspec.py

@@ -12,7 +12,6 @@
     isna,
 )
 import pandas._testing as tm
-from pandas.util.version import Version
 
 
 @pytest.fixture(
@@ -791,11 +790,8 @@ def test_interpolate_timedelta_index(self, request, interp_methods_ind):
         df = pd.DataFrame([0, 1, np.nan, 3], index=ind)
 
         method, kwargs = interp_methods_ind
-        import scipy
 
-        if method in {"cubic", "zero"} or (
-            method == "barycentric" and Version(scipy.__version__) < Version("1.5.0")
-        ):
+        if method in {"cubic", "zero"}:
             request.node.add_marker(
                 pytest.mark.xfail(
                     reason=f"{method} interpolation is not supported for TimedeltaIndex"