Merge pull request #140 from pandas-dev/master

Sync Fork from Upstream Repo

Author: sthagen

.github/workflows/ci.yml

@@ -162,9 +162,7 @@ jobs:
         pytest pandas/tests/groupby/
         pytest pandas/tests/resample/
         pytest pandas/tests/reshape/merge
-
-        pytest pandas/tests/series/methods
-        pytest pandas/tests/series/test_*
+        pytest pandas/tests/series/
 
         # indexing subset (temporary since other tests don't pass yet)
         pytest pandas/tests/indexing/multiindex/test_setitem.py::TestMultiIndexSetItem::test_astype_assignment_with_dups

doc/source/_static/css/pandas.css

@@ -2,7 +2,7 @@
 
 :root {
   /* Use softer blue from bootstrap's default info color */
-  --color-info: 23, 162, 184;
+  --pst-color-info: 23, 162, 184;
 }
 
 /* Getting started index page */

environment.yml

@@ -113,5 +113,5 @@ dependencies:
   - tabulate>=0.8.3  # DataFrame.to_markdown
   - natsort  # DataFrame.sort_values
   - pip:
-    - git+https://github.com/pandas-dev/pydata-sphinx-theme.git@2488b7defbd3d753dd5fcfc890fc4a7e79d25103
+    - git+https://github.com/pydata/pydata-sphinx-theme.git@master
     - numpydoc < 1.2  # 2021-02-09 1.2dev breaking CI

pandas/core/frame.py

@@ -3784,7 +3784,7 @@ def _box_col_values(self, values, loc: int) -> Series:
     # Unsorted
 
     def query(self, expr: str, inplace: bool = False, **kwargs):
-        """
+        r"""
         Query the columns of a DataFrame with a boolean expression.
 
         Parameters
@@ -3799,8 +3799,8 @@ def query(self, expr: str, inplace: bool = False, **kwargs):
             You can refer to column names that are not valid Python variable names
             by surrounding them in backticks. Thus, column names containing spaces
             or punctuations (besides underscores) or starting with digits must be
-            surrounded by backticks. (For example, a column named "Area (cm^2) would
-            be referenced as `Area (cm^2)`). Column names which are Python keywords
+            surrounded by backticks. (For example, a column named "Area (cm^2)" would
+            be referenced as \`Area (cm^2)\`). Column names which are Python keywords
             (like "list", "for", "import", etc) cannot be used.
 
             For example, if one of your columns is called ``a a`` and you want

pandas/core/internals/array_manager.py

@@ -202,7 +202,7 @@ def get_dtypes(self):
     def __repr__(self) -> str:
         output = type(self).__name__
         output += f"\nIndex: {self._axes[0]}"
-        if self.ndim == 1:
+        if self.ndim == 2:
             output += f"\nColumns: {self._axes[1]}"
         output += f"\n{len(self.arrays)} arrays:"
         for arr in self.arrays:
@@ -1138,7 +1138,13 @@ def __init__(
     def _verify_integrity(self) -> None:
         (n_rows,) = self.shape
         assert len(self.arrays) == 1
-        assert len(self.arrays[0]) == n_rows
+        arr = self.arrays[0]
+        assert len(arr) == n_rows
+        if not arr.ndim == 1:
+            raise ValueError(
+                "Passed array should be 1-dimensional, got array with "
+                f"{arr.ndim} dimensions instead."
+            )
 
     @staticmethod
     def _normalize_axis(axis):

pandas/tests/series/indexing/test_getitem.py

@@ -234,10 +234,12 @@ def test_getitem_partial_str_slice_high_reso_with_timedeltaindex(self):
         result = ser["1 days, 10:11:12.001001"]
         assert result == ser.iloc[1001]
 
-    def test_getitem_slice_2d(self, datetime_series):
+    def test_getitem_slice_2d(self, datetime_series, using_array_manager):
         # GH#30588 multi-dimensional indexing deprecated
 
-        with tm.assert_produces_warning(FutureWarning):
+        with tm.assert_produces_warning(
+            FutureWarning, check_stacklevel=not using_array_manager
+        ):
             # GH#30867 Don't want to support this long-term, but
             # for now ensure that the warning from Index
             # doesn't comes through via Series.__getitem__.
@@ -518,9 +520,11 @@ def test_getitem_generator(string_series):
         Series(date_range("2012-01-01", periods=2, tz="CET")),
     ],
 )
-def test_getitem_ndim_deprecated(series):
+def test_getitem_ndim_deprecated(series, using_array_manager):
     with tm.assert_produces_warning(
-        FutureWarning, match="Support for multi-dimensional indexing"
+        FutureWarning,
+        match="Support for multi-dimensional indexing",
+        check_stacklevel=not using_array_manager,
     ):
         result = series[:, None]
 

pandas/tests/series/indexing/test_setitem.py

@@ -306,8 +306,8 @@ def test_dt64tz_setitem_does_not_mutate_dti(self):
         ser = Series(dti)
         assert ser._values is not dti
         assert ser._values._data.base is not dti._data._data.base
-        assert ser._mgr.blocks[0].values is not dti
-        assert ser._mgr.blocks[0].values._data.base is not dti._data._data.base
+        assert ser._mgr.arrays[0] is not dti
+        assert ser._mgr.arrays[0]._data.base is not dti._data._data.base
 
         ser[::3] = NaT
         assert ser[0] is NaT

pandas/tests/series/indexing/test_where.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+import pandas.util._test_decorators as td
+
 from pandas.core.dtypes.common import is_integer
 
 import pandas as pd
@@ -471,6 +473,9 @@ def test_where_categorical(klass):
     tm.assert_equal(exp, res)
 
 
+# TODO(ArrayManager) DataFrame.values not yet correctly returning datetime array
+# for categorical with datetime categories
+@td.skip_array_manager_not_yet_implemented
 def test_where_datetimelike_categorical(tz_naive_fixture):
     # GH#37682
     tz = tz_naive_fixture

requirements-dev.txt

@@ -76,5 +76,5 @@ cftime
 pyreadstat
 tabulate>=0.8.3
 natsort
-git+https://github.com/pandas-dev/pydata-sphinx-theme.git@2488b7defbd3d753dd5fcfc890fc4a7e79d25103
+git+https://github.com/pydata/pydata-sphinx-theme.git@master
 numpydoc < 1.2