Merge branch 'master' into feature/groupby-repr-ellipses-1135

Author: benjaminarjun

doc/source/getting_started/10min.rst

@@ -103,7 +103,7 @@ Display the index, columns:
    df.columns
 
 :meth:`DataFrame.to_numpy` gives a NumPy representation of the underlying data.
-Note that his can be an expensive operation when your :class:`DataFrame` has
+Note that this can be an expensive operation when your :class:`DataFrame` has
 columns with different data types, which comes down to a fundamental difference
 between pandas and NumPy: **NumPy arrays have one dtype for the entire array,
 while pandas DataFrames have one dtype per column**. When you call

doc/source/getting_started/dsintro.rst

@@ -576,14 +576,14 @@ To write code compatible with all versions of Python, split the assignment in tw
 
 .. warning::
 
-   Dependent assignment maybe subtly change the behavior of your code between
+   Dependent assignment may subtly change the behavior of your code between
    Python 3.6 and older versions of Python.
 
-   If you wish write code that supports versions of python before and after 3.6,
+   If you wish to write code that supports versions of python before and after 3.6,
    you'll need to take care when passing ``assign`` expressions that
 
-   * Updating an existing column
-   * Referring to the newly updated column in the same ``assign``
+   * Update an existing column
+   * Refer to the newly updated column in the same ``assign``
 
    For example, we'll update column "A" and then refer to it when creating "B".
 
@@ -665,8 +665,8 @@ row-wise. For example:
 
    df - df.iloc[0]
 
-In the special case of working with time series data, and the DataFrame index
-also contains dates, the broadcasting will be column-wise:
+In the special case of working with time series data, if the DataFrame index
+contains dates, the broadcasting will be column-wise:
 
 .. ipython:: python
    :okwarning:

doc/source/whatsnew/v0.24.2.rst

@@ -30,6 +30,7 @@ Fixed Regressions
 - Fixed regression in :class:`TimedeltaIndex` where ``np.sum(index)`` incorrectly returned a zero-dimensional object instead of a scalar (:issue:`25282`)
 - Fixed regression in ``IntervalDtype`` construction where passing an incorrect string with 'Interval' as a prefix could result in a ``RecursionError``. (:issue:`25338`)
 - Fixed regression in :class:`Categorical`, where constructing it from a categorical ``Series`` and an explicit ``categories=`` that differed from that in the ``Series`` created an invalid object which could trigger segfaults. (:issue:`25318`)
+- Fixed pip installing from source into an environment without NumPy (:issue:`25193`)
 
 .. _whatsnew_0242.enhancements:
 

doc/source/whatsnew/v0.25.0.rst

@@ -196,7 +196,7 @@ Missing
 ^^^^^^^
 
 - Fixed misleading exception message in :meth:`Series.missing` if argument ``order`` is required, but omitted (:issue:`10633`, :issue:`24014`).
--
+- Fixed class type displayed in exception message in :meth:`DataFrame.dropna` if invalid ``axis`` parameter passed (:issue:`25555`)
 -
 
 MultiIndex

pandas/core/generic.py

@@ -358,7 +358,7 @@ def _get_axis_number(cls, axis):
             except KeyError:
                 pass
         raise ValueError('No axis named {0} for object type {1}'
-                         .format(axis, type(cls)))
+                         .format(axis, cls))
 
     @classmethod
     def _get_axis_name(cls, axis):
@@ -372,7 +372,7 @@ def _get_axis_name(cls, axis):
             except KeyError:
                 pass
         raise ValueError('No axis named {0} for object type {1}'
-                         .format(axis, type(cls)))
+                         .format(axis, cls))
 
     def _get_axis(self, axis):
         name = self._get_axis_name(axis)

pandas/io/formats/style.py

@@ -576,10 +576,10 @@ def apply(self, func, axis=0, subset=None, **kwargs):
             on ``axis``), and return an object with the same shape.
             Must return a DataFrame with identical index and
             column labels when ``axis=None``
-        axis : int, str or None
-            apply to each column (``axis=0`` or ``'index'``)
-            or to each row (``axis=1`` or ``'columns'``) or
-            to the entire DataFrame at once with ``axis=None``
+        axis : {0 or 'index', 1 or 'columns', None}, default 0
+            apply to each column (``axis=0`` or ``'index'``), to each row
+            (``axis=1`` or ``'columns'``), or to the entire DataFrame at once
+            with ``axis=None``.
         subset : IndexSlice
             a valid indexer to limit ``data`` to *before* applying the
             function. Consider using a pandas.IndexSlice
@@ -894,10 +894,12 @@ def background_gradient(self, cmap='PuBu', low=0, high=0, axis=0,
             matplotlib colormap
         low, high : float
             compress the range by these values.
-        axis : int or str
-            1 or 'columns' for columnwise, 0 or 'index' for rowwise
+        axis : {0 or 'index', 1 or 'columns', None}, default 0
+            apply to each column (``axis=0`` or ``'index'``), to each row
+            (``axis=1`` or ``'columns'``), or to the entire DataFrame at once
+            with ``axis=None``.
         subset : IndexSlice
-            a valid slice for ``data`` to limit the style application to
+            a valid slice for ``data`` to limit the style application to.
         text_color_threshold : float or int
             luminance threshold for determining text color. Facilitates text
             visibility across varying background colors. From 0 to 1.
@@ -1081,10 +1083,10 @@ def bar(self, subset=None, axis=0, color='#d65f5f', width=100,
         ----------
         subset : IndexSlice, optional
             A valid slice for `data` to limit the style application to.
-        axis : int, str or None, default 0
-            Apply to each column (`axis=0` or `'index'`)
-            or to each row (`axis=1` or `'columns'`) or
-            to the entire DataFrame at once with `axis=None`.
+        axis : {0 or 'index', 1 or 'columns', None}, default 0
+            apply to each column (``axis=0`` or ``'index'``), to each row
+            (``axis=1`` or ``'columns'``), or to the entire DataFrame at once
+            with ``axis=None``.
         color : str or 2-tuple/list
             If a str is passed, the color is the same for both
             negative and positive numbers. If 2-tuple/list is used, the
@@ -1149,11 +1151,12 @@ def highlight_max(self, subset=None, color='yellow', axis=0):
         Parameters
         ----------
         subset : IndexSlice, default None
-            a valid slice for ``data`` to limit the style application to
+            a valid slice for ``data`` to limit the style application to.
         color : str, default 'yellow'
-        axis : int, str, or None; default 0
-            0 or 'index' for columnwise (default), 1 or 'columns' for rowwise,
-            or ``None`` for tablewise
+        axis : {0 or 'index', 1 or 'columns', None}, default 0
+            apply to each column (``axis=0`` or ``'index'``), to each row
+            (``axis=1`` or ``'columns'``), or to the entire DataFrame at once
+            with ``axis=None``.
 
         Returns
         -------
@@ -1169,11 +1172,12 @@ def highlight_min(self, subset=None, color='yellow', axis=0):
         Parameters
         ----------
         subset : IndexSlice, default None
-            a valid slice for ``data`` to limit the style application to
+            a valid slice for ``data`` to limit the style application to.
         color : str, default 'yellow'
-        axis : int, str, or None; default 0
-            0 or 'index' for columnwise (default), 1 or 'columns' for rowwise,
-            or ``None`` for tablewise
+        axis : {0 or 'index', 1 or 'columns', None}, default 0
+            apply to each column (``axis=0`` or ``'index'``), to each row
+            (``axis=1`` or ``'columns'``), or to the entire DataFrame at once
+            with ``axis=None``.
 
         Returns
         -------

pandas/tests/frame/test_analytics.py

@@ -1385,7 +1385,8 @@ def test_idxmin(self, float_frame, int_frame):
                                         skipna=skipna)
                     tm.assert_series_equal(result, expected)
 
-        msg = "No axis named 2 for object type <class 'type'>"
+        msg = ("No axis named 2 for object type"
+               " <class 'pandas.core.frame.DataFrame'>")
         with pytest.raises(ValueError, match=msg):
             frame.idxmin(axis=2)
 
@@ -1402,7 +1403,8 @@ def test_idxmax(self, float_frame, int_frame):
                                         skipna=skipna)
                     tm.assert_series_equal(result, expected)
 
-        msg = "No axis named 2 for object type <class 'type'>"
+        msg = ("No axis named 2 for object type"
+               " <class 'pandas.core.frame.DataFrame'>")
         with pytest.raises(ValueError, match=msg):
             frame.idxmax(axis=2)
 

pandas/tests/frame/test_api.py

@@ -366,7 +366,8 @@ def test_swapaxes(self):
         self._assert_frame_equal(df.T, df.swapaxes(0, 1))
         self._assert_frame_equal(df.T, df.swapaxes(1, 0))
         self._assert_frame_equal(df, df.swapaxes(0, 0))
-        msg = "No axis named 2 for object type <class 'type'>"
+        msg = ("No axis named 2 for object type"
+               r" <class 'pandas.core(.sparse)?.frame.(Sparse)?DataFrame'>")
         with pytest.raises(ValueError, match=msg):
             df.swapaxes(2, 5)
 

pandas/tests/frame/test_axis_select_reindex.py

@@ -1067,7 +1067,8 @@ def test_reindex_axis(self):
         reindexed2 = self.intframe.reindex(index=rows)
         assert_frame_equal(reindexed1, reindexed2)
 
-        msg = "No axis named 2 for object type <class 'type'>"
+        msg = ("No axis named 2 for object type"
+               " <class 'pandas.core.frame.DataFrame'>")
         with pytest.raises(ValueError, match=msg):
             self.intframe.reindex_axis(rows, axis=2)
 

pandas/tests/frame/test_missing.py

@@ -140,7 +140,8 @@ def test_dropna(self):
         assert_frame_equal(dropped, expected)
 
         # bad input
-        msg = "No axis named 3 for object type <class 'type'>"
+        msg = ("No axis named 3 for object type"
+               " <class 'pandas.core.frame.DataFrame'>")
         with pytest.raises(ValueError, match=msg):
             df.dropna(axis=3)
 

pandas/tests/frame/test_quantile.py

@@ -95,10 +95,12 @@ def test_quantile_axis_parameter(self):
         result = df.quantile(.5, axis="columns")
         assert_series_equal(result, expected)
 
-        msg = "No axis named -1 for object type <class 'type'>"
+        msg = ("No axis named -1 for object type"
+               " <class 'pandas.core.frame.DataFrame'>")
         with pytest.raises(ValueError, match=msg):
             df.quantile(0.1, axis=-1)
-        msg = "No axis named column for object type <class 'type'>"
+        msg = ("No axis named column for object type"
+               " <class 'pandas.core.frame.DataFrame'>")
         with pytest.raises(ValueError, match=msg):
             df.quantile(0.1, axis="column")
 

pandas/tests/frame/test_sorting.py

@@ -55,7 +55,8 @@ def test_sort_values(self):
         sorted_df = frame.sort_values(by=['B', 'A'], ascending=[True, False])
         assert_frame_equal(sorted_df, expected)
 
-        msg = "No axis named 2 for object type <class 'type'>"
+        msg = ("No axis named 2 for object type"
+               " <class 'pandas.core.frame.DataFrame'>")
         with pytest.raises(ValueError, match=msg):
             frame.sort_values(by=['A', 'B'], axis=2, inplace=True)
 

pandas/tests/frame/test_timeseries.py

@@ -862,7 +862,8 @@ def test_frame_to_period(self):
         pts = df.to_period('M', axis=1)
         tm.assert_index_equal(pts.columns, exp.columns.asfreq('M'))
 
-        msg = "No axis named 2 for object type <class 'type'>"
+        msg = ("No axis named 2 for object type"
+               " <class 'pandas.core.frame.DataFrame'>")
         with pytest.raises(ValueError, match=msg):
             df.to_period(axis=2)
 

pandas/tests/series/test_analytics.py

@@ -771,6 +771,7 @@ def test_isin_empty(self, empty):
         result = s.isin(empty)
         tm.assert_series_equal(expected, result)
 
+    @pytest.mark.skipif(PY2, reason="pytest.raises match regex fails")
     def test_ptp(self):
         # GH21614
         N = 1000
@@ -796,7 +797,8 @@ def test_ptp(self):
         with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
             tm.assert_series_equal(s.ptp(level=0, skipna=False), expected)
 
-        msg = r"No axis named 1 for object type <(class|type) 'type'>"
+        msg = ("No axis named 1 for object type"
+               " <class 'pandas.core.series.Series'>")
         with pytest.raises(ValueError, match=msg):
             with tm.assert_produces_warning(FutureWarning,
                                             check_stacklevel=False):

pandas/tests/series/test_missing.py

@@ -10,7 +10,7 @@
 import pytz
 
 from pandas._libs.tslib import iNaT
-from pandas.compat import range
+from pandas.compat import PY2, range
 from pandas.errors import PerformanceWarning
 import pandas.util._test_decorators as td
 
@@ -654,14 +654,16 @@ def test_timedelta64_nan(self):
         #     expected = (datetime_series >= -0.5) & (datetime_series <= 0.5)
         #     assert_series_equal(selector, expected)
 
+    @pytest.mark.skipif(PY2, reason="pytest.raises match regex fails")
     def test_dropna_empty(self):
         s = Series([])
         assert len(s.dropna()) == 0
         s.dropna(inplace=True)
         assert len(s) == 0
 
         # invalid axis
-        msg = r"No axis named 1 for object type <(class|type) 'type'>"
+        msg = ("No axis named 1 for object type"
+               " <class 'pandas.core.series.Series'>")
         with pytest.raises(ValueError, match=msg):
             s.dropna(axis=1)
 

pandas/tests/series/test_rank.py

@@ -9,7 +9,7 @@
 from pandas._libs.algos import Infinity, NegInfinity
 from pandas._libs.tslib import iNaT
 import pandas.compat as compat
-from pandas.compat import product
+from pandas.compat import PY2, product
 import pandas.util._test_decorators as td
 
 from pandas import NaT, Series, Timestamp, date_range
@@ -203,10 +203,12 @@ def test_rank_categorical(self):
         assert_series_equal(na_ser.rank(na_option='bottom', pct=True), exp_bot)
         assert_series_equal(na_ser.rank(na_option='keep', pct=True), exp_keep)
 
+    @pytest.mark.skipif(PY2, reason="pytest.raises match regex fails")
     def test_rank_signature(self):
         s = Series([0, 1])
         s.rank(method='average')
-        msg = r"No axis named average for object type <(class|type) 'type'>"
+        msg = ("No axis named average for object type"
+               " <class 'pandas.core.series.Series'>")
         with pytest.raises(ValueError, match=msg):
             s.rank('average')
 

pandas/tests/series/test_sorting.py

@@ -5,6 +5,8 @@
 import numpy as np
 import pytest
 
+from pandas.compat import PY2
+
 from pandas import Categorical, DataFrame, IntervalIndex, MultiIndex, Series
 import pandas.util.testing as tm
 from pandas.util.testing import assert_almost_equal, assert_series_equal
@@ -88,6 +90,7 @@ def test_sort_values(self):
         with pytest.raises(ValueError, match=msg):
             s.sort_values(inplace=True)
 
+    @pytest.mark.skipif(PY2, reason="pytest.raises match regex fails")
     def test_sort_index(self):
         rindex = list(self.ts.index)
         random.shuffle(rindex)
@@ -109,7 +112,8 @@ def test_sort_index(self):
         sorted_series = random_order.sort_index(axis=0)
         assert_series_equal(sorted_series, self.ts)
 
-        msg = r"No axis named 1 for object type <(class|type) 'type'>"
+        msg = ("No axis named 1 for object type"
+               " <class 'pandas.core.series.Series'>")
         with pytest.raises(ValueError, match=msg):
             random_order.sort_values(axis=1)
 

pandas/tests/series/test_timeseries.py

@@ -8,7 +8,7 @@
 
 from pandas._libs.tslib import iNaT
 from pandas._libs.tslibs.np_datetime import OutOfBoundsDatetime
-from pandas.compat import StringIO, lrange, product
+from pandas.compat import PY2, StringIO, lrange, product
 from pandas.errors import NullFrequencyError
 import pandas.util._test_decorators as td
 
@@ -867,6 +867,7 @@ def test_between_time_formats(self):
         for time_string in strings:
             assert len(ts.between_time(*time_string)) == expected_length
 
+    @pytest.mark.skipif(PY2, reason="pytest.raises match regex fails")
     def test_between_time_axis(self):
         # issue 8839
         rng = date_range('1/1/2000', periods=100, freq='10min')
@@ -876,7 +877,8 @@ def test_between_time_axis(self):
 
         assert len(ts.between_time(stime, etime)) == expected_length
         assert len(ts.between_time(stime, etime, axis=0)) == expected_length
-        msg = r"No axis named 1 for object type <(class|type) 'type'>"
+        msg = ("No axis named 1 for object type"
+               " <class 'pandas.core.series.Series'>")
         with pytest.raises(ValueError, match=msg):
             ts.between_time(stime, etime, axis=1)
 

setup.py

@@ -477,6 +477,11 @@ def maybe_cythonize(extensions, *args, **kwargs):
         # Avoid running cythonize on `python setup.py clean`
         # See https://github.com/cython/cython/issues/1495
         return extensions
+    if not cython:
+        # Avoid trying to look up numpy when installing from sdist
+        # https://github.com/pandas-dev/pandas/issues/25193
+        # TODO: See if this can be removed after pyproject.toml added.
+        return extensions
 
     numpy_incl = pkg_resources.resource_filename('numpy', 'core/include')
     # TODO: Is this really necessary here?
@@ -485,11 +490,8 @@ def maybe_cythonize(extensions, *args, **kwargs):
                 numpy_incl not in ext.include_dirs):
             ext.include_dirs.append(numpy_incl)
 
-    if cython:
-        build_ext.render_templates(_pxifiles)
-        return cythonize(extensions, *args, **kwargs)
-    else:
-        return extensions
+    build_ext.render_templates(_pxifiles)
+    return cythonize(extensions, *args, **kwargs)
 
 
 def srcpath(name=None, suffix='.pyx', subdir='src'):