Merge and fix conflict

Author: h-vetinari

ci/code_checks.sh

@@ -241,8 +241,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (GL06, GL07, GL09, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT04, RT05, SA05)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL06,GL07,GL09,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT04,RT05,SA05
+    MSG='Validate docstrings (GL03, GL06, GL07, GL09, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT04, RT05, SA05)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL03,GL06,GL07,GL09,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT04,RT05,SA05
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

doc/source/whatsnew/v0.25.0.rst

@@ -131,7 +131,7 @@ Performance Improvements
 Bug Fixes
 ~~~~~~~~~
 - Bug in :func:`to_datetime` which would raise an (incorrect) ``ValueError`` when called with a date far into the future and the ``format`` argument specified instead of raising ``OutOfBoundsDatetime`` (:issue:`23830`)
--
+- Bug in an error message in :meth:`DataFrame.plot`. Improved the error message if non-numerics are passed to :meth:`DataFrame.plot` (:issue:`25481`)
 -
 
 Categorical
@@ -224,7 +224,7 @@ I/O
 - Bug in :func:`read_json` for ``orient='table'`` when it tries to infer dtypes by default, which is not applicable as dtypes are already defined in the JSON schema (:issue:`21345`)
 - Bug in :func:`read_json` for ``orient='table'`` and float index, as it infers index dtype by default, which is not applicable because index dtype is already defined in the JSON schema (:issue:`25433`)
 - Bug in :func:`read_json` for ``orient='table'`` and string of float column names, as it makes a column name type conversion to Timestamp, which is not applicable because column names are already defined in the JSON schema (:issue:`25435`)
--
+- :meth:`DataFrame.to_html` now raises ``TypeError`` when using an invalid type for the ``classes`` parameter instead of ``AsseertionError`` (:issue:`25608`)
 -
 -
 

pandas/_libs/tslibs/timedeltas.pyx

@@ -1156,7 +1156,6 @@ class Timedelta(_Timedelta):
     Notes
     -----
     The ``.value`` attribute is always in ns.
-
     """
     def __new__(cls, object value=_no_input, unit=None, **kwargs):
         cdef _Timedelta td_base

pandas/core/arrays/datetimes.py

@@ -119,7 +119,7 @@ def f(self):
         return result
 
     f.__name__ = name
-    f.__doc__ = "\n{}\n".format(docstring)
+    f.__doc__ = docstring
     return property(f)
 
 

pandas/core/arrays/sparse.py

@@ -541,7 +541,6 @@ class SparseArray(PandasObject, ExtensionArray, ExtensionOpsMixin):
         3. ``data.dtype.fill_value`` if `fill_value` is None and `dtype`
            is not a ``SparseDtype`` and `data` is a ``SparseArray``.
 
-
     kind : {'integer', 'block'}, default 'integer'
         The type of storage for sparse locations.
 

pandas/core/base.py

@@ -870,7 +870,6 @@ def to_numpy(self, dtype=None, copy=False):
 
         .. versionadded:: 0.24.0
 
-
         Parameters
         ----------
         dtype : str or numpy.dtype, optional

pandas/core/config.py

@@ -651,7 +651,6 @@ def _build_option_description(k):
               .format(rkey=d.rkey if d.rkey else ''))
         s += u(')')
 
-    s += '\n\n'
     return s
 
 

pandas/core/frame.py

@@ -2184,7 +2184,6 @@ def to_html(self, buf=None, columns=None, col_space=None, header=True,
             Convert URLs to HTML links.
 
             .. versionadded:: 0.24.0
-
         %(returns)s
         See Also
         --------
@@ -6027,7 +6026,6 @@ def unstack(self, level=-1, fill_value=None):
     columns, considered measured variables (`value_vars`), are "unpivoted" to
     the row axis, leaving just two non-identifier columns, 'variable' and
     'value'.
-
     %(versionadded)s
     Parameters
     ----------

pandas/core/generic.py

@@ -948,7 +948,6 @@ def swaplevel(self, i=-2, j=-1, axis=0):
 
            The indexes ``i`` and ``j`` are now optional, and default to
            the two innermost levels of the index.
-
         """
         axis = self._get_axis_number(axis)
         result = self.copy()
@@ -4951,9 +4950,7 @@ def pipe(self, func, *args, **kwargs):
 
     _shared_docs['aggregate'] = dedent("""
     Aggregate using one or more operations over the specified axis.
-
     %(versionadded)s
-
     Parameters
     ----------
     func : function, str, list or dict
@@ -4983,17 +4980,13 @@ def pipe(self, func, *args, **kwargs):
         * DataFrame : when DataFrame.agg is called with several functions
 
         Return scalar, Series or DataFrame.
-
     %(see_also)s
-
     Notes
     -----
     `agg` is an alias for `aggregate`. Use the alias.
 
     A passed user-defined-function will be passed a Series for evaluation.
-
-    %(examples)s
-    """)
+    %(examples)s""")
 
     _shared_docs['transform'] = ("""
     Call ``func`` on self producing a %(klass)s with transformed values
@@ -10307,7 +10300,7 @@ def _doc_parms(cls):
 
 Returns
 -------
-%(name1)s or %(name2)s (if level specified)
+%(name1)s or %(name2)s (if level specified)\
 %(see_also)s
 %(examples)s\
 """
@@ -10464,8 +10457,7 @@ def _doc_parms(cls):
 %(name2)s.cumsum : Return cumulative sum over %(name2)s axis.
 %(name2)s.cumprod : Return cumulative product over %(name2)s axis.
 
-%(examples)s
-"""
+%(examples)s"""
 
 _cummin_examples = """\
 Examples

pandas/core/groupby/base.py

@@ -126,9 +126,7 @@ class where members are defined.
     property_wrapper_template = \
         """@property
 def %(name)s(self) :
-    \"""
-    %(doc)s
-    \"""
+    \"""%(doc)s\"""
     return self.__getattr__('%(name)s')"""
 
     for name in whitelist:

pandas/core/groupby/groupby.py

@@ -221,8 +221,7 @@ class providing the base-class of operations.
 
 Examples
 --------
-%(examples)s
-"""
+%(examples)s"""
 
 _transform_template = """
 Call function producing a like-indexed %(klass)s on each group and
@@ -1106,9 +1105,7 @@ def mean(self, *args, **kwargs):
         Returns
         -------
         pandas.Series or pandas.DataFrame
-
         %(see_also)s
-
         Examples
         --------
         >>> df = pd.DataFrame({'A': [1, 1, 2, 1, 2],
@@ -1564,9 +1561,7 @@ def nth(self, n, dropna=None):
         dropna : None or str, optional
             apply the specified dropna operation before counting which row is
             the nth row. Needs to be None, 'any' or 'all'
-
         %(see_also)s
-
         Examples
         --------
 
@@ -2139,9 +2134,7 @@ def head(self, n=5):
 
         Essentially equivalent to ``.apply(lambda x: x.head(n))``,
         except ignores as_index flag.
-
         %(see_also)s
-
         Examples
         --------
 
@@ -2167,9 +2160,7 @@ def tail(self, n=5):
 
         Essentially equivalent to ``.apply(lambda x: x.tail(n))``,
         except ignores as_index flag.
-
         %(see_also)s
-
         Examples
         --------
 

pandas/core/indexes/base.py

@@ -3104,7 +3104,6 @@ def reindex(self, target, method=None, level=None, limit=None,
             Resulting index.
         indexer : np.ndarray or None
             Indices of output values in original index.
-
         """
         # GH6552: preserve names when reindexing to non-named target
         # (i.e. neither Index nor Series).

pandas/io/feather_format.py

@@ -110,7 +110,6 @@ def read_feather(path, columns=None, use_threads=True):
     Returns
     -------
     type of object stored in file
-
     """
 
     feather, pyarrow = _try_import()

pandas/io/formats/html.py

@@ -163,8 +163,8 @@ def _write_table(self, indent=0):
             if isinstance(self.classes, str):
                 self.classes = self.classes.split()
             if not isinstance(self.classes, (list, tuple)):
-                raise AssertionError('classes must be list or tuple, not {typ}'
-                                     .format(typ=type(self.classes)))
+                raise TypeError('classes must be a string, list, or tuple, '
+                                'not {typ}'.format(typ=type(self.classes)))
             _classes.extend(self.classes)
 
         if self.table_id is None:

pandas/plotting/_core.py

@@ -361,10 +361,9 @@ def _compute_plot_data(self):
         except AttributeError:
             is_empty = not len(numeric_data)
 
-        # no empty frames or series allowed
+        # no non-numeric frames or series allowed
         if is_empty:
-            raise TypeError('Empty {0!r}: no numeric data to '
-                            'plot'.format(numeric_data.__class__.__name__))
+            raise TypeError('no numeric data to plot')
 
         self.data = numeric_data
 

pandas/plotting/_misc.py

@@ -303,7 +303,6 @@ def andrews_curves(frame, class_column, ax=None, samples=200, color=None,
     Returns
     -------
     class:`matplotlip.axis.Axes`
-
     """
     from math import sqrt, pi
     import matplotlib.pyplot as plt

pandas/tests/frame/test_asof.py

@@ -6,21 +6,26 @@
 from pandas import DataFrame, Series, Timestamp, date_range, to_datetime
 import pandas.util.testing as tm
 
-from .common import TestData
 
+@pytest.fixture
+def date_range_frame():
+    """
+    Fixture for DataFrame of ints with date_range index
 
-class TestFrameAsof(TestData):
-    def setup_method(self, method):
-        self.N = N = 50
-        self.rng = date_range('1/1/1990', periods=N, freq='53s')
-        self.df = DataFrame({'A': np.arange(N), 'B': np.arange(N)},
-                            index=self.rng)
+    Columns are ['A', 'B'].
+    """
+    N = 50
+    rng = date_range('1/1/1990', periods=N, freq='53s')
+    return DataFrame({'A': np.arange(N), 'B': np.arange(N)}, index=rng)
 
-    def test_basic(self):
-        df = self.df.copy()
+
+class TestFrameAsof():
+
+    def test_basic(self, date_range_frame):
+        df = date_range_frame
+        N = 50
         df.loc[15:30, 'A'] = np.nan
-        dates = date_range('1/1/1990', periods=self.N * 3,
-                           freq='25s')
+        dates = date_range('1/1/1990', periods=N * 3, freq='25s')
 
         result = df.asof(dates)
         assert result.notna().all(1).all()
@@ -35,11 +40,9 @@ def test_basic(self):
         rs = result[mask]
         assert (rs == 14).all(1).all()
 
-    def test_subset(self):
+    def test_subset(self, date_range_frame):
         N = 10
-        rng = date_range('1/1/1990', periods=N, freq='53s')
-        df = DataFrame({'A': np.arange(N), 'B': np.arange(N)},
-                       index=rng)
+        df = date_range_frame.iloc[:N].copy()
         df.loc[4:8, 'A'] = np.nan
         dates = date_range('1/1/1990', periods=N * 3,
                            freq='25s')
@@ -54,20 +57,18 @@ def test_subset(self):
         expected = df.asof(dates)
         tm.assert_frame_equal(result, expected)
 
-        # B gives self.df.asof
+        # B gives df.asof
         result = df.asof(dates, subset='B')
         expected = df.resample('25s', closed='right').ffill().reindex(dates)
         expected.iloc[20:] = 9
 
         tm.assert_frame_equal(result, expected)
 
-    def test_missing(self):
+    def test_missing(self, date_range_frame):
         # GH 15118
         # no match found - `where` value before earliest date in index
         N = 10
-        rng = date_range('1/1/1990', periods=N, freq='53s')
-        df = DataFrame({'A': np.arange(N), 'B': np.arange(N)},
-                       index=rng)
+        df = date_range_frame.iloc[:N].copy()
         result = df.asof('1989-12-31')
 
         expected = Series(index=['A', 'B'], name=Timestamp('1989-12-31'))
@@ -78,22 +79,24 @@ def test_missing(self):
                              columns=['A', 'B'], dtype='float64')
         tm.assert_frame_equal(result, expected)
 
-    def test_all_nans(self):
+    def test_all_nans(self, date_range_frame):
         # GH 15713
         # DataFrame is all nans
         result = DataFrame([np.nan]).asof([0])
         expected = DataFrame([np.nan])
         tm.assert_frame_equal(result, expected)
 
         # testing non-default indexes, multiple inputs
-        dates = date_range('1/1/1990', periods=self.N * 3, freq='25s')
-        result = DataFrame(np.nan, index=self.rng, columns=['A']).asof(dates)
+        N = 150
+        rng = date_range_frame.index
+        dates = date_range('1/1/1990', periods=N, freq='25s')
+        result = DataFrame(np.nan, index=rng, columns=['A']).asof(dates)
         expected = DataFrame(np.nan, index=dates, columns=['A'])
         tm.assert_frame_equal(result, expected)
 
         # testing multiple columns
-        dates = date_range('1/1/1990', periods=self.N * 3, freq='25s')
-        result = DataFrame(np.nan, index=self.rng,
+        dates = date_range('1/1/1990', periods=N, freq='25s')
+        result = DataFrame(np.nan, index=rng,
                            columns=['A', 'B', 'C']).asof(dates)
         expected = DataFrame(np.nan, index=dates, columns=['A', 'B', 'C'])
         tm.assert_frame_equal(result, expected)