Merge branch 'master' of github.com:pandas-dev/pandas into depr/CategoricalAccessor-categorical-name-index

Author: benjaminr

ci/code_checks.sh

@@ -101,7 +101,7 @@ if [[ -z "$CHECK" || "$CHECK" == "lint" ]]; then
 
     # Imports - Check formatting using isort see setup.cfg for settings
     MSG='Check import format using isort ' ; echo $MSG
-    isort --recursive --check-only pandas
+    isort --recursive --check-only pandas asv_bench
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

doc/source/api/general_utility_functions.rst

@@ -63,6 +63,7 @@ Dtype introspection
     api.types.is_datetime64_ns_dtype
     api.types.is_datetime64tz_dtype
     api.types.is_extension_type
+    api.types.is_extension_array_dtype
     api.types.is_float_dtype
     api.types.is_int64_dtype
     api.types.is_integer_dtype

doc/source/whatsnew/v0.24.0.rst

@@ -1791,6 +1791,7 @@ I/O
 - Bug in :meth:`DataFrame.to_dict` when the resulting dict contains non-Python scalars in the case of numeric data (:issue:`23753`)
 - :func:`DataFrame.to_string()`, :func:`DataFrame.to_html()`, :func:`DataFrame.to_latex()` will correctly format output when a string is passed as the ``float_format`` argument (:issue:`21625`, :issue:`22270`)
 - Bug in :func:`read_csv` that caused it to raise ``OverflowError`` when trying to use 'inf' as ``na_value`` with integer index column (:issue:`17128`)
+- Bug in :func:`read_csv` that caused the C engine on Python 3.6+ on Windows to improperly read CSV filenames with accented or special characters (:issue:`15086`)
 - Bug in :func:`read_fwf` in which the compression type of a file was not being properly inferred (:issue:`22199`)
 - Bug in :func:`pandas.io.json.json_normalize` that caused it to raise ``TypeError`` when two consecutive elements of ``record_path`` are dicts (:issue:`22706`)
 - Bug in :meth:`DataFrame.to_stata`, :class:`pandas.io.stata.StataWriter` and :class:`pandas.io.stata.StataWriter117` where a exception would leave a partially written and invalid dta file (:issue:`23573`)

environment.yml

@@ -14,7 +14,7 @@ dependencies:
   - cython>=0.28.2
   - flake8
   - flake8-comprehensions
-  - flake8-rst>=0.6.0
+  - flake8-rst>=0.6.0,<=0.7.0
   - gitpython
   - hypothesis>=3.82
   - isort

pandas/_libs/parsers.pyx

@@ -677,7 +677,13 @@ cdef class TextReader:
 
         if isinstance(source, basestring):
             if not isinstance(source, bytes):
-                source = source.encode(sys.getfilesystemencoding() or 'utf-8')
+                if compat.PY36 and compat.is_platform_windows():
+                    # see gh-15086.
+                    encoding = "mbcs"
+                else:
+                    encoding = sys.getfilesystemencoding() or "utf-8"
+
+                source = source.encode(encoding)
 
             if self.memory_map:
                 ptr = new_mmap(source)

pandas/_libs/tslibs/offsets.pyx

@@ -412,12 +412,12 @@ class _BaseOffset(object):
                           **self.kwds)
 
     def __neg__(self):
-        # Note: we are defering directly to __mul__ instead of __rmul__, as
+        # Note: we are deferring directly to __mul__ instead of __rmul__, as
         # that allows us to use methods that can go in a `cdef class`
         return self * -1
 
     def copy(self):
-        # Note: we are defering directly to __mul__ instead of __rmul__, as
+        # Note: we are deferring directly to __mul__ instead of __rmul__, as
         # that allows us to use methods that can go in a `cdef class`
         return self * 1
 

pandas/core/dtypes/api.py

@@ -5,10 +5,10 @@
     is_categorical_dtype, is_complex, is_complex_dtype,
     is_datetime64_any_dtype, is_datetime64_dtype, is_datetime64_ns_dtype,
     is_datetime64tz_dtype, is_datetimetz, is_dict_like, is_dtype_equal,
-    is_extension_type, is_file_like, is_float, is_float_dtype, is_hashable,
-    is_int64_dtype, is_integer, is_integer_dtype, is_interval,
-    is_interval_dtype, is_iterator, is_list_like, is_named_tuple, is_number,
-    is_numeric_dtype, is_object_dtype, is_period, is_period_dtype, is_re,
-    is_re_compilable, is_scalar, is_signed_integer_dtype, is_sparse,
+    is_extension_array_dtype, is_extension_type, is_file_like, is_float,
+    is_float_dtype, is_hashable, is_int64_dtype, is_integer, is_integer_dtype,
+    is_interval, is_interval_dtype, is_iterator, is_list_like, is_named_tuple,
+    is_number, is_numeric_dtype, is_object_dtype, is_period, is_period_dtype,
+    is_re, is_re_compilable, is_scalar, is_signed_integer_dtype, is_sparse,
     is_string_dtype, is_timedelta64_dtype, is_timedelta64_ns_dtype,
     is_unsigned_integer_dtype, pandas_dtype)

pandas/core/dtypes/common.py

@@ -1700,15 +1700,21 @@ def is_extension_type(arr):
 
 
 def is_extension_array_dtype(arr_or_dtype):
-    """Check if an object is a pandas extension array type.
+    """
+    Check if an object is a pandas extension array type.
+
+    See the :ref:`Use Guide <extending.extension-types>` for more.
 
     Parameters
     ----------
     arr_or_dtype : object
+        For array-like input, the ``.dtype`` attribute will
+        be extracted.
 
     Returns
     -------
     bool
+        Whether the `arr_or_dtype` is an extension array type.
 
     Notes
     -----
@@ -1718,9 +1724,25 @@ def is_extension_array_dtype(arr_or_dtype):
     * Categorical
     * Sparse
     * Interval
+    * Period
+    * DatetimeArray
+    * TimedeltaArray
 
     Third-party libraries may implement arrays or types satisfying
     this interface as well.
+
+    Examples
+    --------
+    >>> from pandas.api.types import is_extension_array_dtype
+    >>> arr = pd.Categorical(['a', 'b'])
+    >>> is_extension_array_dtype(arr)
+    True
+    >>> is_extension_array_dtype(arr.dtype)
+    True
+
+    >>> arr = np.array(['a', 'b'])
+    >>> is_extension_array_dtype(arr.dtype)
+    False
     """
     dtype = getattr(arr_or_dtype, 'dtype', arr_or_dtype)
     return (isinstance(dtype, ExtensionDtype) or

pandas/core/indexing.py

@@ -1405,17 +1405,16 @@ class _IXIndexer(_NDFrameIndexer):
     See more at :ref:`Advanced Indexing <advanced>`.
     """
 
-    def __init__(self, name, obj):
-
-        _ix_deprecation_warning = textwrap.dedent("""
-            .ix is deprecated. Please use
-            .loc for label based indexing or
-            .iloc for positional indexing
+    _ix_deprecation_warning = textwrap.dedent("""
+        .ix is deprecated. Please use
+        .loc for label based indexing or
+        .iloc for positional indexing
 
-            See the documentation here:
-            http://pandas.pydata.org/pandas-docs/stable/indexing.html#ix-indexer-is-deprecated""")  # noqa
+        See the documentation here:
+        http://pandas.pydata.org/pandas-docs/stable/indexing.html#ix-indexer-is-deprecated""")  # noqa
 
-        warnings.warn(_ix_deprecation_warning,
+    def __init__(self, name, obj):
+        warnings.warn(self._ix_deprecation_warning,
                       DeprecationWarning, stacklevel=2)
         super(_IXIndexer, self).__init__(name, obj)
 

pandas/tests/api/test_types.py

@@ -24,7 +24,8 @@ class TestTypes(Base):
                'is_dict_like', 'is_iterator', 'is_file_like',
                'is_list_like', 'is_hashable', 'is_array_like',
                'is_named_tuple',
-               'pandas_dtype', 'union_categoricals', 'infer_dtype']
+               'pandas_dtype', 'union_categoricals', 'infer_dtype',
+               'is_extension_array_dtype']
     deprecated = ['is_period', 'is_datetimetz']
     dtypes = ['CategoricalDtype', 'DatetimeTZDtype',
               'PeriodDtype', 'IntervalDtype']