CLN: Remove u and u_safe from pandas.compat (#25852)

Author: jschendel

Diff for: pandas/compat/__init__.py

@@ -7,7 +7,6 @@
 Key items to import for 2/3 compatible code:
 * iterators: reduce()
 * lists: lrange(), lmap(), lzip(), lfilter()
-* unicode: u() [no unicode builtin in Python 3]
 * longs: long (int in Python 3)
 * iterable method compatibility: iteritems, iterkeys, itervalues
   * Uses the original method if available, otherwise uses items, keys, values.
@@ -256,12 +255,6 @@ class to receive bound method
     text_type = str
     binary_type = bytes
 
-    def u(s):
-        return s
-
-    def u_safe(s):
-        return s
-
     def to_str(s):
         """
         Convert bytes and non-string into Python 3 str
@@ -305,15 +298,6 @@ def set_function_name(f, name, cls):
     text_type = unicode
     binary_type = str
 
-    def u(s):
-        return unicode(s, "unicode_escape")
-
-    def u_safe(s):
-        try:
-            return unicode(s, "unicode_escape")
-        except:
-            return s
-
     def to_str(s):
         """
         Convert unicode and non-string into Python 2 str

Diff for: pandas/compat/pickle_compat.py

@@ -6,7 +6,7 @@
 import pickle as pkl
 import sys
 
-from pandas.compat import string_types, u  # noqa
+from pandas.compat import string_types  # noqa
 
 import pandas  # noqa
 from pandas import Index, compat

Diff for: pandas/conftest.py

@@ -9,7 +9,7 @@
 import pytest
 from pytz import FixedOffset, utc
 
-from pandas.compat import PY3, u
+from pandas.compat import PY3
 import pandas.util._test_decorators as td
 
 import pandas as pd
@@ -561,7 +561,7 @@ def any_numpy_dtype(request):
 # categoricals are handled separately
 _any_skipna_inferred_dtype = [
     ('string', ['a', np.nan, 'c']),
-    ('unicode' if not PY3 else 'string', [u('a'), np.nan, u('c')]),
+    ('unicode' if not PY3 else 'string', ['a', np.nan, 'c']),
     ('bytes' if PY3 else 'string', [b'a', np.nan, b'c']),
     ('empty', [np.nan, np.nan, np.nan]),
     ('empty', []),

Diff for: pandas/core/arrays/categorical.py

@@ -7,7 +7,7 @@
 
 from pandas._libs import algos as libalgos, lib
 import pandas.compat as compat
-from pandas.compat import lzip, u
+from pandas.compat import lzip
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import (
     Appender, Substitution, cache_readonly, deprecate_kwarg)
@@ -1947,10 +1947,10 @@ def _tidy_repr(self, max_vals=10, footer=True):
         head = self[:num]._get_repr(length=False, footer=False)
         tail = self[-(max_vals - num):]._get_repr(length=False, footer=False)
 
-        result = u('{head}, ..., {tail}').format(head=head[:-1], tail=tail[1:])
+        result = '{head}, ..., {tail}'.format(head=head[:-1], tail=tail[1:])
         if footer:
-            result = u('{result}\n{footer}').format(result=result,
-                                                    footer=self._repr_footer())
+            result = '{result}\n{footer}'.format(
+                result=result, footer=self._repr_footer())
 
         return compat.text_type(result)
 
@@ -2008,7 +2008,7 @@ def _repr_categories_info(self):
 
     def _repr_footer(self):
 
-        return u('Length: {length}\n{info}').format(
+        return 'Length: {length}\n{info}'.format(
             length=len(self), info=self._repr_categories_info())
 
     def _get_repr(self, length=True, na_rep='NaN', footer=True):

Diff for: pandas/core/computation/pytables.py

@@ -6,7 +6,7 @@
 import numpy as np
 
 from pandas._libs.tslibs import Timedelta, Timestamp
-from pandas.compat import DeepChainMap, string_types, u
+from pandas.compat import DeepChainMap, string_types
 
 from pandas.core.dtypes.common import is_list_like
 
@@ -182,43 +182,43 @@ def stringify(value):
 
         kind = _ensure_decoded(self.kind)
         meta = _ensure_decoded(self.meta)
-        if kind == u('datetime64') or kind == u('datetime'):
+        if kind == 'datetime64' or kind == 'datetime':
             if isinstance(v, (int, float)):
                 v = stringify(v)
             v = _ensure_decoded(v)
             v = Timestamp(v)
             if v.tz is not None:
                 v = v.tz_convert('UTC')
             return TermValue(v, v.value, kind)
-        elif kind == u('timedelta64') or kind == u('timedelta'):
+        elif kind == 'timedelta64' or kind == 'timedelta':
             v = Timedelta(v, unit='s').value
             return TermValue(int(v), v, kind)
-        elif meta == u('category'):
+        elif meta == 'category':
             metadata = com.values_from_object(self.metadata)
             result = metadata.searchsorted(v, side='left')
 
             # result returns 0 if v is first element or if v is not in metadata
             # check that metadata contains v
             if not result and v not in metadata:
                 result = -1
-            return TermValue(result, result, u('integer'))
-        elif kind == u('integer'):
+            return TermValue(result, result, 'integer')
+        elif kind == 'integer':
             v = int(float(v))
             return TermValue(v, v, kind)
-        elif kind == u('float'):
+        elif kind == 'float':
             v = float(v)
             return TermValue(v, v, kind)
-        elif kind == u('bool'):
+        elif kind == 'bool':
             if isinstance(v, string_types):
-                v = not v.strip().lower() in [u('false'), u('f'), u('no'),
-                                              u('n'), u('none'), u('0'),
-                                              u('[]'), u('{}'), u('')]
+                v = not v.strip().lower() in ['false', 'f', 'no',
+                                              'n', 'none', '0',
+                                              '[]', '{}', '']
             else:
                 v = bool(v)
             return TermValue(v, v, kind)
         elif isinstance(v, string_types):
             # string quoting
-            return TermValue(v, stringify(v), u('string'))
+            return TermValue(v, stringify(v), 'string')
         else:
             raise TypeError("Cannot compare {v} of type {typ} to {kind} column"
                             .format(v=v, typ=type(v), kind=kind))

Diff for: pandas/core/frame.py

@@ -35,7 +35,7 @@
 from pandas import compat
 from pandas.compat import (
     PY36, Iterator, StringIO, lmap, lzip, raise_with_traceback,
-    string_and_binary_types, u)
+    string_and_binary_types)
 from pandas.compat.numpy import function as nv
 from pandas.core.dtypes.cast import (
     maybe_upcast,
@@ -620,7 +620,7 @@ def __unicode__(self):
         Invoked by unicode(df) in py2 only. Yields a Unicode String in both
         py2/py3.
         """
-        buf = StringIO(u(""))
+        buf = StringIO("")
         if self._info_repr():
             self.info(buf=buf)
             return buf.getvalue()
@@ -644,7 +644,7 @@ def _repr_html_(self):
         Mainly for IPython notebook.
         """
         if self._info_repr():
-            buf = StringIO(u(""))
+            buf = StringIO("")
             self.info(buf=buf)
             # need to escape the <class>, should be the first line.
             val = buf.getvalue().replace('<', r'&lt;', 1)

Diff for: pandas/core/indexes/base.py

@@ -12,7 +12,7 @@
 from pandas._libs.tslibs import OutOfBoundsDatetime, Timedelta, Timestamp
 from pandas._libs.tslibs.timezones import tz_compare
 import pandas.compat as compat
-from pandas.compat import set_function_name, u
+from pandas.compat import set_function_name
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import Appender, Substitution, cache_readonly
 
@@ -931,14 +931,14 @@ def __unicode__(self):
         attrs = self._format_attrs()
         space = self._format_space()
 
-        prepr = (u(",%s") %
-                 space).join(u("%s=%s") % (k, v) for k, v in attrs)
+        prepr = (",%s" %
+                 space).join("%s=%s" % (k, v) for k, v in attrs)
 
         # no data provided, just attributes
         if data is None:
             data = ''
 
-        res = u("%s(%s%s)") % (klass, data, prepr)
+        res = "%s(%s%s)" % (klass, data, prepr)
 
         return res
 

Diff for: pandas/core/panel.py

@@ -10,7 +10,6 @@
 import numpy as np
 
 import pandas.compat as compat
-from pandas.compat import u
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import Appender, Substitution, deprecate_kwarg
 from pandas.util._validators import validate_axis_style_args
@@ -356,18 +355,18 @@ def __unicode__(self):
 
         class_name = str(self.__class__)
 
-        dims = u('Dimensions: {dimensions}'.format(dimensions=' x '.join(
+        dims = 'Dimensions: {dimensions}'.format(dimensions=' x '.join(
             ["{shape} ({axis})".format(shape=shape, axis=axis) for axis, shape
-             in zip(self._AXIS_ORDERS, self.shape)])))
+             in zip(self._AXIS_ORDERS, self.shape)]))
 
         def axis_pretty(a):
             v = getattr(self, a)
             if len(v) > 0:
-                return u('{ax} axis: {x} to {y}'.format(ax=a.capitalize(),
-                                                        x=pprint_thing(v[0]),
-                                                        y=pprint_thing(v[-1])))
+                return '{ax} axis: {x} to {y}'.format(ax=a.capitalize(),
+                                                      x=pprint_thing(v[0]),
+                                                      y=pprint_thing(v[-1]))
             else:
-                return u('{ax} axis: None'.format(ax=a.capitalize()))
+                return '{ax} axis: None'.format(ax=a.capitalize())
 
         output = '\n'.join(
             [class_name, dims] + [axis_pretty(a) for a in self._AXIS_ORDERS])

Diff for: pandas/core/reshape/reshape.py

@@ -7,7 +7,7 @@
 
 from pandas._libs import algos as _algos, reshape as _reshape
 from pandas._libs.sparse import IntIndex
-from pandas.compat import PY2, text_type, u
+from pandas.compat import PY2, text_type
 
 from pandas.core.dtypes.cast import maybe_promote
 from pandas.core.dtypes.common import (
@@ -914,7 +914,7 @@ def _make_col_name(prefix, prefix_sep, level):
             if PY2 and (isinstance(prefix, text_type) or
                         isinstance(prefix_sep, text_type) or
                         isinstance(level, text_type)):
-                fstr = u(fstr)
+                fstr = fstr
             return fstr.format(prefix=prefix,
                                prefix_sep=prefix_sep,
                                level=level)

Diff for: pandas/core/series.py

@@ -11,7 +11,7 @@
 
 from pandas._libs import iNaT, index as libindex, lib, tslibs
 import pandas.compat as compat
-from pandas.compat import PY36, StringIO, u
+from pandas.compat import PY36, StringIO
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import Appender, Substitution, deprecate
 from pandas.util._validators import validate_bool_kwarg
@@ -1379,7 +1379,7 @@ def __unicode__(self):
         Invoked by unicode(df) in py2 only. Yields a Unicode String in both
         py2/py3.
         """
-        buf = StringIO(u(""))
+        buf = StringIO("")
         width, height = get_terminal_size()
         max_rows = (height if get_option("display.max_rows") == 0 else
                     get_option("display.max_rows"))

Diff for: pandas/core/strings.py

@@ -2833,7 +2833,7 @@ def normalize(self, form):
         normalized : Series/Index of objects
         """
         import unicodedata
-        f = lambda x: unicodedata.normalize(form, compat.u_safe(x))
+        f = lambda x: unicodedata.normalize(form, x)
         result = _na_map(f, self._parent)
         return self._wrap_result(result)
 
@@ -3187,10 +3187,10 @@ def rindex(self, sub, start=0, end=None):
     istitle = _noarg_wrapper(lambda x: x.istitle(),
                              docstring=_shared_docs['ismethods'] %
                              _shared_docs['istitle'])
-    isnumeric = _noarg_wrapper(lambda x: compat.u_safe(x).isnumeric(),
+    isnumeric = _noarg_wrapper(lambda x: x.isnumeric(),
                                docstring=_shared_docs['ismethods'] %
                                _shared_docs['isnumeric'])
-    isdecimal = _noarg_wrapper(lambda x: compat.u_safe(x).isdecimal(),
+    isdecimal = _noarg_wrapper(lambda x: x.isdecimal(),
                                docstring=_shared_docs['ismethods'] %
                                _shared_docs['isdecimal'])
 

Diff for: pandas/io/excel/_base.py

@@ -6,7 +6,7 @@
 import warnings
 
 import pandas.compat as compat
-from pandas.compat import add_metaclass, string_types, u
+from pandas.compat import add_metaclass, string_types
 from pandas.errors import EmptyDataError
 from pandas.util._decorators import Appender, deprecate_kwarg
 
@@ -715,7 +715,7 @@ def check_extension(cls, ext):
         if ext.startswith('.'):
             ext = ext[1:]
         if not any(ext in extension for extension in cls.supported_extensions):
-            msg = (u("Invalid extension for engine '{engine}': '{ext}'")
+            msg = ("Invalid extension for engine '{engine}': '{ext}'"
                    .format(engine=pprint_thing(cls.engine),
                            ext=pprint_thing(ext)))
             raise ValueError(msg)