CLN: Remove unicode u string prefix (#25864)

Author: jschendel

doc/source/conf.py

@@ -134,8 +134,8 @@
 master_doc = 'index'
 
 # General information about the project.
-project = u'pandas'
-copyright = u'2008-2014, the pandas development team'
+project = 'pandas'
+copyright = '2008-2014, the pandas development team'
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the

doc/source/user_guide/advanced.rst

@@ -797,7 +797,7 @@ values **not** in the categories, similarly to how you can reindex **any** panda
     In [11]: df3 = df3.set_index('B')
 
     In [11]: df3.index
-    Out[11]: CategoricalIndex([u'a', u'a', u'b', u'b', u'c', u'a'], categories=[u'a', u'b', u'c'], ordered=False, name=u'B', dtype='category')
+    Out[11]: CategoricalIndex(['a', 'a', 'b', 'b', 'c', 'a'], categories=['a', 'b', 'c'], ordered=False, name='B', dtype='category')
 
     In [12]: pd.concat([df2, df3])
     TypeError: categories must match existing categories when appending

doc/source/user_guide/options.rst

@@ -484,7 +484,7 @@ If a DataFrame or Series contains these characters, the default output mode may
 
 .. ipython:: python
 
-   df = pd.DataFrame({u'国籍': ['UK', u'日本'], u'名前': ['Alice', u'しのぶ']})
+   df = pd.DataFrame({'国籍': ['UK', '日本'], '名前': ['Alice', 'しのぶ']})
    df
 
 .. image:: ../_static/option_unicode01.png
@@ -507,7 +507,7 @@ By default, an "Ambiguous" character's width, such as "¡" (inverted exclamation
 
 .. ipython:: python
 
-   df = pd.DataFrame({'a': ['xxx', u'¡¡'], 'b': ['yyy', u'¡¡']})
+   df = pd.DataFrame({'a': ['xxx', '¡¡'], 'b': ['yyy', '¡¡']})
    df
 
 .. image:: ../_static/option_unicode03.png

doc/source/user_guide/reshaping.rst

@@ -695,7 +695,7 @@ handling of NaN:
     In [2]: pd.factorize(x, sort=True)
     Out[2]:
     (array([ 2,  2, -1,  3,  0,  1]),
-     Index([3.14, inf, u'A', u'B'], dtype='object'))
+     Index([3.14, inf, 'A', 'B'], dtype='object'))
 
     In [3]: np.unique(x, return_inverse=True)[::-1]
     Out[3]: (array([3, 3, 0, 4, 1, 2]), array([nan, 3.14, inf, 'A', 'B'], dtype=object))

doc/sphinxext/announce.py

@@ -56,7 +56,7 @@
 
 
 def get_authors(revision_range):
-    pat = u'^.*\\t(.*)$'
+    pat = '^.*\\t(.*)$'
     lst_release, cur_release = [r.strip() for r in revision_range.split('..')]
 
     # authors, in current release and previous to current release.
@@ -70,7 +70,7 @@ def get_authors(revision_range):
     pre.discard('Homu')
 
     # Append '+' to new authors.
-    authors = [s + u' +' for s in cur - pre] + [s for s in cur & pre]
+    authors = [s + ' +' for s in cur - pre] + [s for s in cur & pre]
     authors.sort()
     return authors
 
@@ -81,17 +81,17 @@ def get_pull_requests(repo, revision_range):
     # From regular merges
     merges = this_repo.git.log(
         '--oneline', '--merges', revision_range)
-    issues = re.findall(u"Merge pull request \\#(\\d*)", merges)
+    issues = re.findall("Merge pull request \\#(\\d*)", merges)
     prnums.extend(int(s) for s in issues)
 
     # From Homu merges (Auto merges)
-    issues = re. findall(u"Auto merge of \\#(\\d*)", merges)
+    issues = re. findall("Auto merge of \\#(\\d*)", merges)
     prnums.extend(int(s) for s in issues)
 
     # From fast forward squash-merges
     commits = this_repo.git.log(
         '--oneline', '--no-merges', '--first-parent', revision_range)
-    issues = re.findall(u'^.*\\(\\#(\\d+)\\)$', commits, re.M)
+    issues = re.findall('^.*\\(\\#(\\d+)\\)$', commits, re.M)
     prnums.extend(int(s) for s in issues)
 
     # get PR data from github repo

pandas/core/arrays/base.py

@@ -839,16 +839,16 @@ def __repr__(self):
         from pandas.io.formats.printing import format_object_summary
 
         template = (
-            u'{class_name}'
-            u'{data}\n'
-            u'Length: {length}, dtype: {dtype}'
+            '{class_name}'
+            '{data}\n'
+            'Length: {length}, dtype: {dtype}'
         )
         # the short repr has no trailing newline, while the truncated
         # repr does. So we include a newline in our template, and strip
         # any trailing newlines from format_object_summary
         data = format_object_summary(self, self._formatter(),
                                      indent_for_name=False).rstrip(', \n')
-        class_name = u'<{}>\n'.format(self.__class__.__name__)
+        class_name = '<{}>\n'.format(self.__class__.__name__)
         return template.format(class_name=class_name, data=data,
                                length=len(self),
                                dtype=self.dtype)

pandas/core/arrays/categorical.py

@@ -2147,7 +2147,7 @@ def _reverse_indexer(self):
         Categories (3, object): [a, b, c]
 
         In [3]: c.categories
-        Out[3]: Index([u'a', u'b', u'c'], dtype='object')
+        Out[3]: Index(['a', 'b', 'c'], dtype='object')
 
         In [4]: c.codes
         Out[4]: array([0, 0, 1, 2, 0], dtype=int8)

pandas/core/arrays/period.py

@@ -476,7 +476,7 @@ def asfreq(self, freq=None, how='E'):
     # ------------------------------------------------------------------
     # Rendering Methods
 
-    def _format_native_types(self, na_rep=u'NaT', date_format=None, **kwargs):
+    def _format_native_types(self, na_rep='NaT', date_format=None, **kwargs):
         """
         actually format my specific types
         """
@@ -485,7 +485,7 @@ def _format_native_types(self, na_rep=u'NaT', date_format=None, **kwargs):
         if date_format:
             formatter = lambda dt: dt.strftime(date_format)
         else:
-            formatter = lambda dt: u'%s' % dt
+            formatter = lambda dt: '%s' % dt
 
         if self._hasnans:
             mask = self._isnan

pandas/core/computation/pytables.py

@@ -584,11 +584,11 @@ def __init__(self, value, converted, kind):
     def tostring(self, encoding):
         """ quote the string if not encoded
             else encode and return """
-        if self.kind == u'string':
+        if self.kind == 'string':
             if encoding is not None:
                 return self.converted
             return '"{converted}"'.format(converted=self.converted)
-        elif self.kind == u'float':
+        elif self.kind == 'float':
             # python 2 str(float) is not always
             # round-trippable so use repr()
             return repr(self.converted)

pandas/core/dtypes/dtypes.py

@@ -393,9 +393,9 @@ def __eq__(self, other):
             return hash(self) == hash(other)
 
     def __repr__(self):
-        tpl = u'CategoricalDtype(categories={}ordered={})'
+        tpl = 'CategoricalDtype(categories={}ordered={})'
         if self.categories is None:
-            data = u"None, "
+            data = "None, "
         else:
             data = self.categories._format_data(name=self.__class__.__name__)
         return tpl.format(data, self.ordered)

pandas/core/frame.py

@@ -8063,4 +8063,4 @@ def _from_nested_dict(data):
 
 
 def _put_str(s, space):
-    return u'{s}'.format(s=s)[:space].ljust(space)
+    return '{s}'.format(s=s)[:space].ljust(space)

pandas/core/indexes/multi.py

@@ -379,8 +379,8 @@ def from_tuples(cls, tuples, sortorder=None, names=None):
 
         Examples
         --------
-        >>> tuples = [(1, u'red'), (1, u'blue'),
-        ...           (2, u'red'), (2, u'blue')]
+        >>> tuples = [(1, 'red'), (1, 'blue'),
+        ...           (2, 'red'), (2, 'blue')]
         >>> pd.MultiIndex.from_tuples(tuples, names=('number', 'color'))
         MultiIndex(levels=[[1, 2], ['blue', 'red']],
                    codes=[[0, 0, 1, 1], [1, 0, 1, 0]],
@@ -621,25 +621,25 @@ def set_levels(self, levels, level=None, inplace=False,
 
         Examples
         --------
-        >>> idx = pd.MultiIndex.from_tuples([(1, u'one'), (1, u'two'),
-                                            (2, u'one'), (2, u'two')],
+        >>> idx = pd.MultiIndex.from_tuples([(1, 'one'), (1, 'two'),
+                                            (2, 'one'), (2, 'two')],
                                             names=['foo', 'bar'])
         >>> idx.set_levels([['a','b'], [1,2]])
-        MultiIndex(levels=[[u'a', u'b'], [1, 2]],
+        MultiIndex(levels=[['a', 'b'], [1, 2]],
                    codes=[[0, 0, 1, 1], [0, 1, 0, 1]],
-                   names=[u'foo', u'bar'])
+                   names=['foo', 'bar'])
         >>> idx.set_levels(['a','b'], level=0)
-        MultiIndex(levels=[[u'a', u'b'], [u'one', u'two']],
+        MultiIndex(levels=[['a', 'b'], ['one', 'two']],
                    codes=[[0, 0, 1, 1], [0, 1, 0, 1]],
-                   names=[u'foo', u'bar'])
+                   names=['foo', 'bar'])
         >>> idx.set_levels(['a','b'], level='bar')
-        MultiIndex(levels=[[1, 2], [u'a', u'b']],
+        MultiIndex(levels=[[1, 2], ['a', 'b']],
                    codes=[[0, 0, 1, 1], [0, 1, 0, 1]],
-                   names=[u'foo', u'bar'])
+                   names=['foo', 'bar'])
         >>> idx.set_levels([['a','b'], [1,2]], level=[0,1])
-        MultiIndex(levels=[[u'a', u'b'], [1, 2]],
+        MultiIndex(levels=[['a', 'b'], [1, 2]],
                    codes=[[0, 0, 1, 1], [0, 1, 0, 1]],
-                   names=[u'foo', u'bar'])
+                   names=['foo', 'bar'])
         """
         if is_list_like(levels) and not isinstance(levels, Index):
             levels = list(levels)
@@ -740,25 +740,25 @@ def set_codes(self, codes, level=None, inplace=False,
 
         Examples
         --------
-        >>> idx = pd.MultiIndex.from_tuples([(1, u'one'), (1, u'two'),
-                                            (2, u'one'), (2, u'two')],
+        >>> idx = pd.MultiIndex.from_tuples([(1, 'one'), (1, 'two'),
+                                            (2, 'one'), (2, 'two')],
                                             names=['foo', 'bar'])
         >>> idx.set_codes([[1,0,1,0], [0,0,1,1]])
-        MultiIndex(levels=[[1, 2], [u'one', u'two']],
+        MultiIndex(levels=[[1, 2], ['one', 'two']],
                    codes=[[1, 0, 1, 0], [0, 0, 1, 1]],
-                   names=[u'foo', u'bar'])
+                   names=['foo', 'bar'])
         >>> idx.set_codes([1,0,1,0], level=0)
-        MultiIndex(levels=[[1, 2], [u'one', u'two']],
+        MultiIndex(levels=[[1, 2], ['one', 'two']],
                    codes=[[1, 0, 1, 0], [0, 1, 0, 1]],
-                   names=[u'foo', u'bar'])
+                   names=['foo', 'bar'])
         >>> idx.set_codes([0,0,1,1], level='bar')
-        MultiIndex(levels=[[1, 2], [u'one', u'two']],
+        MultiIndex(levels=[[1, 2], ['one', 'two']],
                    codes=[[0, 0, 1, 1], [0, 0, 1, 1]],
-                   names=[u'foo', u'bar'])
+                   names=['foo', 'bar'])
         >>> idx.set_codes([[1,0,1,0], [0,0,1,1]], level=[0,1])
-        MultiIndex(levels=[[1, 2], [u'one', u'two']],
+        MultiIndex(levels=[[1, 2], ['one', 'two']],
                    codes=[[1, 0, 1, 0], [0, 0, 1, 1]],
-                   names=[u'foo', u'bar'])
+                   names=['foo', 'bar'])
         """
         if level is not None and not is_list_like(level):
             if not is_list_like(codes):
@@ -1512,10 +1512,10 @@ def to_hierarchical(self, n_repeat, n_shuffle=1):
 
         Examples
         --------
-        >>> idx = pd.MultiIndex.from_tuples([(1, u'one'), (1, u'two'),
-                                            (2, u'one'), (2, u'two')])
+        >>> idx = pd.MultiIndex.from_tuples([(1, 'one'), (1, 'two'),
+                                            (2, 'one'), (2, 'two')])
         >>> idx.to_hierarchical(3)
-        MultiIndex(levels=[[1, 2], [u'one', u'two']],
+        MultiIndex(levels=[[1, 2], ['one', 'two']],
                    codes=[[0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1],
                           [0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1]])
         """

pandas/core/indexes/period.py

@@ -400,7 +400,7 @@ def _maybe_convert_timedelta(self, other):
     # ------------------------------------------------------------------------
     # Rendering Methods
 
-    def _format_native_types(self, na_rep=u'NaT', quoting=None, **kwargs):
+    def _format_native_types(self, na_rep='NaT', quoting=None, **kwargs):
         # just dispatch, return ndarray
         return self._data._format_native_types(na_rep=na_rep,
                                                quoting=quoting,

pandas/core/indexing.py

@@ -1242,7 +1242,7 @@ def _validate_read_indexer(self, key, indexer, axis, raise_missing=False):
         if missing:
             if missing == len(indexer):
                 raise KeyError(
-                    u"None of [{key}] are in the [{axis}]".format(
+                    "None of [{key}] are in the [{axis}]".format(
                         key=key, axis=self.obj._get_axis_name(axis)))
 
             # We (temporarily) allow for some missing keys with .loc, except in

pandas/core/internals/managers.py

@@ -296,12 +296,12 @@ def __unicode__(self):
         output = pprint_thing(self.__class__.__name__)
         for i, ax in enumerate(self.axes):
             if i == 0:
-                output += u'\nItems: {ax}'.format(ax=ax)
+                output += '\nItems: {ax}'.format(ax=ax)
             else:
-                output += u'\nAxis {i}: {ax}'.format(i=i, ax=ax)
+                output += '\nAxis {i}: {ax}'.format(i=i, ax=ax)
 
         for block in self.blocks:
-            output += u'\n{block}'.format(block=pprint_thing(block))
+            output += '\n{block}'.format(block=pprint_thing(block))
         return output
 
     def _verify_integrity(self):

pandas/core/reshape/pivot.py

@@ -154,7 +154,7 @@ def _add_margins(table, data, values, rows, cols, aggfunc,
     if not isinstance(margins_name, compat.string_types):
         raise ValueError('margins_name argument must be a string')
 
-    msg = u'Conflicting name "{name}" in margins'.format(name=margins_name)
+    msg = 'Conflicting name "{name}" in margins'.format(name=margins_name)
     for level in table.index.names:
         if margins_name in table.index.get_level_values(level):
             raise ValueError(msg)

pandas/errors/__init__.py

@@ -138,7 +138,7 @@ class ParserWarning(Warning):
     Using a `sep` in `pd.read_csv` other than a single character:
 
     >>> import io
-    >>> csv = u'''a;b;c
+    >>> csv = '''a;b;c
     ...           1;1,8
     ...           1;2,1'''
     >>> df = pd.read_csv(io.StringIO(csv), sep='[;,]')  # doctest: +SKIP

pandas/io/formats/format.py

@@ -213,7 +213,7 @@ def _get_footer(self):
 
             series_name = pprint_thing(name,
                                        escape_chars=('\t', '\r', '\n'))
-            footer += ((u"Name: {sname}".format(sname=series_name))
+            footer += (("Name: {sname}".format(sname=series_name))
                        if name is not None else "")
 
         if (self.length is True or
@@ -227,7 +227,7 @@ def _get_footer(self):
             if name:
                 if footer:
                     footer += ', '
-                footer += u'dtype: {typ}'.format(typ=pprint_thing(name))
+                footer += 'dtype: {typ}'.format(typ=pprint_thing(name))
 
         # level infos are added to the end and in a new line, like it is done
         # for Categoricals
@@ -949,10 +949,10 @@ def _format(x):
                     return 'NaT'
                 return self.na_rep
             elif isinstance(x, PandasObject):
-                return u'{x}'.format(x=x)
+                return '{x}'.format(x=x)
             else:
                 # object dtype
-                return u'{x}'.format(x=formatter(x))
+                return '{x}'.format(x=formatter(x))
 
         vals = self.values
         if isinstance(vals, Index):
@@ -968,16 +968,16 @@ def _format(x):
         fmt_values = []
         for i, v in enumerate(vals):
             if not is_float_type[i] and leading_space:
-                fmt_values.append(u' {v}'.format(v=_format(v)))
+                fmt_values.append(' {v}'.format(v=_format(v)))
             elif is_float_type[i]:
                 fmt_values.append(float_format(v))
             else:
                 if leading_space is False:
                     # False specifically, so that the default is
                     # to include a space if we get here.
-                    tpl = u'{v}'
+                    tpl = '{v}'
                 else:
-                    tpl = u' {v}'
+                    tpl = ' {v}'
                 fmt_values.append(tpl.format(v=_format(v)))
 
         return fmt_values

pandas/io/formats/html.py

@@ -118,7 +118,7 @@ def _write_cell(self, s, kind='td', indent=0, tags=None):
         else:
             end_a = ''
 
-        self.write(u'{start}{rs}{end_a}</{kind}>'.format(
+        self.write('{start}{rs}{end_a}</{kind}>'.format(
             start=start_tag, rs=rs, end_a=end_a, kind=kind), indent)
 
     def write_tr(self, line, indent=0, indent_delta=0, header=False,

pandas/io/formats/printing.py

@@ -336,17 +336,17 @@ def best_len(values):
         else:
             return 0
 
-    close = u', '
+    close = ', '
 
     if n == 0:
-        summary = u'[]{}'.format(close)
+        summary = '[]{}'.format(close)
     elif n == 1:
         first = formatter(obj[0])
-        summary = u'[{}]{}'.format(first, close)
+        summary = '[{}]{}'.format(first, close)
     elif n == 2:
         first = formatter(obj[0])
         last = formatter(obj[-1])
-        summary = u'[{}, {}]{}'.format(first, last, close)
+        summary = '[{}, {}]{}'.format(first, last, close)
     else:
 
         if n > max_seq_items: