CLN: replace %s syntax with .format in pandas.core: categorical, common, config, config_init (pandas-dev#17735)

Replaced %s syntax with .format in pandas.core: categorical.py, common.py, config.py, config_init.py. Additionally, made some of the existing positional .format code more explicit.

Author: jschendel

pandas/core/categorical.py

@@ -263,7 +263,8 @@ def __init__(self, values, categories=None, ordered=None, dtype=None,
                 if dtype == 'category':
                     dtype = CategoricalDtype(categories, ordered)
                 else:
-                    raise ValueError("Unknown `dtype` {}".format(dtype))
+                    msg = "Unknown `dtype` {dtype}"
+                    raise ValueError(msg.format(dtype=dtype))
             elif categories is not None or ordered is not None:
                 raise ValueError("Cannot specify both `dtype` and `categories`"
                                  " or `ordered`.")
@@ -931,9 +932,9 @@ def add_categories(self, new_categories, inplace=False):
             new_categories = [new_categories]
         already_included = set(new_categories) & set(self.dtype.categories)
         if len(already_included) != 0:
-            msg = ("new categories must not include old categories: %s" %
-                   str(already_included))
-            raise ValueError(msg)
+            msg = ("new categories must not include old categories: "
+                   "{already_included!s}")
+            raise ValueError(msg.format(already_included=already_included))
         new_categories = list(self.dtype.categories) + list(new_categories)
         new_dtype = CategoricalDtype(new_categories, self.ordered)
 
@@ -989,8 +990,8 @@ def remove_categories(self, removals, inplace=False):
             new_categories = [x for x in new_categories if notna(x)]
 
         if len(not_included) != 0:
-            raise ValueError("removals must all be in old categories: %s" %
-                             str(not_included))
+            msg = "removals must all be in old categories: {not_included!s}"
+            raise ValueError(msg.format(not_included=not_included))
 
         return self.set_categories(new_categories, ordered=self.ordered,
                                    rename=False, inplace=inplace)
@@ -1443,7 +1444,8 @@ def sort_values(self, inplace=False, ascending=True, na_position='last'):
         """
         inplace = validate_bool_kwarg(inplace, 'inplace')
         if na_position not in ['last', 'first']:
-            raise ValueError('invalid na_position: {!r}'.format(na_position))
+            msg = 'invalid na_position: {na_position!r}'
+            raise ValueError(msg.format(na_position=na_position))
 
         codes = np.sort(self._codes)
         if not ascending:
@@ -1653,9 +1655,10 @@ 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 = '%s, ..., %s' % (head[:-1], tail[1:])
+        result = u('{head}, ..., {tail}').format(head=head[:-1], tail=tail[1:])
         if footer:
-            result = '%s\n%s' % (result, self._repr_footer())
+            result = u('{result}\n{footer}').format(result=result,
+                                                    footer=self._repr_footer())
 
         return compat.text_type(result)
 
@@ -1683,7 +1686,8 @@ def _repr_categories_info(self):
         dtype = getattr(self.categories, 'dtype_str',
                         str(self.categories.dtype))
 
-        levheader = "Categories (%d, %s): " % (len(self.categories), dtype)
+        levheader = "Categories ({length}, {dtype}): ".format(
+            length=len(self.categories), dtype=dtype)
         width, height = get_terminal_size()
         max_width = get_option("display.width") or width
         if com.in_ipython_frontend():
@@ -1708,7 +1712,8 @@ def _repr_categories_info(self):
 
     def _repr_footer(self):
 
-        return u('Length: %d\n%s') % (len(self), self._repr_categories_info())
+        return u('Length: {length}\n{info}').format(
+            length=len(self), info=self._repr_categories_info())
 
     def _get_repr(self, length=True, na_rep='NaN', footer=True):
         from pandas.io.formats import format as fmt
@@ -1725,9 +1730,8 @@ def __unicode__(self):
         elif len(self._codes) > 0:
             result = self._get_repr(length=len(self) > _maxlen)
         else:
-            result = ('[], %s' %
-                      self._get_repr(length=False,
-                                     footer=True, ).replace("\n", ", "))
+            msg = self._get_repr(length=False, footer=True).replace("\n", ", ")
+            result = ('[], {repr_msg}'.format(repr_msg=msg))
 
         return result
 
@@ -1869,8 +1873,8 @@ def _reduce(self, op, name, axis=0, skipna=True, numeric_only=None,
         """ perform the reduction type operation """
         func = getattr(self, name, None)
         if func is None:
-            raise TypeError("Categorical cannot perform the operation "
-                            "{op}".format(op=name))
+            msg = 'Categorical cannot perform the operation {op}'
+            raise TypeError(msg.format(op=name))
         return func(numeric_only=numeric_only, **kwds)
 
     def min(self, numeric_only=None, **kwargs):

pandas/core/common.py

@@ -96,8 +96,8 @@ def __init__(self, class_instance):
         self.class_instance = class_instance
 
     def __str__(self):
-        return ("This method must be defined in the concrete class of %s" %
-                self.class_instance.__class__.__name__)
+        msg = "This method must be defined in the concrete class of {name}"
+        return (msg.format(name=self.class_instance.__class__.__name__))
 
 
 def flatten(l):
@@ -150,8 +150,8 @@ def _maybe_match_name(a, b):
 def _get_info_slice(obj, indexer):
     """Slice the info axis of `obj` with `indexer`."""
     if not hasattr(obj, '_info_axis_number'):
-        raise TypeError('object of type %r has no info axis' %
-                        type(obj).__name__)
+        msg = 'object of type {typ!r} has no info axis'
+        raise TypeError(msg.format(typ=type(obj).__name__))
     slices = [slice(None)] * obj.ndim
     slices[obj._info_axis_number] = indexer
     return tuple(slices)
@@ -214,8 +214,8 @@ def _mut_exclusive(**kwargs):
     label1, val1 = item1
     label2, val2 = item2
     if val1 is not None and val2 is not None:
-        raise TypeError('mutually exclusive arguments: %r and %r' %
-                        (label1, label2))
+        msg = 'mutually exclusive arguments: {label1!r} and {label2!r}'
+        raise TypeError(msg.format(label1=label1, label2=label2))
     elif val1 is not None:
         return val1
     else:
@@ -517,7 +517,7 @@ def standardize_mapping(into):
                 collections.defaultdict, into.default_factory)
         into = type(into)
     if not issubclass(into, collections.Mapping):
-        raise TypeError('unsupported type: {}'.format(into))
+        raise TypeError('unsupported type: {into}'.format(into=into))
     elif into == collections.defaultdict:
         raise TypeError(
             'to_dict() only accepts initialized defaultdicts')

pandas/core/config.py

@@ -80,7 +80,7 @@ def _get_single_key(pat, silent):
     if len(keys) == 0:
         if not silent:
             _warn_if_deprecated(pat)
-        raise OptionError('No such keys(s): %r' % pat)
+        raise OptionError('No such keys(s): {pat!r}'.format(pat=pat))
     if len(keys) > 1:
         raise OptionError('Pattern matched multiple keys')
     key = keys[0]
@@ -112,8 +112,8 @@ def _set_option(*args, **kwargs):
     silent = kwargs.pop('silent', False)
 
     if kwargs:
-        raise TypeError('_set_option() got an unexpected keyword '
-                        'argument "{0}"'.format(list(kwargs.keys())[0]))
+        msg = '_set_option() got an unexpected keyword argument "{kwarg}"'
+        raise TypeError(msg.format(list(kwargs.keys())[0]))
 
     for k, v in zip(args[::2], args[1::2]):
         key = _get_single_key(k, silent)
@@ -436,9 +436,11 @@ def register_option(key, defval, doc='', validator=None, cb=None):
     key = key.lower()
 
     if key in _registered_options:
-        raise OptionError("Option '%s' has already been registered" % key)
+        msg = "Option '{key}' has already been registered"
+        raise OptionError(msg.format(key=key))
     if key in _reserved_keys:
-        raise OptionError("Option '%s' is a reserved key" % key)
+        msg = "Option '{key}' is a reserved key"
+        raise OptionError(msg.format(key=key))
 
     # the default value should be legal
     if validator:
@@ -449,22 +451,21 @@ def register_option(key, defval, doc='', validator=None, cb=None):
 
     for k in path:
         if not bool(re.match('^' + tokenize.Name + '$', k)):
-            raise ValueError("%s is not a valid identifier" % k)
+            raise ValueError("{k} is not a valid identifier".format(k=k))
         if keyword.iskeyword(k):
-            raise ValueError("%s is a python keyword" % k)
+            raise ValueError("{k} is a python keyword".format(k=k))
 
     cursor = _global_config
+    msg = "Path prefix to option '{option}' is already an option"
     for i, p in enumerate(path[:-1]):
         if not isinstance(cursor, dict):
-            raise OptionError("Path prefix to option '%s' is already an option"
-                              % '.'.join(path[:i]))
+            raise OptionError(msg.format(option='.'.join(path[:i])))
         if p not in cursor:
             cursor[p] = {}
         cursor = cursor[p]
 
     if not isinstance(cursor, dict):
-        raise OptionError("Path prefix to option '%s' is already an option" %
-                          '.'.join(path[:-1]))
+        raise OptionError(msg.format(option='.'.join(path[:-1])))
 
     cursor[path[-1]] = defval  # initialize
 
@@ -516,8 +517,8 @@ def deprecate_option(key, msg=None, rkey=None, removal_ver=None):
     key = key.lower()
 
     if key in _deprecated_options:
-        raise OptionError("Option '%s' has already been defined as deprecated."
-                          % key)
+        msg = "Option '{key}' has already been defined as deprecated."
+        raise OptionError(msg.format(key=key))
 
     _deprecated_options[key] = DeprecatedOption(key, msg, rkey, removal_ver)
 
@@ -614,11 +615,12 @@ def _warn_if_deprecated(key):
             print(d.msg)
             warnings.warn(d.msg, DeprecationWarning)
         else:
-            msg = "'%s' is deprecated" % key
+            msg = "'{key}' is deprecated".format(key=key)
             if d.removal_ver:
-                msg += ' and will be removed in %s' % d.removal_ver
+                msg += (' and will be removed in {version}'
+                        .format(version=d.removal_ver))
             if d.rkey:
-                msg += ", please use '%s' instead." % d.rkey
+                msg += ", please use '{rkey}' instead.".format(rkey=d.rkey)
             else:
                 msg += ', please refrain from using it.'
 
@@ -633,20 +635,21 @@ def _build_option_description(k):
     o = _get_registered_option(k)
     d = _get_deprecated_option(k)
 
-    s = u('%s ') % k
+    s = u('{k} ').format(k=k)
 
     if o.doc:
         s += '\n'.join(o.doc.strip().split('\n'))
     else:
         s += 'No description available.'
 
     if o:
-        s += u('\n    [default: %s] [currently: %s]') % (o.defval,
-                                                         _get_option(k, True))
+        s += (u('\n    [default: {default}] [currently: {current}]')
+              .format(default=o.defval, current=_get_option(k, True)))
 
     if d:
         s += u('\n    (Deprecated')
-        s += (u(', use `%s` instead.') % d.rkey if d.rkey else '')
+        s += (u(', use `{rkey}` instead.')
+              .format(rkey=d.rkey if d.rkey else ''))
         s += u(')')
 
     s += '\n\n'
@@ -718,7 +721,7 @@ def config_prefix(prefix):
 
     def wrap(func):
         def inner(key, *args, **kwds):
-            pkey = '%s.%s' % (prefix, key)
+            pkey = '{prefix}.{key}'.format(prefix=prefix, key=key)
             return func(pkey, *args, **kwds)
 
         return inner
@@ -754,7 +757,8 @@ def is_type_factory(_type):
 
     def inner(x):
         if type(x) != _type:
-            raise ValueError("Value must have type '%s'" % str(_type))
+            msg = "Value must have type '{typ!s}'"
+            raise ValueError(msg.format(typ=_type))
 
     return inner
 
@@ -777,11 +781,12 @@ def is_instance_factory(_type):
         from pandas.io.formats.printing import pprint_thing
         type_repr = "|".join(map(pprint_thing, _type))
     else:
-        type_repr = "'%s'" % _type
+        type_repr = "'{typ}'".format(typ=_type)
 
     def inner(x):
         if not isinstance(x, _type):
-            raise ValueError("Value must be an instance of %s" % type_repr)
+            msg = "Value must be an instance of {type_repr}"
+            raise ValueError(msg.format(type_repr=type_repr))
 
     return inner
 
@@ -797,10 +802,10 @@ def inner(x):
 
             if not any([c(x) for c in callables]):
                 pp_values = pp("|".join(lmap(pp, legal_values)))
-                msg = "Value must be one of {0}".format(pp_values)
+                msg = "Value must be one of {pp_values}"
                 if len(callables):
                     msg += " or a callable"
-                raise ValueError(msg)
+                raise ValueError(msg.format(pp_values=pp_values))
 
     return inner
 

pandas/core/config_init.py

@@ -453,10 +453,10 @@ def use_inf_as_na_cb(key):
         cf.register_option(ext + '.writer', default, doc, validator=str)
 
     def _register_xlsx(engine, other):
-        cf.register_option('xlsx.writer', engine,
-                           writer_engine_doc.format(ext='xlsx', default=engine,
-                                                    others=", '%s'" % other),
-                           validator=str)
+        others = ", '{other}'".format(other=other)
+        doc = writer_engine_doc.format(ext='xlsx', default=engine,
+                                       others=others)
+        cf.register_option('xlsx.writer', engine, doc, validator=str)
 
     try:
         # better memory footprint