CLN: String formatting % -> f-strings (pandas-dev#29518)

Author: alimcmaster1

pandas/core/arrays/period.py

@@ -596,7 +596,7 @@ def _format_native_types(self, na_rep="NaT", date_format=None, **kwargs):
         if date_format:
             formatter = lambda dt: dt.strftime(date_format)
         else:
-            formatter = lambda dt: "%s" % dt
+            formatter = lambda dt: str(dt)
 
         if self._hasnans:
             mask = self._isnan

pandas/core/common.py

@@ -451,7 +451,7 @@ def pipe(obj, func, *args, **kwargs):
     if isinstance(func, tuple):
         func, target = func
         if target in kwargs:
-            msg = "%s is both the pipe target and a keyword argument" % target
+            msg = f"{target} is both the pipe target and a keyword argument"
             raise ValueError(msg)
         kwargs[target] = obj
         return func(*args, **kwargs)

pandas/core/frame.py

@@ -1805,7 +1805,7 @@ def to_records(
             if isinstance(self.index, ABCMultiIndex):
                 for i, n in enumerate(index_names):
                     if n is None:
-                        index_names[i] = "level_%d" % count
+                        index_names[i] = f"level_{count}"
                         count += 1
             elif index_names[0] is None:
                 index_names = ["index"]
@@ -2454,7 +2454,7 @@ def info(
         exceeds_info_cols = len(self.columns) > max_cols
 
         def _verbose_repr():
-            lines.append("Data columns (total %d columns):" % len(self.columns))
+            lines.append(f"Data columns (total {len(self.columns)} columns):")
             space = max(len(pprint_thing(k)) for k in self.columns) + 4
             counts = None
 
@@ -2846,7 +2846,7 @@ def _getitem_bool_array(self, key):
             )
         elif len(key) != len(self.index):
             raise ValueError(
-                "Item wrong length %d instead of %d." % (len(key), len(self.index))
+                f"Item wrong length {len(key)} instead of {len(self.index)}."
             )
 
         # check_bool_indexer will throw exception if Series key cannot
@@ -2957,7 +2957,7 @@ def _setitem_array(self, key, value):
         if com.is_bool_indexer(key):
             if len(key) != len(self.index):
                 raise ValueError(
-                    "Item wrong length %d instead of %d!" % (len(key), len(self.index))
+                    f"Item wrong length {len(key)} instead of {len(self.index)}!"
                 )
             key = check_bool_indexer(self.index, key)
             indexer = key.nonzero()[0]
@@ -4537,8 +4537,8 @@ def _maybe_casted_values(index, labels=None):
         if not drop:
             if isinstance(self.index, ABCMultiIndex):
                 names = [
-                    n if n is not None else ("level_%d" % i)
-                    for (i, n) in enumerate(self.index.names)
+                    (n if n is not None else f"level_{i}")
+                    for i, n in enumerate(self.index.names)
                 ]
                 to_insert = zip(self.index.levels, self.index.codes)
             else:
@@ -4858,8 +4858,7 @@ def sort_values(
             by = [by]
         if is_sequence(ascending) and len(by) != len(ascending):
             raise ValueError(
-                "Length of ascending (%d) != length of by (%d)"
-                % (len(ascending), len(by))
+                f"Length of ascending ({len(ascending)}) != length of by ({len(by)})"
             )
         if len(by) > 1:
             from pandas.core.sorting import lexsort_indexer

pandas/core/generic.py

@@ -421,8 +421,7 @@ def _construct_axes_from_arguments(
                 if a in kwargs:
                     if alias in kwargs:
                         raise TypeError(
-                            "arguments are mutually exclusive "
-                            "for [%s,%s]" % (a, alias)
+                            f"arguments are mutually exclusive for [{a},{alias}]"
                         )
                     continue
                 if alias in kwargs:
@@ -754,7 +753,7 @@ def transpose(self, *args, **kwargs):
 
         # we must have unique axes
         if len(axes) != len(set(axes)):
-            raise ValueError("Must specify %s unique axes" % self._AXIS_LEN)
+            raise ValueError(f"Must specify {self._AXIS_LEN} unique axes")
 
         new_axes = self._construct_axes_dict_from(
             self, [self._get_axis(x) for x in axes_names]
@@ -2096,7 +2095,7 @@ def __repr__(self) -> str:
         # string representation based upon iterating over self
         # (since, by definition, `PandasContainers` are iterable)
         prepr = "[%s]" % ",".join(map(pprint_thing, self))
-        return "%s(%s)" % (self.__class__.__name__, prepr)
+        return f"{self.__class__.__name__}({prepr})"
 
     def _repr_latex_(self):
         """
@@ -6357,7 +6356,7 @@ def fillna(
             elif isinstance(value, ABCDataFrame) and self.ndim == 2:
                 new_data = self.where(self.notna(), value)
             else:
-                raise ValueError("invalid fill value with a %s" % type(value))
+                raise ValueError(f"invalid fill value with a {type(value)}")
 
         if inplace:
             self._update_inplace(new_data)
@@ -6794,9 +6793,8 @@ def replace(
                 if is_list_like(value):
                     if len(to_replace) != len(value):
                         raise ValueError(
-                            "Replacement lists must match "
-                            "in length. Expecting %d got %d "
-                            % (len(to_replace), len(value))
+                            f"Replacement lists must match in length. "
+                            f"Expecting {len(to_replace)} got {len(value)} "
                         )
 
                     new_data = self._data.replace_list(
@@ -8871,7 +8869,7 @@ def align(
                 fill_axis=fill_axis,
             )
         else:  # pragma: no cover
-            raise TypeError("unsupported type: %s" % type(other))
+            raise TypeError(f"unsupported type: {type(other)}")
 
     def _align_frame(
         self,
@@ -9515,9 +9513,9 @@ def tshift(self, periods=1, freq=None, axis=0):
                 new_data = self._data.copy()
                 new_data.axes[block_axis] = index.shift(periods)
             else:
-                msg = "Given freq %s does not match PeriodIndex freq %s" % (
-                    freq.rule_code,
-                    orig_freq.rule_code,
+                msg = (
+                    f"Given freq {freq.rule_code} does not match"
+                    f" PeriodIndex freq {orig_freq.rule_code}"
                 )
                 raise ValueError(msg)
         else:
@@ -9665,7 +9663,7 @@ def truncate(self, before=None, after=None, axis=None, copy=True):
 
         if before is not None and after is not None:
             if before > after:
-                raise ValueError("Truncate: %s must be after %s" % (after, before))
+                raise ValueError(f"Truncate: {after} must be after {before}")
 
         slicer = [slice(None, None)] * self._AXIS_LEN
         slicer[axis] = slice(before, after)
@@ -9711,7 +9709,7 @@ def _tz_convert(ax, tz):
                 if len(ax) > 0:
                     ax_name = self._get_axis_name(axis)
                     raise TypeError(
-                        "%s is not a valid DatetimeIndex or PeriodIndex" % ax_name
+                        f"{ax_name} is not a valid DatetimeIndex or PeriodIndex"
                     )
                 else:
                     ax = DatetimeIndex([], tz=tz)
@@ -9875,7 +9873,7 @@ def _tz_localize(ax, tz, ambiguous, nonexistent):
                 if len(ax) > 0:
                     ax_name = self._get_axis_name(axis)
                     raise TypeError(
-                        "%s is not a valid DatetimeIndex or PeriodIndex" % ax_name
+                        f"{ax_name} is not a valid DatetimeIndex or PeriodIndex"
                     )
                 else:
                     ax = DatetimeIndex([], tz=tz)

pandas/core/indexes/base.py

@@ -963,14 +963,14 @@ def __repr__(self):
         data = self._format_data()
         attrs = self._format_attrs()
         space = self._format_space()
-
-        prepr = (",%s" % space).join("%s=%s" % (k, v) for k, v in attrs)
+        attrs_str = [f"{k}={v}" for k, v in attrs]
+        prepr = f",{space}".join(attrs_str)
 
         # no data provided, just attributes
         if data is None:
             data = ""
 
-        res = "%s(%s%s)" % (klass, data, prepr)
+        res = f"{klass}({data}{prepr})"
 
         return res
 
@@ -1124,13 +1124,13 @@ def _summary(self, name=None):
             tail = self[-1]
             if hasattr(tail, "format") and not isinstance(tail, str):
                 tail = tail.format()
-            index_summary = ", %s to %s" % (pprint_thing(head), pprint_thing(tail))
+            index_summary = f", {head} to {tail}"
         else:
             index_summary = ""
 
         if name is None:
             name = type(self).__name__
-        return "%s: %s entries%s" % (name, len(self), index_summary)
+        return f"{name}: {len(self)} entries{index_summary}"
 
     def summary(self, name=None):
         """
@@ -1304,7 +1304,7 @@ def _set_names(self, values, level=None):
         if not is_list_like(values):
             raise ValueError("Names must be a list-like")
         if len(values) != 1:
-            raise ValueError("Length of new names must be 1, got %d" % len(values))
+            raise ValueError(f"Length of new names must be 1, got {len(values)}")
 
         # GH 20527
         # All items in 'name' need to be hashable:
@@ -1475,8 +1475,8 @@ def _validate_index_level(self, level):
         if isinstance(level, int):
             if level < 0 and level != -1:
                 raise IndexError(
-                    "Too many levels: Index has only 1 level,"
-                    " %d is not a valid level number" % (level,)
+                    f"Too many levels: Index has only 1 level,"
+                    f" {level} is not a valid level number"
                 )
             elif level > 0:
                 raise IndexError(
@@ -4540,7 +4540,7 @@ def shift(self, periods=1, freq=None):
                        '2012-03-01'],
                       dtype='datetime64[ns]', freq='MS')
         """
-        raise NotImplementedError("Not supported for type %s" % type(self).__name__)
+        raise NotImplementedError(f"Not supported for type {type(self).__name__}")
 
     def argsort(self, *args, **kwargs):
         """
@@ -5047,8 +5047,8 @@ def get_slice_bound(self, label, side, kind):
 
         if side not in ("left", "right"):
             raise ValueError(
-                "Invalid value for side kwarg,"
-                " must be either 'left' or 'right': %s" % (side,)
+                f"Invalid value for side kwarg, must be either"
+                f" 'left' or 'right': {side}"
             )
 
         original_label = label
@@ -5602,7 +5602,7 @@ def _trim_front(strings):
 
 def _validate_join_method(method):
     if method not in ["left", "right", "inner", "outer"]:
-        raise ValueError("do not recognize join method %s" % method)
+        raise ValueError(f"do not recognize join method {method}")
 
 
 def default_index(n):

pandas/core/indexes/category.py

@@ -357,7 +357,7 @@ def _format_attrs(self):
         ]
         if self.name is not None:
             attrs.append(("name", ibase.default_pprint(self.name)))
-        attrs.append(("dtype", "'%s'" % self.dtype.name))
+        attrs.append(("dtype", f"'{self.dtype.name}'"))
         max_seq_items = get_option("display.max_seq_items") or len(self)
         if len(self) > max_seq_items:
             attrs.append(("length", len(self)))

pandas/core/indexes/datetimelike.py

@@ -36,7 +36,6 @@
 from pandas.core.indexes.base import Index, _index_shared_docs
 from pandas.core.tools.timedeltas import to_timedelta
 
-import pandas.io.formats.printing as printing
 from pandas.tseries.frequencies import to_offset
 
 _index_doc_kwargs = dict(ibase._index_doc_kwargs)
@@ -496,7 +495,7 @@ def _format_attrs(self):
             if attrib == "freq":
                 freq = self.freqstr
                 if freq is not None:
-                    freq = "'%s'" % freq
+                    freq = f"{freq!r}"
                 attrs.append(("freq", freq))
         return attrs
 
@@ -686,17 +685,13 @@ def _summary(self, name=None):
         """
         formatter = self._formatter_func
         if len(self) > 0:
-            index_summary = ", %s to %s" % (formatter(self[0]), formatter(self[-1]))
+            index_summary = f", {formatter(self[0])} to {formatter(self[-1])}"
         else:
             index_summary = ""
 
         if name is None:
             name = type(self).__name__
-        result = "%s: %s entries%s" % (
-            printing.pprint_thing(name),
-            len(self),
-            index_summary,
-        )
+        result = f"{name}: {len(self)} entries{index_summary}"
         if self.freq:
             result += "\nFreq: %s" % self.freqstr
 

pandas/core/indexes/datetimes.py

@@ -491,7 +491,7 @@ def _formatter_func(self):
         from pandas.io.formats.format import _get_format_datetime64
 
         formatter = _get_format_datetime64(is_dates_only=self._is_dates_only)
-        return lambda x: "'%s'" % formatter(x, tz=self.tz)
+        return lambda x: f"'{formatter(x, tz=self.tz)}'"
 
     # --------------------------------------------------------------------
     # Set Operation Methods

pandas/core/indexes/frozen.py

@@ -109,7 +109,7 @@ def __str__(self) -> str:
         return pprint_thing(self, quote_strings=True, escape_chars=("\t", "\r", "\n"))
 
     def __repr__(self) -> str:
-        return "%s(%s)" % (self.__class__.__name__, str(self))
+        return f"{self.__class__.__name__}({str(self)})"
 
     __setitem__ = __setslice__ = __delitem__ = __delslice__ = _disabled
     pop = append = extend = remove = sort = insert = _disabled
@@ -153,7 +153,7 @@ def __repr__(self) -> str:
         Return a string representation for this object.
         """
         prepr = pprint_thing(self, escape_chars=("\t", "\r", "\n"), quote_strings=True)
-        return "%s(%s, dtype='%s')" % (type(self).__name__, prepr, self.dtype)
+        return f"{type(self).__name__}({prepr}, dtype='{self.dtype}')"
 
     @deprecate_kwarg(old_arg_name="v", new_arg_name="value")
     def searchsorted(self, value, side="left", sorter=None):

pandas/core/indexes/multi.py

@@ -1329,21 +1329,20 @@ def _get_level_number(self, level) -> int:
         count = self.names.count(level)
         if (count > 1) and not is_integer(level):
             raise ValueError(
-                "The name %s occurs multiple times, use a level number" % level
+                f"The name {level} occurs multiple times, use a level number"
             )
         try:
             level = self.names.index(level)
         except ValueError:
             if not is_integer(level):
-                raise KeyError("Level %s not found" % str(level))
+                raise KeyError(f"Level {level} not found")
             elif level < 0:
                 level += self.nlevels
                 if level < 0:
                     orig_level = level - self.nlevels
                     raise IndexError(
-                        "Too many levels: Index has only %d "
-                        "levels, %d is not a valid level number"
-                        % (self.nlevels, orig_level)
+                        f"Too many levels: Index has only {self.nlevels} levels,"
+                        f" {orig_level} is not a valid level number"
                     )
             # Note: levels are zero-based
             elif level >= self.nlevels:
@@ -2286,8 +2285,8 @@ def reorder_levels(self, order):
         order = [self._get_level_number(i) for i in order]
         if len(order) != self.nlevels:
             raise AssertionError(
-                "Length of order must be same as "
-                "number of levels (%d), got %d" % (self.nlevels, len(order))
+                f"Length of order must be same as number of levels ({self.nlevels}),"
+                f" got {len(order)}"
             )
         new_levels = [self.levels[i] for i in order]
         new_codes = [self.codes[i] for i in order]
@@ -2599,8 +2598,8 @@ def slice_locs(self, start=None, end=None, step=None, kind=None):
     def _partial_tup_index(self, tup, side="left"):
         if len(tup) > self.lexsort_depth:
             raise UnsortedIndexError(
-                "Key length (%d) was greater than MultiIndex"
-                " lexsort depth (%d)" % (len(tup), self.lexsort_depth)
+                f"Key length ({len(tup)}) was greater than MultiIndex lexsort depth"
+                f" ({self.lexsort_depth})"
             )
 
         n = len(tup)
@@ -2611,7 +2610,7 @@ def _partial_tup_index(self, tup, side="left"):
 
             if lab not in lev:
                 if not lev.is_type_compatible(lib.infer_dtype([lab], skipna=False)):
-                    raise TypeError("Level type mismatch: %s" % lab)
+                    raise TypeError(f"Level type mismatch: {lab}")
 
                 # short circuit
                 loc = lev.searchsorted(lab, side=side)