CLN: String formatting % -> f-strings

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"]
@@ -2082,7 +2082,7 @@ def to_stata(
             data_label=data_label,
             write_index=write_index,
             variable_labels=variable_labels,
-            **kwargs
+            **kwargs,
         )
         writer.write_file()
 
@@ -2106,7 +2106,7 @@ def to_parquet(
         compression="snappy",
         index=None,
         partition_cols=None,
-        **kwargs
+        **kwargs,
     ):
         """
         Write a DataFrame to the binary parquet format.
@@ -2186,7 +2186,7 @@ def to_parquet(
             compression=compression,
             index=index,
             partition_cols=partition_cols,
-            **kwargs
+            **kwargs,
         )
 
     @Substitution(
@@ -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]
@@ -4110,7 +4110,7 @@ def fillna(
         inplace=False,
         limit=None,
         downcast=None,
-        **kwargs
+        **kwargs,
     ):
         return super().fillna(
             value=value,
@@ -4119,7 +4119,7 @@ def fillna(
             inplace=inplace,
             limit=limit,
             downcast=downcast,
-            **kwargs
+            **kwargs,
         )
 
     @Appender(_shared_docs["replace"] % _shared_doc_kwargs)
@@ -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
@@ -6566,7 +6565,7 @@ def _gotitem(
         see_also=_agg_summary_and_see_also_doc,
         examples=_agg_examples_doc,
         versionadded="\n.. versionadded:: 0.20.0\n",
-        **_shared_doc_kwargs
+        **_shared_doc_kwargs,
     )
     @Appender(_shared_docs["aggregate"])
     def aggregate(self, func, axis=0, *args, **kwargs):

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]
@@ -2055,7 +2054,7 @@ def __getstate__(self):
             _typ=self._typ,
             _metadata=self._metadata,
             attrs=self.attrs,
-            **meta
+            **meta,
         )
 
     def __setstate__(self, state):
@@ -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(
@@ -7050,7 +7048,7 @@ def interpolate(
         limit_direction="forward",
         limit_area=None,
         downcast=None,
-        **kwargs
+        **kwargs,
     ):
         """
         Interpolate values according to different methods.
@@ -7124,7 +7122,7 @@ def interpolate(
             limit_area=limit_area,
             inplace=inplace,
             downcast=downcast,
-            **kwargs
+            **kwargs,
         )
 
         if inplace:
@@ -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)
@@ -11572,7 +11570,7 @@ def stat_func(
         level=None,
         numeric_only=None,
         min_count=0,
-        **kwargs
+        **kwargs,
     ):
         if name == "sum":
             nv.validate_sum(tuple(), kwargs)

pandas/core/indexes/base.py

@@ -265,7 +265,7 @@ def __new__(
         name=None,
         fastpath=None,
         tupleize_cols=True,
-        **kwargs
+        **kwargs,
     ) -> "Index":
 
         from .range import RangeIndex
@@ -960,14 +960,13 @@ 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)
+        prepr = f",{space}".join(f"{k}={v}" for k, v in attrs)
 
         # no data provided, just attributes
         if data is None:
             data = ""
 
-        res = "%s(%s%s)" % (klass, data, prepr)
+        res = f"{klass}({data}{prepr})"
 
         return res
 
@@ -1121,13 +1120,13 @@ 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", {pprint_thing(head)} to {pprint_thing(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):
         """
@@ -1301,7 +1300,7 @@ 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:
@@ -1472,8 +1471,8 @@ 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(
@@ -4561,7 +4560,7 @@ 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):
         """
@@ -5068,8 +5067,8 @@ 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
@@ -5623,7 +5622,7 @@ 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

@@ -496,7 +496,7 @@ def _format_attrs(self):
             if attrib == "freq":
                 freq = self.freqstr
                 if freq is not None:
-                    freq = "'%s'" % freq
+                    freq = f"'{freq}'"
                 attrs.append(("freq", freq))
         return attrs
 
@@ -686,17 +686,13 @@ 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"{printing.pprint_thing(name)}: {len(self)} entries{index_summary}"
         if self.freq:
             result += "\nFreq: %s" % self.freqstr