CLN: use f-strings where possible

asv_bench/benchmarks/categoricals.py

@@ -89,7 +89,7 @@ def setup(self):
         )
 
         for col in ("int", "float", "timestamp"):
-            self.df[col + "_as_str"] = self.df[col].astype(str)
+            self.df[f"{col}_as_str"] = self.df[col].astype(str)
 
         for col in self.df.columns:
             self.df[col] = self.df[col].astype("category")

asv_bench/benchmarks/frame_methods.py

@@ -125,7 +125,7 @@ def setup(self):
         self.df = DataFrame(np.random.randn(N * 10, N))
         self.df2 = DataFrame(np.random.randn(N * 50, 10))
         self.df3 = DataFrame(
-            np.random.randn(N, 5 * N), columns=["C" + str(c) for c in range(N * 5)]
+            np.random.randn(N, 5 * N), columns=[f"C{c}" for c in range(N * 5)]
         )
         self.df4 = DataFrame(np.random.randn(N * 1000, 10))
 

asv_bench/benchmarks/inference.py

@@ -166,14 +166,15 @@ def time_unique_date_strings(self, cache, count):
 
 
 class ToDatetimeISO8601:
+    sep_format = "%Y-%m-%d %H:%M:%S"
+    nosep_format = "%Y%m%d %H:%M:%S"
+
     def setup(self):
         rng = date_range(start="1/1/2000", periods=20000, freq="H")
-        self.strings = rng.strftime("%Y-%m-%d %H:%M:%S").tolist()
-        self.strings_nosep = rng.strftime("%Y%m%d %H:%M:%S").tolist()
-        self.strings_tz_space = [
-            x.strftime("%Y-%m-%d %H:%M:%S") + " -0800" for x in rng
-        ]
-        self.strings_zero_tz = [x.strftime("%Y-%m-%d %H:%M:%S") + "Z" for x in rng]
+        self.strings = rng.strftime(self.sep_format).tolist()
+        self.strings_nosep = rng.strftime(self.nosep_format).tolist()
+        self.strings_tz_space = [f"{x.strftime(self.sep_format)} -0800" for x in rng]
+        self.strings_zero_tz = [f"{x.strftime(self.sep_format)}Z" for x in rng]
 
     def time_iso8601(self):
         to_datetime(self.strings)
@@ -182,10 +183,10 @@ def time_iso8601_nosep(self):
         to_datetime(self.strings_nosep)
 
     def time_iso8601_format(self):
-        to_datetime(self.strings, format="%Y-%m-%d %H:%M:%S")
+        to_datetime(self.strings, format=self.sep_format)
 
     def time_iso8601_format_no_sep(self):
-        to_datetime(self.strings_nosep, format="%Y%m%d %H:%M:%S")
+        to_datetime(self.strings_nosep, format=self.nosep_format)
 
     def time_iso8601_tz_spaceformat(self):
         to_datetime(self.strings_tz_space)

asv_bench/benchmarks/io/hdf.py

@@ -43,7 +43,7 @@ def setup(self):
             np.random.randn(N, 100), index=date_range("1/1/2000", periods=N)
         )
         self.df_dc = DataFrame(
-            np.random.randn(N, 10), columns=["C%03d" % i for i in range(10)]
+            np.random.randn(N, 10), columns=[f"C{i:03d}" for i in range(10)]
         )
 
         self.fname = "__test__.h5"

pandas/_config/config.py

@@ -499,7 +499,7 @@ def register_option(
     path = key.split(".")
 
     for k in path:
-        if not re.match("^" + tokenize.Name + "$", k):
+        if not re.match(f"^{tokenize.Name}$", k):
             raise ValueError(f"{k} is not a valid identifier")
         if keyword.iskeyword(k):
             raise ValueError(f"{k} is a python keyword")
@@ -707,7 +707,7 @@ def pp_options_list(keys: Iterable[str], width: int = 80, _print: bool = False):
     from textwrap import wrap
 
     def pp(name: str, ks: Iterable[str]) -> list[str]:
-        pfx = "- " + name + ".[" if name else ""
+        pfx = f"- {name}.[" if name else ""
         ls = wrap(
             ", ".join(ks),
             width,
@@ -716,7 +716,7 @@ def pp(name: str, ks: Iterable[str]) -> list[str]:
             break_long_words=False,
         )
         if ls and ls[-1] and name:
-            ls[-1] = ls[-1] + "]"
+            ls[-1] = f"{ls[-1]}]"
         return ls
 
     ls: list[str] = []

pandas/_testing/__init__.py

@@ -569,7 +569,7 @@ def makeCustomIndex(
 
     if names is True:
         # build default names
-        names = [prefix + str(i) for i in range(nlevels)]
+        names = [f"{prefix}{i}" for i in range(nlevels)]
     if names is False:
         # pass None to index constructor for no name
         names = None

pandas/conftest.py

@@ -1770,7 +1770,7 @@ def spmatrix(request):
     """
     from scipy import sparse
 
-    return getattr(sparse, request.param + "_matrix")
+    return getattr(sparse, f"{request.param}_matrix")
 
 
 @pytest.fixture(

pandas/core/apply.py

@@ -1287,7 +1287,7 @@ def _make_unique_kwarg_list(
     [('a', '<lambda>_0'), ('a', '<lambda>_1'), ('b', '<lambda>')]
     """
     return [
-        (pair[0], "_".join([pair[1], str(seq[:i].count(pair))]))
+        (pair[0], f"{pair[1]}_{seq[:i].count(pair)}")
         if seq.count(pair) > 1
         else pair
         for i, pair in enumerate(seq)

pandas/core/arraylike.py

@@ -304,8 +304,7 @@ def array_ufunc(self, ufunc: np.ufunc, method: str, *inputs: Any, **kwargs: Any)
             # well. Previously this raised an internal ValueError. We might
             # support it someday, so raise a NotImplementedError.
             raise NotImplementedError(
-                "Cannot apply ufunc {} to mixed DataFrame and Series "
-                "inputs.".format(ufunc)
+                f"Cannot apply ufunc {ufunc} to mixed DataFrame and Series inputs."
             )
         axes = self.axes
         for obj in alignable[1:]:

pandas/core/arrays/categorical.py

@@ -1890,7 +1890,7 @@ def _repr_categories_info(self) -> str:
         start = True
         cur_col_len = len(levheader)  # header
         sep_len, sep = (3, " < ") if self.ordered else (2, ", ")
-        linesep = sep.rstrip() + "\n"  # remove whitespace
+        linesep = f"{sep.rstrip()}\n"  # remove whitespace
         for val in category_strs:
             if max_width != 0 and cur_col_len + sep_len + len(val) > max_width:
                 levstring += linesep + (" " * (len(levheader) + 1))
@@ -1901,7 +1901,7 @@ def _repr_categories_info(self) -> str:
             levstring += val
             start = False
         # replace to simple save space by
-        return levheader + "[" + levstring.replace(" < ... < ", " ... ") + "]"
+        return f"{levheader}[{levstring.replace(' < ... < ', ' ... ')}]"
 
     def _repr_footer(self) -> str:
         info = self._repr_categories_info()

pandas/core/arrays/masked.py

@@ -1058,7 +1058,7 @@ def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
             data = self.to_numpy("float64", na_value=np.nan)
 
         # median, var, std, skew, kurt, idxmin, idxmax
-        op = getattr(nanops, "nan" + name)
+        op = getattr(nanops, f"nan{name}")
         result = op(data, axis=0, skipna=skipna, mask=mask, **kwargs)
 
         if np.isnan(result):

pandas/core/arrays/string_arrow.py

@@ -317,11 +317,11 @@ def _str_contains(
         return result
 
     def _str_startswith(self, pat: str, na=None):
-        pat = "^" + re.escape(pat)
+        pat = f"^{re.escape(pat)}"
         return self._str_contains(pat, na=na, regex=True)
 
     def _str_endswith(self, pat: str, na=None):
-        pat = re.escape(pat) + "$"
+        pat = f"{re.escape(pat)}$"
         return self._str_contains(pat, na=na, regex=True)
 
     def _str_replace(
@@ -345,14 +345,14 @@ def _str_match(
         self, pat: str, case: bool = True, flags: int = 0, na: Scalar | None = None
     ):
         if not pat.startswith("^"):
-            pat = "^" + pat
+            pat = f"^{pat}"
         return self._str_contains(pat, case, flags, na, regex=True)
 
     def _str_fullmatch(
         self, pat, case: bool = True, flags: int = 0, na: Scalar | None = None
     ):
         if not pat.endswith("$") or pat.endswith("//$"):
-            pat = pat + "$"
+            pat = f"{pat}$"
         return self._str_match(pat, case, flags, na)
 
     def _str_isalnum(self):

pandas/core/computation/expr.py

@@ -410,7 +410,7 @@ def visit(self, node, **kwargs):
                     e.msg = "Python keyword not valid identifier in numexpr query"
                 raise e
 
-        method = "visit_" + type(node).__name__
+        method = f"visit_{type(node).__name__}"
         visitor = getattr(self, method)
         return visitor(node, **kwargs)
 

pandas/core/computation/parsing.py

@@ -59,7 +59,7 @@ def create_valid_python_identifier(name: str) -> str:
     )
 
     name = "".join([special_characters_replacements.get(char, char) for char in name])
-    name = "BACKTICK_QUOTED_STRING_" + name
+    name = f"BACKTICK_QUOTED_STRING_{name}"
 
     if not name.isidentifier():
         raise SyntaxError(f"Could not convert '{name}' to a valid Python identifier.")

pandas/core/computation/scope.py

@@ -250,7 +250,7 @@ def _get_vars(self, stack, scopes: list[str]) -> None:
         variables = itertools.product(scopes, stack)
         for scope, (frame, _, _, _, _, _) in variables:
             try:
-                d = getattr(frame, "f_" + scope)
+                d = getattr(frame, f"f_{scope}")
                 self.scope = DeepChainMap(self.scope.new_child(d))
             finally:
                 # won't remove it, but DECREF it

pandas/core/dtypes/dtypes.py

@@ -802,7 +802,7 @@ def __hash__(self) -> int:
     def __eq__(self, other: Any) -> bool:
         if isinstance(other, str):
             if other.startswith("M8["):
-                other = "datetime64[" + other[3:]
+                other = f"datetime64[{other[3:]}"
             return other == self.name
 
         return (
@@ -1132,7 +1132,7 @@ def __new__(cls, subtype=None, closed: str_type | None = None):
             )
             raise TypeError(msg)
 
-        key = str(subtype) + str(closed)
+        key = f"{subtype}{closed}"
         try:
             return cls._cache_dtypes[key]
         except KeyError:

pandas/core/frame.py

@@ -1095,7 +1095,7 @@ def _repr_html_(self) -> str | None:
             # need to escape the <class>, should be the first line.
             val = buf.getvalue().replace("<", r"&lt;", 1)
             val = val.replace(">", r"&gt;", 1)
-            return "<pre>" + val + "</pre>"
+            return f"<pre>{val}</pre>"
 
         if get_option("display.notebook_repr_html"):
             max_rows = get_option("display.max_rows")
@@ -8945,8 +8945,7 @@ def explode(
         if not self.columns.is_unique:
             duplicate_cols = self.columns[self.columns.duplicated()].tolist()
             raise ValueError(
-                "DataFrame columns must be unique. "
-                + f"Duplicate columns: {duplicate_cols}"
+                f"DataFrame columns must be unique. Duplicate columns: {duplicate_cols}"
             )
 
         columns: list[Hashable]

pandas/core/groupby/groupby.py

@@ -1533,9 +1533,9 @@ def f(g):
                     with np.errstate(all="ignore"):
                         return func(g, *args, **kwargs)
 
-            elif hasattr(nanops, "nan" + func):
+            elif hasattr(nanops, f"nan{func}"):
                 # TODO: should we wrap this in to e.g. _is_builtin_func?
-                f = getattr(nanops, "nan" + func)
+                f = getattr(nanops, f"nan{func}")
 
             else:
                 raise ValueError(

pandas/core/indexes/category.py

@@ -349,7 +349,7 @@ def _format_attrs(self):
         attrs = [
             (
                 "categories",
-                "[" + ", ".join(self._data._repr_categories()) + "]",
+                f"[{', '.join(self._data._repr_categories())}]",
             ),
             ("ordered", self.ordered),
         ]

pandas/core/indexes/interval.py

@@ -845,7 +845,7 @@ def _format_native_types(
     def _format_data(self, name=None) -> str:
         # TODO: integrate with categorical and make generic
         # name argument is unused here; just for compat with base / categorical
-        return self._data._format_data() + "," + self._format_space()
+        return f"{self._data._format_data()},{self._format_space()}"
 
     # --------------------------------------------------------------------
     # Set Operations

pandas/core/interchange/buffer.py

@@ -64,14 +64,9 @@ def __dlpack_device__(self) -> tuple[DlpackDeviceType, int | None]:
         return (DlpackDeviceType.CPU, None)
 
     def __repr__(self) -> str:
-        return (
-            "PandasBuffer("
-            + str(
-                {
-                    "bufsize": self.bufsize,
-                    "ptr": self.ptr,
-                    "device": self.__dlpack_device__()[0].name,
-                }
-            )
-            + ")"
-        )
+        spec = {
+            "bufsize": self.bufsize,
+            "ptr": self.ptr,
+            "device": self.__dlpack_device__()[0].name,
+        }
+        return f"PandasBuffer({spec})"

pandas/core/interchange/column.py

@@ -329,7 +329,7 @@ def _get_validity_buffer(self) -> tuple[PandasBuffer, Any]:
             return buffer, dtype
 
         try:
-            msg = _NO_VALIDITY_BUFFER[null] + " so does not have a separate mask"
+            msg = f"{_NO_VALIDITY_BUFFER[null]} so does not have a separate mask"
         except KeyError:
             # TODO: implement for other bit/byte masks?
             raise NotImplementedError("See self.describe_null")

pandas/core/nanops.py

@@ -1043,7 +1043,7 @@ def nansem(
 
 
 def _nanminmax(meth, fill_value_typ):
-    @bottleneck_switch(name="nan" + meth)
+    @bottleneck_switch(name=f"nan{meth}")
     @_datetimelike_compat
     def reduction(
         values: np.ndarray,