PERF: Use list comprehension to join strings (#41753) (#42173)

* PERF: Use list comprehension to join strings (#41753)

* Fix pre-commit failures

Author: vrserpa

asv_bench/benchmarks/io/csv.py

@@ -291,7 +291,8 @@ class ReadCSVFloatPrecision(StringIORewind):
 
     def setup(self, sep, decimal, float_precision):
         floats = [
-            "".join(random.choice(string.digits) for _ in range(28)) for _ in range(15)
+            "".join([random.choice(string.digits) for _ in range(28)])
+            for _ in range(15)
         ]
         rows = sep.join([f"0{decimal}" + "{}"] * 3) + "\n"
         data = rows * 5
@@ -395,7 +396,7 @@ class ReadCSVCachedParseDates(StringIORewind):
     param_names = ["do_cache", "engine"]
 
     def setup(self, do_cache, engine):
-        data = ("\n".join(f"10/{year}" for year in range(2000, 2100)) + "\n") * 10
+        data = ("\n".join([f"10/{year}" for year in range(2000, 2100)]) + "\n") * 10
         self.StringIO_input = StringIO(data)
 
     def time_read_csv_cached(self, do_cache, engine):

doc/source/user_guide/io.rst

@@ -5699,7 +5699,7 @@ Example of a callable using PostgreSQL `COPY clause
           writer.writerows(data_iter)
           s_buf.seek(0)
 
-          columns = ', '.join('"{}"'.format(k) for k in keys)
+          columns = ', '.join(['"{}"'.format(k) for k in keys])
           if table.schema:
               table_name = '{}.{}'.format(table.schema, table.name)
           else:

pandas/_config/config.py

@@ -157,7 +157,7 @@ def _describe_option(pat: str = "", _print_desc: bool = True):
     if len(keys) == 0:
         raise OptionError("No such keys(s)")
 
-    s = "\n".join(_build_option_description(k) for k in keys)
+    s = "\n".join([_build_option_description(k) for k in keys])
 
     if _print_desc:
         print(s)

pandas/core/computation/engines.py

@@ -37,7 +37,7 @@ def _check_ne_builtin_clash(expr: Expr) -> None:
     overlap = names & _ne_builtins
 
     if overlap:
-        s = ", ".join(repr(x) for x in overlap)
+        s = ", ".join([repr(x) for x in overlap])
         raise NumExprClobberingError(
             f'Variables in expression "{expr}" overlap with builtins: ({s})'
         )

pandas/core/computation/parsing.py

@@ -57,7 +57,7 @@ def create_valid_python_identifier(name: str) -> str:
         }
     )
 
-    name = "".join(special_characters_replacements.get(char, char) for char in name)
+    name = "".join([special_characters_replacements.get(char, char) for char in name])
     name = "BACKTICK_QUOTED_STRING_" + name
 
     if not name.isidentifier():

pandas/core/computation/pytables.py

@@ -575,7 +575,7 @@ def __init__(
                 else:
                     w = _validate_where(w)
                     where[idx] = w
-            _where = " & ".join(f"({w})" for w in com.flatten(where))
+            _where = " & ".join([f"({w})" for w in com.flatten(where)])
         else:
             # _validate_where ensures we otherwise have a string
             _where = where

pandas/core/computation/scope.py

@@ -50,7 +50,7 @@ def _raw_hex_id(obj) -> str:
     """Return the padded hexadecimal id of ``obj``."""
     # interpret as a pointer since that's what really what id returns
     packed = struct.pack("@P", id(obj))
-    return "".join(_replacer(x) for x in packed)
+    return "".join([_replacer(x) for x in packed])
 
 
 DEFAULT_GLOBALS = {

pandas/core/generic.py

@@ -10980,7 +10980,7 @@ def last_valid_index(self) -> Hashable | None:
 def _doc_params(cls):
     """Return a tuple of the doc params."""
     axis_descr = (
-        f"{{{', '.join(f'{a} ({i})' for i, a in enumerate(cls._AXIS_ORDERS))}}}"
+        f"{{{', '.join([f'{a} ({i})' for i, a in enumerate(cls._AXIS_ORDERS)])}}}"
     )
     name = cls._constructor_sliced.__name__ if cls._AXIS_LEN > 1 else "scalar"
     name2 = cls.__name__

pandas/core/internals/blocks.py

@@ -281,7 +281,7 @@ def __repr__(self) -> str:
             result = f"{name}: {len(self)} dtype: {self.dtype}"
         else:
 
-            shape = " x ".join(str(s) for s in self.shape)
+            shape = " x ".join([str(s) for s in self.shape])
             result = f"{name}: {self.mgr_locs.indexer}, {shape}, dtype: {self.dtype}"
 
         return result

pandas/io/formats/excel.py

@@ -769,7 +769,7 @@ def _generate_body(self, coloffset: int) -> Iterable[ExcelCell]:
             series = self.df.iloc[:, colidx]
             for i, val in enumerate(series):
                 if styles is not None:
-                    css = ";".join(a + ":" + str(v) for (a, v) in styles[i, colidx])
+                    css = ";".join([a + ":" + str(v) for (a, v) in styles[i, colidx]])
                     xlstyle = self.style_converter(css)
                 yield ExcelCell(self.rowcounter + i, colidx + coloffset, val, xlstyle)