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

Author: Vitor Serpa

asv_bench/benchmarks/io/csv.py

@@ -291,7 +291,11 @@ 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 +399,7 @@ 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

@@ -5689,7 +5689,7 @@ 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

@@ -579,7 +579,7 @@ 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

@@ -11036,7 +11036,7 @@ 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)
 

pandas/io/formats/latex.py

@@ -358,7 +358,7 @@ def get_result(self) -> str:
             self.bottom_separator,
             self.env_end,
         ]
-        result = "\n".join(item for item in elements if item)
+        result = "\n".join([item for item in elements if item])
         trailing_newline = "\n"
         result += trailing_newline
         return result
@@ -527,13 +527,13 @@ def env_begin(self) -> str:
             f"\\begin{{longtable}}{self._position_macro}{{{self.column_format}}}"
         )
         elements = [first_row, f"{self._caption_and_label()}"]
-        return "\n".join(item for item in elements if item)
+        return "\n".join([item for item in elements if item])
 
     def _caption_and_label(self) -> str:
         if self.caption or self.label:
             double_backslash = "\\\\"
             elements = [f"{self._caption_macro}", f"{self._label_macro}"]
-            caption_and_label = "\n".join(item for item in elements if item)
+            caption_and_label = "\n".join([item for item in elements if item])
             caption_and_label += double_backslash
             return caption_and_label
         else:
@@ -611,7 +611,7 @@ def env_begin(self) -> str:
             f"{self._label_macro}",
             f"\\begin{{tabular}}{{{self.column_format}}}",
         ]
-        return "\n".join(item for item in elements if item)
+        return "\n".join([item for item in elements if item])
 
     @property
     def bottom_separator(self) -> str:

pandas/io/formats/style.py

@@ -2018,7 +2018,7 @@ def set_properties(self, subset: Subset | None = None, **kwargs) -> Styler:
         >>> df.style.set_properties(color="white", align="right")
         >>> df.style.set_properties(**{'background-color': 'yellow'})
         """
-        values = "".join(f"{p}: {v};" for p, v in kwargs.items())
+        values = "".join([f"{p}: {v};" for p, v in kwargs.items()])
         return self.applymap(lambda x: values, subset=subset)
 
     @staticmethod

pandas/io/formats/xml.py

@@ -357,9 +357,9 @@ def build_attribs(self) -> None:
             flat_col = col
             if isinstance(col, tuple):
                 flat_col = (
-                    "".join(str(c) for c in col).strip()
+                    "".join([str(c) for c in col]).strip()
                     if "" in col
-                    else "_".join(str(c) for c in col).strip()
+                    else "_".join([str(c) for c in col]).strip()
                 )
 
             attr_name = f"{self.prefix_uri}{flat_col}"
@@ -384,9 +384,9 @@ def build_elems(self) -> None:
             flat_col = col
             if isinstance(col, tuple):
                 flat_col = (
-                    "".join(str(c) for c in col).strip()
+                    "".join([str(c) for c in col]).strip()
                     if "" in col
-                    else "_".join(str(c) for c in col).strip()
+                    else "_".join([str(c) for c in col]).strip()
                 )
 
             elem_name = f"{self.prefix_uri}{flat_col}"
@@ -529,9 +529,9 @@ def build_attribs(self) -> None:
             flat_col = col
             if isinstance(col, tuple):
                 flat_col = (
-                    "".join(str(c) for c in col).strip()
+                    "".join([str(c) for c in col]).strip()
                     if "" in col
-                    else "_".join(str(c) for c in col).strip()
+                    else "_".join([str(c) for c in col]).strip()
                 )
 
             attr_name = f"{self.prefix_uri}{flat_col}"
@@ -556,9 +556,9 @@ def build_elems(self) -> None:
             flat_col = col
             if isinstance(col, tuple):
                 flat_col = (
-                    "".join(str(c) for c in col).strip()
+                    "".join([str(c) for c in col]).strip()
                     if "" in col
-                    else "_".join(str(c) for c in col).strip()
+                    else "_".join([str(c) for c in col]).strip()
                 )
 
             elem_name = f"{self.prefix_uri}{flat_col}"

pandas/io/html.py

@@ -627,7 +627,7 @@ def _build_xpath_expr(attrs) -> str:
     if "class_" in attrs:
         attrs["class"] = attrs.pop("class_")
 
-    s = " and ".join(f"@{k}={repr(v)}" for k, v in attrs.items())
+    s = " and ".join([f"@{k}={repr(v)}" for k, v in attrs.items()])
     return f"[{s}]"
 
 
@@ -861,7 +861,7 @@ def _parser_dispatch(flavor):
 
 
 def _print_as_set(s) -> str:
-    arg = ", ".join(pprint_thing(el) for el in s)
+    arg = ", ".join([pprint_thing(el) for el in s])
     return f"{{{arg}}}"
 
 

pandas/io/parsers/base_parser.py

@@ -351,7 +351,7 @@ def extract(r):
         # level, then our header was too long.
         for n in range(len(columns[0])):
             if all(ensure_str(col[n]) in self.unnamed_cols for col in columns):
-                header = ",".join(str(x) for x in self.header)
+                header = ",".join([str(x) for x in self.header])
                 raise ParserError(
                     f"Passed header=[{header}] are too many rows "
                     "for this multi_index of columns"
@@ -1138,7 +1138,7 @@ def _try_convert_dates(parser: Callable, colspec, data_dict, columns):
         else:
             colnames.append(c)
 
-    new_name = "_".join(str(x) for x in colnames)
+    new_name = "_".join([str(x) for x in colnames])
     to_parse = [data_dict[c] for c in colnames if c in data_dict]
 
     new_col = parser(*to_parse)

pandas/io/parsers/python_parser.py

@@ -1159,7 +1159,7 @@ def get_rows(self, infer_nrows, skiprows=None):
 
     def detect_colspecs(self, infer_nrows=100, skiprows=None):
         # Regex escape the delimiters
-        delimiters = "".join(fr"\{x}" for x in self.delimiter)
+        delimiters = "".join([fr"\{x}" for x in self.delimiter])
         pattern = re.compile(f"([^{delimiters}]+)")
         rows = self.get_rows(infer_nrows, skiprows)
         if not rows:

pandas/io/pytables.py

@@ -2642,7 +2642,7 @@ def __repr__(self) -> str:
         s = self.shape
         if s is not None:
             if isinstance(s, (list, tuple)):
-                jshape = ",".join(pprint_thing(x) for x in s)
+                jshape = ",".join([pprint_thing(x) for x in s])
                 s = f"[{jshape}]"
             return f"{self.pandas_type:12.12} (shape->{s})"
         return self.pandas_type
@@ -3309,10 +3309,10 @@ def __repr__(self) -> str:
 
         ver = ""
         if self.is_old_version:
-            jver = ".".join(str(x) for x in self.version)
+            jver = ".".join([str(x) for x in self.version])
             ver = f"[{jver}]"
 
-        jindex_axes = ",".join(a.name for a in self.index_axes)
+        jindex_axes = ",".join([a.name for a in self.index_axes])
         return (
             f"{self.pandas_type:12.12}{ver} "
             f"(typ->{self.table_type_short},nrows->{self.nrows},"
@@ -3519,7 +3519,7 @@ def validate_version(self, where=None):
         """are we trying to operate on an old version?"""
         if where is not None:
             if self.version[0] <= 0 and self.version[1] <= 10 and self.version[2] < 1:
-                ws = incompatibility_doc % ".".join(str(x) for x in self.version)
+                ws = incompatibility_doc % ".".join([str(x) for x in self.version])
                 warnings.warn(ws, IncompatibilityWarning)
 
     def validate_min_itemsize(self, min_itemsize):
@@ -4066,7 +4066,7 @@ def get_blk_items(mgr):
                     new_blocks.append(b)
                     new_blk_items.append(b_items)
                 except (IndexError, KeyError) as err:
-                    jitems = ",".join(pprint_thing(item) for item in items)
+                    jitems = ",".join([pprint_thing(item) for item in items])
                     raise ValueError(
                         f"cannot match existing table structure for [{jitems}] "
                         "on appending data"

pandas/io/sql.py

@@ -1913,7 +1913,7 @@ def insert_statement(self, *, num_rows: int):
         col_names = ",".join(bracketed_names)
 
         row_wildcards = ",".join([wld] * len(names))
-        wildcards = ",".join(f"({row_wildcards})" for _ in range(num_rows))
+        wildcards = ",".join([f"({row_wildcards})" for _ in range(num_rows)])
         insert_statement = (
             f"INSERT INTO {escape(self.name)} ({col_names}) VALUES {wildcards}"
         )
@@ -1952,7 +1952,7 @@ def _create_table_setup(self):
                 keys = [self.keys]
             else:
                 keys = self.keys
-            cnames_br = ", ".join(escape(c) for c in keys)
+            cnames_br = ", ".join([escape(c) for c in keys])
             create_tbl_stmts.append(
                 f"CONSTRAINT {self.name}_pk PRIMARY KEY ({cnames_br})"
             )
@@ -1972,7 +1972,7 @@ def _create_table_setup(self):
         ix_cols = [cname for cname, _, is_index in column_names_and_types if is_index]
         if len(ix_cols):
             cnames = "_".join(ix_cols)
-            cnames_br = ",".join(escape(c) for c in ix_cols)
+            cnames_br = ",".join([escape(c) for c in ix_cols])
             create_stmts.append(
                 "CREATE INDEX "
                 + escape("ix_" + self.name + "_" + cnames)

pandas/io/stata.py

@@ -1357,12 +1357,12 @@ def _read_old_header(self, first_char: bytes) -> None:
         try:
             self.typlist = [self.TYPE_MAP[typ] for typ in typlist]
         except ValueError as err:
-            invalid_types = ",".join(str(x) for x in typlist)
+            invalid_types = ",".join([str(x) for x in typlist])
             raise ValueError(f"cannot convert stata types [{invalid_types}]") from err
         try:
             self.dtyplist = [self.DTYPE_MAP[typ] for typ in typlist]
         except ValueError as err:
-            invalid_dtypes = ",".join(str(x) for x in typlist)
+            invalid_dtypes = ",".join([str(x) for x in typlist])
             raise ValueError(f"cannot convert stata dtypes [{invalid_dtypes}]") from err
 
         if self.format_version > 108:

pandas/plotting/_core.py

@@ -866,7 +866,7 @@ def _get_call_args(backend_name, data, args, kwargs):
         if args and isinstance(data, ABCSeries):
             positional_args = str(args)[1:-1]
             keyword_args = ", ".join(
-                f"{name}={repr(value)}" for (name, _), value in zip(arg_def, args)
+                [f"{name}={repr(value)}" for (name, _), value in zip(arg_def, args)]
             )
             msg = (
                 "`Series.plot()` should not be called with positional "

pandas/plotting/_matplotlib/core.py

@@ -714,7 +714,7 @@ def _get_index_name(self) -> str | None:
         if isinstance(self.data.index, ABCMultiIndex):
             name = self.data.index.names
             if com.any_not_none(*name):
-                name = ",".join(pprint_thing(x) for x in name)
+                name = ",".join([pprint_thing(x) for x in name])
             else:
                 name = None
         else:

pandas/tests/generic/test_frame.py

@@ -126,7 +126,7 @@ def finalize(self, other, method=None, **kwargs):
             for name in self._metadata:
                 if method == "concat":
                     value = "+".join(
-                        getattr(o, name) for o in other.objs if getattr(o, name, None)
+                        [getattr(o, name) for o in other.objs if getattr(o, name, None)]
                     )
                     object.__setattr__(self, name, value)
                 else:

pandas/tests/generic/test_series.py

@@ -130,7 +130,7 @@ def finalize(self, other, method=None, **kwargs):
             for name in self._metadata:
                 if method == "concat" and name == "filename":
                     value = "+".join(
-                        getattr(o, name) for o in other.objs if getattr(o, name, None)
+                        [getattr(o, name) for o in other.objs if getattr(o, name, None)]
                     )
                     object.__setattr__(self, name, value)
                 else:

pandas/tests/indexes/period/test_indexing.py

@@ -513,11 +513,10 @@ def test_get_indexer_mismatched_dtype_with_method(self, non_comparable_idx, meth
                 continue
             # Two different error message patterns depending on dtypes
             msg = "|".join(
-                re.escape(msg)
-                for msg in (
+                [re.escape(msg) for msg in (
                     f"Cannot compare dtypes {pi.dtype} and {other.dtype}",
                     " not supported between instances of ",
-                )
+                )]
             )
             with pytest.raises(TypeError, match=msg):
                 pi.get_indexer(other2, method=method)

pandas/tests/io/formats/style/test_align.py

@@ -13,7 +13,7 @@ def bar_grad(a=None, b=None, c=None, d=None):
     return ret + [
         (
             "background",
-            f"linear-gradient(90deg,{','.join(x for x in [a, b, c, d] if x)})",
+            f"linear-gradient(90deg,{','.join([x for x in [a, b, c, d] if x])})",
         )
     ]
 

pandas/tests/io/formats/test_format.py

@@ -1369,7 +1369,7 @@ def test_to_string(self):
         )
         lines = result.split("\n")
         header = lines[0].strip().split()
-        joined = "\n".join(re.sub(r"\s+", " ", x).strip() for x in lines[1:])
+        joined = "\n".join([re.sub(r"\s+", " ", x).strip() for x in lines[1:]])
         recons = read_csv(StringIO(joined), names=header, header=None, sep=" ")
         tm.assert_series_equal(recons["B"], biggie["B"])
         assert recons["A"].count() == biggie["A"].count()