CoW: Set a bunch of Series copy statements to False (#56520)

Author: phofl

pandas/core/groupby/groupby.py

@@ -2200,7 +2200,7 @@ def any(self, skipna: bool = True) -> NDFrameT:
         """
         return self._cython_agg_general(
             "any",
-            alt=lambda x: Series(x).any(skipna=skipna),
+            alt=lambda x: Series(x, copy=False).any(skipna=skipna),
             skipna=skipna,
         )
 
@@ -2257,7 +2257,7 @@ def all(self, skipna: bool = True) -> NDFrameT:
         """
         return self._cython_agg_general(
             "all",
-            alt=lambda x: Series(x).all(skipna=skipna),
+            alt=lambda x: Series(x, copy=False).all(skipna=skipna),
             skipna=skipna,
         )
 
@@ -2451,7 +2451,7 @@ def mean(
         else:
             result = self._cython_agg_general(
                 "mean",
-                alt=lambda x: Series(x).mean(numeric_only=numeric_only),
+                alt=lambda x: Series(x, copy=False).mean(numeric_only=numeric_only),
                 numeric_only=numeric_only,
             )
             return result.__finalize__(self.obj, method="groupby")
@@ -2531,7 +2531,7 @@ def median(self, numeric_only: bool = False) -> NDFrameT:
         """
         result = self._cython_agg_general(
             "median",
-            alt=lambda x: Series(x).median(numeric_only=numeric_only),
+            alt=lambda x: Series(x, copy=False).median(numeric_only=numeric_only),
             numeric_only=numeric_only,
         )
         return result.__finalize__(self.obj, method="groupby")
@@ -2640,7 +2640,7 @@ def std(
         else:
             return self._cython_agg_general(
                 "std",
-                alt=lambda x: Series(x).std(ddof=ddof),
+                alt=lambda x: Series(x, copy=False).std(ddof=ddof),
                 numeric_only=numeric_only,
                 ddof=ddof,
             )
@@ -2747,7 +2747,7 @@ def var(
         else:
             return self._cython_agg_general(
                 "var",
-                alt=lambda x: Series(x).var(ddof=ddof),
+                alt=lambda x: Series(x, copy=False).var(ddof=ddof),
                 numeric_only=numeric_only,
                 ddof=ddof,
             )
@@ -2977,7 +2977,7 @@ def sem(self, ddof: int = 1, numeric_only: bool = False) -> NDFrameT:
             )
         return self._cython_agg_general(
             "sem",
-            alt=lambda x: Series(x).sem(ddof=ddof),
+            alt=lambda x: Series(x, copy=False).sem(ddof=ddof),
             numeric_only=numeric_only,
             ddof=ddof,
         )

pandas/core/groupby/ops.py

@@ -707,7 +707,7 @@ def size(self) -> Series:
             out = np.bincount(ids[ids != -1], minlength=ngroups)
         else:
             out = []
-        return Series(out, index=self.result_index, dtype="int64")
+        return Series(out, index=self.result_index, dtype="int64", copy=False)
 
     @cache_readonly
     def groups(self) -> dict[Hashable, np.ndarray]:

pandas/core/indexes/base.py

@@ -723,7 +723,7 @@ def _format_duplicate_message(self) -> DataFrame:
         assert len(duplicates)
 
         out = (
-            Series(np.arange(len(self)))
+            Series(np.arange(len(self)), copy=False)
             .groupby(self, observed=False)
             .agg(list)[duplicates]
         )

pandas/io/sas/sas7bdat.py

@@ -100,10 +100,10 @@ def _convert_datetimes(sas_datetimes: pd.Series, unit: str) -> pd.Series:
             sas_datetimes._values, unit="s", out_unit="ms"
         )
         dt64ms = millis.view("M8[ms]") + td
-        return pd.Series(dt64ms, index=sas_datetimes.index)
+        return pd.Series(dt64ms, index=sas_datetimes.index, copy=False)
     else:
         vals = np.array(sas_datetimes, dtype="M8[D]") + td
-        return pd.Series(vals, dtype="M8[s]", index=sas_datetimes.index)
+        return pd.Series(vals, dtype="M8[s]", index=sas_datetimes.index, copy=False)
 
 
 class _Column:
@@ -727,15 +727,15 @@ def _chunk_to_dataframe(self) -> DataFrame:
 
             if self._column_types[j] == b"d":
                 col_arr = self._byte_chunk[jb, :].view(dtype=self.byte_order + "d")
-                rslt[name] = pd.Series(col_arr, dtype=np.float64, index=ix)
+                rslt[name] = pd.Series(col_arr, dtype=np.float64, index=ix, copy=False)
                 if self.convert_dates:
                     if self.column_formats[j] in const.sas_date_formats:
                         rslt[name] = _convert_datetimes(rslt[name], "d")
                     elif self.column_formats[j] in const.sas_datetime_formats:
                         rslt[name] = _convert_datetimes(rslt[name], "s")
                 jb += 1
             elif self._column_types[j] == b"s":
-                rslt[name] = pd.Series(self._string_chunk[js, :], index=ix)
+                rslt[name] = pd.Series(self._string_chunk[js, :], index=ix, copy=False)
                 if self.convert_text and (self.encoding is not None):
                     rslt[name] = self._decode_string(rslt[name].str)
                 js += 1

pandas/io/stata.py

@@ -494,11 +494,11 @@ def g(x: datetime) -> int:
     else:
         raise ValueError(f"Format {fmt} is not a known Stata date format")
 
-    conv_dates = Series(conv_dates, dtype=np.float64)
+    conv_dates = Series(conv_dates, dtype=np.float64, copy=False)
     missing_value = struct.unpack("<d", b"\x00\x00\x00\x00\x00\x00\xe0\x7f")[0]
     conv_dates[bad_loc] = missing_value
 
-    return Series(conv_dates, index=index)
+    return Series(conv_dates, index=index, copy=False)
 
 
 excessive_string_length_error: Final = """