feat(python): add map_dict method for Series

py-polars/docs/source/reference/series/computation.rst

@@ -34,6 +34,7 @@ Computation
     Series.kurtosis
     Series.log
     Series.log10
+    Series.map_dict
     Series.pct_change
     Series.peak_max
     Series.peak_min

py-polars/polars/internals/construction.py

@@ -1233,12 +1233,12 @@ def pandas_has_default_index(df: pd.DataFrame) -> bool:
 
     index_cols = df.index.names
 
-    if len(index_cols) > 1:  # noqa: SIM114
-        return False  # not default: more than one index
-    elif index_cols not in ([None], [""]):
-        return False  # not default: index is named
+    if len(index_cols) > 1 or index_cols not in ([None], [""]):
+        # not default: more than one index, or index is named
+        return False
     elif df.index.equals(RangeIndex(start=0, stop=len(df), step=1)):
-        return True  # is default: simple range index
+        # is default: simple range index
+        return True
     else:
         # finally, is the index _equivalent_ to a default unnamed
         # integer index with frame data that was previously sorted

py-polars/polars/internals/expr/expr.py

@@ -6047,9 +6047,9 @@ def map_dict(
         Parameters
         ----------
         remapping
-            Mapping dictionary to use for remapping the values.
+            Dictionary containing the before/after values to map.
         default
-            Value to use when original value was not found in remapping dictionary.
+            Value to use when the remapping dict does not contain the lookup value.
 
         Warnings
         --------
@@ -6097,7 +6097,7 @@ def map_dict(
         │ 3      ┆ DE           ┆ Germany       │
         └────────┴──────────────┴───────────────┘
 
-        Set a default value for values that couldn't be mapped.
+        Set a default value for values that cannot be mapped...
 
         >>> df.with_columns(
         ...     pl.col("country_code")
@@ -6116,7 +6116,7 @@ def map_dict(
         │ 3      ┆ DE           ┆ Germany       │
         └────────┴──────────────┴───────────────┘
 
-        Keep the original value for values that couldn't be mapped.
+        ...or keep the original value:
 
         >>> df.with_columns(
         ...     pl.col("country_code")
@@ -6135,10 +6135,9 @@ def map_dict(
         │ 3      ┆ DE           ┆ Germany       │
         └────────┴──────────────┴───────────────┘
 
-        If you need to access different columns to set a default value for values that
-        couldn't be mapped, a struct needs to be constructed, with in the first field
-        the column that you want to remap and the rest of the fields the other columns
-        you use in the default expression.
+        If you need to access different columns to set a default value, a struct needs
+        to be constructed; in the first field is the column that you want to remap and
+        the rest of the fields are the other columns used in the default expression.
 
         >>> df.with_columns(
         ...     pl.struct(pl.col(["country_code", "row_nr"])).map_dict(

py-polars/polars/internals/series/series.py

@@ -4780,6 +4780,57 @@ def clip_max(self, max_val: int | float) -> Series:
 
         """
 
+    def map_dict(
+        self,
+        remapping: dict[Any, Any],
+        *,
+        default: Any = None,
+    ) -> Self:
+        """
+        Replace values in the Series using a remapping dictionary.
+
+        Parameters
+        ----------
+        remapping
+            Dictionary containing the before/after values to map.
+        default
+            Value to use when the remapping dict does not contain the lookup value.
+
+        Examples
+        --------
+        >>> s = pl.Series("iso3166", ["TUR", "???", "JPN", "NLD"])
+        >>> country_lookup = {
+        ...     "JPN": "Japan",
+        ...     "TUR": "Türkiye",
+        ...     "NLD": "Netherlands",
+        ... }
+
+        Remap, setting a default for unrecognised values...
+
+        >>> s.map_dict(country_lookup, default="Unspecified").rename("country_name")
+        shape: (4,)
+        Series: 'country_name' [str]
+        [
+            "Türkiye"
+            "Unspecified"
+            "Japan"
+            "Netherlands"
+        ]
+
+        ...or keep the original value:
+
+        >>> s.map_dict(country_lookup, default=s).rename("country_name")
+        shape: (4,)
+        Series: 'country_name' [str]
+        [
+            "Türkiye"
+            "???"
+            "Japan"
+            "Netherlands"
+        ]
+
+        """
+
     def reshape(self, dims: tuple[int, ...]) -> Series:
         """
         Reshape this Series to a flat Series or a Series of Lists.
@@ -5136,6 +5187,11 @@ def arr(self) -> ListNameSpace:
         """Create an object namespace of all list related methods."""
         return ListNameSpace(self)
 
+    @property
+    def bin(self) -> BinaryNameSpace:
+        """Create an object namespace of all binary related methods."""
+        return BinaryNameSpace(self)
+
     @property
     def cat(self) -> CatNameSpace:
         """Create an object namespace of all categorical related methods."""
@@ -5151,11 +5207,6 @@ def str(self) -> StringNameSpace:
         """Create an object namespace of all string related methods."""
         return StringNameSpace(self)
 
-    @property
-    def bin(self) -> BinaryNameSpace:
-        """Create an object namespace of all binary related methods."""
-        return BinaryNameSpace(self)
-
     @property
     def struct(self) -> StructNameSpace:
         """Create an object namespace of all struct related methods."""

py-polars/tests/unit/test_exprs.py

@@ -508,7 +508,7 @@ def test_map_dict() -> None:
 
     assert (
         df.with_columns(
-            pl.struct(pl.col(["country_code", "row_nr"]))  # type: ignore[union-attr]
+            pl.struct(pl.col(["country_code", "row_nr"]))
             .map_dict(
                 country_code_dict,
                 default=pl.col("row_nr").cast(pl.Utf8),

py-polars/tests/unit/test_series.py

@@ -2392,3 +2392,17 @@ def test_is_between() -> None:
         True,
         False,
     ]
+
+
+def test_map_dict() -> None:
+    s = pl.Series("s", [-1, 2, None, 4, -5])
+    remap = {1: "one", 2: "two", 3: "three", 4: "four", 5: "five"}
+
+    assert_series_equal(
+        s.abs().map_dict(remap, default="?"),
+        pl.Series("s", ["one", "two", "?", "four", "five"]),
+    )
+    assert_series_equal(
+        s.map_dict(remap, default=s.cast(pl.Utf8)),
+        pl.Series("s", ["-1", "two", None, "four", "-5"]),
+    )