python: drop_nulls expression

py-polars/docs/source/reference/expression.rst

@@ -99,6 +99,7 @@ Manipulation/ selection
     Expr.head
     Expr.tail
     Expr.reinterpret
+    Expr.drop_nulls
 
 Column names
 ------------

py-polars/polars/eager/frame.py

@@ -934,7 +934,7 @@ def __getitem__(self, item: Any) -> Any:
         if isinstance(item, slice):
             # special case df[::-1]
             if item.start is None and item.stop is None and item.step == -1:
-                return self.select(pl.col("*").reverse())
+                return self.select(pl.col("*").reverse())  # type: ignore
 
             if getattr(item, "end", False):
                 raise ValueError("A slice with steps larger than 1 is not supported.")
@@ -954,7 +954,7 @@ def __getitem__(self, item: Any) -> Any:
             else:
                 # df[start:stop:step]
                 return self.select(
-                    pl.col("*").slice(start, length).take_every(item.step)
+                    pl.col("*").slice(start, length).take_every(item.step)  # type: ignore
                 )
 
         # select multiple columns

py-polars/polars/lazy/expr.py

@@ -379,6 +379,14 @@ def slice(self, offset: int, length: int) -> "Expr":
         """
         return wrap_expr(self._pyexpr.slice(offset, length))
 
+    def drop_nulls(self) -> "Expr":
+        """
+        Syntactic sugar for:
+
+        >>> col("foo").filter(col("foo").is_not_null())
+        """
+        return self.filter(self.is_not_null())
+
     def cum_sum(self, reverse: bool = False) -> "Expr":
         """
         Get an array with the cumulative sum computed at every element.
@@ -664,14 +672,14 @@ def over(self, expr: Union[str, "Expr", tp.List["Expr"]]) -> "Expr":
         --------
 
         >>> df = DataFrame({
-            "groups": [1, 1, 2, 2, 1, 2, 3, 3, 1],
-            "values": [1, 2, 3, 4, 5, 6, 7, 8, 8]
-        })
-        >>> print(df.lazy()
-            .select([
-                col("groups")
-                sum("values").over("groups"))
-            ]).collect())
+        >>>    "groups": [1, 1, 2, 2, 1, 2, 3, 3, 1],
+        >>>    "values": [1, 2, 3, 4, 5, 6, 7, 8, 8]
+        >>>})
+        >>> (df.lazy()
+        >>>    .select([
+        >>>       col("groups")
+        >>>       sum("values").over("groups"))
+        >>>   ]).collect())
             ╭────────┬────────╮
             │ groups ┆ values │
             │ ---    ┆ ---    │

py-polars/tests/test_lazy.py

@@ -314,3 +314,8 @@ def test_head_groupby():
     assert out.frame_equal(
         pl.DataFrame({"str": ["a", "a", "b", "c", "c"], "nrs": [3, 5, 6, 1, 2]})
     )
+
+
+def test_drop_nulls():
+    df = pl.DataFrame({"nrs": [1, 2, 3, 4, 5, None]})
+    assert df.select(col("nrs").drop_nulls()).shape == (5, 1)