Add cume_dist

Author: timsaucer

python/datafusion/functions.py

@@ -258,6 +258,7 @@
     "rank",
     "dense_rank",
     "percent_rank",
+    "cume_dist",
 ]
 
 
@@ -1855,28 +1856,54 @@ def dense_rank() -> Expr:
     To set window function parameters use the window builder approach described in the
     ref:`_window_functions` online documentation.
     """
-    return Expr(f.rank())
+    return Expr(f.dense_rank())
 
 
 def percent_rank() -> Expr:
     """Create a percent_rank window function.
 
     This window function is similar to :py:func:`rank` except that the returned values
-    will be consecutive. Here is an example of a dataframe with a window ordered by
-    descending ``points`` and the associated dense rank.
+    are the percentage from 0.0 to 1.0 from first to last. Here is an example of a
+    dataframe with a window ordered by descending ``points`` and the associated percent
+    rank.
 
     ```
-    +--------+------+
-    | points | rank |
-    +--------+------+
-    | 100    | 1    |
-    | 100    | 1    |
-    | 50     | 2    |
-    | 25     | 3    |
-    +--------+------+
+    +--------+--------------+
+    | points | percent_rank |
+    +--------+--------------+
+    | 100    | 0.0          |
+    | 100    | 0.0          |
+    | 50     | 0.666667     |
+    | 25     | 1.0          |
+    +--------+--------------+
     ```
 
     To set window function parameters use the window builder approach described in the
     ref:`_window_functions` online documentation.
     """
-    return Expr(f.rank())
+    return Expr(f.percent_rank())
+
+
+def cume_dist() -> Expr:
+    """Create a cumulative distribution window function.
+
+    This window function is similar to :py:func:`rank` except that the returned values
+    are the ratio of the row number to the total numebr of rows. Here is an example of a
+    dataframe with a window ordered by descending ``points`` and the associated
+    cumulative distribution.
+
+    ```
+    +--------+-----------+
+    | points | cume_dist |
+    +--------+-----------+
+    | 100    | 0.5       |
+    | 100    | 0.5       |
+    | 50     | 0.75      |
+    | 25     | 1.0       |
+    +--------+-----------+
+    ```
+
+    To set window function parameters use the window builder approach described in the
+    ref:`_window_functions` online documentation.
+    """
+    return Expr(f.cume_dist())

python/datafusion/tests/test_dataframe.py

@@ -288,12 +288,12 @@ def test_distinct():
     ),
     (
         "percent_rank",
-        f.window("percent_rank", [], order_by=[f.order_by(column("c"))]),
+        f.percent_rank().order_by(column("c").sort()).build(),
         [0.5, 0, 0.5],
     ),
     (
         "cume_dist",
-        f.window("cume_dist", [], order_by=[f.order_by(column("b"))]),
+        f.cume_dist().order_by(column("b").sort()).build(),
         [0.3333333333333333, 0.6666666666666666, 1.0],
     ),
     (

src/functions.rs

@@ -889,6 +889,11 @@ pub fn percent_rank() -> PyExpr {
     window_function::percent_rank().into()
 }
 
+#[pyfunction]
+pub fn cume_dist() -> PyExpr {
+    window_function::cume_dist().into()
+}
+
 pub(crate) fn init_module(m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_wrapped(wrap_pyfunction!(abs))?;
     m.add_wrapped(wrap_pyfunction!(acos))?;
@@ -1079,6 +1084,7 @@ pub(crate) fn init_module(m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_wrapped(wrap_pyfunction!(rank))?;
     m.add_wrapped(wrap_pyfunction!(dense_rank))?;
     m.add_wrapped(wrap_pyfunction!(percent_rank))?;
+    m.add_wrapped(wrap_pyfunction!(cume_dist))?;
 
     Ok(())
 }