feat(datafusion): add 620 solution

Author: IndexSeek

README.md

@@ -24,7 +24,7 @@ Fiddling around with DataFusion and PyArrow.
 
 ### Basic Aggregate Functions
 
-- [X] [] 620. [Not Boring Movies](https://leetcode.com/problems/not-boring-movies) - Easy
+- [X] [X] 620. [Not Boring Movies](https://leetcode.com/problems/not-boring-movies) - Easy
 - [X] [] 1251. [Average Selling Price](https://leetcode.com/problems/average-selling-price) - Easy
 - [X] [] 1075. [Project Employees I](https://leetcode.com/problems/project-employees-i) - Easy
 - [X] [] 1633. [Percentage of Users Attended a Contest](https://leetcode.com/problems/percentage-of-users-attended-a-contest) - Easy

problems/datafusion.py

@@ -38,7 +38,29 @@ def problem_176(employee: pa.Table) -> datafusion.dataframe.DataFrame:
     return t
 
 
-def problem_1321(customer: pa.Table) -> pa.Table:
+def problem_620(cinema: pa.Table) -> datafusion.dataframe.DataFrame:
+    """Report movies with odd IDs and descriptions not equal to "boring".
+
+    Return the result table ordered by rating in descending order.
+
+    Parameters
+    ----------
+    cinema : pa.Table
+        Table contains information about the name of a movie, genre, and its rating.
+
+    Returns
+    -------
+    pa.Table
+
+    """
+    ctx = datafusion.SessionContext()
+    cinema = ctx.from_arrow(cinema)
+    return cinema.filter(F.col("description") != "boring", F.col("id") % 2 == 1).sort(
+        F.col("id").sort(ascending=False)
+    )
+
+
+def problem_1321(customer: pa.Table) -> datafusion.dataframe.DataFrame:
     """Compute the moving average of how much the customer paid in a seven days window.
 
     You are the restaurant owner and you want to analyze a possible expansion (there

tests/test_datafusion.py

@@ -5,6 +5,7 @@
 
 from problems.datafusion import (
     problem_176,
+    problem_620,
     problem_1321,
     problem_1484,
 )
@@ -41,6 +42,51 @@ def test_problem_176(input_data, expected_data):
     assert result.to_arrow_table().equals(expected_table)
 
 
+@pytest.mark.parametrize(
+    "input_data, expected_data",
+    [
+        pytest.param(
+            {
+                "id": [1, 2, 3, 4],
+                "description": ["interesting", "boring", "exciting", "boring"],
+            },
+            {"id": [3, 1], "description": ["exciting", "interesting"]},
+            id="happy_path_mixed_ids_and_descriptions",
+        ),
+        pytest.param(
+            {"id": [1, 3], "description": ["boring", "boring"]},
+            {"id": [], "description": []},
+            id="edge_case_all_boring",
+        ),
+        pytest.param(
+            {"id": [2, 4], "description": ["interesting", "exciting"]},
+            {"id": [], "description": []},
+            id="edge_case_no_odd_ids",
+        ),
+        pytest.param(
+            {"id": [1], "description": ["interesting"]},
+            {"id": [1], "description": ["interesting"]},
+            id="edge_case_single_row_matching",
+        ),
+        pytest.param(
+            {"id": [2], "description": ["boring"]},
+            {"id": [], "description": []},
+            id="edge_case_single_row_not_matching",
+        ),
+    ],
+)
+def test_problem_620(input_data, expected_data):
+    table = pa.Table.from_pydict(input_data)
+    expected_table = pa.Table.from_pydict(
+        expected_data,
+        schema=pa.schema(
+            [pa.field("id", pa.int64()), pa.field("description", pa.string())]
+        ),
+    )
+    result = problem_620(table)
+    assert result.to_arrow_table().equals(expected_table)
+
+
 @pytest.mark.parametrize(
     "input_data, expected_data",
     [