sqlframe 3.28.0__tar.gz → 3.28.2__tar.gz

{sqlframe-3.28.0 → sqlframe-3.28.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.28.0
+Version: 3.28.2
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.28.0 → sqlframe-3.28.2}/sqlframe/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.28.0'
-__version_tuple__ = version_tuple = (3, 28, 0)
+__version__ = version = '3.28.2'
+__version_tuple__ = version_tuple = (3, 28, 2)

{sqlframe-3.28.0 → sqlframe-3.28.2}/sqlframe/base/dataframe.py

@@ -80,8 +80,6 @@ JOIN_HINTS = {
 }
 
 JOIN_TYPE_MAPPING = {
-    "inner": "inner",
-    "cross": "cross",
     "outer": "full_outer",
     "full": "full_outer",
     "fullouter": "full_outer",
@@ -91,10 +89,8 @@ JOIN_TYPE_MAPPING = {
     "rightouter": "right_outer",
     "semi": "left_semi",
     "leftsemi": "left_semi",
-    "left_semi": "left_semi",
     "anti": "left_anti",
     "leftanti": "left_anti",
-    "left_anti": "left_anti",
 }
 
 DF = t.TypeVar("DF", bound="BaseDataFrame")
@@ -910,6 +906,8 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
 
     @operation(Operation.GROUP_BY)
     def groupBy(self, *cols, **kwargs) -> GROUP_DATA:
+        if cols and isinstance(cols[0], list):
+            cols = cols[0]  # type: ignore
         columns = self._ensure_and_normalize_cols(cols)
         return self._group_data(self, columns, self.last_op)
 
@@ -1026,7 +1024,7 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
     @operation(Operation.FROM)
     def join(
         self,
-        other_df: Self,
+        other: Self,
         on: t.Optional[t.Union[str, t.List[str], Column, t.List[Column]]] = None,
         how: str = "inner",
         **kwargs,
@@ -1042,7 +1040,7 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
             logger.warning("Got cross join with an 'on' value. This will result in an inner join.")
             how = "inner"
 
-        other_df = other_df._convert_leaf_to_cte()
+        other_df = other._convert_leaf_to_cte()
         join_expression = self._add_ctes_to_expression(self.expression, other_df.expression.ctes)
         # We will determine actual "join on" expression later so we don't provide it at first
         join_type = JOIN_TYPE_MAPPING.get(how, how).replace("_", " ")

{sqlframe-3.28.0 → sqlframe-3.28.2}/sqlframe/base/group.py

@@ -47,7 +47,10 @@ class _BaseGroupedData(t.Generic[DF]):
         from sqlframe.base.column import Column
 
         columns = (
-            [Column(f"{agg_func}({column_name})") for column_name, agg_func in exprs[0].items()]
+            [
+                self._get_function_applied_columns(agg_func, (column_name,))[0]
+                for column_name, agg_func in exprs[0].items()
+            ]
             if isinstance(exprs[0], dict)
             else exprs
         )
@@ -55,7 +58,8 @@ class _BaseGroupedData(t.Generic[DF]):
 
         if not self.group_by_cols or not isinstance(self.group_by_cols[0], (list, tuple, set)):
             expression = self._df.expression.group_by(
-                *[x.expression for x in self.group_by_cols]  # type: ignore
+                # User column_expression for group by to avoid alias in group by
+                *[x.column_expression for x in self.group_by_cols]  # type: ignore
             ).select(*[x.expression for x in self.group_by_cols + cols], append=False)  # type: ignore
             group_by_cols = self.group_by_cols
         else:
@@ -66,7 +70,7 @@ class _BaseGroupedData(t.Generic[DF]):
             group_by_cols = []
             for grouping_set in self.group_by_cols:
                 all_grouping_sets.append(
-                    exp.Tuple(expressions=[x.expression for x in grouping_set])  # type: ignore
+                    exp.Tuple(expressions=[x.column_expression for x in grouping_set])  # type: ignore
                 )
                 group_by_cols.extend(grouping_set)  # type: ignore
             group_by_cols = list(dict.fromkeys(group_by_cols))

{sqlframe-3.28.0 → sqlframe-3.28.2}/sqlframe.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.28.0
+Version: 3.28.2
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.28.0 → sqlframe-3.28.2}/tests/integration/test_int_dataframe.py

@@ -431,7 +431,7 @@ def test_join_inner(
 ):
     employee = get_df("employee")
     store = get_df("store")
-    df_joined = pyspark_employee.join(pyspark_store, on=["store_id"], how="inner").select(
+    df_joined = pyspark_employee.join(other=pyspark_store, on=["store_id"], how="inner").select(
         pyspark_employee.employee_id,
         pyspark_employee["fname"],
         F.col("lname"),
@@ -2634,3 +2634,41 @@ def test_rows_between_positive_both_start_end(
     dfs = dfs.withColumn("rolling_price", SF.mean("price").over(swindow))
 
     compare_frames(df, dfs, compare_schema=False)
+
+
+# https://github.com/eakmanrq/sqlframe/issues/356
+def test_array_of_grouping_columns(
+    pyspark_employee: PySparkDataFrame,
+    get_df: t.Callable[[str], BaseDataFrame],
+    compare_frames: t.Callable,
+):
+    df = pyspark_employee.sparkSession.createDataFrame(
+        [(2, "Alice"), (2, "Bob"), (2, "Bob"), (5, "Bob")], schema=["age", "name"]
+    )
+    df = df.groupBy(["name", df.age]).count().sort("name", "age")  # type: ignore
+
+    dfs = get_df("employee").sparkSession.createDataFrame(
+        [(2, "Alice"), (2, "Bob"), (2, "Bob"), (5, "Bob")], schema=["age", "name"]
+    )
+    dfs = dfs.groupBy(["name", dfs.age]).count().sort("name", "age")
+
+    compare_frames(df, dfs, compare_schema=False, sort=True)
+
+
+# https://github.com/eakmanrq/sqlframe/issues/356
+def test_alias_group_by_column(
+    pyspark_employee: PySparkDataFrame,
+    get_df: t.Callable[[str], BaseDataFrame],
+    compare_frames: t.Callable,
+):
+    df = pyspark_employee.sparkSession.createDataFrame(
+        [(2, "Alice"), (2, "Bob"), (2, "Bob"), (5, "Bob")], schema=["age", "name"]
+    )
+    df = df.groupBy(F.col("name").alias("Firstname")).count()
+
+    dfs = get_df("employee").sparkSession.createDataFrame(
+        [(2, "Alice"), (2, "Bob"), (2, "Bob"), (5, "Bob")], schema=["age", "name"]
+    )
+    dfs = dfs.groupBy(SF.col("name").alias("Firstname")).count()
+
+    compare_frames(df, dfs, compare_schema=False, sort=True)

{sqlframe-3.28.0 → sqlframe-3.28.2}/tests/unit/standalone/test_dataframe.py

@@ -156,3 +156,11 @@ def test_unquoted_identifiers(standalone_employee: StandaloneDataFrame):
         standalone_employee.sql(dialect="snowflake", pretty=False, quote_identifiers=False)
         == """SELECT A1.EMPLOYEE_ID AS "employee_id", CAST(A1.FNAME AS TEXT) AS "fname", CAST(A1.LNAME AS TEXT) AS "lname", A1.AGE AS "age", A1.STORE_ID AS "store_id" FROM (VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100)) AS A1(EMPLOYEE_ID, FNAME, LNAME, AGE, STORE_ID)"""
     )
+
+
+# https://github.com/eakmanrq/sqlframe/issues/356
+def test_aliased_dictionary_agg(standalone_employee: StandaloneDataFrame):
+    assert (
+        standalone_employee.groupBy("fname").agg({"age": "avg", "lname": "count"}).sql(pretty=False)
+        == "SELECT CAST(`a1`.`fname` AS STRING) AS `fname`, AVG(`a1`.`age`) AS `avg(age)`, COUNT(CAST(`a1`.`lname` AS STRING)) AS `count(lname)` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`) GROUP BY CAST(`a1`.`fname` AS STRING)"
+    )