sqlframe 3.13.0__tar.gz → 3.13.1__tar.gz

{sqlframe-3.13.0 → sqlframe-3.13.1}/PKG-INFO

@@ -1,12 +1,11 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.13.0
+Version: 3.13.1
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
 Author-email: eakmanrq@gmail.com
 License: MIT
-Platform: UNKNOWN
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -192,5 +191,3 @@ LIMIT 5
 | 1975 |          868,985          |     10.92      |
 +------+---------------------------+----------------+
 ```
-
-

{sqlframe-3.13.0 → sqlframe-3.13.1}/docs/spark.md

@@ -8,13 +8,7 @@ pip install "sqlframe[spark]"
 
 ## Enabling SQLFrame
 
-SQLFrame can be used in two ways:
-
-* Directly importing the `sqlframe.spark` package 
-* Using the [activate](./configuration.md#activating-sqlframe) function to allow for continuing to use `pyspark.sql` but have it use SQLFrame behind the scenes.
-
-### Import
-
+SQLFrame can be enabled by directly importing the `sqlframe.spark` package.
 If converting a PySpark pipeline, all `pyspark.sql` should be replaced with `sqlframe.spark`.
 In addition, many classes will have a `Spark` prefix. 
 For example, `SparkDataFrame` instead of `DataFrame`.
@@ -30,58 +24,18 @@ from sqlframe.spark import functions as F
 from sqlframe.spark import SparkDataFrame
 ```
 
-### Activate
-
-If you would like to continue using `pyspark.sql` but have it use SQLFrame behind the scenes, you can use the [activate](./configuration.md#activating-sqlframe) function.
-
-```python
-from sqlframe import activate
-activate("spark")
-
-from pyspark.sql import SparkSession
-```
-
 ## Creating a Session
 
 SQLFrame's SparkSession is created the same way you would normally create a SparkSession.
 The configuration you apply to the builder will be applied the the SparkSession that SQLFrame will create.
 
-=== "Import"
-
-    ```python
-    from sqlframe.spark import SparkSession
-    
-    spark = SparkSession.builder.appName("MyApp").getOrCreate()
-    
-    # Now you can use SQLFrame
-    ```
-
-=== "Activate + Without Providing SparkSession"
-
-    ```python
-    from sqlframe import activate
-    activate("spark")
-    
-    from pyspark.sql import SparkSession
-    
-    spark = SparkSession.builder.appName("MyApp").getOrCreate()
-    
-    # Now you can use SQLFrame
-    ```
-
-=== "Activate + Providing SparkSession"
-
-    ```python
-    from pyspark.sql import SparkSession
-    from sqlframe import activate
-    activate("spark", conn=SparkSession.builder.appName("MyApp").getOrCreate())
-    
-    from pyspark.sql import SparkSession
-    
-    spark = SparkSession.getOrCreate()
-    
-    # Now you can use SQLFrame
-    ```
+```python
+from sqlframe.spark import SparkSession
+
+spark = SparkSession.builder.appName("MyApp").getOrCreate()
+
+# Now you can use SQLFrame
+```
 
 ## Example Usage
 

{sqlframe-3.13.0 → sqlframe-3.13.1}/setup.py

@@ -43,7 +43,7 @@ setup(
             "pytest-postgresql>=6,<7",
             "pytest-xdist>=3.6,<3.7",
             "pre-commit>=3.7,<5",
-            "ruff>=0.4.4,<0.9",
+            "ruff>=0.4.4,<0.10",
             "types-psycopg2>=2.9,<3",
         ],
         "docs": [

{sqlframe-3.13.0 → sqlframe-3.13.1}/sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.13.0'
-__version_tuple__ = version_tuple = (3, 13, 0)
+__version__ = version = '3.13.1'
+__version_tuple__ = version_tuple = (3, 13, 1)

{sqlframe-3.13.0 → sqlframe-3.13.1}/sqlframe/base/dataframe.py

@@ -806,6 +806,8 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
             )
         else:
             col = self._ensure_and_normalize_col(column)
+        if isinstance(col.expression, exp.Alias):
+            col.expression = col.expression.this
         return self.copy(expression=self.expression.where(col.expression))
 
     filter = where
@@ -1018,9 +1020,9 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         elif not isinstance(ascending, list):
             ascending = [ascending] * len(columns)
         ascending = [bool(x) for i, x in enumerate(ascending)]
-        assert len(columns) == len(
-            ascending
-        ), "The length of items in ascending must equal the number of columns provided"
+        assert len(columns) == len(ascending), (
+            "The length of items in ascending must equal the number of columns provided"
+        )
         col_and_ascending = list(zip(columns, ascending))
         order_by_columns = [
             (
@@ -1282,9 +1284,9 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
             new_values = list(to_replace.values())
         elif not old_values and isinstance(to_replace, list):
             assert isinstance(value, list), "value must be a list since the replacements are a list"
-            assert len(to_replace) == len(
-                value
-            ), "the replacements and values must be the same length"
+            assert len(to_replace) == len(value), (
+                "the replacements and values must be the same length"
+            )
             old_values = to_replace
             new_values = value
         else:

{sqlframe-3.13.0 → sqlframe-3.13.1}/sqlframe.egg-info/PKG-INFO

@@ -1,12 +1,11 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.13.0
+Version: 3.13.1
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
 Author-email: eakmanrq@gmail.com
 License: MIT
-Platform: UNKNOWN
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -192,5 +191,3 @@ LIMIT 5
 | 1975 |          868,985          |     10.92      |
 +------+---------------------------+----------------+
 ```
-
-

{sqlframe-3.13.0 → sqlframe-3.13.1}/sqlframe.egg-info/requires.txt

@@ -24,7 +24,7 @@ pytest-forked
 pytest-postgresql<7,>=6
 pytest-xdist<3.7,>=3.6
 pytest<8.4,>=8.2.0
-ruff<0.9,>=0.4.4
+ruff<0.10,>=0.4.4
 types-psycopg2<3,>=2.9
 
 [docs]

{sqlframe-3.13.0 → sqlframe-3.13.1}/tests/integration/test_int_dataframe.py

@@ -2278,3 +2278,17 @@ def test_self_join(
     )
 
     compare_frames(df_joined, dfs_joined, compare_schema=False)
+
+
+# https://github.com/eakmanrq/sqlframe/issues/232
+def test_filter_alias(
+    pyspark_employee: PySparkDataFrame,
+    get_df: t.Callable[[str], BaseDataFrame],
+    compare_frames: t.Callable,
+):
+    df_filtered = pyspark_employee.where((F.col("age") > 40).alias("age_gt_40"))
+
+    employee = get_df("employee")
+    dfs_filtered = employee.where((SF.col("age") > 40).alias("age_gt_40"))
+
+    compare_frames(df_filtered, dfs_filtered, compare_schema=False)