sqlframe 3.13.0__py3-none-any.whl → 3.13.2__py3-none-any.whl

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 = '3.13.2'
+__version_tuple__ = version_tuple = (3, 13, 2)

sqlframe/base/dataframe.py

@@ -202,6 +202,7 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
     _na: t.Type[NA]
     _stat: t.Type[STAT]
     _group_data: t.Type[GROUP_DATA]
+    _EXPLAIN_PREFIX = "EXPLAIN"
 
     def __init__(
         self,
@@ -806,6 +807,8 @@ 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 +1021,9 @@ 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 = [
             (
@@ -1142,6 +1145,18 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         final_df = filtered_df.select(*all_columns)
         return final_df
 
+    def _get_explain_plan_rows(self) -> t.List[Row]:
+        sql_queries = self.sql(
+            pretty=False, optimize=False, as_list=True, dialect=self.session.execution_dialect
+        )
+        if len(sql_queries) > 1:
+            raise ValueError("Cannot explain a DataFrame with multiple queries")
+        sql_query = " ".join([self._EXPLAIN_PREFIX, sql_queries[0]])
+        results = self.session._collect(sql_query)
+        if len(results) != 1:
+            raise ValueError("Got more than one result from explain query")
+        return results
+
     def explain(
         self, extended: t.Optional[t.Union[bool, str]] = None, mode: t.Optional[str] = None
     ) -> None:
@@ -1210,11 +1225,8 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         ...Statistics...
         ...
         """
-        sql_queries = self.sql(pretty=False, optimize=False, as_list=True)
-        if len(sql_queries) > 1:
-            raise ValueError("Cannot explain a DataFrame with multiple queries")
-        sql_query = "EXPLAIN " + sql_queries[0]
-        self.session._execute(sql_query)
+        results = self._get_explain_plan_rows()
+        print(results[0][0])
 
     @operation(Operation.FROM)
     def fillna(
@@ -1282,9 +1294,9 @@ 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/bigquery/dataframe.py

@@ -72,3 +72,8 @@ class BigQueryDataFrame(
         sql = self.session._to_sql(self.expression)
         query_job = self.session._client.query(sql, job_config=job_config)
         return [field_to_column(field) for field in query_job.schema]
+
+    def explain(
+        self, extended: t.Optional[t.Union[bool, str]] = None, mode: t.Optional[str] = None
+    ) -> None:
+        raise NotImplementedError("BigQuery does not support EXPLAIN")

sqlframe/duckdb/dataframe.py

@@ -46,6 +46,12 @@ class DuckDBDataFrame(
     _stat = DuckDBDataFrameStatFunctions
     _group_data = DuckDBGroupedData
 
+    def explain(
+        self, extended: t.Optional[t.Union[bool, str]] = None, mode: t.Optional[str] = None
+    ) -> None:
+        results = self._get_explain_plan_rows()
+        print(results[0][1])
+
     @t.overload
     def toArrow(self) -> ArrowTable: ...
 

sqlframe/snowflake/dataframe.py

@@ -43,6 +43,7 @@ class SnowflakeDataFrame(
     _na = SnowflakeDataFrameNaFunctions
     _stat = SnowflakeDataFrameStatFunctions
     _group_data = SnowflakeGroupedData
+    _EXPLAIN_PREFIX = "EXPLAIN USING TEXT"
 
     @property
     def _typed_columns(self) -> t.List[CatalogColumn]:

{sqlframe-3.13.0.dist-info → sqlframe-3.13.2.dist-info}/METADATA

@@ -1,12 +1,11 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.13.0
+Version: 3.13.2
 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
@@ -17,52 +16,52 @@ Classifier: Programming Language :: Python :: 3 :: Only
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: prettytable (<4)
-Requires-Dist: sqlglot (<26.1,>=24.0.0)
+Requires-Dist: prettytable <4
+Requires-Dist: sqlglot <26.3,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
-Requires-Dist: google-cloud-bigquery-storage (<3,>=2) ; extra == 'bigquery'
-Requires-Dist: google-cloud-bigquery[pandas] (<4,>=3) ; extra == 'bigquery'
+Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'
+Requires-Dist: google-cloud-bigquery[pandas] <4,>=3 ; extra == 'bigquery'
 Provides-Extra: databricks
-Requires-Dist: databricks-sql-connector (<4,>=3.6) ; extra == 'databricks'
+Requires-Dist: databricks-sql-connector <4,>=3.6 ; extra == 'databricks'
 Provides-Extra: dev
-Requires-Dist: duckdb (<1.2,>=0.9) ; extra == 'dev'
-Requires-Dist: findspark (<3,>=2) ; extra == 'dev'
-Requires-Dist: mypy (<1.15,>=1.10.0) ; extra == 'dev'
-Requires-Dist: openai (<2,>=1.30) ; extra == 'dev'
-Requires-Dist: pandas-stubs (<3,>=2) ; extra == 'dev'
-Requires-Dist: pandas (<3,>=2) ; extra == 'dev'
-Requires-Dist: pre-commit (<5,>=3.7) ; extra == 'dev'
-Requires-Dist: psycopg (<4,>=3.1) ; extra == 'dev'
-Requires-Dist: pyarrow (<19,>=10) ; extra == 'dev'
-Requires-Dist: pyspark (<3.6,>=2) ; extra == 'dev'
+Requires-Dist: duckdb <1.2,>=0.9 ; extra == 'dev'
+Requires-Dist: findspark <3,>=2 ; extra == 'dev'
+Requires-Dist: mypy <1.15,>=1.10.0 ; extra == 'dev'
+Requires-Dist: openai <2,>=1.30 ; extra == 'dev'
+Requires-Dist: pandas-stubs <3,>=2 ; extra == 'dev'
+Requires-Dist: pandas <3,>=2 ; extra == 'dev'
+Requires-Dist: pre-commit <5,>=3.7 ; extra == 'dev'
+Requires-Dist: psycopg <4,>=3.1 ; extra == 'dev'
+Requires-Dist: pyarrow <20,>=10 ; extra == 'dev'
+Requires-Dist: pyspark <3.6,>=2 ; extra == 'dev'
 Requires-Dist: pytest-forked ; extra == 'dev'
-Requires-Dist: pytest-postgresql (<7,>=6) ; extra == 'dev'
-Requires-Dist: pytest-xdist (<3.7,>=3.6) ; extra == 'dev'
-Requires-Dist: pytest (<8.4,>=8.2.0) ; extra == 'dev'
-Requires-Dist: ruff (<0.9,>=0.4.4) ; extra == 'dev'
-Requires-Dist: types-psycopg2 (<3,>=2.9) ; extra == 'dev'
+Requires-Dist: pytest-postgresql <7,>=6 ; extra == 'dev'
+Requires-Dist: pytest-xdist <3.7,>=3.6 ; extra == 'dev'
+Requires-Dist: pytest <8.4,>=8.2.0 ; extra == 'dev'
+Requires-Dist: ruff <0.10,>=0.4.4 ; extra == 'dev'
+Requires-Dist: types-psycopg2 <3,>=2.9 ; extra == 'dev'
 Provides-Extra: docs
-Requires-Dist: mkdocs-include-markdown-plugin (==6.0.6) ; extra == 'docs'
-Requires-Dist: mkdocs-material-extensions (==1.1.1) ; extra == 'docs'
-Requires-Dist: mkdocs-material (==9.0.5) ; extra == 'docs'
-Requires-Dist: mkdocs (==1.4.2) ; extra == 'docs'
+Requires-Dist: mkdocs-include-markdown-plugin ==6.0.6 ; extra == 'docs'
+Requires-Dist: mkdocs-material-extensions ==1.1.1 ; extra == 'docs'
+Requires-Dist: mkdocs-material ==9.0.5 ; extra == 'docs'
+Requires-Dist: mkdocs ==1.4.2 ; extra == 'docs'
 Requires-Dist: pymdown-extensions ; extra == 'docs'
 Provides-Extra: duckdb
-Requires-Dist: duckdb (<1.2,>=0.9) ; extra == 'duckdb'
-Requires-Dist: pandas (<3,>=2) ; extra == 'duckdb'
+Requires-Dist: duckdb <1.2,>=0.9 ; extra == 'duckdb'
+Requires-Dist: pandas <3,>=2 ; extra == 'duckdb'
 Provides-Extra: openai
-Requires-Dist: openai (<2,>=1.30) ; extra == 'openai'
+Requires-Dist: openai <2,>=1.30 ; extra == 'openai'
 Provides-Extra: pandas
-Requires-Dist: pandas (<3,>=2) ; extra == 'pandas'
+Requires-Dist: pandas <3,>=2 ; extra == 'pandas'
 Provides-Extra: postgres
-Requires-Dist: psycopg2 (<3,>=2.8) ; extra == 'postgres'
+Requires-Dist: psycopg2 <3,>=2.8 ; extra == 'postgres'
 Provides-Extra: redshift
-Requires-Dist: redshift-connector (<2.2.0,>=2.1.1) ; extra == 'redshift'
+Requires-Dist: redshift-connector <2.2.0,>=2.1.1 ; extra == 'redshift'
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python[secure-local-storage] (<3.13,>=3.10.0) ; extra == 'snowflake'
+Requires-Dist: snowflake-connector-python[secure-local-storage] <3.13,>=3.10.0 ; extra == 'snowflake'
 Provides-Extra: spark
-Requires-Dist: pyspark (<3.6,>=2) ; extra == 'spark'
+Requires-Dist: pyspark <3.6,>=2 ; extra == 'spark'
 
 <div align="center">
   <img src="https://sqlframe.readthedocs.io/en/stable/docs/images/sqlframe_logo.png" alt="SQLFrame Logo" width="400"/>
@@ -227,5 +226,3 @@ LIMIT 5
 | 1975 |          868,985          |     10.92      |
 +------+---------------------------+----------------+
 ```
-
-

{sqlframe-3.13.0.dist-info → sqlframe-3.13.2.dist-info}/RECORD

@@ -1,10 +1,10 @@
 sqlframe/__init__.py,sha256=wfqm98eLoLid9oV_FzzpG5loKC6LxOhj2lXpfN7SARo,3138
-sqlframe/_version.py,sha256=3fJaN4m_eO3OOhIj24x2tSFiMOpH1Uw0GgL-P7s9_M0,413
+sqlframe/_version.py,sha256=efGc9qGpdvsN2KEWLmdYgdokJecNkK44Rg-Lf6L0IvM,413
 sqlframe/base/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlframe/base/_typing.py,sha256=b2clI5HI1zEZKB_3Msx3FeAJQyft44ubUifJwQRVXyQ,1298
 sqlframe/base/catalog.py,sha256=SzFQalTWdhWzxUY-4ut1f9TfOECp_JmJEgNPfrRKCe0,38457
 sqlframe/base/column.py,sha256=wRghgieYAA51aw4WuFQWOvl0TFOToZbBhBuIamEzxx4,18011
-sqlframe/base/dataframe.py,sha256=c27sJq8kb0AHBGwJJyDofayw58sOdJMePktpjqB2gJk,74452
+sqlframe/base/dataframe.py,sha256=bnF8SYIDhSFPYKchGakRG_oWqgZ-66jKZsdcqUSqCDE,74940
 sqlframe/base/decorators.py,sha256=P56cgs8DANxGRIwVs5uOMnDy-BlXZZYMbf4fdnkpWPI,1889
 sqlframe/base/exceptions.py,sha256=9Uwvqn2eAkDpqm4BrRgbL61qM-GMCbJEMAW8otxO46s,370
 sqlframe/base/function_alternatives.py,sha256=8kDCh1cOXtdCcBPYBQ8byXxRAZvphS9N8GDs4txBzGg,52544
@@ -26,7 +26,7 @@ sqlframe/base/mixins/readwriter_mixins.py,sha256=ap8j_g7PoUGHaHKCPMnRPbXofOsUhUz
 sqlframe/bigquery/__init__.py,sha256=kbaomhYAANPdxeDQhajv8IHfMg_ENKivtYK-rPwaV08,939
 sqlframe/bigquery/catalog.py,sha256=8d36IzT5GPWd1FdxJ9vEljOdbIDepHnFOBjwP0bX6FE,11625
 sqlframe/bigquery/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
-sqlframe/bigquery/dataframe.py,sha256=O7qkwVRuuyqdesfwjXLBMgScQqUugPIYklboQ2vgRyE,2403
+sqlframe/bigquery/dataframe.py,sha256=2qlnwTOpfpHQxr9MCxeZWxKiQoL6txEgGNE8JQsalUQ,2599
 sqlframe/bigquery/functions.py,sha256=MYLs6-sXXqe5o6ghJHHtEpFJlYMeyKzx9-rT3wwXlc4,426
 sqlframe/bigquery/functions.pyi,sha256=KXgV46eZFNIXwXIhPuSJ08BG18iLQzDCQjyI3REBEXg,11925
 sqlframe/bigquery/group.py,sha256=UVBNBRTo8OqS-_cS5YwvTeJYgYxeG-d6R3kfyHmlFqw,391
@@ -50,7 +50,7 @@ sqlframe/databricks/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0
 sqlframe/duckdb/__init__.py,sha256=KAw_uZEhFMwi3D9Wj6AgHAKqLNk-EAx2uDIYu56oL44,872
 sqlframe/duckdb/catalog.py,sha256=YYYVmetLUaJOdObKw4AJ7L0P-msshkta4xHlcZQ9zEA,4795
 sqlframe/duckdb/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
-sqlframe/duckdb/dataframe.py,sha256=OgU4zySAKqz7XhwOhNJuUkwkflU67UvyqV3IbvaFVo4,1706
+sqlframe/duckdb/dataframe.py,sha256=Z8_K69UQGZVeBfVGXVwIJP8OMuIvNBB3DPKTP3Lfu4w,1908
 sqlframe/duckdb/functions.py,sha256=ix2efGGD4HLaY1rtCtEd3IrsicGEVGiBAeKOo5OD8rA,424
 sqlframe/duckdb/functions.pyi,sha256=P0ky6k-J7LdCDrQ0OjfRC3ARIYNHPmAmmaB_jBEO5L0,12383
 sqlframe/duckdb/group.py,sha256=IkhbW42Ng1U5YT3FkIdiB4zBqRkW4QyTb-1detY1e_4,383
@@ -85,7 +85,7 @@ sqlframe/redshift/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,3
 sqlframe/snowflake/__init__.py,sha256=msYAxOnPyjuBSTbpb5s9P5o0pr2N82UUGPxUtv0TNNw,966
 sqlframe/snowflake/catalog.py,sha256=Tp_B9oMTInnqLTiZNsT0UNc-a-aKXu3zFThlCwLeKCA,6507
 sqlframe/snowflake/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
-sqlframe/snowflake/dataframe.py,sha256=X3FOasXh12OPFGF5-YYy1ThxIEdDwqc1xf3hdmuViN0,2142
+sqlframe/snowflake/dataframe.py,sha256=TosBO9tnnqAQ9Y-abX954vQM8VBLYRmN_P50iusMFgQ,2185
 sqlframe/snowflake/functions.py,sha256=g3ELesLGvN7tyRyiEAnPneVyL0rQhSSOxYFvBFuOiaM,391
 sqlframe/snowflake/functions.pyi,sha256=sEqNdyqQBtgqoKtRViUb70QT5yrvpVoP3ZN7VxHNxbw,12612
 sqlframe/snowflake/group.py,sha256=pPP1l2RRo_LgkXrji8a87n2PKo-63ZRPT-WUtvVcBME,395
@@ -119,8 +119,8 @@ sqlframe/standalone/udf.py,sha256=azmgtUjHNIPs0WMVNId05SHwiYn41MKVBhKXsQJ5dmY,27
 sqlframe/standalone/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,35
 sqlframe/testing/__init__.py,sha256=VVCosQhitU74A3NnE52O4mNtGZONapuEXcc20QmSlnQ,132
 sqlframe/testing/utils.py,sha256=PFsGZpwNUE_4-g_f43_vstTqsK0AQ2lBneb5Eb6NkFo,13008
-sqlframe-3.13.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.13.0.dist-info/METADATA,sha256=ojHxGxwoZc-kduIGwSOuWHIMGtAqea0IKU6LXSNwdkM,9053
-sqlframe-3.13.0.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
-sqlframe-3.13.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.13.0.dist-info/RECORD,,
+sqlframe-3.13.2.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.13.2.dist-info/METADATA,sha256=QHITWgwWxHNUam2uSDUcpJq6Y9zCJQPxQ-EN7YtvBtg,8970
+sqlframe-3.13.2.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.13.2.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.13.2.dist-info/RECORD,,

{sqlframe-3.13.0.dist-info → sqlframe-3.13.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.37.1)
+Generator: bdist_wheel (0.42.0)
 Root-Is-Purelib: true
 Tag: py3-none-any