sqlframe 1.4.0__tar.gz → 1.5.0__tar.gz

{sqlframe-1.4.0 → sqlframe-1.5.0}/Makefile

@@ -29,6 +29,7 @@ stubs:
 	stubgen sqlframe/bigquery/functions.py --output ./ --inspect-mode
 	stubgen sqlframe/duckdb/functions.py --output ./ --inspect-mode
 	stubgen sqlframe/postgres/functions.py --output ./ --inspect-mode
+	stubgen sqlframe/snowflake/functions.py --output ./ --inspect-mode
 
 package:
 	pip3 install wheel && python3 setup.py sdist bdist_wheel

{sqlframe-1.4.0 → sqlframe-1.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 1.4.0
+Version: 1.5.0
 Summary: Taking the Spark out of PySpark by converting to SQL
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-1.4.0 → sqlframe-1.5.0}/docs/bigquery.md

@@ -385,7 +385,6 @@ print(session.catalog.listColumns(table_path))
 * [soundex](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.soundex.html)
 * [split](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.split.html)
     * Regular expressions not supported
-* [sqlglot_expression](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sqlglot_expression.html)
 * [sqrt](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sqrt.html)
 * [stddev](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.stddev.html)
 * [stddev_pop](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.stddev_pop.html)

sqlframe-1.5.0/docs/snowflake.md

@@ -0,0 +1,492 @@
+# BigQuery
+
+## Installation
+
+```bash
+pip install "sqlframe[snowflake]"
+```
+
+## Creating a Session
+
+SQLFrame uses the [Snowflake Python Connector](https://docs.snowflake.com/en/developer-guide/python-connector/python-connector) to connect to Snowflake. 
+A SnowflakeQuerySession, which implements the PySpark Session API, can be created by passing in a `snowflake.connector.connection.SnowflakeConnection` object.
+
+```python
+import os
+
+from snowflake.connector import connect
+from sqlframe.snowflake import SnowflakeSession
+from sqlframe.snowflake import functions as F
+
+connection = connect(
+    account=os.environ["SNOWFLAKE_ACCOUNT"],
+    user=os.environ["SNOWFLAKE_USER"],
+    password=os.environ["SNOWFLAKE_PASSWORD"],
+    warehouse=os.environ["SNOWFLAKE_WAREHOUSE"],
+    database=os.environ["SNOWFLAKE_DATABASE"],
+    schema=os.environ["SNOWFLAKE_SCHEMA"],
+)
+session = SnowflakeSession(conn=connection)
+```
+
+## Imports
+
+If converting a PySpark pipeline, all `pyspark.sql` should be replaced with `sqlframe.snowflake`.
+In addition, many classes will have a `Snowflake` prefix. 
+For example, `SnowflakeDataFrame` instead of `DataFrame`.
+
+
+```python
+# PySpark import
+# from pyspark.sql import SparkSession
+# from pyspark.sql import functions as F
+# from pyspark.sql.dataframe import DataFrame
+# SQLFrame import
+from sqlframe.snowflake import SnowflakeSession
+from sqlframe.snowflake import functions as F
+from sqlframe.snowflake import SnowflakeDataFrame
+```
+
+
+## Example Usage
+
+```python
+import os
+
+from snowflake.connector import connect
+from sqlframe.snowflake import SnowflakeSession
+from sqlframe.snowflake import functions as F
+
+connection = connect(
+    account=os.environ["SQLFRAME_SNOWFLAKE_ACCOUNT"],
+    user=os.environ["SQLFRAME_SNOWFLAKE_USER"],
+    password=os.environ["SQLFRAME_SNOWFLAKE_PASSWORD"],
+    warehouse=os.environ["SQLFRAME_SNOWFLAKE_WAREHOUSE"],
+    # Dataset: https://app.snowflake.com/marketplace/listing/GZ1M6ZVQIAF/insights-global-covid-statistics
+    database="GLOBAL_COVID_STATISTICS",
+    schema=os.environ["SQLFRAME_SNOWFLAKE_SCHEMA"],
+)
+
+session = SnowflakeSession(conn=connection)
+df = (
+    session.table("INSIGHTS.COVID19_METRICS_BY_COUNTRY")
+    .where(F.col("date").between("2021-01-01", "2021-12-31"))
+    .groupby("continent", "country")
+    .agg(
+        F.sum("total_case").alias("total_cases"),
+        F.sum("total_deaths").alias("total_deaths"),
+        (F.sum("total_deaths").cast("float") / F.nullif(F.sum("total_case"), F.lit(0))).alias("death_rate"),
+    )
+    .orderBy(F.col("death_rate").desc_nulls_last())
+)
+df.show(5)
+"""
++---------------+---------+-------------+--------------+---------------+
+|   CONTINENT   | COUNTRY | TOTAL_CASES | TOTAL_DEATHS |   DEATH_RATE  |
++---------------+---------+-------------+--------------+---------------+
+|      Asia     |  Yemen  |   2372121   |    475483    |  0.2004463516 |
+| South America |   Peru  |  675530177  |   62217492   | 0.09210172116 |
+| North America |  Mexico |  1039445357 |   89674958   | 0.08627193089 |
+|     Africa    |  Sudan  |   13109385  |    929258    | 0.07088494235 |
+|      Asia     |  Syria  |   9963515   |    654570    | 0.06569669439 |
++---------------+---------+-------------+--------------+---------------+
+"""
+```
+
+## Supported PySpark API Methods
+
+### Catalog Class
+
+* add_table
+    * SQLFrame Specific: Adds a table to known schemas that SQLFrame tracks
+* [currentCatalog](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.currentCatalog.html)
+* [currentDatabase](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.currentDatabase.html)
+* [databaseExists](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.databaseExists.html)
+* [functionExists](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.functionExists.html)
+* [getDatabase](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.getDatabase.html)
+* [getFunction](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.getFunction.html)
+* [getTable](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.getTable.html)
+* get_columns
+    * SQLFrame Specific: Similar to `listColumns` but returns SQLGlot expressions instead
+* get_columns_from_schema
+    * SQLFrame Specific: Gets the columns from the known schemas to SQLFrame
+* [listCatalogs](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.listCatalogs.html)
+* [listColumns](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.listColumns.html)
+* [listDatabases](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.listDatabases.html)
+* [listFunctions](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.listFunctions.html)
+* [listTables](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.listTables.html)
+* [setCurrentCatalog](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.setCurrentCatalog.html)
+* [setCurrentDatabase](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.setCurrentDatabase.html)
+* [tableExists](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Catalog.tableExists.html)
+
+### Column Class
+
+* [alias](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.alias.html)
+* [alias](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.alias.html)
+* [asc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.asc.html)
+* [asc_nulls_first](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.asc_nulls_first.html)
+* [asc_nulls_last](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.asc_nulls_last.html)
+* [between](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.between.html)
+* [cast](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.cast.html)
+* [desc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.desc.html)
+* [desc_nulls_first](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.desc_nulls_first.html)
+* [desc_nulls_last](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.desc_nulls_last.html)
+* [endswith](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.endswith.html)
+* [ilike](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.ilike.html)
+* [isNotNull](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.isNotNull.html)
+* [isNull](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.isNull.html)
+* [isin](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.isin.html)
+* [like](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.like.html)
+* [otherwise](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.otherwise.html)
+* [over](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.over.html)
+* [rlike](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.rlike.html)
+* sql 
+    * SQLFrame Specific: Get the SQL representation of a given column
+* [startswith](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.startswith.html)
+* [substr](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.substr.html)
+* [when](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Column.when.html)
+
+### DataFrame Class
+
+* [agg](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.agg.html)
+* [alias](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.alias.html)
+* [approxQuantile](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.approxQuantile.html)
+* [cache](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.cache.html)
+* [coalesce](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.coalesce.html)
+* [collect](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.collect.html)
+* [columns](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.columns.html)
+* [copy](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.copy.html)
+* [corr](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.corr.html)
+* [count](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.count.html)
+* [cov](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.cov.html)
+* [createOrReplaceTempView](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.createOrReplaceTempView.html)
+* [crossJoin](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.crossJoin.html)
+* [cube](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.cube.html)
+* [distinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.distinct.html)
+* [drop](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.drop.html)
+* [dropDuplicates](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.dropDuplicates.html)
+* [drop_duplicates](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.drop_duplicates.html)
+* [dropna](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.dropna.html)
+* [exceptAll](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.exceptAll.html)
+* [explain](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.explain.html)
+* [fillna](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.fillna.html)
+* [filter](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.filter.html)
+* [first](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.first.html)
+* [groupBy](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.groupBy.html)
+* [groupby](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.groupby.html)
+* [head](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.head.html)
+* [intersect](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.intersect.html)
+* [intersectAll](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.intersectAll.html)
+* [join](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.join.html)
+* [limit](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.limit.html)
+* [na](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.na.html)
+* [orderBy](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.orderBy.html)
+* [persist](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.persist.html)
+* [replace](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.replace.html)
+* [select](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.select.html)
+* [show](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.show.html)
+    * Vertical Argument is not Supported
+* [sort](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.sort.html)
+* sql
+    * SQLFrame Specific: Get the SQL representation of a given DataFrame
+* [stat](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.stat.html)
+* [toDF](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.toDF.html)
+* [toPandas](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.toPandas.html)
+* [union](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.union.html)
+* [unionAll](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.unionAll.html)
+* [unionByName](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.unionByName.html)
+* [where](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.where.html)
+* [withColumn](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.withColumn.html)
+* [withColumnRenamed](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.withColumnRenamed.html)
+* [write](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.write.html)
+
+### Functions
+
+* [abs](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.abs.html)
+* [acos](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.acos.html)
+* [acosh](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.acosh.html)
+* [add_months](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.add_months.html)
+* [approxCountDistinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.approxCountDistinct.html)
+* [approx_count_distinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.approx_count_distinct.html)
+* [array](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array.html)
+* [array_contains](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_contains.html)
+* [array_distinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_distinct.html)
+* [array_except](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_except.html)
+* [array_intersect](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_intersect.html)
+* [array_join](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_join.html)
+  * Null values are repsented as nothing instead of NULL. Ex: "a," instead of "a,NULL"
+* [array_max](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_max.html)
+* [array_min](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_min.html)
+* [array_position](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_position.html)
+* [array_remove](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_remove.html)
+* [array_sort](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_sort.html)
+* [array_union](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_union.html)
+* [arrays_overlap](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.arrays_overlap.html)
+* [asc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.asc.html)
+* [asc_nulls_first](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.asc_nulls_first.html)
+* [asc_nulls_last](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.asc_nulls_last.html)
+* [ascii](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.ascii.html)
+* [asin](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.asin.html)
+* [asinh](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.asinh.html)
+* [atan](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.atan.html)
+* [atan2](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.atan2.html)
+* [atanh](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.atanh.html)
+* [avg](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.avg.html)
+* [base64](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.base64.html)
+* [bit_length](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.bit_length.html)
+* [bitwiseNOT](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.bitwiseNOT.html)
+* [bitwise_not](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.bitwise_not.html)
+* [bround](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.bround.html)
+  * [Input must be a fixed-point nnumber](https://docs.snowflake.com/en/sql-reference/data-types-numeric.html#label-data-types-for-fixed-point-numbers)
+* [cbrt](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.cbrt.html)
+* [ceil](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.ceil.html)
+* [ceiling](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.ceiling.html)
+* [coalesce](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.coalesce.html)
+* [col](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.col.html)
+* [collect_list](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.collect_list.html)
+* [collect_set](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.collect_set.html)
+* [concat](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.concat.html)
+  * Can only concat strings not arrays
+* [concat_ws](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.concat_ws.html)
+* [corr](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.corr.html)
+* [cos](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.cos.html)
+* [cosh](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.cosh.html)
+* [cot](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.cot.html)
+* [count](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.count.html)
+* [countDistinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.countDistinct.html)
+* [count_distinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.count_distinct.html)
+* [covar_pop](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.covar_pop.html)
+* [covar_samp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.covar_samp.html)
+* [create_map](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.create_map.html)
+  * Assumes VARCHAR datatype for key/value unless the column is explicitly casted when calling `create_map`
+* [cume_dist](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.cume_dist.html)
+* [current_date](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.current_date.html)
+* [current_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.current_timestamp.html)
+* [date_add](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.date_add.html)
+* [date_diff](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.date_diff.html)
+* [date_format](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.date_format.html)
+  * [The format string should be in Snowflake syntax](https://docs.snowflake.com/en/sql-reference/functions-conversion#label-date-time-format-conversion)
+* [date_sub](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.date_sub.html)
+* [date_trunc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.date_trunc.html)
+* [dayofmonth](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.dayofmonth.html)
+* [dayofweek](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.dayofweek.html)
+* [dayofyear](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.dayofyear.html)
+* [degrees](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.degrees.html)
+* [dense_rank](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.dense_rank.html)
+* [desc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.desc.html)
+* [desc_nulls_first](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.desc_nulls_first.html)
+* [desc_nulls_last](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.desc_nulls_last.html)
+* [e](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.e.html)
+* [element_at](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.element_at.html)
+* [exp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.exp.html)
+* [explode](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.explode.html)
+* [expm1](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.expm1.html)
+* [expr](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.expr.html)
+* [factorial](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.factorial.html)
+* [flatten](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.flatten.html)
+* [floor](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.floor.html)
+* [format_number](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.format_number.html)
+* [from_unixtime](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.from_unixtime.html)
+* [greatest](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.greatest.html)
+* [grouping_id](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.grouping_id.html)
+* [hash](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.hash.html)
+  * The hash is calculated differently
+* [hex](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.hex.html)
+  * Hex on int does not produce the same result as Spark. Need to research why.
+* [hour](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.hour.html)
+* [initcap](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.initcap.html)
+* [input_file_name](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.input_file_name.html)
+* [inspect](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.inspect.html)
+* [instr](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.instr.html)
+* [isnan](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.isnan.html)
+* [isnull](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.isnull.html)
+* [kurtosis](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.kurtosis.html)
+* [lag](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.lag.html)
+* [last_day](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.last_day.html)
+* [lead](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.lead.html)
+* [least](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.least.html)
+* [length](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.length.html)
+* [levenshtein](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.levenshtein.html)
+  * threshold is not supported
+* [lit](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.lit.html)
+* [locate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.locate.html)
+* [log](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.log.html)
+* [log10](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.log10.html)
+* [log1p](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.log1p.html)
+* [log2](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.log2.html)
+* [lower](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.lower.html)
+* [lpad](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.lpad.html)
+* [ltrim](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.ltrim.html)
+* [make_date](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.make_date.html)
+* [map_concat](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.map_concat.html)
+* [map_keys](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.map_keys.html)
+* [max](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.max.html)
+* [max_by](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.max_by.html)
+* [md5](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.md5.html)
+* [mean](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.mean.html)
+* [min](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.min.html)
+* [min_by](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.min_by.html)
+* [minute](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.minute.html)
+* [module](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.module.html)
+* [month](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.month.html)
+* [months_between](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.months_between.html)
+* [nanvl](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.nanvl.html)
+* [next_day](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.next_day.html)
+* [nth_value](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.nth_value.html)
+  * offset > 1 means that previous values within the partition also share the same result. In Spark rows < offset have a Null value
+* [ntile](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.ntile.html)
+* [nullif](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.nullif.html)
+* [octet_length](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.octet_length.html)
+* [overlay](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.overlay.html)
+* [percent_rank](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.percent_rank.html)
+* [percentile](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.percentile.html)
+  * does not accept an array of percentiles
+* [percentile_approx](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.percentile_approx.html)
+* [posexplode](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.posexplode.html)
+  * Default order of columns are `col`, `pos` instead of `pos`, `col`
+* [pow](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.pow.html)
+* [quarter](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.quarter.html)
+* [radians](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.radians.html)
+* [rand](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.rand.html)
+* [rank](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.rank.html)
+* [regexp_extract](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.regexp_extract.html)
+* [regexp_replace](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.regexp_replace.html)
+* [repeat](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.repeat.html)
+* [rint](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.rint.html)
+* [round](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.round.html)
+* [row_number](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.row_number.html)
+* [rpad](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.rpad.html)
+* [rtrim](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.rtrim.html)
+* [second](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.second.html)
+* [sequence](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sequence.html)
+* [sha1](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sha1.html)
+* [sha2](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sha2.html)
+* [shiftLeft](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.shiftLeft.html)
+* [shiftRight](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.shiftRight.html)
+* [shiftleft](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.shiftleft.html)
+* [shiftright](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.shiftright.html)
+* [signum](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.signum.html)
+* [sin](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sin.html)
+* [sinh](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sinh.html)
+* [size](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.size.html)
+* [skewness](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.skewness.html)
+  * Skewness is calculated differently
+* [slice](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.slice.html)
+* [sort_array](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sort_array.html)
+* [soundex](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.soundex.html)
+* [split](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.split.html)
+  * Regular expressions not supported
+* [sqrt](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sqrt.html)
+* [stddev](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.stddev.html)
+* [stddev_pop](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.stddev_pop.html)
+* [stddev_samp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.stddev_samp.html)
+* [struct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.struct.html)
+* [substring](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.substring.html)
+* [sum](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sum.html)
+* [sumDistinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sumDistinct.html)
+* [sum_distinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.sum_distinct.html)
+* [tan](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.tan.html)
+* [tanh](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.tanh.html)
+* [timestamp_seconds](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.timestamp_seconds.html)
+* [toDegrees](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.toDegrees.html)
+* [toRadians](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.toRadians.html)
+* [to_date](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_date.html)
+  * [The format string should be in Snowflake syntax](https://docs.snowflake.com/en/sql-reference/functions-conversion#label-date-time-format-conversion)
+* [to_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp.html)
+  * [The format string should be in Snowflake syntax](https://docs.snowflake.com/en/sql-reference/functions-conversion#label-date-time-format-conversion)
+* [translate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.translate.html)
+* [trim](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trim.html)
+* [trunc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trunc.html)
+* [unbase64](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.unbase64.html)
+* [unhex](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.unhex.html)
+* [unix_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.unix_timestamp.html)
+  * [The format string should be in Snowflake syntax](https://docs.snowflake.com/en/sql-reference/functions-conversion#label-date-time-format-conversion)
+* [upper](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.upper.html)
+* [var_pop](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.var_pop.html)
+* [var_samp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.var_samp.html)
+* [variance](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.variance.html)
+* [weekofyear](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.weekofyear.html)
+* [when](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.when.html)
+* [year](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.year.html)
+
+### GroupedData Class
+
+* [agg](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.GroupedData.agg.html)
+* [avg](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.GroupedData.avg.html)
+* [count](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.GroupedData.count.html)
+* [max](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.GroupedData.max.html)
+* [mean](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.GroupedData.mean.html)
+* [min](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.GroupedData.min.html)
+* [pivot](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.GroupedData.pivot.html)
+* [sum](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.GroupedData.sum.html)
+
+### DataFrameReader Class
+
+* [csv](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrameReader.csv.html)
+* [json](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrameReader.json.html)
+* [load](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrameReader.load.html)
+* [parquet](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrameReader.parquet.html)
+* [table](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrameReader.table.html)
+
+### DataFrameWriter Class
+
+* [csv](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.csv.html)
+* [insertInto](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.insertInto.html)
+* [json](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.json.html)
+* [mode](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.mode.html)
+* [parquet](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.parquet.html)
+* [saveAsTable](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.saveAsTable.html)
+* sql
+     * SQLFrame Specific: Get the SQL representation of the DataFrame
+
+### SparkSession Class
+
+* [builder](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.SparkSession.builder.html)
+* [catalog](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.SparkSession.catalog.html)
+* [createDataFrame](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.SparkSession.createDataFrame.html)
+* [range](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.SparkSession.range.html)
+* [read](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.SparkSession.read.html)
+* [sql](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.SparkSession.sql.html)
+* [table](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.SparkSession.table.html)
+
+### DataTypes
+
+* [ArrayType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.ArrayType.html)
+* [BinaryType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.BinaryType.html)
+* [BooleanType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.BooleanType.html)
+* [ByteType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.ByteType.html)
+* [CharType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.CharType.html)
+* [DataType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.DataType.html)
+* [DateType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.DateType.html)
+* [DecimalType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.DecimalType.html)
+* [DoubleType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.DoubleType.html)
+* [FloatType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.FloatType.html)
+* [IntegerType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.IntegerType.html)
+* [LongType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.LongType.html)
+* [Row](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/row.html)
+* [ShortType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.ShortType.html)
+* [StringType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.StringType.html)
+* [StructField](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.StructField.html)
+* [StructType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.StructType.html)
+* [TimestampNTZType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.TimestampNTZType.html)
+* [TimestampType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.TimestampType.html)
+* [VarcharType](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.types.VarcharType.html)
+
+### Window Class
+
+* [currentRow](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Window.currentRow.html)
+* [orderBy](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Window.orderBy.html)
+* [partitionBy](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Window.partitionBy.html)
+* [rangeBetween](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Window.rangeBetween.html)
+* [rowsBetween](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Window.rowsBetween.html)
+* [unboundedFollowing](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Window.unboundedFollowing.html)
+* [unboundedPreceding](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.Window.unboundedPreceding.html)
+
+### WindowSpec Class
+
+* [orderBy](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.WindowSpec.orderBy.html)
+* [partitionBy](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.WindowSpec.partitionBy.html)
+* [rangeBetween](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.WindowSpec.rangeBetween.html)
+* [rowsBetween](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.WindowSpec.rowsBetween.html)
+* sql
+    * SQLFrame Specific: Get the SQL representation of the WindowSpec

{sqlframe-1.4.0 → sqlframe-1.5.0}/setup.py

@@ -20,7 +20,7 @@ setup(
     python_requires=">=3.8",
     install_requires=[
         "prettytable<3.11.0",
-        "sqlglot>=24.0.0,<24.1",
+        "sqlglot>=24.0.0,<24.2",
     ],
     extras_require={
         "bigquery": [

{sqlframe-1.4.0 → sqlframe-1.5.0}/sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '1.4.0'
-__version_tuple__ = version_tuple = (1, 4, 0)
+__version__ = version = '1.5.0'
+__version_tuple__ = version_tuple = (1, 5, 0)

{sqlframe-1.4.0 → sqlframe-1.5.0}/sqlframe/base/column.py

@@ -251,6 +251,13 @@ class Column:
             return lit(value)
         return Column(value)
 
+    @property
+    def dtype(self) -> t.Optional[DataType]:
+        expression = self.expression.unalias()
+        if isinstance(expression, exp.Cast):
+            return expression.args.get("to")
+        return None
+
     def copy(self) -> Column:
         return Column(self.expression.copy())