diff options
author | Davies Liu <davies@databricks.com> | 2015-05-20 23:05:54 -0700 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2015-05-20 23:05:54 -0700 |
commit | 8ddcb25b3990ec691463f87d4071e7425f4909a9 (patch) | |
tree | 954ef5cb66813835c5e0ede7de7aa415e96f793b /python/pyspark/sql/context.py | |
parent | 04940c49755fd2e7f1ed7b875da287c946bfebeb (diff) | |
download | spark-8ddcb25b3990ec691463f87d4071e7425f4909a9.tar.gz spark-8ddcb25b3990ec691463f87d4071e7425f4909a9.tar.bz2 spark-8ddcb25b3990ec691463f87d4071e7425f4909a9.zip |
[SPARK-7606] [SQL] [PySpark] add version to Python SQL API docs
Add version info for public Python SQL API.
cc rxin
Author: Davies Liu <davies@databricks.com>
Closes #6295 from davies/versions and squashes the following commits:
cfd91e6 [Davies Liu] add more version for DataFrame API
600834d [Davies Liu] add version to SQL API docs
Diffstat (limited to 'python/pyspark/sql/context.py')
-rw-r--r-- | python/pyspark/sql/context.py | 29 |
1 files changed, 26 insertions, 3 deletions
diff --git a/python/pyspark/sql/context.py b/python/pyspark/sql/context.py index 7543475014..51f12c5bb4 100644 --- a/python/pyspark/sql/context.py +++ b/python/pyspark/sql/context.py @@ -28,6 +28,7 @@ from py4j.protocol import Py4JError from pyspark.rdd import RDD, _prepare_for_python_RDD, ignore_unicode_prefix from pyspark.serializers import AutoBatchedSerializer, PickleSerializer +from pyspark.sql import since from pyspark.sql.types import Row, StringType, StructType, _verify_type, \ _infer_schema, _has_nulltype, _merge_type, _create_converter, _python_to_sql_converter from pyspark.sql.dataframe import DataFrame @@ -106,11 +107,13 @@ class SQLContext(object): self._scala_SQLContext = self._jvm.SQLContext(self._jsc.sc()) return self._scala_SQLContext + @since(1.3) def setConf(self, key, value): """Sets the given Spark SQL configuration property. """ self._ssql_ctx.setConf(key, value) + @since(1.3) def getConf(self, key, defaultValue): """Returns the value of Spark SQL configuration property for the given key. @@ -119,10 +122,12 @@ class SQLContext(object): return self._ssql_ctx.getConf(key, defaultValue) @property + @since("1.3.1") def udf(self): """Returns a :class:`UDFRegistration` for UDF registration.""" return UDFRegistration(self) + @since(1.4) def range(self, start, end, step=1, numPartitions=None): """ Create a :class:`DataFrame` with single LongType column named `id`, @@ -144,6 +149,7 @@ class SQLContext(object): return DataFrame(jdf, self) @ignore_unicode_prefix + @since(1.2) def registerFunction(self, name, f, returnType=StringType()): """Registers a lambda function as a UDF so it can be used in SQL statements. @@ -210,7 +216,8 @@ class SQLContext(object): @ignore_unicode_prefix def inferSchema(self, rdd, samplingRatio=None): - """::note: Deprecated in 1.3, use :func:`createDataFrame` instead. + """ + .. note:: Deprecated in 1.3, use :func:`createDataFrame` instead. """ warnings.warn("inferSchema is deprecated, please use createDataFrame instead") @@ -221,7 +228,8 @@ class SQLContext(object): @ignore_unicode_prefix def applySchema(self, rdd, schema): - """::note: Deprecated in 1.3, use :func:`createDataFrame` instead. + """ + .. note:: Deprecated in 1.3, use :func:`createDataFrame` instead. """ warnings.warn("applySchema is deprecated, please use createDataFrame instead") @@ -233,6 +241,7 @@ class SQLContext(object): return self.createDataFrame(rdd, schema) + @since(1.3) @ignore_unicode_prefix def createDataFrame(self, data, schema=None, samplingRatio=None): """ @@ -337,6 +346,7 @@ class SQLContext(object): df = self._ssql_ctx.applySchemaToPythonRDD(jrdd.rdd(), schema.json()) return DataFrame(df, self) + @since(1.3) def registerDataFrameAsTable(self, df, tableName): """Registers the given :class:`DataFrame` as a temporary table in the catalog. @@ -349,6 +359,7 @@ class SQLContext(object): else: raise ValueError("Can only register DataFrame as table") + @since(1.0) def parquetFile(self, *paths): """Loads a Parquet file, returning the result as a :class:`DataFrame`. @@ -367,6 +378,7 @@ class SQLContext(object): jdf = self._ssql_ctx.parquetFile(jpaths) return DataFrame(jdf, self) + @since(1.0) def jsonFile(self, path, schema=None, samplingRatio=1.0): """Loads a text file storing one JSON object per line as a :class:`DataFrame`. @@ -407,6 +419,7 @@ class SQLContext(object): return DataFrame(df, self) @ignore_unicode_prefix + @since(1.0) def jsonRDD(self, rdd, schema=None, samplingRatio=1.0): """Loads an RDD storing one JSON object per string as a :class:`DataFrame`. @@ -449,6 +462,7 @@ class SQLContext(object): df = self._ssql_ctx.jsonRDD(jrdd.rdd(), scala_datatype) return DataFrame(df, self) + @since(1.3) def load(self, path=None, source=None, schema=None, **options): """Returns the dataset in a data source as a :class:`DataFrame`. @@ -460,6 +474,7 @@ class SQLContext(object): """ return self.read.load(path, source, schema, **options) + @since(1.3) def createExternalTable(self, tableName, path=None, source=None, schema=None, **options): """Creates an external table based on the dataset in a data source. @@ -489,6 +504,7 @@ class SQLContext(object): return DataFrame(df, self) @ignore_unicode_prefix + @since(1.0) def sql(self, sqlQuery): """Returns a :class:`DataFrame` representing the result of the given query. @@ -499,6 +515,7 @@ class SQLContext(object): """ return DataFrame(self._ssql_ctx.sql(sqlQuery), self) + @since(1.0) def table(self, tableName): """Returns the specified table as a :class:`DataFrame`. @@ -510,6 +527,7 @@ class SQLContext(object): return DataFrame(self._ssql_ctx.table(tableName), self) @ignore_unicode_prefix + @since(1.3) def tables(self, dbName=None): """Returns a :class:`DataFrame` containing names of tables in the given database. @@ -528,6 +546,7 @@ class SQLContext(object): else: return DataFrame(self._ssql_ctx.tables(dbName), self) + @since(1.3) def tableNames(self, dbName=None): """Returns a list of names of tables in the database ``dbName``. @@ -544,25 +563,29 @@ class SQLContext(object): else: return [name for name in self._ssql_ctx.tableNames(dbName)] + @since(1.0) def cacheTable(self, tableName): """Caches the specified table in-memory.""" self._ssql_ctx.cacheTable(tableName) + @since(1.0) def uncacheTable(self, tableName): """Removes the specified table from the in-memory cache.""" self._ssql_ctx.uncacheTable(tableName) + @since(1.3) def clearCache(self): """Removes all cached tables from the in-memory cache. """ self._ssql_ctx.clearCache() @property + @since(1.4) def read(self): """ Returns a :class:`DataFrameReader` that can be used to read data in as a :class:`DataFrame`. - ::note: Experimental + .. note:: Experimental >>> sqlContext.read <pyspark.sql.readwriter.DataFrameReader object at ...> |