From 7af3818c6b2bf35bfa531ab7cc3a4a714385015e Mon Sep 17 00:00:00 2001 From: Davies Liu Date: Sat, 23 May 2015 00:00:30 -0700 Subject: [SPARK-6806] [SPARKR] [DOCS] Fill in SparkR examples in programming guide sqlCtx -> sqlContext You can check the docs by: ``` $ cd docs $ SKIP_SCALADOC=1 jekyll serve ``` cc shivaram Author: Davies Liu Closes #5442 from davies/r_docs and squashes the following commits: 7a12ec6 [Davies Liu] remove rdd in R docs 8496b26 [Davies Liu] remove the docs related to RDD e23b9d6 [Davies Liu] delete R docs for RDD API 222e4ff [Davies Liu] Merge branch 'master' into r_docs 89684ce [Davies Liu] Merge branch 'r_docs' of github.com:davies/spark into r_docs f0a10e1 [Davies Liu] address comments from @shivaram f61de71 [Davies Liu] Update pairRDD.R 3ef7cf3 [Davies Liu] use + instead of function(a,b) a+b 2f10a77 [Davies Liu] address comments from @cafreeman 9c2a062 [Davies Liu] mention R api together with Python API 23f751a [Davies Liu] Fill in SparkR examples in programming guide --- docs/_plugins/copy_api_dirs.rb | 68 ++++---- docs/api.md | 3 +- docs/index.md | 23 ++- docs/programming-guide.md | 21 ++- docs/quick-start.md | 18 +- docs/sql-programming-guide.md | 373 ++++++++++++++++++++++++++++++++++++++++- 6 files changed, 445 insertions(+), 61 deletions(-) (limited to 'docs') diff --git a/docs/_plugins/copy_api_dirs.rb b/docs/_plugins/copy_api_dirs.rb index 0ea3f8eab4..6073b3626c 100644 --- a/docs/_plugins/copy_api_dirs.rb +++ b/docs/_plugins/copy_api_dirs.rb @@ -18,50 +18,52 @@ require 'fileutils' include FileUtils -if not (ENV['SKIP_API'] == '1' or ENV['SKIP_SCALADOC'] == '1') - # Build Scaladoc for Java/Scala +if not (ENV['SKIP_API'] == '1') + if not (ENV['SKIP_SCALADOC'] == '1') + # Build Scaladoc for Java/Scala - puts "Moving to project root and building API docs." - curr_dir = pwd - cd("..") + puts "Moving to project root and building API docs." + curr_dir = pwd + cd("..") - puts "Running 'build/sbt -Pkinesis-asl compile unidoc' from " + pwd + "; this may take a few minutes..." - puts `build/sbt -Pkinesis-asl compile unidoc` + puts "Running 'build/sbt -Pkinesis-asl compile unidoc' from " + pwd + "; this may take a few minutes..." + puts `build/sbt -Pkinesis-asl compile unidoc` - puts "Moving back into docs dir." - cd("docs") + puts "Moving back into docs dir." + cd("docs") - # Copy over the unified ScalaDoc for all projects to api/scala. - # This directory will be copied over to _site when `jekyll` command is run. - source = "../target/scala-2.10/unidoc" - dest = "api/scala" + # Copy over the unified ScalaDoc for all projects to api/scala. + # This directory will be copied over to _site when `jekyll` command is run. + source = "../target/scala-2.10/unidoc" + dest = "api/scala" - puts "Making directory " + dest - mkdir_p dest + puts "Making directory " + dest + mkdir_p dest - # From the rubydoc: cp_r('src', 'dest') makes src/dest, but this doesn't. - puts "cp -r " + source + "/. " + dest - cp_r(source + "/.", dest) + # From the rubydoc: cp_r('src', 'dest') makes src/dest, but this doesn't. + puts "cp -r " + source + "/. " + dest + cp_r(source + "/.", dest) - # Append custom JavaScript - js = File.readlines("./js/api-docs.js") - js_file = dest + "/lib/template.js" - File.open(js_file, 'a') { |f| f.write("\n" + js.join()) } + # Append custom JavaScript + js = File.readlines("./js/api-docs.js") + js_file = dest + "/lib/template.js" + File.open(js_file, 'a') { |f| f.write("\n" + js.join()) } - # Append custom CSS - css = File.readlines("./css/api-docs.css") - css_file = dest + "/lib/template.css" - File.open(css_file, 'a') { |f| f.write("\n" + css.join()) } + # Append custom CSS + css = File.readlines("./css/api-docs.css") + css_file = dest + "/lib/template.css" + File.open(css_file, 'a') { |f| f.write("\n" + css.join()) } - # Copy over the unified JavaDoc for all projects to api/java. - source = "../target/javaunidoc" - dest = "api/java" + # Copy over the unified JavaDoc for all projects to api/java. + source = "../target/javaunidoc" + dest = "api/java" - puts "Making directory " + dest - mkdir_p dest + puts "Making directory " + dest + mkdir_p dest - puts "cp -r " + source + "/. " + dest - cp_r(source + "/.", dest) + puts "cp -r " + source + "/. " + dest + cp_r(source + "/.", dest) + end # Build Sphinx docs for Python diff --git a/docs/api.md b/docs/api.md index 0346038333..45df77ac05 100644 --- a/docs/api.md +++ b/docs/api.md @@ -7,4 +7,5 @@ Here you can API docs for Spark and its submodules. - [Spark Scala API (Scaladoc)](api/scala/index.html) - [Spark Java API (Javadoc)](api/java/index.html) -- [Spark Python API (Epydoc)](api/python/index.html) +- [Spark Python API (Sphinx)](api/python/index.html) +- [Spark R API (Roxygen2)](api/R/index.html) diff --git a/docs/index.md b/docs/index.md index b5b016e347..5ef6d983c4 100644 --- a/docs/index.md +++ b/docs/index.md @@ -6,7 +6,7 @@ description: Apache Spark SPARK_VERSION_SHORT documentation homepage --- Apache Spark is a fast and general-purpose cluster computing system. -It provides high-level APIs in Java, Scala and Python, +It provides high-level APIs in Java, Scala, Python and R, and an optimized engine that supports general execution graphs. It also supports a rich set of higher-level tools including [Spark SQL](sql-programming-guide.html) for SQL and structured data processing, [MLlib](mllib-guide.html) for machine learning, [GraphX](graphx-programming-guide.html) for graph processing, and [Spark Streaming](streaming-programming-guide.html). @@ -20,13 +20,13 @@ Spark runs on both Windows and UNIX-like systems (e.g. Linux, Mac OS). It's easy locally on one machine --- all you need is to have `java` installed on your system `PATH`, or the `JAVA_HOME` environment variable pointing to a Java installation. -Spark runs on Java 6+ and Python 2.6+. For the Scala API, Spark {{site.SPARK_VERSION}} uses +Spark runs on Java 6+, Python 2.6+ and R 3.1+. For the Scala API, Spark {{site.SPARK_VERSION}} uses Scala {{site.SCALA_BINARY_VERSION}}. You will need to use a compatible Scala version ({{site.SCALA_BINARY_VERSION}}.x). # Running the Examples and Shell -Spark comes with several sample programs. Scala, Java and Python examples are in the +Spark comes with several sample programs. Scala, Java, Python and R examples are in the `examples/src/main` directory. To run one of the Java or Scala sample programs, use `bin/run-example [params]` in the top-level Spark directory. (Behind the scenes, this invokes the more general @@ -54,6 +54,15 @@ Example applications are also provided in Python. For example, ./bin/spark-submit examples/src/main/python/pi.py 10 +Spark also provides an experimental R API since 1.4 (only DataFrames APIs included). +To run Spark interactively in a R interpreter, use `bin/sparkR`: + + ./bin/sparkR --master local[2] + +Example applications are also provided in R. For example, + + ./bin/spark-submit examples/src/main/r/dataframe.R + # Launching on a Cluster The Spark [cluster mode overview](cluster-overview.html) explains the key concepts in running on a cluster. @@ -71,7 +80,7 @@ options for deployment: * [Quick Start](quick-start.html): a quick introduction to the Spark API; start here! * [Spark Programming Guide](programming-guide.html): detailed overview of Spark - in all supported languages (Scala, Java, Python) + in all supported languages (Scala, Java, Python, R) * Modules built on Spark: * [Spark Streaming](streaming-programming-guide.html): processing real-time data streams * [Spark SQL and DataFrames](sql-programming-guide.html): support for structured data and relational queries @@ -83,7 +92,8 @@ options for deployment: * [Spark Scala API (Scaladoc)](api/scala/index.html#org.apache.spark.package) * [Spark Java API (Javadoc)](api/java/index.html) -* [Spark Python API (Epydoc)](api/python/index.html) +* [Spark Python API (Sphinx)](api/python/index.html) +* [Spark R API (Roxygen2)](api/R/index.html) **Deployment Guides:** @@ -124,4 +134,5 @@ options for deployment: available online for free. * [Code Examples](http://spark.apache.org/examples.html): more are also available in the `examples` subfolder of Spark ([Scala]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/scala/org/apache/spark/examples), [Java]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/java/org/apache/spark/examples), - [Python]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/python)) + [Python]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/python), + [R]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/r)) diff --git a/docs/programming-guide.md b/docs/programming-guide.md index 07a4d29fe7..5d9df282ef 100644 --- a/docs/programming-guide.md +++ b/docs/programming-guide.md @@ -98,9 +98,9 @@ to your version of HDFS. Some common HDFS version tags are listed on the [Prebuilt packages](http://spark.apache.org/downloads.html) are also available on the Spark homepage for common HDFS versions. -Finally, you need to import some Spark classes into your program. Add the following lines: +Finally, you need to import some Spark classes into your program. Add the following line: -{% highlight scala %} +{% highlight python %} from pyspark import SparkContext, SparkConf {% endhighlight %} @@ -478,7 +478,6 @@ the [Converter examples]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main for examples of using Cassandra / HBase ```InputFormat``` and ```OutputFormat``` with custom converters. - ## RDD Operations @@ -915,7 +914,8 @@ The following table lists some of the common transformations supported by Spark. RDD API doc ([Scala](api/scala/index.html#org.apache.spark.rdd.RDD), [Java](api/java/index.html?org/apache/spark/api/java/JavaRDD.html), - [Python](api/python/pyspark.html#pyspark.RDD)) + [Python](api/python/pyspark.html#pyspark.RDD), + [R](api/R/index.html)) and pair RDD functions doc ([Scala](api/scala/index.html#org.apache.spark.rdd.PairRDDFunctions), [Java](api/java/index.html?org/apache/spark/api/java/JavaPairRDD.html)) @@ -1028,7 +1028,9 @@ The following table lists some of the common actions supported by Spark. Refer t RDD API doc ([Scala](api/scala/index.html#org.apache.spark.rdd.RDD), [Java](api/java/index.html?org/apache/spark/api/java/JavaRDD.html), - [Python](api/python/pyspark.html#pyspark.RDD)) + [Python](api/python/pyspark.html#pyspark.RDD), + [R](api/R/index.html)) + and pair RDD functions doc ([Scala](api/scala/index.html#org.apache.spark.rdd.PairRDDFunctions), [Java](api/java/index.html?org/apache/spark/api/java/JavaPairRDD.html)) @@ -1565,7 +1567,8 @@ You can see some [example Spark programs](http://spark.apache.org/examples.html) In addition, Spark includes several samples in the `examples` directory ([Scala]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/scala/org/apache/spark/examples), [Java]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/java/org/apache/spark/examples), - [Python]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/python)). + [Python]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/python), + [R]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/r)). You can run Java and Scala examples by passing the class name to Spark's `bin/run-example` script; for instance: ./bin/run-example SparkPi @@ -1574,6 +1577,10 @@ For Python examples, use `spark-submit` instead: ./bin/spark-submit examples/src/main/python/pi.py +For R examples, use `spark-submit` instead: + + ./bin/spark-submit examples/src/main/r/dataframe.R + For help on optimizing your programs, the [configuration](configuration.html) and [tuning](tuning.html) guides provide information on best practices. They are especially important for making sure that your data is stored in memory in an efficient format. @@ -1581,4 +1588,4 @@ For help on deploying, the [cluster mode overview](cluster-overview.html) descri in distributed operation and supported cluster managers. Finally, full API documentation is available in -[Scala](api/scala/#org.apache.spark.package), [Java](api/java/) and [Python](api/python/). +[Scala](api/scala/#org.apache.spark.package), [Java](api/java/), [Python](api/python/) and [R](api/R/). diff --git a/docs/quick-start.md b/docs/quick-start.md index 81143da865..bb39e4111f 100644 --- a/docs/quick-start.md +++ b/docs/quick-start.md @@ -184,10 +184,10 @@ scala> linesWithSpark.cache() res7: spark.RDD[String] = spark.FilteredRDD@17e51082 scala> linesWithSpark.count() -res8: Long = 15 +res8: Long = 19 scala> linesWithSpark.count() -res9: Long = 15 +res9: Long = 19 {% endhighlight %} It may seem silly to use Spark to explore and cache a 100-line text file. The interesting part is @@ -202,10 +202,10 @@ a cluster, as described in the [programming guide](programming-guide.html#initia >>> linesWithSpark.cache() >>> linesWithSpark.count() -15 +19 >>> linesWithSpark.count() -15 +19 {% endhighlight %} It may seem silly to use Spark to explore and cache a 100-line text file. The interesting part is @@ -423,14 +423,14 @@ dependencies to `spark-submit` through its `--py-files` argument by packaging th We can run this application using the `bin/spark-submit` script: -{% highlight python %} +{% highlight bash %} # Use spark-submit to run your application $ YOUR_SPARK_HOME/bin/spark-submit \ --master local[4] \ SimpleApp.py ... Lines with a: 46, Lines with b: 23 -{% endhighlight python %} +{% endhighlight %} @@ -444,7 +444,8 @@ Congratulations on running your first Spark application! * Finally, Spark includes several samples in the `examples` directory ([Scala]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/scala/org/apache/spark/examples), [Java]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/java/org/apache/spark/examples), - [Python]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/python)). + [Python]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/python), + [R]({{site.SPARK_GITHUB_URL}}/tree/master/examples/src/main/r)). You can run them as follows: {% highlight bash %} @@ -453,4 +454,7 @@ You can run them as follows: # For Python examples, use spark-submit directly: ./bin/spark-submit examples/src/main/python/pi.py + +# For R examples, use spark-submit directly: +./bin/spark-submit examples/src/main/r/dataframe.R {% endhighlight %} diff --git a/docs/sql-programming-guide.md b/docs/sql-programming-guide.md index 78b8e8ad51..5b41c0ee6e 100644 --- a/docs/sql-programming-guide.md +++ b/docs/sql-programming-guide.md @@ -16,9 +16,9 @@ Spark SQL is a Spark module for structured data processing. It provides a progra A DataFrame is a distributed collection of data organized into named columns. It is conceptually equivalent to a table in a relational database or a data frame in R/Python, but with richer optimizations under the hood. DataFrames can be constructed from a wide array of sources such as: structured data files, tables in Hive, external databases, or existing RDDs. -The DataFrame API is available in [Scala](api/scala/index.html#org.apache.spark.sql.DataFrame), [Java](api/java/index.html?org/apache/spark/sql/DataFrame.html), and [Python](api/python/pyspark.sql.html#pyspark.sql.DataFrame). +The DataFrame API is available in [Scala](api/scala/index.html#org.apache.spark.sql.DataFrame), [Java](api/java/index.html?org/apache/spark/sql/DataFrame.html), [Python](api/python/pyspark.sql.html#pyspark.sql.DataFrame), and [R](api/R/index.html). -All of the examples on this page use sample data included in the Spark distribution and can be run in the `spark-shell` or the `pyspark` shell. +All of the examples on this page use sample data included in the Spark distribution and can be run in the `spark-shell`, `pyspark` shell, or `sparkR` shell. ## Starting Point: `SQLContext` @@ -64,6 +64,17 @@ from pyspark.sql import SQLContext sqlContext = SQLContext(sc) {% endhighlight %} + + +
+ +The entry point into all relational functionality in Spark is the +`SQLContext` class, or one of its decedents. To create a basic `SQLContext`, all you need is a SparkContext. + +{% highlight r %} +sqlContext <- sparkRSQL.init(sc) +{% endhighlight %} +
@@ -130,6 +141,19 @@ df.show() {% endhighlight %} + +
+{% highlight r %} +sqlContext <- SQLContext(sc) + +df <- jsonFile(sqlContext, "examples/src/main/resources/people.json") + +# Displays the content of the DataFrame to stdout +showDF(df) +{% endhighlight %} + +
+ @@ -296,6 +320,57 @@ df.groupBy("age").count().show() {% endhighlight %} + +
+{% highlight r %} +sqlContext <- sparkRSQL.init(sc) + +# Create the DataFrame +df <- jsonFile(sqlContext, "examples/src/main/resources/people.json") + +# Show the content of the DataFrame +showDF(df) +## age name +## null Michael +## 30 Andy +## 19 Justin + +# Print the schema in a tree format +printSchema(df) +## root +## |-- age: long (nullable = true) +## |-- name: string (nullable = true) + +# Select only the "name" column +showDF(select(df, "name")) +## name +## Michael +## Andy +## Justin + +# Select everybody, but increment the age by 1 +showDF(select(df, df$name, df$age + 1)) +## name (age + 1) +## Michael null +## Andy 31 +## Justin 20 + +# Select people older than 21 +showDF(where(df, df$age > 21)) +## age name +## 30 Andy + +# Count people by age +showDF(count(groupBy(df, "age"))) +## age count +## null 1 +## 19 1 +## 30 1 + +{% endhighlight %} + +
+ @@ -325,6 +400,14 @@ sqlContext = SQLContext(sc) df = sqlContext.sql("SELECT * FROM table") {% endhighlight %} + +
+{% highlight r %} +sqlContext <- sparkRSQL.init(sc) +df <- sql(sqlContext, "SELECT * FROM table") +{% endhighlight %} +
+ @@ -719,6 +802,15 @@ df.select("name", "favorite_color").save("namesAndFavColors.parquet") {% endhighlight %} + + +
+ +{% highlight r %} +df <- loadDF(sqlContext, "people.parquet") +saveDF(select(df, "name", "age"), "namesAndAges.parquet") +{% endhighlight %} +
@@ -760,6 +852,16 @@ df.select("name", "age").save("namesAndAges.parquet", "parquet") {% endhighlight %} + +
+ +{% highlight r %} + +df <- loadDF(sqlContext, "people.json", "json") +saveDF(select(df, "name", "age"), "namesAndAges.parquet", "parquet") + +{% endhighlight %} +
@@ -908,6 +1010,31 @@ for teenName in teenNames.collect(): +
+ +{% highlight r %} +# sqlContext from the previous example is used in this example. + +schemaPeople # The DataFrame from the previous example. + +# DataFrames can be saved as Parquet files, maintaining the schema information. +saveAsParquetFile(schemaPeople, "people.parquet") + +# Read in the Parquet file created above. Parquet files are self-describing so the schema is preserved. +# The result of loading a parquet file is also a DataFrame. +parquetFile <- parquetFile(sqlContext, "people.parquet") + +# Parquet files can also be registered as tables and then used in SQL statements. +registerTempTable(parquetFile, "parquetFile"); +teenagers <- sql(sqlContext, "SELECT name FROM parquetFile WHERE age >= 13 AND age <= 19") +teenNames <- map(teenagers, function(p) { paste("Name:", p$name)}) +for (teenName in collect(teenNames)) { + cat(teenName, "\n") +} +{% endhighlight %} + +
+
{% highlight sql %} @@ -1033,7 +1160,7 @@ df2 = sqlContext.createDataFrame(sc.parallelize(range(6, 11)) df2.save("data/test_table/key=2", "parquet") # Read the partitioned table -df3 = sqlContext.parquetFile("data/test_table") +df3 = sqlContext.load("data/test_table", "parquet") df3.printSchema() # The final schema consists of all 3 columns in the Parquet files together @@ -1047,6 +1174,33 @@ df3.printSchema()
+
+ +{% highlight r %} +# sqlContext from the previous example is used in this example. + +# Create a simple DataFrame, stored into a partition directory +saveDF(df1, "data/test_table/key=1", "parquet", "overwrite") + +# Create another DataFrame in a new partition directory, +# adding a new column and dropping an existing column +saveDF(df2, "data/test_table/key=2", "parquet", "overwrite") + +# Read the partitioned table +df3 <- loadDF(sqlContext, "data/test_table", "parquet") +printSchema(df3) + +# The final schema consists of all 3 columns in the Parquet files together +# with the partiioning column appeared in the partition directory paths. +# root +# |-- single: int (nullable = true) +# |-- double: int (nullable = true) +# |-- triple: int (nullable = true) +# |-- key : int (nullable = true) +{% endhighlight %} + +
+ ### Configuration @@ -1238,6 +1392,40 @@ anotherPeople = sqlContext.jsonRDD(anotherPeopleRDD) {% endhighlight %} +
+Spark SQL can automatically infer the schema of a JSON dataset and load it as a DataFrame. +This conversion can be done using one of two methods in a `SQLContext`: + +* `jsonFile` - loads data from a directory of JSON files where each line of the files is a JSON object. + +Note that the file that is offered as _jsonFile_ is not a typical JSON file. Each +line must contain a separate, self-contained valid JSON object. As a consequence, +a regular multi-line JSON file will most often fail. + +{% highlight r %} +# sc is an existing SparkContext. +sqlContext <- sparkRSQL.init(sc) + +# A JSON dataset is pointed to by path. +# The path can be either a single text file or a directory storing text files. +path <- "examples/src/main/resources/people.json" +# Create a DataFrame from the file(s) pointed to by path +people <- jsonFile(sqlContex,t path) + +# The inferred schema can be visualized using the printSchema() method. +printSchema(people) +# root +# |-- age: integer (nullable = true) +# |-- name: string (nullable = true) + +# Register this DataFrame as a table. +registerTempTable(people, "people") + +# SQL statements can be run by using the sql methods provided by `sqlContext`. +teenagers <- sql(sqlContext, "SELECT name FROM people WHERE age >= 13 AND age <= 19") +{% endhighlight %} +
+
{% highlight sql %} @@ -1314,10 +1502,7 @@ Row[] results = sqlContext.sql("FROM src SELECT key, value").collect();
When working with Hive one must construct a `HiveContext`, which inherits from `SQLContext`, and -adds support for finding tables in the MetaStore and writing queries using HiveQL. In addition to -the `sql` method a `HiveContext` also provides an `hql` methods, which allows queries to be -expressed in HiveQL. - +adds support for finding tables in the MetaStore and writing queries using HiveQL. {% highlight python %} # sc is an existing SparkContext. from pyspark.sql import HiveContext @@ -1331,6 +1516,24 @@ results = sqlContext.sql("FROM src SELECT key, value").collect() {% endhighlight %} +
+ +
+ +When working with Hive one must construct a `HiveContext`, which inherits from `SQLContext`, and +adds support for finding tables in the MetaStore and writing queries using HiveQL. +{% highlight r %} +# sc is an existing SparkContext. +sqlContext <- sparkRHive.init(sc) + +hql(sqlContext, "CREATE TABLE IF NOT EXISTS src (key INT, value STRING)") +hql(sqlContext, "LOAD DATA LOCAL INPATH 'examples/src/main/resources/kv1.txt' INTO TABLE src") + +# Queries can be expressed in HiveQL. +results = sqlContext.sql("FROM src SELECT key, value").collect() + +{% endhighlight %} +
@@ -1430,6 +1633,16 @@ df = sqlContext.load(source="jdbc", url="jdbc:postgresql:dbserver", dbtable="sch +
+ +{% highlight r %} + +df <- loadDF(sqlContext, source="jdbc", url="jdbc:postgresql:dbserver", dbtable="schema.tablename") + +{% endhighlight %} + +
+
{% highlight sql %} @@ -2354,5 +2567,151 @@ from pyspark.sql.types import *
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Data typeValue type in RAPI to access or create a data type
ByteType + integer
+ Note: Numbers will be converted to 1-byte signed integer numbers at runtime. + Please make sure that numbers are within the range of -128 to 127. + 		+ "byte" +
ShortType + integer
+ Note: Numbers will be converted to 2-byte signed integer numbers at runtime. + Please make sure that numbers are within the range of -32768 to 32767. + 		+ "short" +
IntegerType integer + "integer" +
LongType + integer
+ Note: Numbers will be converted to 8-byte signed integer numbers at runtime. + Please make sure that numbers are within the range of + -9223372036854775808 to 9223372036854775807. + Otherwise, please convert data to decimal.Decimal and use DecimalType. + 		+ "long" +
FloatType + numeric
+ Note: Numbers will be converted to 4-byte single-precision floating + point numbers at runtime. + 		+ "float" +
DoubleType numeric + "double" +
DecimalType Not supported + Not supported +
StringType character + "string" +
BinaryType raw + "binary" +
BooleanType logical + "bool" +
TimestampType POSIXct + "timestamp" +
DateType Date + "date" +
ArrayType vector or list + list(type="array", elementType=elementType, containsNull=[containsNull])
+ Note: The default value of containsNull is True. +
MapType enviroment + list(type="map", keyType=keyType, valueType=valueType, valueContainsNull=[valueContainsNull])
+ Note: The default value of valueContainsNull is True. +
StructType named list + list(type="struct", fields=fields)
+ Note: fields is a Seq of StructFields. Also, two fields with the same + name are not allowed. +
StructField The value type in R of the data type of this field + (For example, integer for a StructField with the data type IntegerType) + list(name=name, type=dataType, nullable=nullable) +
+ +
+ -- cgit v1.2.3