diff options
author | Olivier Girardot <o.girardot@lateral-thoughts.com> | 2015-04-17 16:23:10 -0500 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2015-04-17 16:27:02 -0500 |
commit | d305e686b3d73213784bd75cdad7d168b22a1dc4 (patch) | |
tree | f724ac89e5b2eb13f1bd51b55ee761be20b10bba /docs/sql-programming-guide.md | |
parent | 59e206deb7346148412bbf5ba4ab626718fadf18 (diff) | |
download | spark-d305e686b3d73213784bd75cdad7d168b22a1dc4.tar.gz spark-d305e686b3d73213784bd75cdad7d168b22a1dc4.tar.bz2 spark-d305e686b3d73213784bd75cdad7d168b22a1dc4.zip |
SPARK-6988 : Fix documentation regarding DataFrames using the Java API
This patch includes :
* adding how to use map after an sql query using javaRDD
* fixing the first few java examples that were written in Scala
Thank you for your time,
Olivier.
Author: Olivier Girardot <o.girardot@lateral-thoughts.com>
Closes #5564 from ogirardot/branch-1.3 and squashes the following commits:
9f8d60e [Olivier Girardot] SPARK-6988 : Fix documentation regarding DataFrames using the Java API
(cherry picked from commit 6b528dc139da594ef2e651d84bd91fe0f738a39d)
Signed-off-by: Reynold Xin <rxin@databricks.com>
Diffstat (limited to 'docs/sql-programming-guide.md')
-rw-r--r-- | docs/sql-programming-guide.md | 14 |
1 files changed, 7 insertions, 7 deletions
diff --git a/docs/sql-programming-guide.md b/docs/sql-programming-guide.md index 03500867df..d49233714a 100644 --- a/docs/sql-programming-guide.md +++ b/docs/sql-programming-guide.md @@ -193,8 +193,8 @@ df.groupBy("age").count().show() <div data-lang="java" markdown="1"> {% highlight java %} -val sc: JavaSparkContext // An existing SparkContext. -val sqlContext = new org.apache.spark.sql.SQLContext(sc) +JavaSparkContext sc // An existing SparkContext. +SQLContext sqlContext = new org.apache.spark.sql.SQLContext(sc) // Create the DataFrame DataFrame df = sqlContext.jsonFile("examples/src/main/resources/people.json"); @@ -308,8 +308,8 @@ val df = sqlContext.sql("SELECT * FROM table") <div data-lang="java" markdown="1"> {% highlight java %} -val sqlContext = ... // An existing SQLContext -val df = sqlContext.sql("SELECT * FROM table") +SQLContext sqlContext = ... // An existing SQLContext +DataFrame df = sqlContext.sql("SELECT * FROM table") {% endhighlight %} </div> @@ -435,7 +435,7 @@ DataFrame teenagers = sqlContext.sql("SELECT name FROM people WHERE age >= 13 AN // The results of SQL queries are DataFrames and support all the normal RDD operations. // The columns of a row in the result can be accessed by ordinal. -List<String> teenagerNames = teenagers.map(new Function<Row, String>() { +List<String> teenagerNames = teenagers.javaRDD().map(new Function<Row, String>() { public String call(Row row) { return "Name: " + row.getString(0); } @@ -599,7 +599,7 @@ DataFrame results = sqlContext.sql("SELECT name FROM people"); // The results of SQL queries are DataFrames and support all the normal RDD operations. // The columns of a row in the result can be accessed by ordinal. -List<String> names = results.map(new Function<Row, String>() { +List<String> names = results.javaRDD().map(new Function<Row, String>() { public String call(Row row) { return "Name: " + row.getString(0); } @@ -860,7 +860,7 @@ DataFrame parquetFile = sqlContext.parquetFile("people.parquet"); //Parquet files can also be registered as tables and then used in SQL statements. parquetFile.registerTempTable("parquetFile"); DataFrame teenagers = sqlContext.sql("SELECT name FROM parquetFile WHERE age >= 13 AND age <= 19"); -List<String> teenagerNames = teenagers.map(new Function<Row, String>() { +List<String> teenagerNames = teenagers.javaRDD().map(new Function<Row, String>() { public String call(Row row) { return "Name: " + row.getString(0); } |