diff options
author | Davies Liu <davies@databricks.com> | 2015-04-08 13:31:45 -0700 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2015-04-08 13:31:45 -0700 |
commit | 6ada4f6f52cf1d992c7ab0c32318790cf08b0a0d (patch) | |
tree | 495c9bb86bb98de40365538bebcf9144547d8cce /examples/src/main | |
parent | 66159c35010af35098dd1ec75475bb5d4d0fd6ca (diff) | |
download | spark-6ada4f6f52cf1d992c7ab0c32318790cf08b0a0d.tar.gz spark-6ada4f6f52cf1d992c7ab0c32318790cf08b0a0d.tar.bz2 spark-6ada4f6f52cf1d992c7ab0c32318790cf08b0a0d.zip |
[SPARK-6781] [SQL] use sqlContext in python shell
Use `sqlContext` in PySpark shell, make it consistent with SQL programming guide. `sqlCtx` is also kept for compatibility.
Author: Davies Liu <davies@databricks.com>
Closes #5425 from davies/sqlCtx and squashes the following commits:
af67340 [Davies Liu] sqlCtx -> sqlContext
15a278f [Davies Liu] use sqlContext in python shell
Diffstat (limited to 'examples/src/main')
3 files changed, 14 insertions, 14 deletions
diff --git a/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java b/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java index dee794840a..8159ffbe2d 100644 --- a/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java +++ b/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java @@ -55,7 +55,7 @@ public class JavaSparkSQL { public static void main(String[] args) throws Exception { SparkConf sparkConf = new SparkConf().setAppName("JavaSparkSQL"); JavaSparkContext ctx = new JavaSparkContext(sparkConf); - SQLContext sqlCtx = new SQLContext(ctx); + SQLContext sqlContext = new SQLContext(ctx); System.out.println("=== Data source: RDD ==="); // Load a text file and convert each line to a Java Bean. @@ -74,11 +74,11 @@ public class JavaSparkSQL { }); // Apply a schema to an RDD of Java Beans and register it as a table. - DataFrame schemaPeople = sqlCtx.createDataFrame(people, Person.class); + DataFrame schemaPeople = sqlContext.createDataFrame(people, Person.class); schemaPeople.registerTempTable("people"); // SQL can be run over RDDs that have been registered as tables. - DataFrame teenagers = sqlCtx.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19"); + DataFrame teenagers = sqlContext.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19"); // 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. @@ -99,12 +99,12 @@ public class JavaSparkSQL { // 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. - DataFrame parquetFile = sqlCtx.parquetFile("people.parquet"); + DataFrame parquetFile = sqlContext.parquetFile("people.parquet"); //Parquet files can also be registered as tables and then used in SQL statements. parquetFile.registerTempTable("parquetFile"); DataFrame teenagers2 = - sqlCtx.sql("SELECT name FROM parquetFile WHERE age >= 13 AND age <= 19"); + sqlContext.sql("SELECT name FROM parquetFile WHERE age >= 13 AND age <= 19"); teenagerNames = teenagers2.toJavaRDD().map(new Function<Row, String>() { @Override public String call(Row row) { @@ -120,7 +120,7 @@ public class JavaSparkSQL { // The path can be either a single text file or a directory storing text files. String path = "examples/src/main/resources/people.json"; // Create a DataFrame from the file(s) pointed by path - DataFrame peopleFromJsonFile = sqlCtx.jsonFile(path); + DataFrame peopleFromJsonFile = sqlContext.jsonFile(path); // Because the schema of a JSON dataset is automatically inferred, to write queries, // it is better to take a look at what is the schema. @@ -133,8 +133,8 @@ public class JavaSparkSQL { // Register this DataFrame as a table. peopleFromJsonFile.registerTempTable("people"); - // SQL statements can be run by using the sql methods provided by sqlCtx. - DataFrame teenagers3 = sqlCtx.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19"); + // SQL statements can be run by using the sql methods provided by sqlContext. + DataFrame teenagers3 = sqlContext.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19"); // The results of SQL queries are DataFrame and support all the normal RDD operations. // The columns of a row in the result can be accessed by ordinal. @@ -151,7 +151,7 @@ public class JavaSparkSQL { List<String> jsonData = Arrays.asList( "{\"name\":\"Yin\",\"address\":{\"city\":\"Columbus\",\"state\":\"Ohio\"}}"); JavaRDD<String> anotherPeopleRDD = ctx.parallelize(jsonData); - DataFrame peopleFromJsonRDD = sqlCtx.jsonRDD(anotherPeopleRDD.rdd()); + DataFrame peopleFromJsonRDD = sqlContext.jsonRDD(anotherPeopleRDD.rdd()); // Take a look at the schema of this new DataFrame. peopleFromJsonRDD.printSchema(); @@ -164,7 +164,7 @@ public class JavaSparkSQL { peopleFromJsonRDD.registerTempTable("people2"); - DataFrame peopleWithCity = sqlCtx.sql("SELECT name, address.city FROM people2"); + DataFrame peopleWithCity = sqlContext.sql("SELECT name, address.city FROM people2"); List<String> nameAndCity = peopleWithCity.toJavaRDD().map(new Function<Row, String>() { @Override public String call(Row row) { diff --git a/examples/src/main/python/ml/simple_text_classification_pipeline.py b/examples/src/main/python/ml/simple_text_classification_pipeline.py index d281f4fa44..c73edb7fd6 100644 --- a/examples/src/main/python/ml/simple_text_classification_pipeline.py +++ b/examples/src/main/python/ml/simple_text_classification_pipeline.py @@ -33,7 +33,7 @@ pipeline in Python. Run with: if __name__ == "__main__": sc = SparkContext(appName="SimpleTextClassificationPipeline") - sqlCtx = SQLContext(sc) + sqlContext = SQLContext(sc) # Prepare training documents, which are labeled. LabeledDocument = Row("id", "text", "label") diff --git a/examples/src/main/python/mllib/dataset_example.py b/examples/src/main/python/mllib/dataset_example.py index b5a70db2b9..fcbf56cbf0 100644 --- a/examples/src/main/python/mllib/dataset_example.py +++ b/examples/src/main/python/mllib/dataset_example.py @@ -44,19 +44,19 @@ if __name__ == "__main__": print >> sys.stderr, "Usage: dataset_example.py <libsvm file>" exit(-1) sc = SparkContext(appName="DatasetExample") - sqlCtx = SQLContext(sc) + sqlContext = SQLContext(sc) if len(sys.argv) == 2: input = sys.argv[1] else: input = "data/mllib/sample_libsvm_data.txt" points = MLUtils.loadLibSVMFile(sc, input) - dataset0 = sqlCtx.inferSchema(points).setName("dataset0").cache() + dataset0 = sqlContext.inferSchema(points).setName("dataset0").cache() summarize(dataset0) tempdir = tempfile.NamedTemporaryFile(delete=False).name os.unlink(tempdir) print "Save dataset as a Parquet file to %s." % tempdir dataset0.saveAsParquetFile(tempdir) print "Load it back and summarize it again." - dataset1 = sqlCtx.parquetFile(tempdir).setName("dataset1").cache() + dataset1 = sqlContext.parquetFile(tempdir).setName("dataset1").cache() summarize(dataset1) shutil.rmtree(tempdir) |