diff options
Diffstat (limited to 'examples/src/main/java')
4 files changed, 34 insertions, 34 deletions
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaCrossValidatorExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaCrossValidatorExample.java index 247d2a5e31..0fbee6e433 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaCrossValidatorExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaCrossValidatorExample.java @@ -33,7 +33,7 @@ import org.apache.spark.ml.param.ParamMap; import org.apache.spark.ml.tuning.CrossValidator; import org.apache.spark.ml.tuning.CrossValidatorModel; import org.apache.spark.ml.tuning.ParamGridBuilder; -import org.apache.spark.sql.SchemaRDD; +import org.apache.spark.sql.DataFrame; import org.apache.spark.sql.SQLContext; import org.apache.spark.sql.Row; @@ -71,7 +71,7 @@ public class JavaCrossValidatorExample { new LabeledDocument(9L, "a e c l", 0.0), new LabeledDocument(10L, "spark compile", 1.0), new LabeledDocument(11L, "hadoop software", 0.0)); - SchemaRDD training = jsql.applySchema(jsc.parallelize(localTraining), LabeledDocument.class); + DataFrame training = jsql.applySchema(jsc.parallelize(localTraining), LabeledDocument.class); // Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr. Tokenizer tokenizer = new Tokenizer() @@ -112,11 +112,11 @@ public class JavaCrossValidatorExample { new Document(5L, "l m n"), new Document(6L, "mapreduce spark"), new Document(7L, "apache hadoop")); - SchemaRDD test = jsql.applySchema(jsc.parallelize(localTest), Document.class); + DataFrame test = jsql.applySchema(jsc.parallelize(localTest), Document.class); // Make predictions on test documents. cvModel uses the best model found (lrModel). - cvModel.transform(test).registerAsTable("prediction"); - SchemaRDD predictions = jsql.sql("SELECT id, text, score, prediction FROM prediction"); + cvModel.transform(test).registerTempTable("prediction"); + DataFrame predictions = jsql.sql("SELECT id, text, score, prediction FROM prediction"); for (Row r: predictions.collect()) { System.out.println("(" + r.get(0) + ", " + r.get(1) + ") --> score=" + r.get(2) + ", prediction=" + r.get(3)); diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java index 5b92655e2e..eaaa344be4 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java @@ -28,7 +28,7 @@ import org.apache.spark.ml.param.ParamMap; import org.apache.spark.ml.classification.LogisticRegression; import org.apache.spark.mllib.linalg.Vectors; import org.apache.spark.mllib.regression.LabeledPoint; -import org.apache.spark.sql.SchemaRDD; +import org.apache.spark.sql.DataFrame; import org.apache.spark.sql.SQLContext; import org.apache.spark.sql.Row; @@ -48,13 +48,13 @@ public class JavaSimpleParamsExample { // Prepare training data. // We use LabeledPoint, which is a JavaBean. Spark SQL can convert RDDs of JavaBeans - // into SchemaRDDs, where it uses the bean metadata to infer the schema. + // into DataFrames, where it uses the bean metadata to infer the schema. List<LabeledPoint> localTraining = Lists.newArrayList( new LabeledPoint(1.0, Vectors.dense(0.0, 1.1, 0.1)), new LabeledPoint(0.0, Vectors.dense(2.0, 1.0, -1.0)), new LabeledPoint(0.0, Vectors.dense(2.0, 1.3, 1.0)), new LabeledPoint(1.0, Vectors.dense(0.0, 1.2, -0.5))); - SchemaRDD training = jsql.applySchema(jsc.parallelize(localTraining), LabeledPoint.class); + DataFrame training = jsql.applySchema(jsc.parallelize(localTraining), LabeledPoint.class); // Create a LogisticRegression instance. This instance is an Estimator. LogisticRegression lr = new LogisticRegression(); @@ -94,14 +94,14 @@ public class JavaSimpleParamsExample { new LabeledPoint(1.0, Vectors.dense(-1.0, 1.5, 1.3)), new LabeledPoint(0.0, Vectors.dense(3.0, 2.0, -0.1)), new LabeledPoint(1.0, Vectors.dense(0.0, 2.2, -1.5))); - SchemaRDD test = jsql.applySchema(jsc.parallelize(localTest), LabeledPoint.class); + DataFrame test = jsql.applySchema(jsc.parallelize(localTest), LabeledPoint.class); // Make predictions on test documents using the Transformer.transform() method. // LogisticRegression.transform will only use the 'features' column. // Note that model2.transform() outputs a 'probability' column instead of the usual 'score' // column since we renamed the lr.scoreCol parameter previously. - model2.transform(test).registerAsTable("results"); - SchemaRDD results = + model2.transform(test).registerTempTable("results"); + DataFrame results = jsql.sql("SELECT features, label, probability, prediction FROM results"); for (Row r: results.collect()) { System.out.println("(" + r.get(0) + ", " + r.get(1) + ") -> prob=" + r.get(2) diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleTextClassificationPipeline.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleTextClassificationPipeline.java index 74db449fad..82d665a3e1 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleTextClassificationPipeline.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleTextClassificationPipeline.java @@ -29,7 +29,7 @@ import org.apache.spark.ml.PipelineStage; import org.apache.spark.ml.classification.LogisticRegression; import org.apache.spark.ml.feature.HashingTF; import org.apache.spark.ml.feature.Tokenizer; -import org.apache.spark.sql.SchemaRDD; +import org.apache.spark.sql.DataFrame; import org.apache.spark.sql.SQLContext; import org.apache.spark.sql.Row; @@ -54,7 +54,7 @@ public class JavaSimpleTextClassificationPipeline { new LabeledDocument(1L, "b d", 0.0), new LabeledDocument(2L, "spark f g h", 1.0), new LabeledDocument(3L, "hadoop mapreduce", 0.0)); - SchemaRDD training = jsql.applySchema(jsc.parallelize(localTraining), LabeledDocument.class); + DataFrame training = jsql.applySchema(jsc.parallelize(localTraining), LabeledDocument.class); // Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr. Tokenizer tokenizer = new Tokenizer() @@ -79,11 +79,11 @@ public class JavaSimpleTextClassificationPipeline { new Document(5L, "l m n"), new Document(6L, "mapreduce spark"), new Document(7L, "apache hadoop")); - SchemaRDD test = jsql.applySchema(jsc.parallelize(localTest), Document.class); + DataFrame test = jsql.applySchema(jsc.parallelize(localTest), Document.class); // Make predictions on test documents. - model.transform(test).registerAsTable("prediction"); - SchemaRDD predictions = jsql.sql("SELECT id, text, score, prediction FROM prediction"); + model.transform(test).registerTempTable("prediction"); + DataFrame predictions = jsql.sql("SELECT id, text, score, prediction FROM prediction"); for (Row r: predictions.collect()) { System.out.println("(" + r.get(0) + ", " + r.get(1) + ") --> score=" + r.get(2) + ", prediction=" + r.get(3)); 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 b70804635d..8defb769ff 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 @@ -26,9 +26,9 @@ import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.function.Function; -import org.apache.spark.sql.SQLContext; -import org.apache.spark.sql.SchemaRDD; +import org.apache.spark.sql.DataFrame; import org.apache.spark.sql.Row; +import org.apache.spark.sql.SQLContext; public class JavaSparkSQL { public static class Person implements Serializable { @@ -74,13 +74,13 @@ public class JavaSparkSQL { }); // Apply a schema to an RDD of Java Beans and register it as a table. - SchemaRDD schemaPeople = sqlCtx.applySchema(people, Person.class); + DataFrame schemaPeople = sqlCtx.applySchema(people, Person.class); schemaPeople.registerTempTable("people"); // SQL can be run over RDDs that have been registered as tables. - SchemaRDD teenagers = sqlCtx.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19"); + DataFrame teenagers = sqlCtx.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19"); - // The results of SQL queries are SchemaRDDs and support all the normal RDD operations. + // 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.toJavaRDD().map(new Function<Row, String>() { @Override @@ -93,17 +93,17 @@ public class JavaSparkSQL { } System.out.println("=== Data source: Parquet File ==="); - // JavaSchemaRDDs can be saved as parquet files, maintaining the schema information. + // DataFrames can be saved as parquet files, maintaining the schema information. schemaPeople.saveAsParquetFile("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 JavaSchemaRDD. - SchemaRDD parquetFile = sqlCtx.parquetFile("people.parquet"); + // The result of loading a parquet file is also a DataFrame. + DataFrame parquetFile = sqlCtx.parquetFile("people.parquet"); //Parquet files can also be registered as tables and then used in SQL statements. parquetFile.registerTempTable("parquetFile"); - SchemaRDD teenagers2 = + DataFrame teenagers2 = sqlCtx.sql("SELECT name FROM parquetFile WHERE age >= 13 AND age <= 19"); teenagerNames = teenagers2.toJavaRDD().map(new Function<Row, String>() { @Override @@ -119,8 +119,8 @@ public class JavaSparkSQL { // A JSON dataset is pointed by path. // 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 JavaSchemaRDD from the file(s) pointed by path - SchemaRDD peopleFromJsonFile = sqlCtx.jsonFile(path); + // Create a DataFrame from the file(s) pointed by path + DataFrame peopleFromJsonFile = sqlCtx.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. @@ -130,13 +130,13 @@ public class JavaSparkSQL { // |-- age: IntegerType // |-- name: StringType - // Register this JavaSchemaRDD as a table. + // Register this DataFrame as a table. peopleFromJsonFile.registerTempTable("people"); // SQL statements can be run by using the sql methods provided by sqlCtx. - SchemaRDD teenagers3 = sqlCtx.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19"); + DataFrame teenagers3 = sqlCtx.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19"); - // The results of SQL queries are JavaSchemaRDDs and support all the normal RDD operations. + // 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. teenagerNames = teenagers3.toJavaRDD().map(new Function<Row, String>() { @Override @@ -146,14 +146,14 @@ public class JavaSparkSQL { System.out.println(name); } - // Alternatively, a JavaSchemaRDD can be created for a JSON dataset represented by + // Alternatively, a DataFrame can be created for a JSON dataset represented by // a RDD[String] storing one JSON object per string. List<String> jsonData = Arrays.asList( "{\"name\":\"Yin\",\"address\":{\"city\":\"Columbus\",\"state\":\"Ohio\"}}"); JavaRDD<String> anotherPeopleRDD = ctx.parallelize(jsonData); - SchemaRDD peopleFromJsonRDD = sqlCtx.jsonRDD(anotherPeopleRDD.rdd()); + DataFrame peopleFromJsonRDD = sqlCtx.jsonRDD(anotherPeopleRDD.rdd()); - // Take a look at the schema of this new JavaSchemaRDD. + // Take a look at the schema of this new DataFrame. peopleFromJsonRDD.printSchema(); // The schema of anotherPeople is ... // root @@ -164,7 +164,7 @@ public class JavaSparkSQL { peopleFromJsonRDD.registerTempTable("people2"); - SchemaRDD peopleWithCity = sqlCtx.sql("SELECT name, address.city FROM people2"); + DataFrame peopleWithCity = sqlCtx.sql("SELECT name, address.city FROM people2"); List<String> nameAndCity = peopleWithCity.toJavaRDD().map(new Function<Row, String>() { @Override public String call(Row row) { |