Skip to content
Permalink
Browse files
  • Loading branch information
leerho committed Mar 9, 2022
2 parents 2fdbe99 + 18c8677 commit 042781e0487ff99a0b054d7627b925612bcee2b4
Showing 15 changed files with 59 additions and 60 deletions.
@@ -3,11 +3,10 @@
| Component | Release | ZIP | ASC | SHA512 | Date-Time | SVN ID | Committer |
|:---------:|:-------:|:---:|:---:|:------:|:---------:|:------:|:---------:|
| Java Core | 3.1.0 | [Download](https://www.apache.org/dyn/closer.lua/datasketches/java/3.1.0/apache-datasketches-java-3.1.0-src.zip) | [Signature](https://downloads.apache.org/datasketches/java/3.1.0/apache-datasketches-java-3.1.0-src.zip.asc) | [Hash](https://downloads.apache.org/datasketches/java/3.1.0/apache-datasketches-java-3.1.0-src.zip.sha512) | 2022-01-26T19:20:10Z | 52288 | leerho |
| C++,Python Core | 3.2.0 | [Download](https://www.apache.org/dyn/closer.lua/datasketches/cpp/3.2.0/apache-datasketches-cpp-3.2.0-src.zip) | [Signature](https://downloads.apache.org/datasketches/cpp/3.2.0/apache-datasketches-cpp-3.2.0-src.zip.asc) | [Hash](https://downloads.apache.org/datasketches/cpp/3.2.0/apache-datasketches-cpp-3.2.0-src.zip.sha512) | 2021-09-29T18:15:32Z | 50186 | jmalkin |
| C++,Python Core | 3.3.0 | [Download](https://www.apache.org/dyn/closer.lua/datasketches/cpp/3.3.0/apache-datasketches-cpp-3.3.0-src.zip) | [Signature](https://downloads.apache.org/datasketches/cpp/3.3.0/apache-datasketches-cpp-3.3.0-src.zip.asc) | [Hash](https://downloads.apache.org/datasketches/cpp/3.3.0/apache-datasketches-cpp-3.3.0-src.zip.sha512) | 2021-12-23T19:54:24Z | 51742 | alsay |
| Java Memory | 2.0.0 | [Download](https://www.apache.org/dyn/closer.lua/datasketches/memory/2.0.0/apache-datasketches-memory-2.0.0-src.zip) | [Signature](https://downloads.apache.org/datasketches/memory/2.0.0/apache-datasketches-memory-2.0.0-src.zip.asc) | [Hash](https://downloads.apache.org/datasketches/memory/2.0.0/apache-datasketches-memory-2.0.0-src.zip.sha512) | 2021-09-14T18:30:11Z | 49937 | leerho |
| Java Hive Adaptor | 1.1.0-incubating | [Download](https://www.apache.org/dyn/closer.lua/datasketches/hive/1.1.0-incubating/apache-datasketches-hive-1.1.0-incubating-src.zip) | [Signature](https://downloads.apache.org/datasketches/hive/1.1.0-incubating/apache-datasketches-hive-1.1.0-incubating-src.zip.asc) | [Hash](https://downloads.apache.org/datasketches/hive/1.1.0-incubating/apache-datasketches-hive-1.1.0-incubating-src.zip.sha512) | 2020-07-06T20:51:06Z | 40324 | leerho |
| Java Pig Adaptor | 1.0.0-incubating | [Download](https://www.apache.org/dyn/closer.lua/datasketches/pig/1.0.0-incubating/apache-datasketches-pig-1.0.0-incubating-src.zip) | [Signature](https://downloads.apache.org/datasketches/pig/1.0.0-incubating/apache-datasketches-pig-1.0.0-incubating-src.zip.asc) | [Hash](https://downloads.apache.org/datasketches/pig/1.0.0-incubating/apache-datasketches-pig-1.0.0-incubating-src.zip.sha512) | 2019-10-19T01:24:36Z | 36385 | leerho |
| Java Hive Adaptor | 1.2.0 | [Download](https://www.apache.org/dyn/closer.lua/datasketches/hive/1.2.0/apache-datasketches-hive-1.2.0-src.zip) | [Signature](https://downloads.apache.org/datasketches/hive/1.2.0/apache-datasketches-hive-1.2.0-src.zip.asc) | [Hash](https://downloads.apache.org/datasketches/hive/1.2.0/apache-datasketches-hive-1.2.0-src.zip.sha512) | 2022-03-07T23:30:20Z | 52909 | alsay |
| Java Pig Adaptor | 1.1.0 | [Download](https://www.apache.org/dyn/closer.lua/datasketches/pig/1.1.0/apache-datasketches-pig-1.1.0-src.zip) | [Signature](https://downloads.apache.org/datasketches/pig/1.1.0/apache-datasketches-pig-1.1.0-src.zip.asc) | [Hash](https://downloads.apache.org/datasketches/pig/1.1.0/apache-datasketches-pig-1.1.0-src.zip.sha512) | 2022-02-17T19:42:16Z | 52612 | alsay |
| C++ PostgreSQL Adaptor | 1.5.0 | [Download](https://www.apache.org/dyn/closer.lua/datasketches/postgresql/1.5.0/apache-datasketches-postgresql-1.5.0-src.zip) | [Signature](https://downloads.apache.org/datasketches/postgresql/1.5.0/apache-datasketches-postgresql-1.5.0-src.zip.asc) | [Hash](https://downloads.apache.org/datasketches/postgresql/1.5.0/apache-datasketches-postgresql-1.5.0-src.zip.sha512) | 2021-08-09T22:54:59Z | 49403 | alsay |

<!-- End _includes/downloadsInclude.txt -->
@@ -23,9 +23,9 @@ layout: doc_page

### Building sketches, merging sketches and getting estimates

add jar datasketches-memory-1.2.0-incubating.jar;
add jar datasketches-java-1.2.0-incubating.jar;
add jar datasketches-hive-1.0.0-incubating.jar;
add jar datasketches-memory-2.0.0.jar;
add jar datasketches-java-3.1.0.jar;
add jar datasketches-hive-1.2.0.jar;

create temporary function data2sketch as 'org.apache.datasketches.hive.cpc.DataToSketchUDAF';
create temporary function unionSketches as 'org.apache.datasketches.hive.cpc.UnionSketchUDAF';
@@ -62,9 +62,9 @@ layout: doc_page

Notice the difference between UnionUDF in this example, which takes two sketches, and UnionUDAF in the previous example, which is an aggregate function taking a collection of sketches as one parameter.

add jar datasketches-memory-1.2.0-incubating.jar;
add jar datasketches-java-1.2.0-incubating.jar;
add jar datasketches-hive-1.0.0-incubating.jar;
add jar datasketches-memory-2.0.0.jar;
add jar datasketches-java-3.1.0.jar;
add jar datasketches-hive-1.2.0.jar;

create temporary function data2sketch as 'org.apache.datasketches.hive.cpc.DataToSketchUDAF';
create temporary function union2 as 'org.apache.datasketches.hive.cpc.UnionSketchUDF';
@@ -32,9 +32,9 @@ layout: doc_page

### cpc.pig script: building sketches, merging sketches and getting estimates

register datasketches-memory-1.2.0-incubating.jar;
register datasketches-java-1.2.0-incubating.jar;
register datasketches-pig-1.0.0-incubating.jar;
register datasketches-memory-2.0.0.jar;
register datasketches-java-3.1.0.jar;
register datasketches-pig-1.1.0.jar;

define dataToSketch org.apache.datasketches.pig.cpc.DataToSketch('12');
define unionSketch org.apache.datasketches.pig.cpc.UnionSketch('12');
@@ -21,9 +21,9 @@ layout: doc_page
-->
## Frequent Items Sketch Hive UDFs

add jar datasketches-memory-1.2.0-incubating.jar;
add jar datasketches-java-1.2.0-incubating.jar;
add jar datasketches-hive-1.0.0-incubating.jar;
add jar datasketches-memory-2.0.0.jar;
add jar datasketches-java-3.1.0.jar;
add jar datasketches-hive-1.2.0.jar;

create temporary function data2sketch as 'org.apache.datasketches.hive.frequencies.DataToStringsSketchUDAF';
create temporary function union as 'org.apache.datasketches.hive.frequencies.UnionStringsSketchUDAF';
@@ -32,9 +32,9 @@ layout: doc_page

### frequent_items.pig script

register datasketches-memory-1.2.0-incubating.jar;
register datasketches-java-1.2.0-incubating.jar;
register datasketches-pig-1.0.0-incubating.jar;
register datasketches-memory-2.0.0.jar;
register datasketches-java-3.1.0.jar;
register datasketches-pig-1.1.0.jar;

-- very small sketch just for the purpose of this tiny example
define dataToSketch org.apache.datasketches.pig.frequencies.DataToFrequentStringsSketch('8');
@@ -23,9 +23,9 @@ layout: doc_page

### Building sketches, computing unions and getting estimates

add jar datasketches-memory-1.2.0-incubating.jar;
add jar datasketches-java-1.2.0-incubating.jar;
add jar datasketches-hive-1.0.0-incubating.jar;
add jar datasketches-memory-2.0.0.jar;
add jar datasketches-java-3.1.0.jar;
add jar datasketches-hive-1.2.0.jar;

create temporary function data2sketch as 'org.apache.datasketches.hive.hll.DataToSketchUDAF';
create temporary function unionSketches as 'org.apache.datasketches.hive.hll.UnionSketchUDAF';
@@ -60,9 +60,9 @@ layout: doc_page

Notice the difference between UnionUDF in this example, which takes two sketches, and UnionUDAF in the previous example, which is an aggregate function taking a collection of sketches as one parameter.

add jar datasketches-memory-1.2.0-incubating.jar;
add jar datasketches-java-1.2.0-incubating.jar;
add jar datasketches-hive-1.0.0-incubating.jar;
add jar datasketches-memory-2.0.0.jar;
add jar datasketches-java-3.1.0.jar;
add jar datasketches-hive-1.2.0.jar;

create temporary function data2sketch as 'org.apache.datasketches.hive.hll.DataToSketchUDAF';
create temporary function estimate as 'org.apache.datasketches.hive.hll.SketchToEstimateUDF';
@@ -34,9 +34,9 @@ This functionality appeared in sketches-pig-0.10.0. Depends on sketches-core-0.1

### hll.pig script: build sketches, union sketches and get estimates

register datasketches-memory-1.2.0-incubating.jar;
register datasketches-java-1.2.0-incubating.jar;
register datasketches-pig-1.0.0-incubating.jar;
register datasketches-memory-2.0.0.jar;
register datasketches-java-3.1.0.jar;
register datasketches-pig-1.1.0.jar;

-- Parameters are optional. Default is 12
define dataToSketch org.apache.datasketches.pig.hll.DataToSketch('10');
@@ -95,9 +95,9 @@ From 'dump h':

### hll_union.pig script: union sketches from different columns

register datasketches-memory-1.2.0-incubating.jar;
register datasketches-java-1.2.0-incubating.jar;
register datasketches-pig-1.0.0-incubating.jar;
register datasketches-memory-2.0.0.jar;
register datasketches-java-3.1.0.jar;
register datasketches-pig-1.1.0.jar;

define dataToSketch org.apache.datasketches.pig.hll.DataToSketch();
define unionSketch org.apache.datasketches.pig.hll.UnionSketch();
@@ -23,9 +23,9 @@ layout: doc_page

### DoublesSketch example

add jar datasketches-memory-1.2.0-incubating.jar;
add jar datasketches-java-1.2.0-incubating.jar;
add jar datasketches-hive-1.0.0-incubating.jar;
add jar datasketches-memory-2.0.0.jar;
add jar datasketches-java-3.1.0.jar;
add jar datasketches-hive-1.2.0.jar;

create temporary function data2sketch as 'org.apache.datasketches.hive.quantiles.DataToDoublesSketchUDAF';
create temporary function unionSketches as 'org.apache.datasketches.hive.quantiles.UnionDoublesSketchUDAF';
@@ -32,9 +32,9 @@ layout: doc_page

### quantiles.pig script

register datasketches-memory-1.2.0-incubating.jar;
register datasketches-java-1.2.0-incubating.jar;
register datasketches-pig-1.0.0-incubating.jar;
register datasketches-memory-2.0.0.jar;
register datasketches-java-3.1.0.jar;
register datasketches-pig-1.1.0.jar;

define dataToSketch org.apache.datasketches.pig.quantiles.DataToDoublesSketch();
define unionSketch org.apache.datasketches.pig.quantiles.UnionDoublesSketch();
@@ -32,9 +32,9 @@ layout: doc_page

### reservoir_example.pig script

register datasketches-memory-1.2.0-incubating.jar;
register datasketches-java-1.2.0-incubating.jar;
register datasketches-pig-1.0.0-incubating.jar;
register datasketches-memory-2.0.0.jar;
register datasketches-java-3.1.0.jar;
register datasketches-pig-1.1.0.jar;

-- very small sketch just for the purpose of this tiny example
DEFINE ReservoirSampling org.apache.datasketches.pig.sampling.ReservoirSampling('4');
@@ -32,9 +32,9 @@ layout: doc_page

### varopt_example.pig script

register datasketches-memory-1.2.0-incubating.jar;
register datasketches-java-1.2.0-incubating.jar;
register datasketches-pig-1.0.0-incubating.jar;
register datasketches-memory-2.0.0.jar;
register datasketches-java-3.1.0.jar;
register datasketches-pig-1.1.0.jar;

-- very small sketch just for the purpose of this tiny example
DEFINE DataToSketch org.apache.datasketches.pig.sampling.DataToVarOptSketch('4', '0');
@@ -23,9 +23,9 @@ layout: doc_page

### Building sketches, merging sketches and getting estimates

add jar datasketches-memory-1.2.0-incubating.jar;
add jar datasketches-java-1.2.0-incubating.jar;
add jar datasketches-hive-1.0.0-incubating.jar;
add jar datasketches-memory-2.0.0.jar;
add jar datasketches-java-3.1.0.jar;
add jar datasketches-hive-1.2.0.jar;

create temporary function data2sketch as 'org.apache.datasketches.hive.theta.DataToSketchUDAF';
create temporary function unionSketches as 'org.apache.datasketches.hive.theta.UnionSketchUDAF';
@@ -56,9 +56,9 @@ layout: doc_page

Notice the difference between UnionUDF in this example, which takes two sketches, and UnionUDAF in the previous example, which is an aggregate function taking a collection of sketches as one parameter. The same is true about IntersectSketchUDF and IntersectSketchUDAF.

add jar datasketches-memory-1.2.0-incubating.jar;
add jar datasketches-java-1.2.0-incubating.jar;
add jar datasketches-hive-1.0.0-incubating.jar;
add jar datasketches-memory-2.0.0.jar;
add jar datasketches-java-3.1.0.jar;
add jar datasketches-hive-1.2.0.jar;

create temporary function data2sketch as 'org.apache.datasketches.hive.theta.DataToSketchUDAF';
create temporary function estimate as 'org.apache.datasketches.hive.theta.EstimateSketchUDF';
@@ -32,9 +32,9 @@ layout: doc_page

### theta.pig script: building sketches, merging sketches and getting estimates

register datasketches-memory-1.2.0-incubating.jar;
register datasketches-java-1.2.0-incubating.jar;
register datasketches-pig-1.0.0-incubating.jar;
register datasketches-memory-2.0.0.jar;
register datasketches-java-3.1.0.jar;
register datasketches-pig-1.1.0.jar;

define dataToSketch org.apache.datasketches.pig.theta.DataToSketch('32');
define unionSketch org.apache.datasketches.pig.theta.Union('32');
@@ -79,9 +79,9 @@ to show the estimation mode for the purposes of this example.

### theta_setops.pig script: set operations on sketches

register datasketches-memory-1.2.0-incubating.jar;
register datasketches-java-1.2.0-incubating.jar;
register datasketches-pig-1.0.0-incubating.jar;
register datasketches-memory-2.0.0-incubating.jar;
register datasketches-java-3.1.0.jar;
register datasketches-pig-1.1.0.jar;

define dataToSketch org.apache.datasketches.pig.theta.DataToSketch('32');
define unionSketch org.apache.datasketches.pig.theta.Union();
@@ -21,9 +21,9 @@ layout: doc_page
-->
## Tuple Sketch Hive UDFs

add jar datasketches-memory-1.2.0-incubating.jar;
add jar datasketches-java-1.2.0-incubating.jar;
add jar datasketches-hive-1.0.0-incubating.jar;
add jar datasketches-memory-2.0.0.jar;
add jar datasketches-java-3.1.0.jar;
add jar datasketches-hive-1.2.0.jar;

create temporary function data2sketch as 'org.apache.datasketches.hive.tuple.DataToArrayOfDoublesSketchUDAF';
create temporary function unionSketches as 'org.apache.datasketches.hive.tuple.UnionArrayOfDoublesSketchUDAF';
@@ -32,9 +32,9 @@ layout: doc_page

### tuple.pig script

register datasketches-memory-1.2.0-incubating.jar;
register datasketches-java-1.2.0-incubating.jar;
register datasketches-pig-1.0.0-incubating.jar;
register datasketches-memory-2.0.0.jar;
register datasketches-java-3.1.0.jar;
register datasketches-pig-1.1.0.jar;

define dataToSketch org.apache.datasketches.pig.tuple.DataToDoubleSummarySketch('32');
define unionSketch org.apache.datasketches.pig.tuple.UnionDoubleSummarySketch('32');

0 comments on commit 042781e

Please sign in to comment.