diff --git a/CHANGELOG b/CHANGELOG index 7ae0d8e08396..6efbf8a6a5ac 100644 --- a/CHANGELOG +++ b/CHANGELOG @@ -1,3 +1,18 @@ +======== +5.3.2 +======== +---------------- +Bug Fixes +---------------- +* Fix and add notebooks to import models from Hugging Face + * Add ONNX and TensorFlow notebooks + * Fix XlnetForSeqeunceClassification and added XlnetForTokenClassificaiton + * Rename DistilBertForZeroShotClassification + * Add missing notebooks +* Add MPNetEmbeddings to annotator +* Fix XLMRoBertaForQuestionAnswering, XLMRoBertaForTokenClassification, and XLMRoBertaForSequenceClassification: Reverted the change in tfFile naming that was causing exceptions while loading and saving the models +* Fix documentation for sparknlp.start() + ======== 5.3.1 ======== diff --git a/README.md b/README.md index dfff9ca155cf..08bcdc51dd69 100644 --- a/README.md +++ b/README.md @@ -165,7 +165,7 @@ To use Spark NLP you need the following requirements: **GPU (optional):** -Spark NLP 5.3.1 is built with ONNX 1.17.0 and TensorFlow 2.7.1 deep learning engines. The minimum following NVIDIA® software are only required for GPU support: +Spark NLP 5.3.2 is built with ONNX 1.17.0 and TensorFlow 2.7.1 deep learning engines. The minimum following NVIDIA® software are only required for GPU support: - NVIDIA® GPU drivers version 450.80.02 or higher - CUDA® Toolkit 11.2 @@ -181,7 +181,7 @@ $ java -version $ conda create -n sparknlp python=3.7 -y $ conda activate sparknlp # spark-nlp by default is based on pyspark 3.x -$ pip install spark-nlp==5.3.1 pyspark==3.3.1 +$ pip install spark-nlp==5.3.2 pyspark==3.3.1 ``` In Python console or Jupyter `Python3` kernel: @@ -226,7 +226,7 @@ For more examples, you can visit our dedicated [examples](https://github.com/Joh ## Apache Spark Support -Spark NLP *5.3.1* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x +Spark NLP *5.3.2* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x | Spark NLP | Apache Spark 3.5.x | Apache Spark 3.4.x | Apache Spark 3.3.x | Apache Spark 3.2.x | Apache Spark 3.1.x | Apache Spark 3.0.x | Apache Spark 2.4.x | Apache Spark 2.3.x | |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------| @@ -270,7 +270,7 @@ Find out more about `Spark NLP` versions from our [release notes](https://github ## Databricks Support -Spark NLP 5.3.1 has been tested and is compatible with the following runtimes: +Spark NLP 5.3.2 has been tested and is compatible with the following runtimes: **CPU:** @@ -343,7 +343,7 @@ Spark NLP 5.3.1 has been tested and is compatible with the following runtimes: ## EMR Support -Spark NLP 5.3.1 has been tested and is compatible with the following EMR releases: +Spark NLP 5.3.2 has been tested and is compatible with the following EMR releases: - emr-6.2.0 - emr-6.3.0 @@ -393,11 +393,11 @@ Spark NLP supports all major releases of Apache Spark 3.0.x, Apache Spark 3.1.x, ```sh # CPU -spark-shell --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 +spark-shell --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 -pyspark --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 +pyspark --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 -spark-submit --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 +spark-submit --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` The `spark-nlp` has been published to @@ -406,11 +406,11 @@ the [Maven Repository](https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/s ```sh # GPU -spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.1 +spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.2 -pyspark --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.1 +pyspark --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.2 -spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.1 +spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.2 ``` @@ -420,11 +420,11 @@ the [Maven Repository](https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/s ```sh # AArch64 -spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.1 +spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.2 -pyspark --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.1 +pyspark --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.2 -spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.1 +spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.2 ``` @@ -434,11 +434,11 @@ the [Maven Repository](https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/s ```sh # M1/M2 (Apple Silicon) -spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.1 +spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.2 -pyspark --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.1 +pyspark --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.2 -spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.1 +spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.2 ``` @@ -452,7 +452,7 @@ set in your SparkSession: spark-shell \ --driver-memory 16g \ --conf spark.kryoserializer.buffer.max=2000M \ - --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 + --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` ## Scala @@ -470,7 +470,7 @@ coordinates: com.johnsnowlabs.nlp spark-nlp_2.12 - 5.3.1 + 5.3.2 ``` @@ -481,7 +481,7 @@ coordinates: com.johnsnowlabs.nlp spark-nlp-gpu_2.12 - 5.3.1 + 5.3.2 ``` @@ -492,7 +492,7 @@ coordinates: com.johnsnowlabs.nlp spark-nlp-aarch64_2.12 - 5.3.1 + 5.3.2 ``` @@ -503,7 +503,7 @@ coordinates: com.johnsnowlabs.nlp spark-nlp-silicon_2.12 - 5.3.1 + 5.3.2 ``` @@ -513,28 +513,28 @@ coordinates: ```sbtshell // https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/spark-nlp -libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp" % "5.3.1" +libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp" % "5.3.2" ``` **spark-nlp-gpu:** ```sbtshell // https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/spark-nlp-gpu -libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-gpu" % "5.3.1" +libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-gpu" % "5.3.2" ``` **spark-nlp-aarch64:** ```sbtshell // https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/spark-nlp-aarch64 -libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-aarch64" % "5.3.1" +libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-aarch64" % "5.3.2" ``` **spark-nlp-silicon:** ```sbtshell // https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/spark-nlp-silicon -libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-silicon" % "5.3.1" +libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-silicon" % "5.3.2" ``` Maven @@ -556,7 +556,7 @@ If you installed pyspark through pip/conda, you can install `spark-nlp` through Pip: ```bash -pip install spark-nlp==5.3.1 +pip install spark-nlp==5.3.2 ``` Conda: @@ -585,7 +585,7 @@ spark = SparkSession.builder .config("spark.driver.memory", "16G") .config("spark.driver.maxResultSize", "0") .config("spark.kryoserializer.buffer.max", "2000M") - .config("spark.jars.packages", "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1") + .config("spark.jars.packages", "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2") .getOrCreate() ``` @@ -656,7 +656,7 @@ Use either one of the following options - Add the following Maven Coordinates to the interpreter's library list ```bash -com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 +com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` - Add a path to pre-built jar from [here](#compiled-jars) in the interpreter's library list making sure the jar is @@ -667,7 +667,7 @@ com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 Apart from the previous step, install the python module through pip ```bash -pip install spark-nlp==5.3.1 +pip install spark-nlp==5.3.2 ``` Or you can install `spark-nlp` from inside Zeppelin by using Conda: @@ -695,7 +695,7 @@ launch the Jupyter from the same Python environment: $ conda create -n sparknlp python=3.8 -y $ conda activate sparknlp # spark-nlp by default is based on pyspark 3.x -$ pip install spark-nlp==5.3.1 pyspark==3.3.1 jupyter +$ pip install spark-nlp==5.3.2 pyspark==3.3.1 jupyter $ jupyter notebook ``` @@ -712,7 +712,7 @@ export PYSPARK_PYTHON=python3 export PYSPARK_DRIVER_PYTHON=jupyter export PYSPARK_DRIVER_PYTHON_OPTS=notebook -pyspark --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 +pyspark --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` Alternatively, you can mix in using `--jars` option for pyspark + `pip install spark-nlp` @@ -739,7 +739,7 @@ This script comes with the two options to define `pyspark` and `spark-nlp` versi # -s is for spark-nlp # -g will enable upgrading libcudnn8 to 8.1.0 on Google Colab for GPU usage # by default they are set to the latest -!wget https://setup.johnsnowlabs.com/colab.sh -O - | bash /dev/stdin -p 3.2.3 -s 5.3.1 +!wget https://setup.johnsnowlabs.com/colab.sh -O - | bash /dev/stdin -p 3.2.3 -s 5.3.2 ``` [Spark NLP quick start on Google Colab](https://colab.research.google.com/github/JohnSnowLabs/spark-nlp/blob/master/examples/python/quick_start_google_colab.ipynb) @@ -762,7 +762,7 @@ This script comes with the two options to define `pyspark` and `spark-nlp` versi # -s is for spark-nlp # -g will enable upgrading libcudnn8 to 8.1.0 on Kaggle for GPU usage # by default they are set to the latest -!wget https://setup.johnsnowlabs.com/colab.sh -O - | bash /dev/stdin -p 3.2.3 -s 5.3.1 +!wget https://setup.johnsnowlabs.com/colab.sh -O - | bash /dev/stdin -p 3.2.3 -s 5.3.2 ``` [Spark NLP quick start on Kaggle Kernel](https://www.kaggle.com/mozzie/spark-nlp-named-entity-recognition) is a live @@ -781,9 +781,9 @@ demo on Kaggle Kernel that performs named entity recognitions by using Spark NLP 3. In `Libraries` tab inside your cluster you need to follow these steps: - 3.1. Install New -> PyPI -> `spark-nlp==5.3.1` -> Install + 3.1. Install New -> PyPI -> `spark-nlp==5.3.2` -> Install - 3.2. Install New -> Maven -> Coordinates -> `com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1` -> Install + 3.2. Install New -> Maven -> Coordinates -> `com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2` -> Install 4. Now you can attach your notebook to the cluster and use Spark NLP! @@ -834,7 +834,7 @@ A sample of your software configuration in JSON on S3 (must be public access): "spark.kryoserializer.buffer.max": "2000M", "spark.serializer": "org.apache.spark.serializer.KryoSerializer", "spark.driver.maxResultSize": "0", - "spark.jars.packages": "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1" + "spark.jars.packages": "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2" } }] ``` @@ -843,7 +843,7 @@ A sample of AWS CLI to launch EMR cluster: ```.sh aws emr create-cluster \ ---name "Spark NLP 5.3.1" \ +--name "Spark NLP 5.3.2" \ --release-label emr-6.2.0 \ --applications Name=Hadoop Name=Spark Name=Hive \ --instance-type m4.4xlarge \ @@ -907,7 +907,7 @@ gcloud dataproc clusters create ${CLUSTER_NAME} \ --enable-component-gateway \ --metadata 'PIP_PACKAGES=spark-nlp spark-nlp-display google-cloud-bigquery google-cloud-storage' \ --initialization-actions gs://goog-dataproc-initialization-actions-${REGION}/python/pip-install.sh \ - --properties spark:spark.serializer=org.apache.spark.serializer.KryoSerializer,spark:spark.driver.maxResultSize=0,spark:spark.kryoserializer.buffer.max=2000M,spark:spark.jars.packages=com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 + --properties spark:spark.serializer=org.apache.spark.serializer.KryoSerializer,spark:spark.driver.maxResultSize=0,spark:spark.kryoserializer.buffer.max=2000M,spark:spark.jars.packages=com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` 2. On an existing one, you need to install spark-nlp and spark-nlp-display packages from PyPI. @@ -950,7 +950,7 @@ spark = SparkSession.builder .config("spark.kryoserializer.buffer.max", "2000m") .config("spark.jsl.settings.pretrained.cache_folder", "sample_data/pretrained") .config("spark.jsl.settings.storage.cluster_tmp_dir", "sample_data/storage") - .config("spark.jars.packages", "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1") + .config("spark.jars.packages", "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2") .getOrCreate() ``` @@ -964,7 +964,7 @@ spark-shell \ --conf spark.kryoserializer.buffer.max=2000M \ --conf spark.jsl.settings.pretrained.cache_folder="sample_data/pretrained" \ --conf spark.jsl.settings.storage.cluster_tmp_dir="sample_data/storage" \ - --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 + --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` **pyspark:** @@ -977,7 +977,7 @@ pyspark \ --conf spark.kryoserializer.buffer.max=2000M \ --conf spark.jsl.settings.pretrained.cache_folder="sample_data/pretrained" \ --conf spark.jsl.settings.storage.cluster_tmp_dir="sample_data/storage" \ - --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 + --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` **Databricks:** @@ -1249,7 +1249,7 @@ spark = SparkSession.builder .config("spark.driver.memory", "16G") .config("spark.driver.maxResultSize", "0") .config("spark.kryoserializer.buffer.max", "2000M") - .config("spark.jars", "/tmp/spark-nlp-assembly-5.3.1.jar") + .config("spark.jars", "/tmp/spark-nlp-assembly-5.3.2.jar") .getOrCreate() ``` @@ -1258,7 +1258,7 @@ spark = SparkSession.builder version (3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x) - If you are local, you can load the Fat JAR from your local FileSystem, however, if you are in a cluster setup you need to put the Fat JAR on a distributed FileSystem such as HDFS, DBFS, S3, etc. ( - i.e., `hdfs:///tmp/spark-nlp-assembly-5.3.1.jar`) + i.e., `hdfs:///tmp/spark-nlp-assembly-5.3.2.jar`) Example of using pretrained Models and Pipelines in offline: diff --git a/build.sbt b/build.sbt index 70c46d429421..2a438828c1f3 100644 --- a/build.sbt +++ b/build.sbt @@ -6,7 +6,7 @@ name := getPackageName(is_silicon, is_gpu, is_aarch64) organization := "com.johnsnowlabs.nlp" -version := "5.3.1" +version := "5.3.2" (ThisBuild / scalaVersion) := scalaVer diff --git a/conda/meta.yaml b/conda/meta.yaml index a3940f274721..809bebe14ee7 100644 --- a/conda/meta.yaml +++ b/conda/meta.yaml @@ -1,5 +1,5 @@ {% set name = "spark-nlp" %} -{% set version = "5.3.1" %} +{% set version = "5.3.2" %} package: name: {{ name|lower }} @@ -7,7 +7,7 @@ package: source: url: https://pypi.io/packages/source/{{ name[0] }}/{{ name }}/spark-nlp-{{ version }}.tar.gz - sha256: 3680f6ca4b0ba95dafafe5c74cee5751226b34d4548824da1009e276a9ff6d2d + sha256: c98d14d51778c799ef43526e2eaeb5d76245ed1eda2ac3205c11e58cbbe825b6 build: noarch: python diff --git a/docs/README.md b/docs/README.md index c07d04cf0fe5..c91bad2c1e75 100644 --- a/docs/README.md +++ b/docs/README.md @@ -173,7 +173,7 @@ To use Spark NLP you need the following requirements: **GPU (optional):** -Spark NLP 5.3.1 is built with ONNX 1.16.3 and TensorFlow 2.7.1 deep learning engines. The minimum following NVIDIA® software are only required for GPU support: +Spark NLP 5.3.2 is built with ONNX 1.16.3 and TensorFlow 2.7.1 deep learning engines. The minimum following NVIDIA® software are only required for GPU support: - NVIDIA® GPU drivers version 450.80.02 or higher - CUDA® Toolkit 11.2 @@ -189,7 +189,7 @@ $ java -version $ conda create -n sparknlp python=3.7 -y $ conda activate sparknlp # spark-nlp by default is based on pyspark 3.x -$ pip install spark-nlp==5.3.1 pyspark==3.3.1 +$ pip install spark-nlp==5.3.2 pyspark==3.3.1 ``` In Python console or Jupyter `Python3` kernel: @@ -234,7 +234,7 @@ For more examples, you can visit our dedicated [examples](https://github.com/Joh ## Apache Spark Support -Spark NLP *5.3.1* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x +Spark NLP *5.3.2* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x | Spark NLP | Apache Spark 3.5.x | Apache Spark 3.4.x | Apache Spark 3.3.x | Apache Spark 3.2.x | Apache Spark 3.1.x | Apache Spark 3.0.x | Apache Spark 2.4.x | Apache Spark 2.3.x | |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------| @@ -276,7 +276,7 @@ Find out more about `Spark NLP` versions from our [release notes](https://github ## Databricks Support -Spark NLP 5.3.1 has been tested and is compatible with the following runtimes: +Spark NLP 5.3.2 has been tested and is compatible with the following runtimes: **CPU:** @@ -343,7 +343,7 @@ Spark NLP 5.3.1 has been tested and is compatible with the following runtimes: ## EMR Support -Spark NLP 5.3.1 has been tested and is compatible with the following EMR releases: +Spark NLP 5.3.2 has been tested and is compatible with the following EMR releases: - emr-6.2.0 - emr-6.3.0 @@ -390,11 +390,11 @@ Spark NLP supports all major releases of Apache Spark 3.0.x, Apache Spark 3.1.x, ```sh # CPU -spark-shell --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 +spark-shell --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 -pyspark --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 +pyspark --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 -spark-submit --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 +spark-submit --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` The `spark-nlp` has been published to @@ -403,11 +403,11 @@ the [Maven Repository](https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/s ```sh # GPU -spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.1 +spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.2 -pyspark --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.1 +pyspark --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.2 -spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.1 +spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-gpu_2.12:5.3.2 ``` @@ -417,11 +417,11 @@ the [Maven Repository](https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/s ```sh # AArch64 -spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.1 +spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.2 -pyspark --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.1 +pyspark --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.2 -spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.1 +spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-aarch64_2.12:5.3.2 ``` @@ -431,11 +431,11 @@ the [Maven Repository](https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/s ```sh # M1/M2 (Apple Silicon) -spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.1 +spark-shell --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.2 -pyspark --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.1 +pyspark --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.2 -spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.1 +spark-submit --packages com.johnsnowlabs.nlp:spark-nlp-silicon_2.12:5.3.2 ``` @@ -449,7 +449,7 @@ set in your SparkSession: spark-shell \ --driver-memory 16g \ --conf spark.kryoserializer.buffer.max=2000M \ - --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 + --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` ## Scala @@ -467,7 +467,7 @@ coordinates: com.johnsnowlabs.nlp spark-nlp_2.12 - 5.3.1 + 5.3.2 ``` @@ -478,7 +478,7 @@ coordinates: com.johnsnowlabs.nlp spark-nlp-gpu_2.12 - 5.3.1 + 5.3.2 ``` @@ -489,7 +489,7 @@ coordinates: com.johnsnowlabs.nlp spark-nlp-aarch64_2.12 - 5.3.1 + 5.3.2 ``` @@ -500,7 +500,7 @@ coordinates: com.johnsnowlabs.nlp spark-nlp-silicon_2.12 - 5.3.1 + 5.3.2 ``` @@ -510,28 +510,28 @@ coordinates: ```sbtshell // https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/spark-nlp -libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp" % "5.3.1" +libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp" % "5.3.2" ``` **spark-nlp-gpu:** ```sbtshell // https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/spark-nlp-gpu -libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-gpu" % "5.3.1" +libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-gpu" % "5.3.2" ``` **spark-nlp-aarch64:** ```sbtshell // https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/spark-nlp-aarch64 -libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-aarch64" % "5.3.1" +libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-aarch64" % "5.3.2" ``` **spark-nlp-silicon:** ```sbtshell // https://mvnrepository.com/artifact/com.johnsnowlabs.nlp/spark-nlp-silicon -libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-silicon" % "5.3.1" +libraryDependencies += "com.johnsnowlabs.nlp" %% "spark-nlp-silicon" % "5.3.2" ``` Maven @@ -553,7 +553,7 @@ If you installed pyspark through pip/conda, you can install `spark-nlp` through Pip: ```bash -pip install spark-nlp==5.3.1 +pip install spark-nlp==5.3.2 ``` Conda: @@ -582,7 +582,7 @@ spark = SparkSession.builder .config("spark.driver.memory", "16G") .config("spark.driver.maxResultSize", "0") .config("spark.kryoserializer.buffer.max", "2000M") - .config("spark.jars.packages", "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1") + .config("spark.jars.packages", "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2") .getOrCreate() ``` @@ -653,7 +653,7 @@ Use either one of the following options - Add the following Maven Coordinates to the interpreter's library list ```bash -com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 +com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` - Add a path to pre-built jar from [here](#compiled-jars) in the interpreter's library list making sure the jar is @@ -664,7 +664,7 @@ com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 Apart from the previous step, install the python module through pip ```bash -pip install spark-nlp==5.3.1 +pip install spark-nlp==5.3.2 ``` Or you can install `spark-nlp` from inside Zeppelin by using Conda: @@ -692,7 +692,7 @@ launch the Jupyter from the same Python environment: $ conda create -n sparknlp python=3.8 -y $ conda activate sparknlp # spark-nlp by default is based on pyspark 3.x -$ pip install spark-nlp==5.3.1 pyspark==3.3.1 jupyter +$ pip install spark-nlp==5.3.2 pyspark==3.3.1 jupyter $ jupyter notebook ``` @@ -709,7 +709,7 @@ export PYSPARK_PYTHON=python3 export PYSPARK_DRIVER_PYTHON=jupyter export PYSPARK_DRIVER_PYTHON_OPTS=notebook -pyspark --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 +pyspark --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` Alternatively, you can mix in using `--jars` option for pyspark + `pip install spark-nlp` @@ -736,7 +736,7 @@ This script comes with the two options to define `pyspark` and `spark-nlp` versi # -s is for spark-nlp # -g will enable upgrading libcudnn8 to 8.1.0 on Google Colab for GPU usage # by default they are set to the latest -!wget https://setup.johnsnowlabs.com/colab.sh -O - | bash /dev/stdin -p 3.2.3 -s 5.3.1 +!wget https://setup.johnsnowlabs.com/colab.sh -O - | bash /dev/stdin -p 3.2.3 -s 5.3.2 ``` [Spark NLP quick start on Google Colab](https://colab.research.google.com/github/JohnSnowLabs/spark-nlp/blob/master/examples/python/quick_start_google_colab.ipynb) @@ -759,7 +759,7 @@ This script comes with the two options to define `pyspark` and `spark-nlp` versi # -s is for spark-nlp # -g will enable upgrading libcudnn8 to 8.1.0 on Kaggle for GPU usage # by default they are set to the latest -!wget https://setup.johnsnowlabs.com/colab.sh -O - | bash /dev/stdin -p 3.2.3 -s 5.3.1 +!wget https://setup.johnsnowlabs.com/colab.sh -O - | bash /dev/stdin -p 3.2.3 -s 5.3.2 ``` [Spark NLP quick start on Kaggle Kernel](https://www.kaggle.com/mozzie/spark-nlp-named-entity-recognition) is a live @@ -778,9 +778,9 @@ demo on Kaggle Kernel that performs named entity recognitions by using Spark NLP 3. In `Libraries` tab inside your cluster you need to follow these steps: - 3.1. Install New -> PyPI -> `spark-nlp==5.3.1` -> Install + 3.1. Install New -> PyPI -> `spark-nlp==5.3.2` -> Install - 3.2. Install New -> Maven -> Coordinates -> `com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1` -> Install + 3.2. Install New -> Maven -> Coordinates -> `com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2` -> Install 4. Now you can attach your notebook to the cluster and use Spark NLP! @@ -831,7 +831,7 @@ A sample of your software configuration in JSON on S3 (must be public access): "spark.kryoserializer.buffer.max": "2000M", "spark.serializer": "org.apache.spark.serializer.KryoSerializer", "spark.driver.maxResultSize": "0", - "spark.jars.packages": "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1" + "spark.jars.packages": "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2" } }] ``` @@ -840,7 +840,7 @@ A sample of AWS CLI to launch EMR cluster: ```.sh aws emr create-cluster \ ---name "Spark NLP 5.3.1" \ +--name "Spark NLP 5.3.2" \ --release-label emr-6.2.0 \ --applications Name=Hadoop Name=Spark Name=Hive \ --instance-type m4.4xlarge \ @@ -904,7 +904,7 @@ gcloud dataproc clusters create ${CLUSTER_NAME} \ --enable-component-gateway \ --metadata 'PIP_PACKAGES=spark-nlp spark-nlp-display google-cloud-bigquery google-cloud-storage' \ --initialization-actions gs://goog-dataproc-initialization-actions-${REGION}/python/pip-install.sh \ - --properties spark:spark.serializer=org.apache.spark.serializer.KryoSerializer,spark:spark.driver.maxResultSize=0,spark:spark.kryoserializer.buffer.max=2000M,spark:spark.jars.packages=com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 + --properties spark:spark.serializer=org.apache.spark.serializer.KryoSerializer,spark:spark.driver.maxResultSize=0,spark:spark.kryoserializer.buffer.max=2000M,spark:spark.jars.packages=com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` 2. On an existing one, you need to install spark-nlp and spark-nlp-display packages from PyPI. @@ -947,7 +947,7 @@ spark = SparkSession.builder .config("spark.kryoserializer.buffer.max", "2000m") .config("spark.jsl.settings.pretrained.cache_folder", "sample_data/pretrained") .config("spark.jsl.settings.storage.cluster_tmp_dir", "sample_data/storage") - .config("spark.jars.packages", "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1") + .config("spark.jars.packages", "com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2") .getOrCreate() ``` @@ -961,7 +961,7 @@ spark-shell \ --conf spark.kryoserializer.buffer.max=2000M \ --conf spark.jsl.settings.pretrained.cache_folder="sample_data/pretrained" \ --conf spark.jsl.settings.storage.cluster_tmp_dir="sample_data/storage" \ - --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 + --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` **pyspark:** @@ -974,7 +974,7 @@ pyspark \ --conf spark.kryoserializer.buffer.max=2000M \ --conf spark.jsl.settings.pretrained.cache_folder="sample_data/pretrained" \ --conf spark.jsl.settings.storage.cluster_tmp_dir="sample_data/storage" \ - --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.1 + --packages com.johnsnowlabs.nlp:spark-nlp_2.12:5.3.2 ``` **Databricks:** @@ -1246,7 +1246,7 @@ spark = SparkSession.builder .config("spark.driver.memory", "16G") .config("spark.driver.maxResultSize", "0") .config("spark.kryoserializer.buffer.max", "2000M") - .config("spark.jars", "/tmp/spark-nlp-assembly-5.3.1.jar") + .config("spark.jars", "/tmp/spark-nlp-assembly-5.3.2.jar") .getOrCreate() ``` @@ -1255,7 +1255,7 @@ spark = SparkSession.builder version (3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x) - If you are local, you can load the Fat JAR from your local FileSystem, however, if you are in a cluster setup you need to put the Fat JAR on a distributed FileSystem such as HDFS, DBFS, S3, etc. ( - i.e., `hdfs:///tmp/spark-nlp-assembly-5.3.1.jar`) + i.e., `hdfs:///tmp/spark-nlp-assembly-5.3.2.jar`) Example of using pretrained Models and Pipelines in offline: diff --git a/docs/_layouts/landing.html b/docs/_layouts/landing.html index 5b7438dde12b..be26c3c2915f 100755 --- a/docs/_layouts/landing.html +++ b/docs/_layouts/landing.html @@ -201,7 +201,7 @@

{{ _section.title }}

{% highlight bash %} # Using PyPI - $ pip install spark-nlp==5.3.1 + $ pip install spark-nlp==5.3.2 # Using Anaconda/Conda $ conda install -c johnsnowlabs spark-nlp diff --git a/docs/api/com/index.html b/docs/api/com/index.html index 42cdc142ffa4..12609bf9a7ab 100644 --- a/docs/api/com/index.html +++ b/docs/api/com/index.html @@ -3,9 +3,9 @@ - Spark NLP 5.3.1 ScalaDoc - com - - + Spark NLP 5.3.2 ScalaDoc - com + + @@ -28,7 +28,7 @@