spark-nlp 5.3.1__py2.py3-none-any.whl → 5.3.2__py2.py3-none-any.whl

spark_nlp-5.3.2.dist-info/.uuid

@@ -0,0 +1 @@
+90f78083-0ee0-43e9-8240-7263731b6707

{spark_nlp-5.3.1.dist-info → spark_nlp-5.3.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spark-nlp
-Version: 5.3.1
+Version: 5.3.2
 Summary: John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.
 Home-page: https://github.com/JohnSnowLabs/spark-nlp
 Author: John Snow Labs
@@ -197,7 +197,7 @@ 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
@@ -213,7 +213,7 @@ $ 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:
@@ -258,7 +258,7 @@ 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 |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -302,7 +302,7 @@ 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:**
 
@@ -375,7 +375,7 @@ 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
@@ -425,11 +425,11 @@ 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
@@ -438,11 +438,11 @@ 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
 
 ```
 
@@ -452,11 +452,11 @@ 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
 
 ```
 
@@ -466,11 +466,11 @@ 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
 
 ```
 
@@ -484,7 +484,7 @@ 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
@@ -502,7 +502,7 @@ coordinates:
 <dependency>
     <groupId>com.johnsnowlabs.nlp</groupId>
     <artifactId>spark-nlp_2.12</artifactId>
-    <version>5.3.1</version>
+    <version>5.3.2</version>
 </dependency>
 ```
 
@@ -513,7 +513,7 @@ coordinates:
 <dependency>
     <groupId>com.johnsnowlabs.nlp</groupId>
     <artifactId>spark-nlp-gpu_2.12</artifactId>
-    <version>5.3.1</version>
+    <version>5.3.2</version>
 </dependency>
 ```
 
@@ -524,7 +524,7 @@ coordinates:
 <dependency>
     <groupId>com.johnsnowlabs.nlp</groupId>
     <artifactId>spark-nlp-aarch64_2.12</artifactId>
-    <version>5.3.1</version>
+    <version>5.3.2</version>
 </dependency>
 ```
 
@@ -535,7 +535,7 @@ coordinates:
 <dependency>
     <groupId>com.johnsnowlabs.nlp</groupId>
     <artifactId>spark-nlp-silicon_2.12</artifactId>
-    <version>5.3.1</version>
+    <version>5.3.2</version>
 </dependency>
 ```
 
@@ -545,28 +545,28 @@ 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
@@ -588,7 +588,7 @@ 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:
@@ -617,7 +617,7 @@ 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()
 ```
 
@@ -688,7 +688,7 @@ 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
@@ -699,7 +699,7 @@ 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:
@@ -727,7 +727,7 @@ 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
 ```
 
@@ -744,7 +744,7 @@ 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`
@@ -771,7 +771,7 @@ 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)
@@ -794,7 +794,7 @@ 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
@@ -813,9 +813,9 @@ 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!
 
@@ -866,7 +866,7 @@ 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"
     }
 }]
 ```
@@ -875,7 +875,7 @@ 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 \
@@ -939,7 +939,7 @@ 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.
@@ -982,7 +982,7 @@ 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()
 ```
 
@@ -996,7 +996,7 @@ 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:**
@@ -1009,7 +1009,7 @@ 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:**
@@ -1281,7 +1281,7 @@ 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()
 ```
 
@@ -1290,7 +1290,7 @@ 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:
 

{spark_nlp-5.3.1.dist-info → spark_nlp-5.3.2.dist-info}/RECORD

@@ -1,7 +1,7 @@
 com/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 com/johnsnowlabs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 com/johnsnowlabs/nlp/__init__.py,sha256=DPIVXtONO5xXyOk-HB0-sNiHAcco17NN13zPS_6Uw8c,294
-sparknlp/__init__.py,sha256=fP6mNHdeh0JvNOydT4WGsALtBOM5HLWx5Kz9MplSS8s,13588
+sparknlp/__init__.py,sha256=N74jXyWIf6cZnJADb-aBShj-r4eCjcLGDPmXcRNEBN0,13588
 sparknlp/annotation.py,sha256=I5zOxG5vV2RfPZfqN9enT1i4mo6oBcn3Lrzs37QiOiA,5635
 sparknlp/annotation_audio.py,sha256=iRV_InSVhgvAwSRe9NTbUH9v6OGvTM-FPCpSAKVu0mE,1917
 sparknlp/annotation_image.py,sha256=xhCe8Ko-77XqWVuuYHFrjKqF6zPd8Z-RY_rmZXNwCXU,2547
@@ -224,7 +224,8 @@ sparknlp/training/_tf_graph_builders_1x/ner_dl/dataset_encoder.py,sha256=R4yHFN3
 sparknlp/training/_tf_graph_builders_1x/ner_dl/ner_model.py,sha256=EoCSdcIjqQ3wv13MAuuWrKV8wyVBP0SbOEW41omHlR0,23189
 sparknlp/training/_tf_graph_builders_1x/ner_dl/ner_model_saver.py,sha256=k5CQ7gKV6HZbZMB8cKLUJuZxoZWlP_DFWdZ--aIDwsc,2356
 sparknlp/training/_tf_graph_builders_1x/ner_dl/sentence_grouper.py,sha256=pAxjWhjazSX8Vg0MFqJiuRVw1IbnQNSs-8Xp26L4nko,870
-spark_nlp-5.3.1.dist-info/METADATA,sha256=cfK1KW9iG7FnwuiQH9bBTakLsWE7H_1zHTnMPOICjE8,57087
-spark_nlp-5.3.1.dist-info/WHEEL,sha256=bb2Ot9scclHKMOLDEHY6B2sicWOgugjFKaJsT7vwMQo,110
-spark_nlp-5.3.1.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
-spark_nlp-5.3.1.dist-info/RECORD,,
+spark_nlp-5.3.2.dist-info/.uuid,sha256=1f6hF51aIuv9yCvh31NU9lOpS34NE-h3a0Et7R9yR6A,36
+spark_nlp-5.3.2.dist-info/METADATA,sha256=lvuYdEbmUUpC9QYY4YIfuMhBUIhy5axZrrX3XgPc0uQ,57087
+spark_nlp-5.3.2.dist-info/WHEEL,sha256=bb2Ot9scclHKMOLDEHY6B2sicWOgugjFKaJsT7vwMQo,110
+spark_nlp-5.3.2.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
+spark_nlp-5.3.2.dist-info/RECORD,,

sparknlp/__init__.py

@@ -128,7 +128,7 @@ def start(gpu=False,
         The initiated Spark session.
 
     """
-    current_version = "5.3.1"
+    current_version = "5.3.2"
 
     if params is None:
         params = {}
@@ -309,4 +309,4 @@ def version():
     str
         The current Spark NLP version.
     """
-    return '5.3.1'
+    return '5.3.2'