object SparkNLP
- Alphabetic
- By Inheritance
- SparkNLP
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- val MavenGpuSpark3: String
- val MavenSpark3: String
- val MavenSparkAarch64: String
- val MavenSparkSilicon: String
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
- val currentVersion: String
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
def
start(gpu: Boolean = false, apple_silicon: Boolean = false, aarch64: Boolean = false, memory: String = "16G", cache_folder: String = "", log_folder: String = "", cluster_tmp_dir: String = "", params: Map[String, String] = Map.empty): SparkSession
Start SparkSession with Spark NLP
Start SparkSession with Spark NLP
- gpu
start Spark NLP with GPU
- apple_silicon
start Spark NLP for Apple M1 & M2 systems
- aarch64
start Spark NLP for Linux Aarch64 systems
- memory
set driver memory for SparkSession
- cache_folder
The location to download and extract pretrained Models and Pipelines (by default, it will be in the users home directory under
cache_pretrained
.)- log_folder
The location to use on a cluster for temporarily files such as unpacking indexes for WordEmbeddings. By default, this locations is the location of
hadoop.tmp.dir
set via Hadoop configuration for Apache Spark. NOTE:S3
is not supported and it must be local, HDFS, or DBFS.- cluster_tmp_dir
The location to save logs from annotators during training (By default, it will be in the users home directory under
annotator_logs
.)- params
Custom parameters to set for the Spark configuration (Default:
Map.empty
)- returns
SparkSession
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- AnyRef → Any
- def version(): String
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()