- class PreprocessNLPStage(c, vocab_hash_file='data/bert-base-cased-hash.txt', truncation=False, do_lower_case=False, add_special_tokens=False, stride=- 1, column='data')[source]
Bases:
morpheus.stages.preprocess.preprocess_base_stage.PreprocessBaseStage
Prepare NLP input DataFrames for inference.
- Parameters
-
c :
morpheus.config.Config
- vocab_hash_file
- truncation
- do_lower_case
- add_special_tokens
- stride
- column
Pipeline configuration instance.
Path to hash file containing vocabulary of words with token-ids. This can be created from the raw vocabulary using the
cudf.utils.hash_vocab_utils.hash_vocab
function.If set to true, strings will be truncated and padded to max_length. Each input string will result in exactly one output sequence. If set to false, there may be multiple output sequences when the max_length is smaller than generated tokens.
If set to true, original text will be lowercased before encoding.
Whether to encode the sequences with the special tokens of the BERT classification model.
If
truncation
== False and the tokenized string is larger than max_length, the sequences containing the overflowing token-ids can contain duplicated token-ids from the main sequence. If max_length is equal to stride there are no duplicated-id tokens. If stride is 80% of max_length, 20% of the first sequence will be repeated on the second sequence and so on until the entire sentence is encoded.Name of the column containing the data that needs to be preprocessed.
-
c :
- Attributes
has_multi_input_ports
has_multi_output_ports
input_ports
is_built
is_pre_built
name
output_ports
unique_name
Indicates if this stage has multiple input ports.
Indicates if this stage has multiple output ports.
Input ports to this stage.
Indicates if this stage has been built.
Indicates if this stage has been built.
The name of the stage.
Output ports from this stage.
Unique name of stage.
Methods
accepted_types
()Returns accepted input types for this stage. build
(builder[, do_propagate])Build this stage. can_build
([check_ports])Determines if all inputs have been built allowing this node to be built. can_pre_build
([check_ports])Determines if all inputs have been built allowing this node to be built. compute_schema
(schema)Compute the schema for this stage based on the incoming schema from upstream stages. get_all_input_stages
()Get all input stages to this stage. get_all_inputs
()Get all input senders to this stage. get_all_output_stages
()Get all output stages from this stage. get_all_outputs
()Get all output receivers from this stage. get_needed_columns
()Stages which need to have columns inserted into the dataframe, should populate the self._needed_columns
dictionary with mapping of column names tomorpheus.common.TypeId
.join
()Awaitable method that stages can implement this to perform cleanup steps when pipeline is stopped. pre_process_batch
(message, vocab_hash_file, ...)For NLP category use cases, this function performs pre-processing. start_async
()This function is called along with on_start during stage initialization. stop
()Stages can implement this to perform cleanup steps when pipeline is stopped. supports_cpp_node
()Specifies whether this Stage is capable of creating C++ nodes. process_control_message process_multi_message - _build(builder, input_nodes)[source]
This function is responsible for constructing this stage’s internal
mrc.SegmentObject
object. The input of this function contains the returned value from the upstream stage.The input values are the
mrc.Builder
for this stage and a list of parent nodes.- Parameters
-
builder :
mrc.Builder
-
input_nodes :
list[mrc.SegmentObject]
mrc.Builder
object for the pipeline. This should be used to construct/attach the internalmrc.SegmentObject
.List containing the input
mrc.SegmentObject
objects.-
builder :
- Returns
list[mrc.SegmentObject]
List of tuples containing the output
mrc.SegmentObject
object from this stage.
- accepted_types()[source]
Returns accepted input types for this stage.
- build(builder, do_propagate=True)[source]
Build this stage.
- Parameters
-
builder :
mrc.Builder
- do_propagate
MRC segment for this stage.
Whether to propagate to build output stages, by default True.
-
builder :
- can_build(check_ports=False)[source]
Determines if all inputs have been built allowing this node to be built.
- Parameters
- check_ports
Check if we can build based on the input ports, by default False.
- Returns
- bool
True if we can build, False otherwise.
- can_pre_build(check_ports=False)[source]
Determines if all inputs have been built allowing this node to be built.
- Parameters
- check_ports
Check if we can build based on the input ports, by default False.
- Returns
- bool
True if we can build, False otherwise.
- compute_schema(schema)[source]
Compute the schema for this stage based on the incoming schema from upstream stages.
Incoming schema and type information from upstream stages is available via the
schema.input_schemas
andschema.input_types
properties.Derived classes need to override this method, can set the output type(s) on
schema
by callingset_type
for all output ports. For example a simple pass-thru stage might perform the following:If the port types in
upstream_schema
are incompatible the stage should raise aRuntimeError
.- get_all_input_stages()[source]
Get all input stages to this stage.
- Returns
- list[
morpheus.pipeline.pipeline.StageBase
]
All input stages.
- list[
- get_all_inputs()[source]
Get all input senders to this stage.
- Returns
- list[
morpheus.pipeline.pipeline.Sender
]
All input senders.
- list[
- get_all_output_stages()[source]
Get all output stages from this stage.
- Returns
- list[
morpheus.pipeline.pipeline.StageBase
]
All output stages.
- list[
- get_all_outputs()[source]
Get all output receivers from this stage.
- Returns
- list[
morpheus.pipeline.pipeline.Receiver
]
All output receivers.
- list[
- get_needed_columns()[source]
Stages which need to have columns inserted into the dataframe, should populate the
self._needed_columns
dictionary with mapping of column names tomorpheus.common.TypeId
. This will ensure that the columns are allocated and populated with null values.- property has_multi_input_ports: bool
Indicates if this stage has multiple input ports.
- Returns
- bool
True if stage has multiple input ports, False otherwise.
- property has_multi_output_ports: bool
Indicates if this stage has multiple output ports.
- Returns
- bool
True if stage has multiple output ports, False otherwise.
- property input_ports: list[morpheus.pipeline.receiver.Receiver]
Input ports to this stage.
- Returns
- list[
morpheus.pipeline.pipeline.Receiver
]
Input ports to this stage.
- list[
- property is_built: bool
Indicates if this stage has been built.
- Returns
- bool
True if stage is built, False otherwise.
- property is_pre_built: bool
Indicates if this stage has been built.
- Returns
- bool
True if stage is built, False otherwise.
- async join()[source]
Awaitable method that stages can implement this to perform cleanup steps when pipeline is stopped. Typically this is called after
stop
during a graceful shutdown, but may not be called if the pipeline is terminated.- property name: str
The name of the stage. Used in logging. Each derived class should override this property with a unique name.
- Returns
- str
Name of a stage.
- property output_ports: list[morpheus.pipeline.sender.Sender]
Output ports from this stage.
- Returns
- list[
morpheus.pipeline.pipeline.Sender
]
Output ports from this stage.
- list[
- static pre_process_batch(message, vocab_hash_file, do_lower_case, seq_len, stride, truncation, add_special_tokens, column)[source]
For NLP category use cases, this function performs pre-processing.
[parameters are the same as the original function]
- Returns
morpheus.pipeline.messages.MultiInferenceNLPMessage
NLP inference message.
- async start_async()[source]
This function is called along with on_start during stage initialization. Allows stages to utilize the asyncio loop if needed.
- stop()[source]
Stages can implement this to perform cleanup steps when pipeline is stopped.
- supports_cpp_node()[source]
Specifies whether this Stage is capable of creating C++ nodes. During the build phase, this value will be combined with
CppConfig.get_should_use_cpp()
to determine whether or not a C++ node is created. This is an instance method to allow runtime decisions and derived classes to override base implementations.- property unique_name: str
Unique name of stage. Generated by appending stage id to stage name.
- Returns
- str
Unique name of stage.
morpheus.stages.preprocess.preprocess_nlp_stage.PreprocessNLPStage
Previous
morpheus.stages.preprocess.preprocess_nlp_stage
Next
morpheus.stages.preprocess.train_ae_stage