files/arthur-docs-markdown/user-guide/walkthroughs/model-onboarding/nlp_onboarding.md.txt

# NLP Onboarding

This page walks through the basics of setting up a natural language processing (NLP) model and onboarding it to the 
Arthur system to monitor language-specific performance.

## Getting Started

The first step is to import functions from the `arthurai` package  and establish a connection with Arthur.

```python
# Arthur imports
from arthurai import ArthurAI
from arthurai.common.constants import InputType, OutputType, Stage

arthur = ArthurAI(url="https://app.arthur.ai", 
                  login="<YOUR_USERNAME_OR_EMAIL>")
```

## Registering an NLP Model

Each NLP model is created with a name and with `input_type = InputType.NLP`. Here, we register a classification model 
on text specifying a `text_delimiter` of `NOT_WORD`:

```python
arthur_nlp_model = arthur.model(name="NLPQuickstart",
                               input_type=InputType.NLP,
                               model_type=OutputType.Multiclass,
                               text_delimiter=TextDelimiter.NOT_WORD)
```

The different `OutputType` values currently supported for NLP models are classification, multi-labeling, and regression.

### Text Delimiter

NLP models also require specifying a `text_delimiter`, which specifies how a raw document is split into tokens.

A common choice for `text_delimiter` will be `TextDelimiter.NOT_WORD`, since that will ignore punctuation and tokenize 
text based only on the words present. However, if punctuation and non-word text needs to be considered by your model, 
you should consider using other options for a delimiter to ensure those other pieces of text are processed by your NLP 
model.

For a full list of available text delimiters with examples, see the 
[TextDelimiter constant documentation](https://docs.arthur.ai/sdk/sdk_v3/apiref/arthurai.common.constants.TextDelimiter.html) 
in our SDK reference.

## Formatting Reference/Inference Data

Column names can contain only alphanumeric and underscore characters. The rest of the string values can have 
additional characters as raw text.

```python
    text_attr                      pred_value   ground_truth    non_input_1   
0   'Here-is some text'            0.1          0               0.2  
1   'saying a whole lot'           0.05         0              -0.3 
2   'of important things!'         0.02         1               0.7     
3   'With all kinds of chars?!'    0.2          0               0.1    ...
4   'But attribute/column names'   0.6          1              -0.6
5   'can only use underscore.'     0.9          1              -0.9
                                ...
```

### Reviewing the Model Schema

Before you register your model with Arthur by calling `arthur_model.save()`, you can call `arthur_model.review()` the 
model schema to check that your data is parsed correctly.

For an NLP model, the model schema should look like this:

```python
     name           stage                 value_type          categorical   is_unique  
0    text_attr      PIPELINE_INPUT        UNSTRUCTURED_TEXT   False         True   
1    pred_value     PREDICTED_VALUE       FLOAT               False         False      ...
2    ground_truth   GROUND_TRUTH          INTEGER             True          False   
3    non_input_1    NON_INPUT_DATA        FLOAT               False         False   
                                        ...
```

## Finishing Onboarding

Once you have finished formatting your reference data and your model schema looks correct using `arthur_model.review()`,
you are finished registering your model and its attributes - so you are ready to complete onboarding your model.

To finish onboarding your NLP model, the following steps apply, which is the same for NLP models as it is for models
of any `InputType` and `OutputType`:

```{include} finishing_onboarding.md
```

## Enrichments

For an overview of configuring enrichments for NLP models, see the {doc}`/user-guide/walkthroughs/enrichments` guide.

For a step-by-step walkthrough of setting up the explainability Enrichment for NLP models, see
{ref}`nlp_explainability`.