Streamlit visualization Examples

This page contains examples and tutorials on how to visualize the 10000+ state-of-the-art NLP models in just 1 line of code in streamlit. It includes simple 1-liners you can sprinkle into your Streamlit app to for features like Dependency Trees, Named Entities (NER), text classification results, semantic simmilarity, embedding visualizations via ELMO, BERT, ALBERT, XLNET and much more . Additionally, improvements for T5 and various resolvers have been added.

This is the ultimate NLP research tool. You can visualize and compare the results of hundreds of context aware deep learning embeddings and compare them with classical vanilla embeddings like Glove and can see with your own eyes how context is encoded by transformer models like BERT or XLNETand many more ! Besides that, you can also compare the results of the 200+ NER models John Snow Labs provides and see how peformances changes with varrying ebeddings, like Contextual, Static and Domain Specific Embeddings.

Install

pip install streamlit sklearn plotly 

Problems? Connect with us on Slack!

Impatient and want some action?

Just run this Streamlit app, you can use it to generate python code for each Streamlit building block

streamlit run https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/examples/streamlit/01_dashboard.py

Quick Starter cheat sheet - All you need to know in 1 picture for NLP + Streamlit

For NLP models to load, see the NLP namespace or the John Snow Labs Modelshub or go straight to the source.

Examples

Just try out any of these. You can use the first example to generate python-code snippets which you can recycle as building blocks in your streamlit apps!

Example: 01_dashboard

streamlit run https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/examples/streamlit/01_dashboard.py

Example: 02_NER

streamlit run https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/examples/streamlit/02_NER.py

Example: 03_text_similarity_matrix

streamlit run https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/examples/streamlit/03_text_similarity_matrix.py

Example: 04_dependency_tree

streamlit run https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/examples/streamlit/04_dependency_tree.py

Example: 05_classifiers

streamlit run https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/examples/streamlit/05_classifiers.py

Example: 06_token_features

streamlit run https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/examples/streamlit/06_token_features.py

Example: 07_token_embedding_dimension_reduction

streamlit run https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/examples/streamlit/07_token_embedding_manifolds.py

Example: 08_token_embedding_dimension_reduction

streamlit run https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/examples/streamlit/08_sentence_embedding_manifolds.py

Example: 09_entity_embedding_dimension_reduction

streamlit run https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/examples/streamlit/09_entity_embedding_manifolds.py

How to use the nlp module?

All you need to know about the nlp module is that there is the nlp.load() method which returns a NLUPipeline object which has a .predict() that works on most common data types in the pydata stack like Pandas dataframes .
Ontop of that, there are various visualization methods a NLUPipeline provides easily integrate in Streamlit as re-usable components. viz() method

Overview of NLP + Streamlit buildingblocks

| Method | Description | |——————————————————————————–|————————————————————————————————————————————————————————————————————————————————————————-| | nlp.load('<Model>').predict(data) | Load any of the 1000+ models by providing the model name any predict on most Pythontic data strucutres like Pandas, strings, arrays of strings and more | | nlp.load('<Model>').viz_streamlit(data) | Display full NLP exploration dashboard, that showcases every feature avaiable with dropdown selectors for 1000+ models | | nlp.load('<Model>').viz_streamlit_similarity([string1, string2]) | Display similarity matrix and scalar similarity for every word embedding loaded and 2 strings. | | nlp.load('<Model>').viz_streamlit_ner(data) | Visualize predicted NER tags from Named Entity Recognizer model | | nlp.load('<Model>').viz_streamlit_dep_tree(data) | Visualize Dependency Tree together with Part of Speech labels | | nlp.load('<Model>').viz_streamlit_classes(data) | Display all extracted class features and confidences for every classifier loaded in pipeline | | nlp.load('<Model>').viz_streamlit_token(data) | Display all detected token features and informations in Streamlit | | nlp.load('<Model>').viz(data, write_to_streamlit=True) | Display the raw visualization without any UI elements. See viz docs for more info. By default all aplicable nlp model references will be shown. | | nlp.enable_streamlit_caching() | Enable caching the nlp.load() call. Once enabled, the nlp.load() method will automatically cached. **
This is recommended** to run first and for large peformance gans |

Detailed visualizer information and API docs

function pipe.viz_streamlit

Display a highly configurable UI that showcases almost every feature available for Streamlit visualization with model selection dropdowns in your applications.
Ths includes :

• Similarity Matrix & Scalars & Embedding Information for any of the 100+ Word Embedding Models
• NER visualizations for any of the 200+ Named entity recognizers
• Labled & Unlabled Dependency Trees visualizations with Part of Speech Tags for any of the 100+ Part of Speech Models
• Token informations predicted by any of the 1000+ models
• Classification results predicted by any of the 100+ models classification models
• Pipeline Configuration & Model Information & Link to John Snow Labs Modelshub for all loaded pipelines
• Auto generate Python code that can be copy pasted to re-create the individual Streamlit visualization blocks. NlLU takes the first model specified as nlp.load() for the first visualization run.
  Once the Streamlit app is running, additional models can easily be added via the UI.
  It is recommended to run this first, since you can generate Python code snippets to recreate individual Streamlit visualization blocks

nlp.load('ner').viz_streamlit(['I love NLP and Streamlit!', 'I hate buggy software'])

function parameters pipe.viz_streamlit

function pipe.viz_streamlit_classes

Visualize the predicted classes and their confidences and additional metadata to streamlit. Aplicable with any of the 100+ classifiers

nlp.load('sentiment').viz_streamlit_classes(
    ['I love NLP and Streamlit!', 'I love buggy software', 'Sign up now get a chance to win 1000$ !',
     'I am afraid of Snakes', 'Unicorns have been sighted on Mars!', 'Where is the next bus stop?'])

function parameters pipe.viz_streamlit_classes

function pipe.viz_streamlit_ner

Visualize the predicted classes and their confidences and additional metadata to Streamlit. Aplicable with any of the 250+ NER models.
You can filter which NER tags to highlight via the dropdown in the main window.

Basic usage

nlp.load('ner').viz_streamlit_ner('Donald Trump from America and Angela Merkel from Germany dont share many views')

Example for coloring

# Color all entities of class GPE black
nlp.load('ner').viz_streamlit_ner('Donald Trump from America and Angela Merkel from Germany dont share many views',
                                  colors={'PERSON': '#6e992e', 'GPE': '#000000'})

function parameters pipe.viz_streamlit_ner

function pipe.viz_streamlit_dep_tree

Visualize a typed dependency tree, the relations between tokens and part of speech tags predicted. Aplicable with any of the 100+ Part of Speech(POS) models and dep tree model

nlp.load('dep.typed').viz_streamlit_dep_tree(
    'POS tags define a grammatical label for each token and the Dependency Tree classifies Relations between the tokens')

function parameters pipe.viz_streamlit_dep_tree

function pipe.viz_streamlit_token

Visualize predicted token and text features for every model loaded. You can use this with any of the 1000+ models and select them from the left dropdown.

nlp.load('stemm pos spell').viz_streamlit_token('I liek pentut buttr and jelly !')

function parameters pipe.viz_streamlit_token

function pipe.viz_streamlit_similarity

• Displays a similarity matrix, where x-axis is every token in the first text and y-axis is every token in the second text.
• Index i,j in the matrix describes the similarity of token-i to token-j based on the loaded embeddings and distance metrics, based on Sklearns Pariwise Metrics. . See this article for more elaboration on similarities
• Displays a dropdown selectors from which various similarity metrics and over 100 embeddings can be selected. -There will be one similarity matrix per metric and embedding pair selected. num_plots = num_metric*num_embeddings Also displays embedding vector information. Applicable with any of the 100+ Word Embedding models

nlp.load('bert').viz_streamlit_word_similarity(
    ['I love love loooove NLP! <3', 'I also love love looove  Streamlit! <3'])

function parameters pipe.viz_streamlit_similarity

Embedding visualization via Manifold and Matrix Decomposition algorithms

function pipe.viz_streamlit_word_embed_manifold

Visualize Word Embeddings in 1-D, 2-D, or 3-D by Reducing Dimensionality via 11 Supported methods from Manifold Algorithms and Matrix Decomposition Algorithms . Additionally, you can color the lower dimensional points with a label that has been previously assigned to the text by specifying a list of nlp references in the additional_classifiers_for_coloring parameter.

• Reduces Dimensionality of high dimensional Word Embeddings to 1-D, 2-D, or 3-D and plot the resulting data in an interactive Plotly plot
• Applicable with any of the 100+ Word Embedding models
• Color points by classifying with any of the 100+ Parts of Speech Classifiers or Document Classifiers
• Gemerates NUM-DIMENSIONS * NUM-EMBEDDINGS * NUM-DIMENSION-REDUCTION-ALGOS plots

nlp.load('bert', verbose=True).viz_streamlit_word_embed_manifold(default_texts=['I love NLU <3', 'I love streamlit <3'],
                                                                 default_algos_to_apply=['TSNE'], MAX_DISPLAY_NUM=5)

function parameters pipe.viz_streamlit_word_embed_manifold

Larger Example showcasing more dimension reduction techniques on a larger corpus :

function pipe.viz_streamlit_sentence_embed_manifold

Visualize Sentence Embeddings in 1-D, 2-D, or 3-D by Reducing Dimensionality via 12 Supported methods from Manifold Algorithms and Matrix Decomposition Algorithms . Additionally, you can color the lower dimensional points with a label that has been previously assigned to the text by specifying a list of nlp references in the additional_classifiers_for_coloring parameter. You can also select additional classifiers via the GUI.

• Reduces Dimensionality of high dimensional Sentence Embeddings to 1-D, 2-D, or 3-D and plot the resulting data in an interactive Plotly plot
• Applicable with any of the 100+ Sentence Embedding models
• Color points by classifying with any of the 100+ Document Classifiers
• Gemerates NUM-DIMENSIONS * NUM-EMBEDDINGS * NUM-DIMENSION-REDUCTION-ALGOS plots

nlp.load('embed_sentence.bert').viz_streamlit_sentence_embed_manifold(['text1', 'text2tdo'])

function parameters pipe.viz_streamlit_sentence_embed_manifold

Streamlit Entity Manifold visualization

function pipe.viz_streamlit_entity_embed_manifold

Visualize recognized entities by NER models via their Entity Embeddings in 1-D, 2-D, or 3-D by Reducing Dimensionality via 10+ Supported methods from Manifold Algorithms and Matrix Decomposition Algorithms . You can pick additional NER models and compare them via the GUI dropdown on the left.

• Reduces Dimensionality of high dimensional Entity Embeddings to 1-D, 2-D, or 3-D and plot the resulting data in an interactive Plotly plot
• Applicable with any of the 330+ Named Entity Recognizer models
• Generates NUM-DIMENSIONS * NUM-NER-MODELS * NUM-DIMENSION-REDUCTION-ALGOS plots

nlp.load('ner').viz_streamlit_sentence_embed_manifold(['Hello From John Snow Labs', 'Peter loves to visit New York'])

function parameters pipe.viz_streamlit_sentence_embed_manifold

Supported Manifold Algorithms for Word, Sentence, and Entity Embeddings

• TSNE
• ISOMAP
• LLE
• Spectral Embedding
• MDS

Supported Matrix Decomposition Algorithms for Word, Sentence and Entity Embeddings

• PCA
• Truncated SVD aka LSA
• DictionaryLearning
• FactorAnalysis
• FastICA
• KernelPCA
• Latent Dirichlet Allocation