👑 spaCy building blocks and visualizers for Streamlit apps

Last update: Dec 29, 2022

Overview

spacy-streamlit: spaCy building blocks for Streamlit apps

This package contains utilities for visualizing spaCy models and building interactive spaCy-powered apps with Streamlit. It includes various building blocks you can use in your own Streamlit app, like visualizers for syntactic dependencies, named entities, text classification, semantic similarity via word vectors, token attributes, and more.

🚀 Quickstart

You can install spacy-streamlit from pip:

pip install spacy-streamlit

The package includes building blocks that call into Streamlit and set up all the required elements for you. You can either use the individual components directly and combine them with other elements in your app, or call the visualize function to embed the whole visualizer.

Download the English model from spaCy to get started.

python -m spacy download en_core_web_sm

Then put the following example code in a file.

# streamlit_app.py
import spacy_streamlit

models = ["en_core_web_sm", "en_core_web_md"]
default_text = "Sundar Pichai is the CEO of Google."
spacy_streamlit.visualize(models, default_text)

You can then run your app with streamlit run streamlit_app.py. The app should pop up in your web browser. 😀

📦 Example: `01_out-of-the-box.py`

Use the embedded visualizer with custom settings out-of-the-box.

streamlit run https://raw.githubusercontent.com/explosion/spacy-streamlit/master/examples/01_out-of-the-box.py

👑 Example: `02_custom.py`

Use individual components in your existing app.

streamlit run https://raw.githubusercontent.com/explosion/spacy-streamlit/master/examples/02_custom.py

🎛 API

Visualizer components

These functions can be used in your Streamlit app. They call into streamlit under the hood and set up the required elements.

`function` `visualize`

Embed the full visualizer with selected components.

import spacy_streamlit

models = ["en_core_web_sm", "/path/to/model"]
default_text = "Sundar Pichai is the CEO of Google."
visualizers = ["ner", "textcat"]
spacy_streamlit.visualize(models, default_text, visualizers)

Argument	Type	Description
`models`	List[str] / Dict[str, str]	Names of loadable spaCy models (paths or package names). The models become selectable via a dropdown. Can either be a list of names or the names mapped to descriptions to display in the dropdown.
`default_text`	str	Default text to analyze on load. Defaults to `""`.
`default_model`	Optional[str]	Optional name of default model. If not set, the first model in the list of `models` is used.
`visualizers`	List[str]	Names of visualizers to show. Defaults to `["parser", "ner", "textcat", "similarity", "tokens"]`.
`ner_labels`	Optional[List[str]]	NER labels to include. If not set, all labels present in the `"ner"` pipeline component will be used.
`ner_attrs`	List[str]	Span attributes shown in table of named entities. See `visualizer.py` for defaults.
`token_attrs`	List[str]	Token attributes to show in token visualizer. See `visualizer.py` for defaults.
`similarity_texts`	Tuple[str, str]	The default texts to compare in the similarity visualizer. Defaults to `("apple", "orange")`.
`show_json_doc`	bool	Show button to toggle JSON representation of the `Doc`. Defaults to `True`.
`show_meta`	bool	Show button to toggle `meta.json` of the current pipeline. Defaults to `True`.
`show_config`	bool	Show button to toggle `config.cfg` of the current pipeline. Defaults to `True`.
`show_visualizer_select`	bool	Show sidebar dropdown to select visualizers to display (based on enabled visualizers). Defaults to `False`.
`sidebar_title`	Optional[str]	Title shown in the sidebar. Defaults to `None`.
`sidebar_description`	Optional[str]	Description shown in the sidebar. Accepts Markdown-formatted text.
`show_logo`	bool	Show the spaCy logo in the sidebar. Defaults to `True`.
`color`	Optional[str]	Experimental: Primary color to use for some of the main UI elements (`None` to disable hack). Defaults to `"#09A3D5"`.
`get_default_text`	Callable[[Language], str]	Optional callable that takes the currently loaded `nlp` object and returns the default text. Can be used to provide language-specific default texts. If the function returns `None`, the value of `default_text` is used, if available. Defaults to `None`.

`function` `visualize_parser`

Visualize the dependency parse and part-of-speech tags using spaCy's displacy visualizer.

import spacy
from spacy_streamlit import visualize_parser

nlp = spacy.load("en_core_web_sm")
doc = nlp("This is a text")
visualize_parser(doc)

Argument	Type	Description
`doc`	`Doc`	The spaCy `Doc` object to visualize.
keyword-only
`title`	Optional[str]	Title of the visualizer block.
`sidebar_title`	Optional[str]	Title of the config settings in the sidebar.

`function` `visualize_ner`

Visualize the named entities in a Doc using spaCy's displacy visualizer.

import spacy
from spacy_streamlit import visualize_ner

nlp = spacy.load("en_core_web_sm")
doc = nlp("Sundar Pichai is the CEO of Google.")
visualize_ner(doc, labels=nlp.get_pipe("ner").labels)

Argument	Type	Description
`doc`	`Doc`	The spaCy `Doc` object to visualize.
keyword-only
`labels`	Sequence[str]	The labels to show in the labels dropdown.
`attrs`	List[str]	The span attributes to show in entity table.
`show_table`	bool	Whether to show a table of entities and their attributes. Defaults to `True`.
`title`	Optional[str]	Title of the visualizer block.
`sidebar_title`	Optional[str]	Title of the config settings in the sidebar.
`colors`	Dict[str,str]	A dictionary mapping labels to display colors ({"LABEL": "COLOR"})

`function` `visualize_textcat`

Visualize text categories predicted by a trained text classifier.

import spacy
from spacy_streamlit import visualize_textcat

nlp = spacy.load("./my_textcat_model")
doc = nlp("This is a text about a topic")
visualize_textcat(doc)

Argument	Type	Description
`doc`	`Doc`	The spaCy `Doc` object to visualize.
keyword-only
`title`	Optional[str]	Title of the visualizer block.

`visualize_similarity`

Visualize semantic similarity using the model's word vectors. Will show a warning if no vectors are present in the model.

import spacy
from spacy_streamlit import visualize_similarity

nlp = spacy.load("en_core_web_lg")
visualize_similarity(nlp, ("pizza", "fries"))

Argument	Type	Description
`nlp`	`Language`	The loaded `nlp` object with vectors.
`default_texts`	Tuple[str, str]	The default texts to compare on load. Defaults to `("apple", "orange")`.
keyword-only
`threshold`	float	Threshold for what's considered "similar". If the similarity score is greater than the threshold, the result is shown as similar. Defaults to `0.5`.
`title`	Optional[str]	Title of the visualizer block.

`function` `visualize_tokens`

Visualize the tokens in a Doc and their attributes.

import spacy
from spacy_streamlit import visualize_tokens

nlp = spacy.load("en_core_web_sm")
doc = nlp("This is a text")
visualize_tokens(doc, attrs=["text", "pos_", "dep_", "ent_type_"])

Argument	Type	Description
`doc`	`Doc`	The spaCy `Doc` object to visualize.
keyword-only
`attrs`	List[str]	The names of token attributes to use. See `visualizer.py` for defaults.
`title`	Optional[str]	Title of the visualizer block.

Cached helpers

These helpers attempt to cache loaded models and created Doc objects.

`function` `process_text`

Process a text with a model of a given name and create a Doc object. Calls into the load_model helper to load the model.

import streamlit as st
from spacy_streamlit import process_text

spacy_model = st.sidebar.selectbox("Model name", ["en_core_web_sm", "en_core_web_md"])
text = st.text_area("Text to analyze", "This is a text")
doc = process_text(spacy_model, text)

Argument	Type	Description
`model_name`	str	Loadable spaCy model name. Can be path or package name.
`text`	str	The text to process.
RETURNS	`Doc`	The processed document.

`function` `load_model`

Load a spaCy model from a path or installed package and return a loaded nlp object.

import streamlit as st
from spacy_streamlit import load_model

spacy_model = st.sidebar.selectbox("Model name", ["en_core_web_sm", "en_core_web_md"])
nlp = load_model(spacy_model)

Argument	Type	Description
`name`	str	Loadable spaCy model name. Can be path or package name.
RETURNS	`Language`	The loaded `nlp` object.

Comments

Support for span categorizer?

Is it possible to visualize spancat predictions via spacy-streamlit yet? Either directly or by customizing one of the existing visualizers? I haven't been able to find any examples of this.
enhancement

opened by jonmcalder 5
Pass manual=True to visualize_ner

Adjusted visualize_ner to include manual as an argument that is passed into displacy_render, and added a new file 03_visualize-ner-manual.py to show how it works.

Let me know if this PR can be improved, as this is one of my first open-source contributions, and I am still learning :)

Closes #14

opened by callistachang 4
Be able to specify port & host

I'm currently running the spacy-streamlit app on a server. I prefer to have this on my server on my local network because otherwise my laptop gets very hot during training. In order to properly host it though I need to be able to customise the port-number as well as the host. It seems like these settings are currently missing. Would @ines you be open to these commands? I wouldn't mind picking this up.
enhancement

opened by koaning 4
'NoneType' object has no attribute 'replace'

When I ran the example:

import spacy_streamlit models = ["en_core_web_sm", "en_core_web_md"] default_text = "Sundar Pichai is the CEO of Google." spacy_streamlit.visualize(models, default_text)

Have this problem

AttributeError Traceback (most recent call last) in 3 models = ["en_core_web_sm", "en_core_web_md"] 4 default_text = "Sundar Pichai is the CEO of Google." ----> 5 spacy_streamlit.visualize(models, default_text)

~/anaconda3/lib/python3.7/site-packages/spacy_streamlit/visualizer.py in visualize(models, default_text, visualizers, ner_labels, ner_attrs, similarity_texts, token_attrs, show_json_doc, show_model_meta, sidebar_title, sidebar_description, show_logo, color) 51 52 if "parser" in visualizers: ---> 53 visualize_parser(doc) 54 if "ner" in visualizers: 55 ner_labels = ner_labels or nlp.get_pipe("ner").labels

~/anaconda3/lib/python3.7/site-packages/spacy_streamlit/visualizer.py in visualize_parser(doc, title, sidebar_title) 98 html = displacy.render(sent, options=options, style="dep") 99 # Double newlines seem to mess with the rendering --> 100 html = html.replace("\n\n", "\n") 101 if split_sents and len(docs) > 1: 102 st.markdown(f"> {sent.text}")

AttributeError: 'NoneType' object has no attribute 'replace'

opened by PilarHidalgo 4
`visualize_spans` function + `manual` argument + docstrings
Adds a visualize_spans function for using the span visualization in displaCy.

I made a few choices that may need justification:

Even though spans_key is part of the options passed to displaCy, it feels critical enough to pass as an argument to visualize_spans rather than as a key/value in a dict to displacy_options - but we can obviously undo this.

I didn't include the span viz in the "display everything" visualize function because none of the base models will have labeled spans in them, so it wouldn't display anything useful.

Compared to visualize_ner:

I removed the manual argument because there's no such option for that with displaCy for spans

There's no label filtering/selection with spans, so all labels will be displayed for spans within a span_key. This removes the keys and labels args.

Extra:

Also added a missing docstring for the show_table argument on visualize_ner (as well as visualize_spans)

Open questions:

Is there a script to generate the nice readme.md documentation so we can include the new function?

I'm not totally sure what needs to happen for a release, but I'm happy to help do whatever needs to be done!
opened by pmbaumgartner 2

NotImplementedError: [E894] The 'noun_chunks' syntax iterator is not implemented for language 'it'.

I'm trying to use the italian model and getting this error why usine visualize_parser.

File "/home/irfan/environments/The-Entities-Swissknife/lib/python3.7/site-packages/streamlit/scriptrunner/script_runner.py", line 443, in _run_script
    exec(code, module.__dict__)
  File "/home/irfan/PycharmProjects/TES-Clone/main.py", line 385, in <module>
    visualize_parser(doc)
  File "/home/irfan/environments/The-Entities-Swissknife/lib/python3.7/site-packages/spacy_streamlit/visualizer.py", line 156, in visualize_parser
    html = displacy.render(sent, options=options, style="dep")
  File "/home/irfan/environments/The-Entities-Swissknife/lib/python3.7/site-packages/spacy/displacy/__init__.py", line 57, in render
    parsed = [converter(doc, options) for doc in docs] if not manual else docs  # type: ignore
  File "/home/irfan/environments/The-Entities-Swissknife/lib/python3.7/site-packages/spacy/displacy/__init__.py", line 57, in <listcomp>
    parsed = [converter(doc, options) for doc in docs] if not manual else docs  # type: ignore
  File "/home/irfan/environments/The-Entities-Swissknife/lib/python3.7/site-packages/spacy/displacy/__init__.py", line 131, in parse_deps
    for np in list(doc.noun_chunks):
  File "spacy/tokens/doc.pyx", line 852, in noun_chunks
NotImplementedError: [E894] The 'noun_chunks' syntax iterator is not implemented for language 'it'.

Here are the models and library info

en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.2.0/en_core_web_sm-3.2.0-py3-none-any.whl
it-core-news-sm @ https://github.com/explosion/spacy-models/releases/download/it_core_news_sm-3.2.0/it_core_news_sm-3.2.0-py3-none-any.whl
spacy==3.2.4
spacy-legacy==3.0.9
spacy-loggers==1.0.2
spacy-streamlit==1.0.3

opened by mirfan899 2

OSError: [E050] Can't find model 'en_core_web_sm'. It doesn't seem to be a Python package or a valid path to a data directory.
Hi. 👋 This is my first time ever submitting an issue on Github. I resolved the issue somehow myself but I thought it's important to report and share the possible bug anyway. I'll try my best to follow the github issue submit best practices, I hope I'm doing it correctly.

My code

import spacy nlp = spacy.load('en')

Errors I ran into

Error 1

OSError: [E050] Can't find model 'en_core_web_sm'. It doesn't seem to be a Python package or a valid path to a data directory.

Error 2

[E053] Could not read config.cfg from c:\users\Pycharmprojects\my_project_foler\venv\lib\site-packages\en_core_web_sm\en_core_web_sm-2.2.0\config.cfg

After Error 1, I tried the following link. https://github.com/explosion/spaCy/issues/4577

Then the first error resolved and pycharm threw the error 2 right after. I tried all the pip install github_links but didn't work. https://github.com/explosion/spaCy/issues/7453

Unsuccessful attempts in order

download python3 -m spacy download en_core_web_sm

Upgrade pip3 install -U spacy

Github link 1 pip3 install https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.2.0/en_core_web_sm-2.2.0.tar.gz

Github link 2 pip install https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0.tar.gz Failed to build spacy

validate python -m spacy validate

install pip install --no-cache-dir spacy

What worked

python -m spacy download en

As of spaCy v3.0, shortcuts like 'en' are deprecated. Please use the full pipeline package name 'en_core_web_sm' instead. Collecting en-core-web-sm==3.2.0

The terminal automatically downloaded en_core_web_sm and it worked. But this was the first thing I had tried. Is it because I used python3 instead of python in the command...?

Thank you!
opened by deep-woods 2
Text from a scanned document.

Many research institutes in humanities scan documents and books and get text via OCR. We can analyze the text, but is there a standard way to connect the scan and the text when you know the coefficient of where the word or phrase is on the image.

opened by ericvanderlinden 2
Getting text or disabling text box from .visualizer
When you use:

spacy_streamlit.visualize()

How do you get the textual data input into the text box? Can we disable that text box and feed directly into visualize instead?
question
opened by ritchieng 2
'labels' parameter of visualize_ner()
Hi! The default labels parameter of visualize_ner() is an empty tuple and I think we can make it more explicit because today I was debugging to figure out why my custom entities were not being displayed :P. Maybe I'm missing something, what does keyword-only mean? (docs table)

Back to the labels parameter, I'm not sure if it's best to:

modify the method to check if the tuple is empty and if so get all labels from the doc

simply add a required label in the docs

I modified the docs because it's more straightforward, let me know if you think it's not a good path. Thanks!
opened by dmesquita 2

AttributeError: module 'spacy_streamlit' has no attribute 'visualizer'

import spacy_streamlit

models = ["en_core_web_sm", "en_core_web_md"]
default_text = "Sundar Pichai is the CEO of Google."
spacy_streamlit.visualize(models, default_text)

gives the error:

AttributeError: module 'spacy_streamlit' has no attribute 'visualizer'
Traceback:

File "e:\wpy-3710\python-3.7.1.amd64\lib\site-packages\streamlit\ScriptRunner.py", line 322, in _run_script
    exec(code, module.__dict__)
File "e:\work\Python\spacy_streamlit.py", line 1, in <module>
    import spacy_streamlit
File "e:\work\Python\spacy_streamlit.py", line 5, in <module>
    spacy_streamlit.visualizer(models, default_text)

I am using Windows 10 WinPython 3.7.1

Python 3.7.1 (v3.7.1:260ec2c36a, Oct 20 2018, 14:57:15) [MSC v.1915 64 bit (AMD64)] on win32

opened by Code4SAFrankie 2

ModuleNotFoundError in demo

when opening https://ines-spacy-streamlit-demo-app-a6h19v.streamlit.app/ I encounter a ModuleNotFoundError

Traceback: File "/home/appuser/venv/lib/python3.7/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 565, in _run_script exec(code, module.dict) File "/app/spacy-streamlit-demo/app.py", line 1, in import spacy_streamlit File "/home/appuser/venv/lib/python3.7/site-packages/spacy_streamlit/init.py", line 1, in from .visualizer import visualize, visualize_parser, visualize_ner, visualize_spans File "/home/appuser/venv/lib/python3.7/site-packages/spacy_streamlit/visualizer.py", line 3, in import spacy File "/home/appuser/venv/lib/python3.7/site-packages/spacy/init.py", line 14, in from .cli.info import info # noqa: F401 File "/home/appuser/venv/lib/python3.7/site-packages/spacy/cli/init.py", line 3, in from ._util import app, setup_cli # noqa: F401 File "/home/appuser/venv/lib/python3.7/site-packages/spacy/cli/_util.py", line 8, in import typer File "/home/appuser/venv/lib/python3.7/site-packages/typer/init.py", line 29, in from .main import Typer as Typer File "/home/appuser/venv/lib/python3.7/site-packages/typer/main.py", line 11, in from .completion import get_completion_inspect_parameters File "/home/appuser/venv/lib/python3.7/site-packages/typer/completion.py", line 10, in import click._bashcomplete

opened by bsenst 1

Visualization of nested spans

Dear all,

I'm trying to use the new span visualizer to display some custom, nested spans predicted by spancat. This is my code:

MODEL_PATH = # ...
DEFAULT_TEXT = """Cetuximab ist ein monoklonaler Antikörper, der gegen den epidermalen Wachstumsfaktorrezeptor (EGFR) gerichtet ist und \
    dient zur Therapie des fortgeschrittenen kolorektalen Karzinoms zusammen mit Irinotecan oder in Kombination mit FOLFOX bzw. \
    allein nach Versagen einer Behandlung mit Oxaliplatin und Irinotecan."""

st.set_page_config(layout="wide")

text = st.text_area("Text to analyze", DEFAULT_TEXT)
doc = process_text(MODEL_PATH, text)

visualize_spans(doc, spans_key="snomed", displacy_options=
    {"colors": {
        "Clinical_Drug": "#99FF99", "External_Substance" : "#CCFFCC", "Nutrient_or_Body_Substance" : "#E5FFCC", 
        "Therapeutic" : "#66B2FF", "Diagnostic" : "#CCE5FF",
        "Other_Finding" : "#FFE5CC", "Diagnosis_or_Pathology" : "#FFCCCC"}} )

myapp

The nested spans are all shown on the same line, which makes it very hard to read. I learned from the feature on LinkedIn, where a video was shown with nested spans nicely displayed.

demo

How can I achieve this behavior? Do I need to pass some other options?

opened by phlobo 0

visualize_spans

I have been trying to use this but keep on getting this error ImportError: cannot import name 'visualize_spans' from partially initialized module 'spacy_streamlit' (most likely due to a circular import)

spacy 3.3.1 spacy_streamlit 1.0.4

opened by monWork 2
Unexpected keyword errors

Hello,

I aa looking to use spacy-streamlit to visualise custom sentences and entities output from my own model.

When running some of your example .py files, I have found errors https://github.com/explosion/spacy-streamlit/tree/master/examples

03_visualize-ner-manual.py The error says: TypeError: visualize_ner() got an unexpected keyword argument 'manual'

04_visualize-ner-extra-options.pyThe error says: TypeError: visualize_ner() got an unexpected keyword argument 'displacy_options'

I think this may be a big. Is there a way around this?

opened by rory-hurley-gds 1

Releases(v1.0.4)

v1.0.4(Jun 14, 2022)
✨ New features and improvements

NEW visualize_spans for span support in displaCy.:

PR https://github.com/explosion/spacy-streamlit/pull/37

visualize_{parser,ner,spans} functions now take a manual argument for rendering data manually

Updated docstrings with correct arguments & types

visualize_parser now takes displacy_options for providing options for that visualizer.

New examples scripts:

05_visualize-spans.py

👥 Contributors

@pmbaumgartner, @svlandeg, @rmitsch

What's Changed

Fix title in example 03 by @svlandeg in https://github.com/explosion/spacy-streamlit/pull/35

visualize_spans function + manual argument + docstrings by @pmbaumgartner in https://github.com/explosion/spacy-streamlit/pull/37

Full Changelog: https://github.com/explosion/spacy-streamlit/compare/v1.0.3...v1.0.4
Source code(tar.gz)
Source code(zip)
v1.0.3(Mar 31, 2022)
✨ New features and improvements

Improvements to visualize_ner:

PR https://github.com/explosion/spacy-streamlit/pull/26: UX and layout improvements

PR https://github.com/explosion/spacy-streamlit/pull/27: Allow manual option in visualize_ner

PR https://github.com/explosion/spacy-streamlit/pull/31: Allow extra displacy_options to be passed to visualize_ner

PR https://github.com/explosion/spacy-streamlit/pull/25: Use the streamlit theming options directly in visualizer.py

PR https://github.com/explosion/spacy-streamlit/pull/29: Ensure the correct texts are passed onwards in visualize_similarity

New examples scripts:

03_visualize-ner-manual.py

04_visualize-ner-extra-options.py

👥 Contributors

@callistachang, @honnibal, @ines, @Jette16, @narayanacharya6, @svlandeg
Source code(tar.gz)
Source code(zip)
v1.0.2(Aug 25, 2021)
Remove deprecated beta_ prefixes for compatibility with streamlit v0.86.0+.

Source code(tar.gz)
Source code(zip)
v1.0.0(Mar 12, 2021)
Update for spaCy v3.0.

Source code(tar.gz)
Source code(zip)
v1.0.0rc1(Jan 27, 2021)
🌙 This release is a pre-release and requires spaCy v3 (nightly).

Upgrade to latest Streamlit and use columns and expander widgets for controls.

Move visualizer-specific settings into main content instead of sidebar.

Add show_config setting to show config.cfg of currently loaded model.

Add default_model setting to specify option to auto-select in dropdown.

Add show_pipeline_info setting to toggle pipeline description in sidebar.

Update default token attributes to include Token.morph and Token.is_sent_start.

Add get_default_text callback to generate default text based on nlp object (e.g. language).

Source code(tar.gz)
Source code(zip)
v1.0.0rc0(Oct 15, 2020)
🌙 This release is a pre-release and requires spaCy v3 (nightly).

Upgrade to latest Streamlit and use columns and expander widgets for controls.

Move visualizer-specific settings into main content instead of sidebar.

Add show_config setting to show config.cfg of currently loaded model.

Add default_model setting to specify option to auto-select in dropdown.

Add show_pipeline_info setting to toggle pipeline description in sidebar.

Update default token attributes to include Token.morph and Token.is_sent_start.

Source code(tar.gz)
Source code(zip)
v0.1.0(Sep 19, 2020)
Clean up custom CSS for color theme.

Support both lists of model names as well as a dict mapping models to descriptions to display in the dropdown.

Add show_visualizer_select option to allow user to toggle displayed visualizers (based on the specified options).

Use checkboxes instead of buttons for JSON Doc and model meta.

Source code(tar.gz)
Source code(zip)
v0.0.3(Sep 2, 2020)
Add key argument to widgets to prevent problem with duplicate widgets.

Add colors parameter to ner_visualizer.

Thanks to @Jcharis, @yagays, @pmbaumgartner, @andfanilo and @discdiver for the pull requests!
Source code(tar.gz)
Source code(zip)
v0.0.2(Jun 23, 2020)

Source code(tar.gz)
Source code(zip)
v0.0.1(Jun 23, 2020)

Source code(tar.gz)
Source code(zip)

Owner

Explosion

A software company specializing in developer tools for Artificial Intelligence and Natural Language Processing

GitHub Repository https://share.streamlit.io/ines/spacy-streamlit-demo/master/app.py

NLP and Text Generation Experiments in TensorFlow 2.x / 1.x

Code has been run on Google Colab, thanks Google for providing computational resources Contents Natural Language Processing（自然语言处理） Text Classificati

1.5k Nov 14, 2022

BERTAC (BERT-style transformer-based language model with Adversarially pretrained Convolutional neural network)

BERTAC (BERT-style transformer-based language model with Adversarially pretrained Convolutional neural network) BERTAC is a framework that combines a

6 Jan 24, 2022

Automatically search Stack Overflow for the command you want to run

stackshell Automatically search Stack Overflow (and other Stack Exchange sites) for the command you want to ru Use the up and down arrows to change be

22 Oct 27, 2021

Auto_code_complete is a auto word-completetion program which allows you to customize it on your needs

auto_code_complete is a auto word-completetion program which allows you to customize it on your needs. the model for this program is one of the deep-learning NLP(Natural Language Process) model struc

2 Feb 22, 2022

This repo stores the codes for topic modeling on palliative care journals.

This repo stores the codes for topic modeling on palliative care journals. Data Preparation You first need to download the journal papers. bash 1_down

3 Dec 20, 2022

Lingtrain Aligner — ML powered library for the accurate texts alignment.

Lingtrain Aligner ML powered library for the accurate texts alignment in different languages. Purpose Main purpose of this alignment tool is to build

76 Dec 14, 2022

PIZZA - a task-oriented semantic parsing dataset

The PIZZA dataset continues the exploration of task-oriented parsing by introducing a new dataset for parsing pizza and drink orders, whose semantics cannot be captured by flat slots and intents.

17 Dec 14, 2022

Script and models for clustering LAION-400m CLIP embeddings.

clustering-laion400m Script and models for clustering LAION-400m CLIP embeddings. Models were fit on the first million or so image embeddings. A subje

22 Oct 04, 2022

本项目是作者们根据个人面试和经验总结出的自然语言处理(NLP)面试准备的学习笔记与资料，该资料目前包含自然语言处理各领域的面试题积累。

【关于 NLP】那些你不知道的事作者：杨夕、芙蕖、李玲、陈海顺、twilight、LeoLRH、JimmyDU、艾春辉、张永泰、金金金介绍本项目是作者们根据个人面试和经验总结出的自然语言处理(NLP)面试准备的学习笔记与资料，该资料目前包含自然语言处理各领域的面试题积累。目录架构一、【

1.4k Dec 30, 2022

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Tensor2Tensor Tensor2Tensor, or T2T for short, is a library of deep learning models and datasets designed to make deep learning more accessible and ac

12.9k Jan 07, 2023

Pre-training BERT masked language models with custom vocabulary

Pre-training BERT Masked Language Models (MLM) This repository contains the method to pre-train a BERT model using custom vocabulary. It was used to p

14 Nov 02, 2022

Simple Python script to scrape youtube channles of "Parity Technologies and Web3 Foundation" and translate them to well-known braille language or any language

Simple Python script to scrape youtube channles of "Parity Technologies and Web3 Foundation" and translate them to well-known braille language or any

1 Apr 28, 2022

Repository for the paper: VoiceMe: Personalized voice generation in TTS

🗣 VoiceMe: Personalized voice generation in TTS Abstract Novel text-to-speech systems can generate entirely new voices that were not seen during trai

80 Dec 29, 2022

The (extremely) naive sentiment classification function based on NBSVM trained on wisesight_sentiment

thai_sentiment The naive sentiment classification function based on NBSVM trained on wisesight_sentiment วิธีติดตั้ง pip install thai_sentiment==0.1.3

7 Dec 08, 2022

BERT Attention Analysis

BERT Attention Analysis This repository contains code for What Does BERT Look At? An Analysis of BERT's Attention. It includes code for getting attent

401 Dec 11, 2022

Official Stanford NLP Python Library for Many Human Languages

6.4k Jan 02, 2023

Use the state-of-the-art m2m100 to translate large data on CPU/GPU/TPU. Super Easy!

Easy-Translate is a script for translating large text files in your machine using the M2M100 models from Facebook/Meta AI. We also privide a script fo

41 Dec 15, 2022

Negative sampling for solving the unlabeled entity problem in NER. ICLR-2021 paper: Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition.

Negative Sampling for NER Unlabeled entity problem is prevalent in many NER scenarios (e.g., weakly supervised NER). Our paper in ICLR-2021 proposes u

128 Dec 29, 2022

MILES is a multilingual text simplifier inspired by LSBert - A BERT-based lexical simplification approach proposed in 2018. Unlike LSBert, MILES uses the bert-base-multilingual-uncased model, as well as simple language-agnostic approaches to complex word identification (CWI) and candidate ranking.

MILES Multilingual Lexical Simplifier Explore the docs » Read LSBert Paper · Report Bug · Request Feature About The Project MILES is a multilingual te

45 Oct 19, 2022

A2T: Towards Improving Adversarial Training of NLP Models (EMNLP 2021 Findings)

A2T: Towards Improving Adversarial Training of NLP Models This is the source code for the EMNLP 2021 (Findings) paper "Towards Improving Adversarial T

17 Oct 15, 2022

👑 spaCy building blocks and visualizers for Streamlit apps

Related tags

Overview

spacy-streamlit: spaCy building blocks for Streamlit apps

🚀 Quickstart

📦 Example: 01_out-of-the-box.py

👑 Example: 02_custom.py

🎛 API

Visualizer components

function visualize

function visualize_parser

function visualize_ner

function visualize_textcat

visualize_similarity

function visualize_tokens

Cached helpers

function process_text

function load_model

Comments

My code

Errors I ran into

Unsuccessful attempts in order

What worked