Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #5168 from svlandeg/fix/streamlit 

fix showing dep arcs in streamlit script
This commit is contained in:
Ines Montani 2020-03-22 11:35:31 +01:00 committed by GitHub
parent 558032017e 02d87a8b2b
commit 341e8687f7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
examples/streamlit_spacy.py
View File

@ -1,7 +1,7 @@
# coding: utf-8 # coding: utf-8
""" """
Example of a Streamlit app for an interactive spaCy model visualizer. You can Example of a Streamlit app for an interactive spaCy model visualizer. You can
either download the script, or point streamlit run to the raw URL of this either download the script, or point `streamlit run` to the raw URL of this
file. For more details, see https://streamlit.io. file. For more details, see https://streamlit.io.
Installation: Installation:
@ -15,6 +15,8 @@ streamlit run streamlit_spacy.py
""" """
from __future__ import unicode_literals from __future__ import unicode_literals
import base64
import streamlit as st import streamlit as st
import spacy import spacy
from spacy import displacy from spacy import displacy
@ -54,6 +56,14 @@ model_load_state.empty()
text = st.text_area("Text to analyze", DEFAULT_TEXT) text = st.text_area("Text to analyze", DEFAULT_TEXT)
doc = process_text(spacy_model, text) doc = process_text(spacy_model, text)
def render_svg(svg):
"""Renders the given svg string."""
b64 = base64.b64encode(svg.encode('utf-8')).decode("utf-8")
html = r'<img src="data:image/svg+xml;base64,%s"/>' % b64
st.write(html, unsafe_allow_html=True)
if "parser" in nlp.pipe_names: if "parser" in nlp.pipe_names:
st.header("Dependency Parse & Part-of-speech tags") st.header("Dependency Parse & Part-of-speech tags")
st.sidebar.header("Dependency Parse") st.sidebar.header("Dependency Parse")
@ -68,12 +78,14 @@ if "parser" in nlp.pipe_names:
} }
docs = [span.as_doc() for span in doc.sents] if split_sents else [doc] docs = [span.as_doc() for span in doc.sents] if split_sents else [doc]
for sent in docs: for sent in docs:
html = displacy.render(sent, options=options) html = displacy.render(sent, options=options, style="dep")
# Double newlines seem to mess with the rendering # Double newlines seem to mess with the rendering
html = html.replace("\n\n", "\n") html = html.replace("\n\n", "\n")
if split_sents and len(docs) > 1: if split_sents and len(docs) > 1:
st.markdown(f"> {sent.text}") st.markdown(f"> {sent.text}")
st.write(HTML_WRAPPER.format(html), unsafe_allow_html=True) render_svg(html)
# this didn't show the dep arc labels properly, cf #5089
# st.write(HTML_WRAPPER.format(html), unsafe_allow_html=True)
if "ner" in nlp.pipe_names: if "ner" in nlp.pipe_names:
st.header("Named Entities") st.header("Named Entities")