Simple NER visualization using displaCy

20201025-ner-vis-displacy.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import spacy\n",
    "from spacy import displacy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2.3.2'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "spacy.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "doc_text = \"A common human skin tumour is caused by activating mutations in beta-catenin.\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "start_end_labels = [[15, 26, \"disease\"], [64, 76, \"protein\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "colors = {\"DISEASE\": \"linear-gradient(90deg, #999999, #cccccc)\",\n",
    "          \"PROTEIN\": \"linear-gradient(90deg, #aa9cfc, #fc9ce7)\"\n",
    "          }\n",
    "options = {\"ents\": [\"DISEASE\", \"PROTEIN\"], \"colors\": colors}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<span class=\"tex2jax_ignore\"><h2 style=\"margin: 0\">Displacy test from Jupyter</h2>\n",
       "\n",
       "<div class=\"entities\" style=\"line-height: 2.5; direction: ltr\">A common human \n",
       "<mark class=\"entity\" style=\"background: linear-gradient(90deg, #999999, #cccccc); padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
       "    skin tumour\n",
       "    <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; text-transform: uppercase; vertical-align: middle; margin-left: 0.5rem\">disease</span>\n",
       "</mark>\n",
       " is caused by activating mutations in \n",
       "<mark class=\"entity\" style=\"background: linear-gradient(90deg, #aa9cfc, #fc9ce7); padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
       "    beta-catenin\n",
       "    <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; text-transform: uppercase; vertical-align: middle; margin-left: 0.5rem\">protein</span>\n",
       "</mark>\n",
       ".</div></span>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ex = [{\"text\": doc_text,\n",
    "       \"ents\": [{\"start\": x[0], \"end\": x[1], \"label\": x[2]} for x in start_end_labels],\n",
    "       \"title\": \"Displacy test from Jupyter\"}]\n",
    "html = displacy.render(ex, style=\"ent\", manual=True, options=options)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}

20201025-ner-vis-displacy.png

20201025-ner-vis-displacy.py

#!/usr/bin/env python
# coding: utf-8

# In[1]:


import spacy
from spacy import displacy


# In[2]:


spacy.__version__


# In[3]:


doc_text = "A common human skin tumour is caused by activating mutations in beta-catenin."


# In[4]:


start_end_labels = [[15, 26, "disease"], [64, 76, "protein"]]


# In[5]:


colors = {"DISEASE": "linear-gradient(90deg, #999999, #cccccc)",
          "PROTEIN": "linear-gradient(90deg, #aa9cfc, #fc9ce7)"
          }
options = {"ents": ["DISEASE", "PROTEIN"], "colors": colors}


# In[6]:


ex = [{"text": doc_text,
       "ents": [{"start": x[0], "end": x[1], "label": x[2]} for x in start_end_labels],
       "title": "Displacy test from Jupyter"}]
html = displacy.render(ex, style="ent", manual=True, options=options)

info.md

Link to blog post: https://www.alexanderjunge.net/blog/ner-vis-displacy/