Streamlit NLP App JCharisTech

Building A Natural Language Processing App with Streamlit,SpaCy and Python

Streamlit is Awesome!!!. In this post, we will build a simple Natural Language Processing App(NLP) app with streamlit in python. Our app will be useful for some interesting aspect of NLP such as:

  • Tokenization and Lemmatization of Text
  • Named Entity Recognition
  • Sentiment Analysis
  • Text Summarization

We will be using the wonderful SpaCy library for our tokenization and our named entity recognition. For our sentiment analysis we will use TextBlob, a simple but powerful package for sentiment analysis that gives both the polarity and the subjectivity of sentiment. Moreover we will utilize Gensim and Sumy for our text summarization.

Finally,will add some awesomeness to our NLP app using Streamlit.

Let us begin.

Installation of the Required Packages

# NLP Pkgs
pip install spacy textblob 
# Summarization Pkgs
pip install gensim sumy
# Awesome Pkg
pip install streamlit

We will create a file where all our code will be. And then run our app in our terminal using

streamlit run

We will place all our codes inside a main function and run it as such.

Below is the entire code for our NLP app

import streamlit as st 
import os

# NLP Pkgs
from textblob import TextBlob 
import spacy
from gensim.summarization import summarize

# Sumy Pkg
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lex_rank import LexRankSummarizer

# Sumy Summarization
def sumy_summarizer(docx):
	parser = PlaintextParser.from_string(docx,Tokenizer("english"))
	lex_summarizer = LexRankSummarizer()
	summary = lex_summarizer(parser.document,3)
	summary_list = [str(sentence) for sentence in summary]
	result = ' '.join(summary_list)
	return result

# Function For Analysing Tokens and Lemma
def text_analyzer(my_text):
	nlp = spacy.load('en')
	docx = nlp(my_text)
	# tokens = [ token.text for token in docx]
	allData = [('"Token":{},\n"Lemma":{}'.format(token.text,token.lemma_))for token in docx ]
	return allData

# Function For Extracting Entities
def entity_analyzer(my_text):
	nlp = spacy.load('en')
	docx = nlp(my_text)
	tokens = [ token.text for token in docx]
	entities = [(entity.text,entity.label_)for entity in docx.ents]
	allData = ['"Token":{},\n"Entities":{}'.format(tokens,entities)]
	return allData

def main():
	""" NLP Based App with Streamlit """

	# Title
	st.title("NLPiffy with Streamlit")
	st.subheader("Natural Language Processing On the Go..")

	# Tokenization
	if st.checkbox("Show Tokens and Lemma"):
		st.subheader("Tokenize Your Text")

		message = st.text_area("Enter Text","Type Here ..")
		if st.button("Analyze"):
			nlp_result = text_analyzer(message)

	# Entity Extraction
	if st.checkbox("Show Named Entities"):
		st.subheader("Analyze Your Text")

		message = st.text_area("Enter Text","Type Here ..")
		if st.button("Extract"):
			entity_result = entity_analyzer(message)

	# Sentiment Analysis
	if st.checkbox("Show Sentiment Analysis"):
		st.subheader("Analyse Your Text")

		message = st.text_area("Enter Text","Type Here ..")
		if st.button("Analyze"):
			blob = TextBlob(message)
			result_sentiment = blob.sentiment

	# Summarization
	if st.checkbox("Show Text Summarization"):
		st.subheader("Summarize Your Text")

		message = st.text_area("Enter Text","Type Here ..")
		summary_options = st.selectbox("Choose Summarizer",['sumy','gensim'])
		if st.button("Summarize"):
			if summary_options == 'sumy':
				st.text("Using Sumy Summarizer ..")
				summary_result = sumy_summarizer(message)
			elif summary_options == 'gensim':
				st.text("Using Gensim Summarizer ..")
				summary_result = summarize(rawtext)
				st.warning("Using Default Summarizer")
				st.text("Using Gensim Summarizer ..")
				summary_result = summarize(rawtext)


	st.sidebar.subheader("About App")
	st.sidebar.text("NLPiffy App with Streamlit")"Cudos to the Streamlit Team")

	st.sidebar.text("Jesse E.Agbe(JCharis)")
	st.sidebar.text("Jesus saves@JCharisTech")

if __name__ == '__main__':


You can also check the entire video tutorial here.

Streamlit is awesome!!. With just this simple code we have been able to build something awesome. Great work by the Streamlit Team.

Thanks For Your Time

Jesus Saves

By Jesse E.Agbe(JCharis)



9 thoughts on “Building A Natural Language Processing App with Streamlit,SpaCy and Python”

  1. OSError: [E050] Can’t find model ‘en’. It doesn’t seem to be a shortcut link, a Python package or a valid path to a data directory.
    File “/opt/anaconda3/lib/python3.7/site-packages/streamlit/”, line 311, in _run_script
    exec(code, module.__dict__)
    File “/Users/sauce_god/Documents/Programs/Streamlit/nlp-app/”, line 41, in
    File “/Users/sauce_god/Documents/Programs/Streamlit/nlp-app/”, line 28, in main
    nlp_result = text_analyzer(message)
    File “/Users/sauce_god/Documents/Programs/Streamlit/nlp-app/”, line 10, in text_analyzer
    nlp = spacy.load(‘en’)
    File “/opt/anaconda3/lib/python3.7/site-packages/spacy/”, line 30, in load
    return cli_info(model, markdown, silent)
    File “/opt/anaconda3/lib/python3.7/site-packages/spacy/”, line 169, in load_model
    data_dir = ‘%s_%s-%s’ % (meta[‘lang’], meta[‘name’], meta[‘version’])

    1. Hi Braucuss, you will have to download the ‘en’ model for spacy
      python -m spacy download en

      Method 2
      python -m spacy download’en_core_web_sm
      nlp = spacy.load(‘en_core_web_sm’)
      Hope it helps

  2. Hello there, just became aware of your blog through Google, and found that it’s really informative. I am gonna watch out for brussels. I抣l appreciate if you continue this in future. Many people will be benefited from your writing. Cheers!

  3. Hi Jesse! Thanks for sharing your code! My spacy package is not working, maybe you have a hint on why?
    “No module named spacy” but it’s installed.

    1. jesse_jcharis

      Hi Paola. Can you try reinstall it again or use a virtual env eg virtualenv or pipenv or conda.
      In case none of them work you can try Google Colab which is free with your gmail account.
      Hope it helps.

  4. Hello. Thank you for this interesting article.
    Can we build this kind of app to upload a word/pdf file and extract some information (to build a table with that) ?

    1. Yes Rone, it is possible to build such an app. You can check the Youtube Channel for such implementation.
      Hope this helps

Leave a Comment

Your email address will not be published. Required fields are marked *