Spaces:
Sleeping
Sleeping
File size: 4,565 Bytes
566200c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 |
# Import libraries
import streamlit as st
from streamlit_extras.stylable_container import stylable_container
import nltk
nltk.download('punkt_tab')
from nltk.tokenize import word_tokenize
import re
import time
import pandas as pd
import numpy as np
from transformers import pipeline
# Title
st.title(":blue[Named Entity Recognition (NER) and Question Answering (QA)]")
st.write("made by [nlpblogs](https://nlpblogs.com/)")
st.write("License [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/deed.en)")
container = st.container(border=True)
container.write("**With this demo app you can tag entities in your text and retrieve answers to your questions.**")
st.divider()
# Text input
def clear_text():
st.session_state["text"] = ""
text = st.text_area("Paste your text here and then press **Ctrl + Enter**. The length of your text should not exceed 500 words.", key="text")
st.button("Clear text", on_click=clear_text)
# Word limit
text1 = re.sub(r'[^\w\s]','',text)
tokens = word_tokenize(text1)
st.divider()
number = 500
if text is not None and len(tokens) > number:
st.warning('The length of your text should not exceed 500 words.')
st.stop()
# Sidebar
with st.sidebar:
with stylable_container(
key="test_button",
css_styles="""
button {
background-color: blue;
border: 3px solid red;
padding: 5px;
color: white;
}
""",
):
st.button("DEMO APP")
st.write("**Original text**")
container = st.container(border=True)
container.write(text)
st.write("Length", len(tokens))
# NER
with st.spinner('Wait for it...'):
time.sleep(5)
if text is not None:
token_classifier = pipeline(model="huggingface-course/bert-finetuned-ner", aggregation_strategy="max")
tokens = token_classifier(text)
df = pd.DataFrame(tokens)
properties = {"border": "2px solid gray", "color": "blue", "font-size": "16px"}
df_styled = df.style.set_properties(**properties)
st.subheader(":red[Named Entity Recognition (NER)]", divider = "red")
tab1, tab2, = st.tabs(["Entities", "Explanations"])
with tab1:
st.table(df_styled)
with tab2:
st.write("**PER** Person's name")
st.write("**LOC** Location name")
st.write("**ORG** Organization name")
st.write("**MISC** Miscellaneous")
st.write("**entity_group** This is the tag that has been assigned to an entity.")
st.write("**score** This indicates the confidence level that a tag has been assigned to an entity.")
st.write("**word** This is the entity that has been extracted from your text data.")
st.write("**start** This is the index of the start of the corresponding entity in your text data.")
st.write("**end** This is the index of the end of the corresponding entity in your text data")
# Download
import zipfile
import io
dfa = pd.DataFrame(
data = {
'PER': ['Person'],
'ORG': ['Organization'],
'LOC': ['Location'],
'MISC': ['Miscellaneous'],
'entity_group': ['tag'],
'score': ['confidence level'],
'word': ['entity'],
'start': ['index of the start of the corresponding entity'],
'end': ['index of the end of the corresponding entity'],
}
)
buf = io.BytesIO()
with zipfile.ZipFile(buf, "x") as myzip:
if text is not None:
myzip.writestr("Summary of the results.csv", df.to_csv())
myzip.writestr("Glossary of tags.csv", dfa.to_csv())
with stylable_container(
key="button",
css_styles="""
button {
background-color: blue;
border: 3px solid red;
padding: 5px;
color: white;
}
""",
):
st.download_button(
label = "Download zip file",
data=buf.getvalue(),
file_name="zip file.zip",
mime="application/zip",
)
st.divider()
# QA
st.subheader(":red[Question Answering (QA)]", divider = "red")
qa = pipeline("question-answering", model="deepset/roberta-base-squad2")
def clear_question():
st.session_state["question"] = ""
question = st.text_input("Ask a question:", key="question")
st.button("Clear question", on_click=clear_question)
if st.button("Get Answer"):
answer = qa(question, text)
st.divider()
st.write("Answer:", answer['answer'])
st.write("Score:", answer['score'] * 100)
|