Spaces:
Runtime error
Runtime error
Gbadamosi_oluwaseyi
commited on
Commit
•
c20a951
1
Parent(s):
d210bc0
v1
Browse files- README.md +45 -2
- app.py +119 -0
- function.py +106 -0
- requirements.txt +6 -0
- summarizer_database.db +0 -0
README.md
CHANGED
@@ -1,2 +1,45 @@
|
|
1 |
-
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: Article Text Summarizer
|
3 |
+
emoji: 💻
|
4 |
+
colorFrom: green
|
5 |
+
colorTo: green
|
6 |
+
sdk: streamlit
|
7 |
+
app_file: app.py
|
8 |
+
pinned: false
|
9 |
+
---
|
10 |
+
|
11 |
+
# Configuration
|
12 |
+
|
13 |
+
`title`: _string_
|
14 |
+
Display title for the Space
|
15 |
+
|
16 |
+
`emoji`: _string_
|
17 |
+
Space emoji (emoji-only character allowed)
|
18 |
+
|
19 |
+
`colorFrom`: _string_
|
20 |
+
Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
|
21 |
+
|
22 |
+
`colorTo`: _string_
|
23 |
+
Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
|
24 |
+
|
25 |
+
`sdk`: _string_
|
26 |
+
Can be either `gradio`, `streamlit`, or `static`
|
27 |
+
|
28 |
+
`sdk_version` : _string_
|
29 |
+
Only applicable for `streamlit` SDK.
|
30 |
+
See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
|
31 |
+
|
32 |
+
`app_file`: _string_
|
33 |
+
Path to your main application file (which contains either `gradio` or `streamlit` Python code, or `static` html code).
|
34 |
+
Path is relative to the root of the repository.
|
35 |
+
|
36 |
+
`models`: _List[string]_
|
37 |
+
HF model IDs (like "gpt2" or "deepset/roberta-base-squad2") used in the Space.
|
38 |
+
Will be parsed automatically from your code if not specified here.
|
39 |
+
|
40 |
+
`datasets`: _List[string]_
|
41 |
+
HF dataset IDs (like "common_voice" or "oscar-corpus/OSCAR-2109") used in the Space.
|
42 |
+
Will be parsed automatically from your code if not specified here.
|
43 |
+
|
44 |
+
`pinned`: _boolean_
|
45 |
+
Whether the Space stays on top of your list.
|
app.py
ADDED
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Core Pkgs
|
2 |
+
import streamlit as st
|
3 |
+
from function import *
|
4 |
+
# EDA Pkgs
|
5 |
+
import pandas as pd
|
6 |
+
import matplotlib.pyplot as plt
|
7 |
+
from wordcloud import WordCloud
|
8 |
+
# Utils
|
9 |
+
from datetime import datetime
|
10 |
+
warnings.filterwarnings("ignore")
|
11 |
+
|
12 |
+
st.set_option('deprecation.showPyplotGlobalUse', False)
|
13 |
+
|
14 |
+
def main():
|
15 |
+
menu = ["Home","Storage","About"]
|
16 |
+
create_table()
|
17 |
+
|
18 |
+
choice = st.sidebar.selectbox("Menu",menu)
|
19 |
+
|
20 |
+
if choice == "Home":
|
21 |
+
st.title("Demo")
|
22 |
+
|
23 |
+
st.sidebar.subheader("Tuning/Settings")
|
24 |
+
# max_length= st.sidebar.slider("Maximum length of the generated text ",30,100)
|
25 |
+
# top_k= st.sidebar.slider(" limits the sampled tokens to the top k values ",1,100)
|
26 |
+
# temperature= st.sidebar.slider("Controls the craziness of the text ",0.7,100.0)
|
27 |
+
model_type = st.sidebar.selectbox("Model type", options=["Bart","T5"])
|
28 |
+
|
29 |
+
upload_doc = st.file_uploader("Upload a .txt, .pdf, .docx file for summarization")
|
30 |
+
|
31 |
+
st.markdown("<h3 style='text-align: center; color: red;'>OR</h3>",unsafe_allow_html=True,)
|
32 |
+
|
33 |
+
plain_text = st.text_area("Type your Message...",height=200)
|
34 |
+
|
35 |
+
if upload_doc:
|
36 |
+
clean_text = preprocess_plain_text(extract_text_from_file(upload_doc))
|
37 |
+
else:
|
38 |
+
clean_text = preprocess_plain_text(plain_text)
|
39 |
+
|
40 |
+
summarize = st.button("Summarize...")
|
41 |
+
|
42 |
+
# called on toggle button [summarize]
|
43 |
+
if summarize:
|
44 |
+
if model_type == "Bart":
|
45 |
+
text_to_summarize = clean_text
|
46 |
+
|
47 |
+
with st.spinner(
|
48 |
+
text="Loading Bart Model and Extracting summary. This might take a few seconds depending on the length of your text..."):
|
49 |
+
summarizer_model = bart()
|
50 |
+
summarized_text = summarizer_model(text_to_summarize, max_length=100, min_length=30)
|
51 |
+
summarized_text = ' '.join([summ['summary_text'] for summ in summarized_text])
|
52 |
+
st.success("Data Submitted for model retraining")
|
53 |
+
postdate = datetime.now()
|
54 |
+
# Add Data To Database
|
55 |
+
add_data(text_to_summarize,summarized_text,postdate)
|
56 |
+
|
57 |
+
elif model_type == "T5":
|
58 |
+
text_to_summarize = clean_text
|
59 |
+
|
60 |
+
with st.spinner(
|
61 |
+
text="Loading T5 Model and Extracting summary. This might take a few seconds depending on the length of your text..."):
|
62 |
+
summarizer_model = t5()
|
63 |
+
summarized_text = summarizer_model(text_to_summarize, max_length=100, min_length=30)
|
64 |
+
summarized_text = ' '.join([summ['summary_text'] for summ in summarized_text])
|
65 |
+
st.success("Data Submitted for model retraining")
|
66 |
+
postdate = datetime.now()
|
67 |
+
# Add Data To Database
|
68 |
+
add_data(text_to_summarize,summarized_text,postdate)
|
69 |
+
|
70 |
+
# else:
|
71 |
+
# text_to_summarize = clean_text
|
72 |
+
|
73 |
+
# with st.spinner(
|
74 |
+
# text="Loading Pegasus Model and Extracting summary. This might take a few seconds depending on the length of your text..."):
|
75 |
+
# summarizer_model = pegasus()
|
76 |
+
# summarized_text = summarizer_model(text_to_summarize, max_length=100, min_length=30)
|
77 |
+
# # summarized_text = ' '.join([summ['summary_text'] for summ in summarized_text])
|
78 |
+
# st.success("Data Submitted for model retraining")
|
79 |
+
# postdate = datetime.now()
|
80 |
+
# # Add Data To Database
|
81 |
+
# # add_data(text_to_summarize,summarized_text,postdate)
|
82 |
+
|
83 |
+
res_col1 ,res_col2 = st.columns(2)
|
84 |
+
with res_col1:
|
85 |
+
st.subheader("Generated Text Visualization")
|
86 |
+
# Create and generate a word cloud image:
|
87 |
+
wordcloud = WordCloud().generate(summarized_text)
|
88 |
+
# Display the generated image:
|
89 |
+
plt.imshow(wordcloud, interpolation='bilinear')
|
90 |
+
plt.axis("off")
|
91 |
+
plt.show()
|
92 |
+
st.pyplot()
|
93 |
+
summary_downloader(summarized_text)
|
94 |
+
|
95 |
+
with res_col2:
|
96 |
+
st.subheader("Summarized Text Output")
|
97 |
+
st.success("Summarized Text")
|
98 |
+
st.write(summarized_text)
|
99 |
+
|
100 |
+
elif choice == "Storage":
|
101 |
+
st.title("Manage & Monitor Results")
|
102 |
+
# stored_data = view_all_data()
|
103 |
+
# new_df = pd.DataFrame(stored_data,columns=["text_to_summarize","summarized_text","postdate"])
|
104 |
+
# st.dataframe(new_df)
|
105 |
+
# new_df['postdate'] = pd.to_datetime(new_df['postdate'])
|
106 |
+
|
107 |
+
|
108 |
+
else:
|
109 |
+
st.subheader("About")
|
110 |
+
# html_temp ="""<div>
|
111 |
+
# <p></p>
|
112 |
+
# <p></p>
|
113 |
+
# </div>"""
|
114 |
+
# st.markdown(html_temp, unsafe_allow_html=True)
|
115 |
+
|
116 |
+
|
117 |
+
|
118 |
+
if __name__ == '__main__':
|
119 |
+
main()
|
function.py
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Core Pkgs
|
2 |
+
import streamlit as st
|
3 |
+
from transformers import pipeline
|
4 |
+
from PyPDF2 import PdfFileReader
|
5 |
+
import docx2txt
|
6 |
+
import base64
|
7 |
+
import re
|
8 |
+
import sqlite3
|
9 |
+
import time
|
10 |
+
from io import StringIO
|
11 |
+
import warnings
|
12 |
+
warnings.filterwarnings("ignore")
|
13 |
+
|
14 |
+
time_str = time.strftime("%Y%m%d-%H%M%S")
|
15 |
+
# Loading function the model pipeline from huggingface model
|
16 |
+
@st.cache(allow_output_mutation=True)
|
17 |
+
def bart():
|
18 |
+
''' Loading bart model using pipeline api '''
|
19 |
+
summarizer = pipeline('summarization',model='amazon/bort')
|
20 |
+
return summarizer
|
21 |
+
|
22 |
+
def t5():
|
23 |
+
''' Loading t5 model using pipeline api '''
|
24 |
+
summarizer = pipeline("summarization", model="t5-base", tokenizer="t5-base", framework="tf")
|
25 |
+
return summarizer
|
26 |
+
|
27 |
+
# def pegasus():
|
28 |
+
# ''' Loading pegasus model using pipeline api '''
|
29 |
+
# summarizer = pipeline('summarization',model='google/pegasus-xsum')
|
30 |
+
# return summarizer
|
31 |
+
|
32 |
+
def preprocess_plain_text(x):
|
33 |
+
|
34 |
+
x = x.encode("ascii", "ignore").decode() # unicode
|
35 |
+
x = re.sub(r"https*\S+", " ", x) # url
|
36 |
+
x = re.sub(r"@\S+", " ", x) # mentions
|
37 |
+
x = re.sub(r"#\S+", " ", x) # hastags
|
38 |
+
x = re.sub(r"\s{2,}", " ", x) # over spaces
|
39 |
+
x = re.sub("[^.,!?A-Za-z0-9]+", " ", x) # special charachters except .,!?
|
40 |
+
|
41 |
+
return x
|
42 |
+
|
43 |
+
def extract_pdf(file):
|
44 |
+
|
45 |
+
'''Extract text from PDF file'''
|
46 |
+
|
47 |
+
pdfReader = PdfFileReader(file)
|
48 |
+
count = pdfReader.numPages
|
49 |
+
all_text = ""
|
50 |
+
for i in range(count):
|
51 |
+
page = pdfReader.getPage(i)
|
52 |
+
all_text += page.extractText()
|
53 |
+
|
54 |
+
return all_text
|
55 |
+
|
56 |
+
|
57 |
+
def extract_text_from_file(file):
|
58 |
+
|
59 |
+
'''Extract text from uploaded file'''
|
60 |
+
|
61 |
+
# read text file
|
62 |
+
if file.type == "text/plain":
|
63 |
+
# To convert to a string based IO:
|
64 |
+
stringio = StringIO(file.getvalue().decode("utf-8"))
|
65 |
+
|
66 |
+
# To read file as string:
|
67 |
+
file_text = stringio.read()
|
68 |
+
|
69 |
+
# read pdf file
|
70 |
+
elif file.type == "application/pdf":
|
71 |
+
file_text = extract_pdf(file)
|
72 |
+
|
73 |
+
# read docx file
|
74 |
+
elif (
|
75 |
+
file.type
|
76 |
+
== "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
|
77 |
+
):
|
78 |
+
file_text = docx2txt.process(file)
|
79 |
+
|
80 |
+
return file_text
|
81 |
+
|
82 |
+
def summary_downloader(raw_text):
|
83 |
+
|
84 |
+
b64 = base64.b64encode(raw_text.encode()).decode()
|
85 |
+
new_filename = "new_text_file_{}_.txt".format(time_str)
|
86 |
+
st.markdown("#### Download Summary as a File ###")
|
87 |
+
href = f'<a href="data:file/txt;base64,{b64}" download="{new_filename}">Click to Download!!</a>'
|
88 |
+
st.markdown(href,unsafe_allow_html=True)
|
89 |
+
|
90 |
+
|
91 |
+
# Storage in A Database
|
92 |
+
conn = sqlite3.connect('summarizer_database.db',check_same_thread=False)
|
93 |
+
c = conn.cursor()
|
94 |
+
# Create Fxn From SQL
|
95 |
+
def create_table():
|
96 |
+
c.execute('CREATE TABLE IF NOT EXISTS TextTable(text_to_summarize TEXT,summarized_text TEXT,postdate DATE)')
|
97 |
+
|
98 |
+
|
99 |
+
def add_data(text_to_summarize,summarized_text,postdate):
|
100 |
+
c.execute('INSERT INTO TextTable(text_to_summarize,summarized_text,postdate) VALUES (?,?,?)',(text_to_summarize,summarized_text,postdate))
|
101 |
+
conn.commit()
|
102 |
+
|
103 |
+
def view_all_data():
|
104 |
+
c.execute("SELECT * FROM TextTable")
|
105 |
+
data = c.fetchall()
|
106 |
+
return data
|
requirements.txt
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
docx2txt==0.8
|
2 |
+
pandas==1.3.5
|
3 |
+
PyPDF2==1.26.0
|
4 |
+
regex==2021.8.28
|
5 |
+
transformers==4.17.0
|
6 |
+
wordcloud== 1.8.1
|
summarizer_database.db
ADDED
Binary file (16.4 kB). View file
|
|