Spaces:
Runtime error
Runtime error
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# -*- coding: utf-8 -*-
|
2 |
+
"""Untitled11.ipynb
|
3 |
+
|
4 |
+
Automatically generated by Colaboratory.
|
5 |
+
|
6 |
+
Original file is located at
|
7 |
+
https://colab.research.google.com/drive/1Y2vv_pZ5nKXKLrXrmsSu6z8hz6ncjWOz
|
8 |
+
"""
|
9 |
+
|
10 |
+
import streamlit as st
|
11 |
+
from transformers import BartForConditionalGeneration, BartTokenizer
|
12 |
+
import nltk
|
13 |
+
from nltk.corpus import stopwords
|
14 |
+
from nltk.tokenize import word_tokenize
|
15 |
+
from wordcloud import WordCloud
|
16 |
+
import matplotlib.pyplot as plt
|
17 |
+
from nltk.probability import FreqDist
|
18 |
+
|
19 |
+
nltk.download('punkt')
|
20 |
+
nltk.download('stopwords')
|
21 |
+
|
22 |
+
st.title("NLP Text Analyzer")
|
23 |
+
|
24 |
+
user_input = st.text_area("Enter your text:", "Type here...")
|
25 |
+
|
26 |
+
if user_input:
|
27 |
+
st.header("Summary:")
|
28 |
+
|
29 |
+
# Load pre-trained BART model and tokenizer
|
30 |
+
model = BartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
|
31 |
+
tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
|
32 |
+
|
33 |
+
# Tokenize the input text
|
34 |
+
inputs = tokenizer.encode("summarize: " + user_input, return_tensors="pt", max_length=1024, truncation=True)
|
35 |
+
|
36 |
+
# Generate the summary
|
37 |
+
summary_ids = model.generate(inputs, max_length=150, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True)
|
38 |
+
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
|
39 |
+
|
40 |
+
st.write(summary)
|
41 |
+
|
42 |
+
# Your previous code for creating the Word Cloud plot
|
43 |
+
st.header("Word Cloud:")
|
44 |
+
wordcloud = WordCloud(stopwords=set(stopwords.words('english')), background_color='white').generate(user_input)
|
45 |
+
plt.figure(figsize=(8, 6)) # Adjust the figsize as needed
|
46 |
+
plt.imshow(wordcloud, interpolation='bilinear')
|
47 |
+
plt.axis("off")
|
48 |
+
|
49 |
+
# Display the Word Cloud plot using st.pyplot() with the explicit figure object
|
50 |
+
st.pyplot(plt.gcf())
|
51 |
+
|
52 |
+
st.header("Most Common Words:")
|
53 |
+
words = word_tokenize(user_input) # Tokenize the user input text
|
54 |
+
fdist = nltk.FreqDist(words)
|
55 |
+
most_common_words = fdist.most_common(10)
|
56 |
+
|
57 |
+
# Prepare data for tabular format
|
58 |
+
data = {
|
59 |
+
"Word": [word[0] for word in most_common_words],
|
60 |
+
"Frequency": [word[1] for word in most_common_words]
|
61 |
+
}
|
62 |
+
|
63 |
+
# Display as a table
|
64 |
+
st.table(data)
|