Spaces:
Runtime error
Runtime error
File size: 5,187 Bytes
c2ad08f 92000af c2ad08f 92000af d7a8932 c2ad08f 44f1a7e c2ad08f 44f1a7e c2ad08f 44f1a7e c2ad08f 44f1a7e c2ad08f 44f1a7e c2ad08f d7a8932 c2ad08f d7a8932 c2ad08f 67b3c11 115c396 c2ad08f 115c396 |
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 |
import streamlit as st
import requests
import nltk
from transformers import pipeline
from rake_nltk import Rake
from nltk.corpus import stopwords
from fuzzywuzzy import fuzz
st.title("Exploring Torch, Transformers, Rake, and Others analyzing Text")
# Define the options for the dropdown menu, Selecting a remote txt file already created to analyze the text
options = ['None','Apprecitation Letter', 'Regret Letter', 'Kindness Tale', 'Lost Melody Tale', 'Twitter Example 1', 'Twitter Example 2']
# Create a dropdown menu to select options
selected_option = st.selectbox("Select a preset option", options)
# Define URLs for different options
url_option1 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Appreciation_Letter.txt"
url_option2 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Regret_Letter.txt"
url_option3 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Kindness_Tale.txt"
url_option4 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Lost_Melody_Tale.txt"
url_option5 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Twitter_Example_1.txt"
url_option6 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Twitter_Example_2.txt"
# Function to fetch text content based on selected option
def fetch_text_content(selected_option):
if selected_option == 'Apprecitation Letter':
return requests.get(url_option1).text
elif selected_option == 'Regret Letter':
return requests.get(url_option2).text
elif selected_option == 'Kindness Tale':
return requests.get(url_option3).text
elif selected_option == 'Lost Melody Tale':
return requests.get(url_option4).text
elif selected_option == 'Twitter Example 1':
return requests.get(url_option5).text
elif selected_option == 'Twitter Example 2':
return requests.get(url_option6).text
else:
return ""
# Fetch text content based on selected option
jd = fetch_text_content(selected_option)
# Display text content in a text area
#jd = st.text_area("Text File Content", text_content)
# Download NLTK resources
nltk.download('punkt')
nltk.download('stopwords')
# Initialize pipeline for sentiment analysis
pipe_sent = pipeline('sentiment-analysis')
# Initialize pipeline for summarization
pipe_summ = pipeline("summarization", model="facebook/bart-large-cnn")
# Function to extract keywords and remove duplicates
def extract_keywords(text):
r = Rake()
r.extract_keywords_from_text(text)
# Get all phrases scored
phrases_with_scores = r.get_ranked_phrases_with_scores()
# Filter out stopwords
stop_words = set(stopwords.words('english'))
keywords = []
for score, phrase in phrases_with_scores:
# Check if the phrase is not a stopword and add to the list
if phrase.lower() not in stop_words:
keywords.append((score, phrase))
# Sort keywords by score in descending order
keywords.sort(key=lambda x: x[0], reverse=True)
# Remove duplicates and merge similar keywords
unique_keywords = []
seen_phrases = set()
for score, phrase in keywords:
if phrase not in seen_phrases:
# Check if the phrase is similar to any of the seen phrases
similar_phrases = [seen_phrase for seen_phrase in seen_phrases if fuzz.ratio(phrase, seen_phrase) > 70]
if similar_phrases:
# If similar phrases are found, merge them into one phrase
merged_phrase = max([phrase] + similar_phrases, key=len)
unique_keywords.append((score, merged_phrase))
else:
unique_keywords.append((score, phrase))
seen_phrases.add(phrase)
return unique_keywords[:10] # Return only the first 10 keywords
text = st.text_area('Enter the text to analyze', jd)
if st.button("Start Analysis"):
with st.spinner("Analyzing Sentiment"):
with st.expander("Sentiment Analysis - ✅ Completed", expanded=False):
# Sentiment analysis
out_sentiment = pipe_sent(text)
# Display sentiment analysis result
sentiment_score = out_sentiment[0]['score']
sentiment_label = out_sentiment[0]['label']
sentiment_emoji = '😊' if sentiment_label == 'POSITIVE' else '😞'
sentiment_text = f"Sentiment Score: {sentiment_score}, Sentiment Label: {sentiment_label.capitalize()} {sentiment_emoji}"
st.write(sentiment_text)
with st.spinner("Summarizing - This may take a while"):
with st.expander("Summarization - ✅ Completed", expanded=False):
# Summarization
out_summ = pipe_summ(text)
summarized_text = out_summ[0]['summary_text']
st.write(summarized_text)
with st.spinner("Extracting Keywords"):
with st.expander("Keywords Extraction - ✅ Completed", expanded=False):
# Keyword extraction
keywords = extract_keywords(text)
keyword_list = [keyword[1] for keyword in keywords]
st.write(keyword_list)
|