Create app.py

app.py

@@ -0,0 +1,100 @@
+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
+
+s.title("Exploring Torch, Transformers, Rake, and Others analyzing Text")
+
+# Define the options for the dropdown menu
+options = ['Option 1', 'Option 2']
+
+# Create a dropdown menu to select options
+selected_option = st.selectbox("Select an option", options)
+
+# Define URLs for different options
+url_option1 = "https://raw.githubusercontent.com/peteciank/me/main/jd_sm.txt"
+url_option2 = "https://raw.githubusercontent.com/peteciank/me/main/jd_controller.txt"
+
+# Function to fetch text content based on selected option
+def fetch_text_content(selected_option):
+    if selected_option == 'Option 1':
+        return requests.get(url_option1).text
+    elif selected_option == 'Option 2':
+        return requests.get(url_option2).text
+    else:
+        return ""
+
+# Fetch text content based on selected option
+text_content = 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 text:
+    # Sentiment analysis
+    st.write("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)
+
+    # Summarization
+    st.write("Summarization")
+    out_summ = pipe_summ(text)
+    summarized_text = out_summ[0]['summary_text']
+    st.write(summarized_text)
+
+    # Keyword extraction
+    st.write("Keywords")
+    keywords = extract_keywords(text)
+    keyword_list = [keyword[1] for keyword in keywords]
+    st.write(keyword_list)