File size: 3,310 Bytes
80dc37e |
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 |
import streamlit as st
import pickle
import re
from sklearn.feature_extraction.text import TfidfVectorizer
from nltk.corpus import stopwords
import nltk
from ntscraper import Nitter
# Download stopwords once, using Streamlit's caching
@st.cache_resource
def load_stopwords():
nltk.download('stopwords')
return stopwords.words('english')
# Load model and vectorizer once
@st.cache_resource
def load_model_and_vectorizer():
with open('model.pkl', 'rb') as model_file:
model = pickle.load(model_file)
with open('vectorizer.pkl', 'rb') as vectorizer_file:
vectorizer = pickle.load(vectorizer_file)
return model, vectorizer
# Define sentiment prediction function
def predict_sentiment(text, model, vectorizer, stop_words):
# Preprocess text
text = re.sub('[^a-zA-Z]', ' ', text)
text = text.lower()
text = text.split()
text = [word for word in text if word not in stop_words]
text = ' '.join(text)
text = [text]
text = vectorizer.transform(text)
# Predict sentiment
sentiment = model.predict(text)
return "Negative" if sentiment == 0 else "Positive"
# Initialize Nitter scraper
@st.cache_resource
def initialize_scraper():
return Nitter(log_level=1)
# Function to create a colored card
def create_card(tweet_text, sentiment):
color = "green" if sentiment == "Positive" else "red"
card_html = f"""
<div style="background-color: {color}; padding: 10px; border-radius: 5px; margin: 10px 0;">
<h5 style="color: white;">{sentiment} Sentiment</h5>
<p style="color: white;">{tweet_text}</p>
</div>
"""
return card_html
# Main app logic
def main():
st.title("Twitter Sentiment Analysis")
# Load stopwords, model, vectorizer, and scraper only once
stop_words = load_stopwords()
model, vectorizer = load_model_and_vectorizer()
scraper = initialize_scraper()
# User input: either text input or Twitter username
option = st.selectbox("Choose an option", ["Input text", "Get tweets from user"])
if option == "Input text":
text_input = st.text_area("Enter text to analyze sentiment")
if st.button("Analyze"):
sentiment = predict_sentiment(text_input, model, vectorizer, stop_words)
st.write(f"Sentiment: {sentiment}")
elif option == "Get tweets from user":
username = st.text_input("Enter Twitter username")
if st.button("Fetch Tweets"):
tweets_data = scraper.get_tweets(username, mode='user', number=5)
if 'tweets' in tweets_data: # Check if the 'tweets' key exists
for tweet in tweets_data['tweets']:
tweet_text = tweet['text'] # Access the text of the tweet
sentiment = predict_sentiment(tweet_text, model, vectorizer, stop_words) # Predict sentiment of the tweet text
# Create and display the colored card for the tweet
card_html = create_card(tweet_text, sentiment)
st.markdown(card_html, unsafe_allow_html=True)
else:
st.write("No tweets found or an error occurred.")
if __name__ == "__main__":
main()
|