Code Editor for app.py

import streamlit as st
import pandas as pd
from textblob import TextBlob
import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
import re

# Download required NLTK data
try:
    nltk.data.find('tokenizers/punkt')
    nltk.data.find('corpora/stopwords')
    nltk.data.find('corpora/wordnet')
except LookupError:
    nltk.download('punkt')
    nltk.download('stopwords')
    nltk.download('wordnet')

def clean_text(text):
    # Convert to lowercase
    text = text.lower()
    # Remove URLs
    text = re.sub(r'http\S+|www\S+|https\S+', '', text, flags=re.MULTILINE)
    # Remove user @ references and '#' from tweet
    text = re.sub(r'\@\w+|\#\w+', '', text)
    # Remove punctuations and numbers
    text = re.sub(r'[^\w\s]', '', text)
    # Remove numbers
    text = re.sub(r'\d+', '', text)
    return text

def preprocess_text(text):
    # Clean the text
    text = clean_text(text)
    
    # Tokenization
    tokens = word_tokenize(text)
    
    # Remove stopwords
    stop_words = set(stopwords.words('english'))
    tokens = [token for token in tokens if token not in stop_words]
    
    # Lemmatization
    lemmatizer = WordNetLemmatizer()
    tokens = [lemmatizer.lemmatize(token) for token in tokens]
    
    return ' '.join(tokens)

def analyze_sentiment(text):
    analysis = TextBlob(text)
    if analysis.sentiment.polarity > 0:
        return 'Positive'
    elif analysis.sentiment.polarity < 0:
        return 'Negative'
    else:
        return 'Neutral'

def get_sentiment_score(text):
    analysis = TextBlob(text)
    return analysis.sentiment.polarity

st.title('Tweet Sentiment Analysis')

# File upload option
st.header('Option 1: Upload CSV file')
uploaded_file = st.file_uploader("Choose a CSV file", type="csv")

# Text input option
st.header('Option 2: Enter Tweet Text')
tweet_text = st.text_area("Enter tweet text here:", height=100)

if uploaded_file is not None:
    # Read CSV file
    df = pd.read_csv(uploaded_file)
    
    # Check if 'text' or 'tweet' column exists
    text_column = None
    possible_columns = ['text', 'tweet', 'content', 'Tweet']
    for col in possible_columns:
        if col in df.columns:
            text_column = col
            break
    
    if text_column:
        st.write("Processing tweets from CSV file...")
        
        # Create progress bar
        progress_bar = st.progress(0)
        
        # Process each tweet
        df['processed_text'] = df[text_column].astype(str).apply(preprocess_text)
        df['sentiment'] = df['processed_text'].apply(analyze_sentiment)
        df['sentiment_score'] = df['processed_text'].apply(get_sentiment_score)
        
        # Show results
        st.subheader('Analysis Results')
        
        # Display sentiment distribution
        sentiment_counts = df['sentiment'].value_counts()
        st.bar_chart(sentiment_counts)
        
        # Display the dataframe with results
        st.write(df[[text_column, 'sentiment', 'sentiment_score']])
        
        # Download results
        csv = df.to_csv(index=False)
        st.download_button(
            label="Download results as CSV",
            data=csv,
            file_name="sentiment_analysis_results.csv",
            mime="text/csv"
        )
    else:
        st.error("Could not find a text column in the CSV file. Please ensure your CSV has a column named 'text', 'tweet', or 'content'.")

elif tweet_text:
    st.subheader('Analysis Results')
    
    # Process the input text
    processed_text = preprocess_text(tweet_text)
    sentiment = analyze_sentiment(processed_text)
    sentiment_score = get_sentiment_score(processed_text)
    
    # Display results
    col1, col2 = st.columns(2)
    
    with col1:
        st.metric("Sentiment", sentiment)
    
    with col2:
        st.metric("Sentiment Score", round(sentiment_score, 3))
    
    # Show processed text
    st.subheader('Processed Text')
    st.write(processed_text)

# Add information about the analysis
st.sidebar.title('About')
st.sidebar.info('''
This app performs sentiment analysis on tweets using TextBlob.
- Sentiment scores range from -1 (most negative) to 1 (most positive)
- Text preprocessing includes:
  - Removing URLs, mentions, and hashtags
  - Converting to lowercase
  - Removing punctuation and numbers
  - Removing stopwords
  - Lemmatization
''')