app.py

import streamlit as st
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from wordcloud import WordCloud
from sentiment_labeling import add_sentiment_column
from keras.models import load_model
import pickle

# Load the model and tokenizer
model = load_model('model.h5')
with open('tokenizer.pkl', 'rb') as f:
    tokenizer = pickle.load(f)

def predict_sentiment(text):
    # Tokenize and pad the input text
    seq = tokenizer.texts_to_sequences([text])
    padded_seq = pad_sequences(seq, maxlen=MAX_LENGTH)
    # Predict using the model
    prediction = model.predict(padded_seq)
    return np.argmax(prediction)

# Streamlit app
st.title("Thread Review Sentiment Analysis")

# Upload CSV file
uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
if uploaded_file:
    data = pd.read_csv(uploaded_file)
    st.write("Data Loaded Successfully!")
    
    # Display raw data
    if st.checkbox("Show raw data"):
        st.write(data)

    # Add sentiment column
    data = add_sentiment_column(data)
    
    # Distribution of sentiments
    st.subheader("Distribution of Sentiments")
    sentiment_counts = data['sentiment'].value_counts()
    fig, ax = plt.subplots()
    sentiment_counts.plot(kind='bar', ax=ax)
    ax.set_title('Distribution of Sentiments')
    ax.set_xlabel('Sentiment')
    ax.set_ylabel('Count')
    st.pyplot(fig)

    # Word cloud for each sentiment
    st.subheader("Word Clouds for Sentiments")
    sentiments = ['positive', 'neutral', 'negative']
    for sentiment in sentiments:
        st.write(f"Word Cloud for {sentiment}")
        subset = data[data['sentiment'] == sentiment]
        text = " ".join(review for review in subset['review'])
        wordcloud = WordCloud(max_words=100, background_color="white").generate(text)
        plt.figure()
        plt.imshow(wordcloud, interpolation="bilinear")
        plt.axis("off")
        st.pyplot()

    # Individual review prediction
    user_input = st.text_area("Type a review here to predict its sentiment:")
    if user_input:
        sentiment_pred = predict_sentiment(user_input)
        st.write(f"The predicted sentiment is: {sentiment_pred}")