marcelomoreno26's picture
Update app.py
a6f40d0 verified
raw
history blame
3.3 kB
from model_functions import *
from preprocessor import *
import streamlit as st
import pandas as pd
@st.cache
def load_example_file(file):
with open(file, "rb") as f:
return f.read()
def main():
# Load models
tokenizer_sentiment, model_sentiment = load_sentiment_analyzer()
tokenizer_summary, model_summary = load_summarizer()
pipe_ner = load_NER()
st.title("WhatsApp Analysis Tool")
st.markdown("This app summarizes Whatsapp chats and provides named entity recognition as well as sentiment analysis for the conversation")
st.markdown("**NOTE**: *This app can only receive chats downloaded from IOS as the downloaded chat format is different than from Android.*")
st.markdown("Download your whatsapp chat by going to Settings > Chats > Export Chat and there select the chat you want to summarize (download 'Without Media').")
st.markdown("**Example Files**: Download example zip files to test the app:")
example_files = {
"Example 1": "example1.zip",
"Example 2": "example2.zip",
"Example 3": "example3.zip"
}
for name, file in example_files.items():
data = load_example_file(file)
st.download_button(label=name, data=data, file_name=file, mime="application/zip")
# File uploader
uploaded_file = st.file_uploader("Choose a file (.zip)", type=['zip'])
if uploaded_file is not None:
file_type = detect_file_type(uploaded_file.name)
if file_type == "zip":
# Process the file
data = preprocess_whatsapp_messages(uploaded_file, file_type)
if data.empty:
st.write("No messages found or the file could not be processed.")
else:
# Date selector
date_options = data['date'].dt.strftime('%Y-%m-%d').unique()
selected_date = st.selectbox("Select a date for analysis:", date_options)
if selected_date:
text_for_analysis = get_dated_input(data, selected_date)
with st.expander("Show/Hide Original Conversation"):
st.markdown(f"```\n{text_for_analysis}\n```", unsafe_allow_html=True)
process = st.button('Process')
if process:
# Perform analysis
sentiment = get_sentiment_analysis(text_for_analysis, tokenizer_sentiment, model_sentiment)
summary = generate_summary(text_for_analysis, tokenizer_summary, model_summary)
ner_results = get_NER(summary, pipe_ner)
# Display results
st.subheader("Sentiment Analysis")
st.write("Sentiment:", sentiment)
st.subheader("Summary")
st.write("Summary:", summary)
st.subheader("Named Entity Recognition")
ner_df = pd.DataFrame(ner_results, columns=["Word", "Entity Group"])
st.write(ner_df)
else:
st.error("Unsupported file type. Please upload a .txt or .zip file.")
else:
st.info("Please upload a file to proceed.")
if __name__ == "__main__":
main()