app.py

import streamlit as st
import pandas as pd
import numpy as np
from utils import (
    read_csv, read_excel, read_pdf, detect_file_type,
    clean_dataframe, generate_summary_stats, extract_financial_kpis,
    FileProcessingError
)
import visualizations
import logging

# Configure the app
st.set_page_config(
    page_title="Financial Document Analyzer",
    page_icon="📊",
    layout="wide"
)

# Initialize session state
if 'data' not in st.session_state:
    st.session_state.data = None
if 'file_type' not in st.session_state:
    st.session_state.file_type = None
if 'summary_stats' not in st.session_state:
    st.session_state.summary_stats = None
if 'kpis' not in st.session_state:
    st.session_state.kpis = None

def main():
    st.title("📊 Financial Document Analyzer")
    st.write("""
    Upload your financial documents (CSV, Excel, or PDF) for automated analysis and visualization.
    This tool will help you extract key financial metrics and generate insightful visualizations.
    """)

    # File upload
    uploaded_file = st.file_uploader("Choose a file", type=['csv', 'xlsx', 'xls', 'pdf'])

    if uploaded_file is not None:
        try:
            # Detect file type and read file
            file_type = detect_file_type(uploaded_file.name)
            st.session_state.file_type = file_type

            with st.spinner('Reading and processing file...'):
                if file_type == 'csv':
                    df = read_csv(uploaded_file)
                elif file_type == 'excel':
                    df = read_excel(uploaded_file)
                elif file_type == 'pdf':
                    df = read_pdf(uploaded_file)

                # Clean the dataframe
                df = clean_dataframe(df)
                st.session_state.data = df

                # Generate summary statistics
                st.session_state.summary_stats = generate_summary_stats(df)
                
                # Extract KPIs
                st.session_state.kpis = extract_financial_kpis(df)

            # Display success message
            st.success('File processed successfully!')

            # Create tabs for different analyses
            tab1, tab2, tab3, tab4 = st.tabs([
                "📊 Data Overview",
                "📈 Financial KPIs",
                "🔍 Detailed Analysis",
                "📉 Visualizations"
            ])

            with tab1:
                st.header("Data Overview")
                st.write("First few rows of the data:")
                st.dataframe(df.head())
                
                st.subheader("Summary Statistics")
                col1, col2 = st.columns(2)
                with col1:
                    st.write("Basic Information:")
                    st.write(f"- Rows: {st.session_state.summary_stats['row_count']}")
                    st.write(f"- Columns: {st.session_state.summary_stats['column_count']}")
                with col2:
                    st.write("Column Types:")
                    st.write(f"- Numeric Columns: {', '.join(st.session_state.summary_stats['numeric_columns'])}")
                    st.write(f"- Categorical Columns: {', '.join(st.session_state.summary_stats['categorical_columns'])}")

            with tab2:
                st.header("Financial KPIs")
                if st.session_state.kpis:
                    # Display KPIs in a dashboard
                    st.plotly_chart(visualizations.create_summary_dashboard(st.session_state.kpis), use_container_width=True)
                else:
                    st.warning("No financial KPIs could be extracted from this document.")

            with tab3:
                st.header("Detailed Analysis")
                
                # Correlation analysis for numeric columns
                if len(st.session_state.summary_stats['numeric_columns']) > 1:
                    st.subheader("Correlation Analysis")
                    st.plotly_chart(visualizations.create_correlation_heatmap(df), use_container_width=True)
                
                # Distribution analysis
                st.subheader("Distribution Analysis")
                selected_column = st.selectbox(
                    "Select column for distribution analysis",
                    st.session_state.summary_stats['numeric_columns']
                )
                if selected_column:
                    st.plotly_chart(visualizations.create_distribution_plots(df, selected_column), use_container_width=True)

            with tab4:
                st.header("Visualizations")
                
                # Time series analysis if date column exists
                date_columns = df.select_dtypes(include=['datetime64']).columns
                if len(date_columns) > 0:
                    st.subheader("Time Series Analysis")
                    date_col = st.selectbox("Select date column", date_columns)
                    value_col = st.selectbox("Select value column", st.session_state.summary_stats['numeric_columns'])
                    st.plotly_chart(visualizations.create_time_series_plot(df, date_col, value_col), use_container_width=True)
                
                # Categorical analysis
                if len(st.session_state.summary_stats['categorical_columns']) > 0:
                    st.subheader("Categorical Analysis")
                    cat_col = st.selectbox("Select categorical column", st.session_state.summary_stats['categorical_columns'])
                    val_col = st.selectbox("Select value column for analysis", st.session_state.summary_stats['numeric_columns'])
                    st.plotly_chart(visualizations.create_categorical_analysis(df, cat_col, val_col), use_container_width=True)

        except FileProcessingError as e:
            st.error(f"Error processing file: {str(e)}")
        except Exception as e:
            st.error(f"An unexpected error occurred: {str(e)}")
            logging.exception("Unexpected error in main application")

if __name__ == "__main__":
    main()