app.py

import os
import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
import dask.dataframe as dd
from dotenv import load_dotenv
from itertools import combinations
from collections import defaultdict

# Load environment variables
load_dotenv()

# Configuration from environment variables
FILE_UPLOAD_LIMIT = int(os.getenv('FILE_UPLOAD_LIMIT', 200))
EXECUTION_TIME_LIMIT = int(os.getenv('EXECUTION_TIME_LIMIT', 300))
RESOURCE_LIMIT = int(os.getenv('RESOURCE_LIMIT', 1024))  # in MB
DATA_DIR = os.getenv('DATA_DIR', './data')
CONFIG_FLAG = os.getenv('CONFIG_FLAG', 'default')

# Main application logic
def main():
    st.title("CyberOps Dashboard")

    # Sidebar for user inputs
    st.sidebar.header("Options")

    # Main frame for introduction and navigation
    with st.container():
        st.subheader("Welcome to CyberOps Dashboard")
        st.write("""
            The CyberOps Dashboard is designed to assist cybersecurity professionals in analyzing and visualizing data efficiently.
            With this tool, you can upload CSV files, visualize data trends, and perform advanced data analysis.
        """)

        # Navigation section
        st.subheader("Navigation")
        st.write("Use the buttons below to navigate to different sections:")
        col1, col2, col3 = st.columns(3)

        with col1:
            if st.button("Data Upload"):
                uploaded_file = st.sidebar.file_uploader("Select a CSV file:", type=["csv"], key="file_uploader_data_upload")

        with col2:
            if st.button("Data Visualization"):
                st.sidebar.selectbox('Select X-axis:', [], key="data_visualization_x")
                st.sidebar.selectbox('Select Y-axis:', [], key="data_visualization_y")

        with col3:
            if st.button("Analysis Tools"):
                st.sidebar.multiselect('Select columns for combinations:', [], key="analysis_tools_columns")

    uploaded_file = st.sidebar.file_uploader("Select a CSV file:", type=["csv"], key="file_uploader_main")

    if uploaded_file:
        @st.cache_data
        def load_csv(file):
            return pd.read_csv(file)

        @st.cache_data
        def load_dask_csv(file):
            return dd.read_csv(file)

        if os.path.getsize(uploaded_file) < RESOURCE_LIMIT * 1024 * 1024:
            df = load_csv(uploaded_file)
        else:
            df = load_dask_csv(uploaded_file)

        if not df.empty:
            st.write("Data Preview:")
            st.dataframe(df.compute() if isinstance(df, dd.DataFrame) else df)

            # Select columns for plotting
            x_column = st.sidebar.selectbox('Select X-axis:', df.columns, key="x_column_plot")
            y_column = st.sidebar.selectbox('Select Y-axis:', df.columns, key="y_column_plot")

            # Plotting
            fig, ax = plt.subplots()
            ax.plot(df[x_column], df[y_column], marker='o')
            ax.set_xlabel(x_column)
            ax.set_ylabel(y_column)
            ax.set_title(f"{y_column} vs {x_column}")
            st.pyplot(fig)

            # Combinatorial analysis
            col_combinations = st.sidebar.multiselect('Select columns for combinations:', df.columns, key="col_combinations")
            if col_combinations:
                st.write("Column Combinations:")
                comb = list(combinations(col_combinations, 2))
                st.write(comb)

            # Grouping and aggregation
            group_by_column = st.sidebar.selectbox('Select column to group by:', df.columns, key="group_by_column")
            if group_by_column:
                grouped_df = df.groupby(group_by_column).agg(list)
                st.write("Grouped Data:")
                st.dataframe(grouped_df.compute() if isinstance(grouped_df, dd.DataFrame) else grouped_df)

if __name__ == "__main__":
    main()