weekly.py

import pandas as pd
import streamlit as st
import plotly.graph_objects as go
from pre import preprocess_uploaded_file
from datetime import datetime

def generate_weekly_report(uploaded_files):
    if not uploaded_files:
        st.error("No files uploaded. Please upload CSV files for analysis.")
        return

    combined_data = pd.DataFrame()
    for uploaded_file in uploaded_files:
        data = preprocess_uploaded_file(uploaded_file)
        # Extract date and time from filename
        filename_parts = uploaded_file.name.split('_')
        if len(filename_parts) >= 4:
            file_datetime_str = f"{filename_parts[-2]}_{filename_parts[-1].split('.')[0]}"
            try:
                file_datetime = datetime.strptime(file_datetime_str, '%Y%m%d_%H%M%S')
                file_date = file_datetime.date()
            except ValueError:
                st.error(f"Invalid date format in filename: {uploaded_file.name}")
                return
        else:
            st.error(f"Filename does not contain expected date format: {uploaded_file.name}")
            return
        
        data['File Date'] = file_date
        combined_data = pd.concat([combined_data, data], ignore_index=True)

    if combined_data.empty:
        st.error("No data found in the uploaded files. Please check the file contents.")
        return

    failed_data = combined_data[combined_data['Status'] == 'FAILED']

    if failed_data.empty:
        st.warning("No failed scenarios found in the uploaded data.")
        return

    # Use 'File Date' for grouping
    failed_data['Date'] = failed_data['File Date']

    # UI for selecting environments and functional areas
    environments = combined_data['Environment'].unique()
    selected_environments = st.multiselect("Select Environments", options=environments, default=environments)

    all_functional_areas = failed_data['Functional area'].unique()
    area_choice = st.radio("Choose Functional Areas to Display", ['All', 'Select Functional Areas'])

    if area_choice == 'Select Functional Areas':
        selected_functional_areas = st.multiselect("Select Functional Areas", options=all_functional_areas)
        if not selected_functional_areas:
            st.error("Please select at least one functional area.")
            return
    else:
        selected_functional_areas = all_functional_areas

    # Date range selection
    min_date = failed_data['Date'].min()
    max_date = failed_data['Date'].max()
    col1, col2 = st.columns(2)
    with col1:
        start_date = st.date_input("Start Date", min_value=min_date, max_value=max_date, value=min_date)
    with col2:
        end_date = st.date_input("End Date", min_value=min_date, max_value=max_date, value=max_date)

    # Filter data based on selections and date range
    filtered_data = failed_data[
        (failed_data['Environment'].isin(selected_environments)) &
        (failed_data['Date'] >= start_date) &
        (failed_data['Date'] <= end_date)
    ]
    if area_choice == 'Select Functional Areas':
        filtered_data = filtered_data[filtered_data['Functional area'].isin(selected_functional_areas)]

    # Group by Date, Environment, and Functional area
    daily_failures = filtered_data.groupby(['Date', 'Environment', 'Functional area']).size().unstack(level=[1, 2], fill_value=0)

    # Ensure we have a continuous date range
    date_range = pd.date_range(start=start_date, end=end_date)
    daily_failures = daily_failures.reindex(date_range, fill_value=0)

    # Y-axis scaling option
    y_axis_scale = st.radio("Y-axis Scaling", ["Fixed", "Dynamic"])

    # Create an interactive plot using Plotly
    fig = go.Figure()

    for env in selected_environments:
        if env in daily_failures.columns.levels[0]:
            env_data = daily_failures[env]
            if area_choice == 'All':
                total_failures = env_data.sum(axis=1)
                fig.add_trace(go.Scatter(x=daily_failures.index, y=total_failures,
                                         mode='lines+markers', name=f'{env} - All Areas'))
            else:
                for area in selected_functional_areas:
                    if area in env_data.columns:
                        fig.add_trace(go.Scatter(x=daily_failures.index, y=env_data[area],
                                                 mode='lines+markers', name=f'{env} - {area}'))

    fig.update_layout(
        title='Failure Rates Comparison Across Environments Over Time',
        xaxis_title='Date',
        yaxis_title='Number of Failures',
        legend_title='Environment - Functional Area',
        hovermode='closest'
    )

    if y_axis_scale == "Fixed":
        fig.update_yaxes(rangemode="tozero")
    else:
        pass

    # Use st.plotly_chart to display the interactive chart
    st.plotly_chart(fig, use_container_width=True)

    # Add interactivity for scenario details
    st.write("Select a date and environment to see detailed scenario information:")

    selected_date = st.date_input("Select a date", min_value=start_date, max_value=end_date, value=start_date)
    selected_env = st.selectbox("Select an environment", options=selected_environments)

    if selected_date and selected_env:
        st.write(f"### Detailed Scenarios for {selected_date} - {selected_env}")

        day_scenarios = filtered_data[(filtered_data['Date'] == selected_date) & 
                                      (filtered_data['Environment'] == selected_env)]

        if not day_scenarios.empty:
            st.dataframe(day_scenarios[['Functional area', 'Scenario name', 'Error message', 'Time spent(m:s)']])
        else:
            st.write("No failing scenarios found for the selected date and environment.")

    # Summary Statistics
    st.write("### Summary Statistics")
    for env in selected_environments:
        env_data = filtered_data[filtered_data['Environment'] == env]
        total_failures = len(env_data)

        if len(daily_failures) > 0:
            avg_daily_failures = total_failures / len(daily_failures)
            if env in daily_failures.columns.levels[0]:
                max_daily_failures = daily_failures[env].sum(axis=1).max()
                min_daily_failures = daily_failures[env].sum(axis=1).min()
            else:
                max_daily_failures = min_daily_failures = 0
        else:
            avg_daily_failures = max_daily_failures = min_daily_failures = 0

        st.write(f"**{env}**:")
        st.write(f"  - Total Failures: {total_failures}")
        st.write(f"  - Average Daily Failures: {avg_daily_failures:.2f}")
        st.write(f"  - Max Daily Failures: {max_daily_failures}")
        st.write(f"  - Min Daily Failures: {min_daily_failures}")

        if area_choice == 'Select Functional Areas':
            st.write("\n  **Failures by Functional Area:**")
            for area in selected_functional_areas:
                area_total = len(env_data[env_data['Functional area'] == area])
                st.write(f"    - {area}: {area_total}")

        st.write("---")

    # Display raw data for verification
    if st.checkbox("Show Raw Data"):
        st.write(daily_failures)