Updated ui look for second.py compare

second.py

@@ -1,18 +1,15 @@
-# Import necessary libraries
 import pandas as pd 
 import streamlit as st
-import csv
-import io
-import matplotlib.pyplot as plt
-import numpy as np
+import plotly.graph_objects as go
 from pre import preprocess_uploaded_file
 
+def convert_df(df):
+    return df.to_csv(index=False).encode('utf-8')
 
-# Main function to process 2 uploaded CSV files 
-def double_main(uploaded_file1,uploaded_file2):
-
-  # Check if both files are uploaded
-  if uploaded_file1 is not None and uploaded_file2 is not None:
+def double_main(uploaded_file1, uploaded_file2):
+    if uploaded_file1 is None or uploaded_file2 is None:
+        st.warning("Please upload both CSV files for comparison.")
+        return
 
     # Preprocess the uploaded CSV files
     data_1 = preprocess_uploaded_file(uploaded_file1) 
@@ -20,16 +17,14 @@ def double_main(uploaded_file1,uploaded_file2):
 
     # Determine which file is older and newer
     if data_1['Start datetime'].min() < data_2['Start datetime'].min():
-      older_df = data_1  
-      newer_df = data_2
+        older_df, newer_df = data_1, data_2
     else:
-      older_df = data_2
-      newer_df = data_1
+        older_df, newer_df = data_2, data_1
 
     # Convert time columns to MM:SS format  
     older_df['Time spent'] = pd.to_datetime(older_df['Time spent'], unit='s').dt.strftime('%M:%S')
     newer_df['Time spent'] = pd.to_datetime(newer_df['Time spent'], unit='s').dt.strftime('%M:%S')
-  
+
     # Get start datetime of each file  
     older_datetime = older_df['Start datetime'].min()
     newer_datetime = newer_df['Start datetime'].min()
@@ -41,84 +36,107 @@ def double_main(uploaded_file1,uploaded_file2):
     # Merge dataframes on 'scenario name' 
     merged_df = pd.merge(older_df, newer_df, on=['Functional area', 'Scenario name'], suffixes=('_old', '_new'))
 
-    # Filter scenarios that were failing and are still failing
+    # Filter scenarios
     fail_to_fail_scenarios = merged_df[(merged_df['Status_old'] == 'FAILED') & (merged_df['Status_new'] == 'FAILED')]
-    
-    # Display Consistent Failures section
-    st.markdown("### Consistent Failures(previously failing, now failing)")
-
-    # Get failing scenarios count
-    fail_count = len(fail_to_fail_scenarios)
-    st.write(f"Failing scenarios Count: {fail_count}")
-
-    # Display filtered dataframe 
-    columns_to_display1 = ['Functional area', 'Scenario name', 'Error message_old', 'Error message_new']
-    st.write(fail_to_fail_scenarios[columns_to_display1])
-
-    # Filter scenarios that were passing and now failing
     pass_to_fail_scenarios = merged_df[(merged_df['Status_old'] == 'PASSED') & (merged_df['Status_new'] == 'FAILED')]
+    fail_to_pass_scenarios = merged_df[(merged_df['Status_old'] == 'FAILED') & (merged_df['Status_new'] == 'PASSED')]
 
-    # Display New Failures section 
-    st.markdown("### New Failures(previously passing, now failing)")
-
-    # Get failing scenarios count
+    # Get counts
+    fail_count = len(fail_to_fail_scenarios)
     pass_fail_count = len(pass_to_fail_scenarios)
-    st.write(f"Failing scenarios Count: {pass_fail_count}")
-
-    # Display filtered dataframe
-    columns_to_display2 = ['Functional area', 'Scenario name', 'Error message_new', 'Time spent_old','Time spent_new',] 
-    st.write(pass_to_fail_scenarios[columns_to_display2])
-
-    # Filter scenarios that were failing and now passing
-    fail_to_pass_scenarios = merged_df[(merged_df['Status_old'] == 'FAILED') & (merged_df['Status_new'] == 'PASSED')]
+    pass_count = len(fail_to_pass_scenarios)
 
-    # Display New Passes section
-    st.markdown("### New Passes(previously failing, now passing)")
+    # Display summary chart
+    status_counts = {
+        'Consistent Failures': fail_count,
+        'New Failures': pass_fail_count,
+        'New Passes': pass_count
+    }
+    status_df = pd.DataFrame.from_dict(status_counts, orient='index', columns=['Count'])
     
-    # Get passing scenarios count
-    pass_count = len(fail_to_pass_scenarios)
-    st.write(f"Passing scenarios Count: {pass_count}")
-
-    # Display filtered dataframe
-    columns_to_display3 = ['Functional area', 'Scenario name', 'Error message_old', 'Time spent_old','Time spent_new',]
-    st.write(fail_to_pass_scenarios[columns_to_display3])
-
-
-    # Create a Pandas Excel writer using XlsxWriter as the engine
-    try:
-        # Create a Pandas Excel writer using XlsxWriter as the engine
-        excel_writer = pd.ExcelWriter('comparison_results.xlsx', engine='xlsxwriter')
-        
-        # Write each section to a separate sheet
-        fail_to_fail_scenarios.loc[:, columns_to_display1].to_excel(excel_writer, sheet_name='Consistent Failures', index=False)
-        pass_to_fail_scenarios.loc[:, columns_to_display2].to_excel(excel_writer, sheet_name='New Failures', index=False)
-        fail_to_pass_scenarios.loc[:, columns_to_display3].to_excel(excel_writer, sheet_name='New Passes', index=False)
+    st.subheader("Summary of Scenario Status Changes")
+    
+    # Create a bar chart using Plotly
+    fig = go.Figure(data=[
+        go.Bar(
+            x=status_df.index,
+            y=status_df['Count'],
+            text=status_df['Count'],
+            textposition='outside',
+            textfont=dict(size=14),
+            marker_color=['#1f77b4', '#ff7f0e', '#2ca02c'],  # Custom colors for each bar
+            width=0.6  # Adjust bar width
+        )
+    ])
+    
+    # Customize the layout
+    fig.update_layout(
+        yaxis=dict(
+            title='Count',
+            range=[0, max(status_df['Count']) * 1.1]  # Extend y-axis range by 10% to fit labels
+        ),
+        xaxis_title="Status",
+        hoverlabel=dict(bgcolor="white", font_size=16),
+        margin=dict(l=20, r=20, t=40, b=20),
+        uniformtext_minsize=8,
+        uniformtext_mode='hide'
+    )
+    
+    # Ensure all bars are visible
+    fig.update_traces(marker_line_width=1, marker_line_color="black", selector=dict(type="bar"))
+    
+    # Add hover text
+    fig.update_traces(
+        hovertemplate="<b>%{x}</b><br>Count: %{y}<extra></extra>"
+    )
     
-        # Add a sheet to store information about CSV versions
-        csv_version_sheet = excel_writer.book.add_worksheet('CSV Details')
-        
-        # Write the CSV version information
-        csv_version_sheet.write('A1', 'Older CSV:')
-        csv_version_sheet.write('B1', 'Newer CSV:')
-        csv_version_sheet.write('A2', older_df['Start datetime'].min().strftime('%Y-%m-%d %H:%M:%S'))
-        csv_version_sheet.write('B2', newer_df['Start datetime'].min().strftime('%Y-%m-%d %H:%M:%S'))
-        
-    except Exception as e:
-        print(f"Error encountered: {e}")
-        # Handle or print the error
-        pass
-
-    try:
-        # Save the Excel file
-        excel_writer.close()
-    except Exception as e:
-        print(f"Error encountered during saving: {e}")
-        # Handle or print the error
-        pass
-
-# Create a Download Excel button
-    st.markdown("### Download Excel Report")
-    st.markdown("Click below to download the comparison results in Excel format:")
-    with open('comparison_results.xlsx', 'rb') as excel_file:
-        excel_bytes = excel_file.read()
-    st.download_button(label='Download Excel Report', data=excel_bytes, file_name='comparison_results.xlsx', key='excel-download')
+    # Display the chart
+    st.plotly_chart(fig, use_container_width=True)
+
+    # Use tabs to display data
+    tab1, tab2, tab3 = st.tabs(["Consistent Failures", "New Failures", "New Passes"])
+
+    with tab1:
+        st.write(f"Failing scenarios Count: {fail_count}")
+        columns_to_display1 = ['Functional area', 'Scenario name', 'Error message_old', 'Error message_new']
+        st.dataframe(fail_to_fail_scenarios[columns_to_display1])
+        csv = convert_df(fail_to_fail_scenarios[columns_to_display1])
+        st.download_button("Download Consistent Failures as CSV", data=csv, file_name='consistent_failures.csv', mime='text/csv')
+
+    with tab2:
+        st.write(f"Failing scenarios Count: {pass_fail_count}")
+        columns_to_display2 = ['Functional area', 'Scenario name', 'Error message_new', 'Time spent_old', 'Time spent_new']
+        st.dataframe(pass_to_fail_scenarios[columns_to_display2])
+        csv = convert_df(pass_to_fail_scenarios[columns_to_display2])
+        st.download_button("Download New Failures as CSV", data=csv, file_name='new_failures.csv', mime='text/csv')
+
+    with tab3:
+        st.write(f"Passing scenarios Count: {pass_count}")
+        columns_to_display3 = ['Functional area', 'Scenario name', 'Error message_old', 'Time spent_old', 'Time spent_new']
+        st.dataframe(fail_to_pass_scenarios[columns_to_display3])
+        csv = convert_df(fail_to_pass_scenarios[columns_to_display3])
+        st.download_button("Download New Passes as CSV", data=csv, file_name='new_passes.csv', mime='text/csv')
+
+def main():
+    st.title("CSV Comparison Tool")
+
+    st.markdown("""
+    This tool compares two CSV files and highlights the differences in the scenarios.
+    Please upload the older and newer CSV files below.
+    """)
+
+    col1, col2 = st.columns(2)
+
+    with col1:
+        uploaded_file1 = st.file_uploader("Upload the older CSV file", type='csv', key='uploader1')
+
+    with col2:
+        uploaded_file2 = st.file_uploader("Upload the newer CSV file", type='csv', key='uploader2')
+
+    if uploaded_file1 is not None and uploaded_file2 is not None:
+        with st.spinner('Processing...'):
+            double_main(uploaded_file1, uploaded_file2)
+        st.success('Comparison Complete!')
+
+if __name__ == "__main__":
+    main()