Update weekly.py

weekly.py

@@ -2,13 +2,14 @@ import pandas as pd
 import streamlit as st
 import matplotlib.pyplot as plt
 import io
-from pre import preprocess_uploaded_file, add_app_description
+from pre import preprocess_uploaded_file
 
 from collections import defaultdict
 
 def generate_weekly_report(uploaded_files):
-    # Create a defaultdict to store the number of failures for each day
-    daily_failures = defaultdict(int)
+
+    # Create a dictionary to store the number of failures for each environment and day
+    environment_daily_failures = {}
 
     for uploaded_file in uploaded_files:
         # Preprocess the uploaded CSV file (you can use your existing preprocessing code)
@@ -20,38 +21,53 @@ def generate_weekly_report(uploaded_files):
         # Calculate the number of failures for this file
         num_failures = len(data[data['Status'] == 'FAILED'])
 
-        # Add the number of failures to the corresponding day in the defaultdict
-        daily_failures[start_date] += num_failures
+        # Get the environment variable from the data frame
+        environment = data['Environment'].iloc[0]
 
-    # Sort the dictionary by date
-    sorted_daily_failures = dict(sorted(daily_failures.items()))
+        # Create a unique key for each environment and day
+        key = (environment, start_date)
 
-    # Extract dates and failures from the sorted dictionary
-    dates = list(sorted_daily_failures.keys())
-    failures = list(sorted_daily_failures.values())
+        # Add the number of failures to the corresponding environment and day in the dictionary
+        if key in environment_daily_failures:
+            environment_daily_failures[key] += num_failures
+        else:
+            environment_daily_failures[key] = num_failures
 
+    # Create a list of unique environments
+    unique_environments = list(set([key[0] for key in environment_daily_failures.keys()]))
 
-     # Format the dates as "DD-Mon" strings (e.g., "07-Feb")
-    formatted_dates = [date.strftime("%d-%b") for date in dates]
+    # Create a larger line chart with separate lines for each environment
+    plt.figure(figsize=(12, 8))
 
-     # Get the environment variable from the first file (assuming it's the same for all files)
-    environment = data['Environment'].iloc[0]
+    for environment in unique_environments:
+        # Filter the data for the current environment
+        environment_data = [(key[1], value) for key, value in environment_daily_failures.items() if key[0] == environment]
 
+        # Sort the data by date
+        environment_data.sort(key=lambda x: x[0])
 
-        # Create a larger line chart to show the trend in failure rates over days
-    plt.figure(figsize=(12, 8))
-    plt.plot(formatted_dates, failures, marker='o', linestyle='-')
-    plt.xlabel('Date', fontsize=14)  # Increase font size for X-axis label
-    plt.ylabel('Number of Failures', fontsize=14)  # Increase font size for Y-axis label
-    plt.title(f'Trends in Failure Rates Over Days for Environment: {environment}', fontsize=16) # Increase title font size
-    plt.xticks(rotation=45, fontsize=12)  # Increase font size and rotation for X-axis ticks
-    plt.yticks(fontsize=12)  # Increase font size for Y-axis ticks
-    plt.grid(False)
+        # Extract dates and failures for the current environment
+        dates = [date.strftime("%d-%b") for date, _ in environment_data]
+        failures = [count for _, count in environment_data]
+
+        # Plot the data as a line
+        plt.plot(dates, failures, marker='o', linestyle='-', label=f'Environment: {environment}')
+
+    plt.xlabel('Date', fontsize=14)
+    plt.ylabel('Number of Failures', fontsize=14)
+    plt.title('Trends in Failure Rates Over Days', fontsize=16)
+    plt.xticks(rotation=45, fontsize=12)
+    plt.yticks(fontsize=12)
+    plt.grid(True)
+    plt.legend(fontsize=12)  # Add a legend to differentiate environments
     
     # Add labels with the number of failures at each data point with larger font
-    for i in range(len(dates)):
-        plt.text(formatted_dates[i], failures[i], str(failures[i]), ha='center', va='bottom', fontsize=12)
+    for environment in unique_environments:
+        environment_data = [(key[1], value) for key, value in environment_daily_failures.items() if key[0] == environment]
+        for i in range(len(environment_data)):
+            plt.text(environment_data[i][0].strftime("%d-%b"), environment_data[i][1], str(environment_data[i][1]), ha='center', va='bottom', fontsize=12)
 
     plt.tight_layout()
-    # Display the bar chart
-    st.pyplot(plt)
+
+    # Display the larger line chart
+    st.pyplot(plt)