Update app.py

app.py

@@ -3,20 +3,36 @@ import pandas as pd
 import matplotlib.pyplot as plt
 
 def process_data(df):
-    # Convert dates and filter relevant period
-    df['Start Date'] = pd.to_datetime(df['Date'].str.split(' to ').str[0], format='%d/%b/%y')
-    df['End Date'] = pd.to_datetime(df['Date'].str.split(' to ').str[1], format='%d/%b/%y')
+    # Clean and transform data
+    df = df[df['Project Category'].notna()]
     
-    # Categorize into weeks
+    # Create Week buckets
+    df['Start Date'] = pd.to_datetime(df['Date'].str.split(' to ').str[0], format='%d/%b/%y')
     df['Week'] = df['Start Date'].apply(lambda x: 1 if x <= pd.Timestamp('2025-01-05') else 2)
     
-    return df
+    # Aggregate utilization data
+    utilization = df.groupby(['Week', 'Project Category'])['Logged'].sum().unstack(fill_value=0)
+    
+    # Calculate percentages
+    total_hours = utilization.sum(axis=1)
+    utilization_percent = utilization.div(total_hours, axis=0) * 100
+    
+    # Select relevant categories
+    utilization_percent = utilization_percent[['Fixed Bid Projects - Billable', 
+                                              'Non-Billable', 
+                                              'Leaves']].rename(columns={
+        'Fixed Bid Projects - Billable': 'Billable',
+        'Non-Billable': 'Non-Billable',
+        'Leaves': 'Leaves'
+    })
+    
+    return utilization_percent
 
 def create_utilization_chart(week_data, week_number):
     fig, ax = plt.subplots()
     wedges, texts, autotexts = ax.pie(
-        week_data[['Billable', 'Non-Billable', 'Leaves']].values[0],
-        labels=['Billable', 'Non-Billable', 'Leaves'],
+        week_data.values,
+        labels=week_data.index,
         autopct='%1.1f%%',
         colors=['#4CAF50', '#FFC107', '#9E9E9E']
     )
@@ -24,18 +40,6 @@ def create_utilization_chart(week_data, week_number):
     ax.set_title(f'Week {week_number} Utilization', pad=20)
     return fig
 
-def create_non_billable_breakdown(df):
-    non_billable = df[df['Project Category'] == 'Non-Billable']
-    breakdown = non_billable.groupby('Epic')['Logged'].sum().reset_index()
-    breakdown = breakdown[breakdown['Epic'] != 'No Epic']
-    
-    fig, ax = plt.subplots()
-    breakdown.plot(kind='bar', x='Epic', y='Logged', ax=ax, legend=False)
-    ax.set_title('Non-Billable Time Breakdown')
-    ax.set_ylabel('Hours')
-    plt.xticks(rotation=45)
-    return fig
-
 def main():
     st.title('QA Team Utilization Dashboard')
     
@@ -43,37 +47,19 @@ def main():
     
     if uploaded_file:
         df = pd.read_excel(uploaded_file, sheet_name='Report')
-        df = process_data(df)
+        utilization_percent = process_data(df)
         
         # Page 4 Visualization
         st.header("Bi-Weekly Utilization Report")
         col1, col2 = st.columns(2)
         
         with col1:
-            week1 = df[df['Week'] == 1]
+            week1 = utilization_percent.loc[1]
             st.pyplot(create_utilization_chart(week1, 1))
         
         with col2:
-            week2 = df[df['Week'] == 2]
+            week2 = utilization_percent.loc[2]
             st.pyplot(create_utilization_chart(week2, 2))
-        
-        # Page 5 Visualization
-        st.header("Non-Billable Time Breakdown")
-        st.pyplot(create_non_billable_breakdown(df))
-        
-        # Page 6 Visualization
-        st.header("Solution Accelerators Progress")
-        accelerators = df[(df['Project Category'] == 'Non-Billable') & 
-                         (df['Epic'] == 'Solution Accelerators')]
-        
-        st.dataframe(
-            accelerators[['Project', 'Logged', 'Key']].rename(columns={
-                'Project': 'Initiative',
-                'Logged': 'Hours',
-                'Key': 'Status'
-            }),
-            hide_index=True
-        )
 
 if __name__ == "__main__":
     main()