Update app.py

app.py

@@ -92,18 +92,18 @@ with col2:
 
 # Visualizations
 if viz_type == "Complaint Types":
-    st.subheader("Interactive Complaint Types Pie Chart")
+    st.subheader("Top 5 Complaint Types Pie Chart")
     
-    # Prepare data
-    complaint_counts = filtered_data['Type of Complaint'].value_counts().reset_index()
-    complaint_counts.columns = ['Complaint Type', 'Count']
+    # Prepare data: Select the top 5 complaint types
+    top_complaints = filtered_data['Type of Complaint'].value_counts().nlargest(5).reset_index()
+    top_complaints.columns = ['Complaint Type', 'Count']
     
     # Create an interactive pie chart with hover tooltips
     fig = px.pie(
-        complaint_counts,
+        top_complaints,
         names='Complaint Type',
         values='Count',
-        title="Distribution of Complaint Types",
+        title="Top 5 Complaint Types Distribution",
         color_discrete_sequence=px.colors.qualitative.Set2,
         labels={"Count": "Number of Complaints", "Complaint Type": "Type of Complaint"},
         hover_data=['Count']
@@ -115,19 +115,37 @@ if viz_type == "Complaint Types":
     
     # Updated write-up
     st.write("""
-    **Write-up:** This visualization displays the distribution of complaint types using an interactive pie chart. 
-    Hovering over each segment reveals the complaint type, the number of complaints, and its percentage of the total. 
-    The vibrant colors highlight differences between complaint categories, providing an accessible and informative view of the data.
+    **What this visualization shows:**  
+    This interactive pie chart displays the distribution of the top 5 complaint types.  
+    **Why it's interesting:**  
+    Hovering over each segment reveals detailed information, including the complaint type, the number of complaints, and its percentage of the total. By focusing on the top 5 complaint categories, this visualization helps identify the most commonly reported issues, enabling better prioritization of resources and targeted interventions.  
+    **Color Scheme:**  
+    Each complaint type is represented by a unique color, making it easy to differentiate between categories and interpret the data at a glance.  
     """)
 
 
 elif viz_type == "Geographic Distribution":
     st.subheader("Clustered Heatmap of Complaints")
+    
+    # Generate the heatmap
     map_center = [filtered_data['Latitude'].mean(), filtered_data['Longitude'].mean()]
     m = folium.Map(location=map_center, zoom_start=12)
     heat_data = filtered_data[['Latitude', 'Longitude']].dropna().values.tolist()
     HeatMap(heat_data).add_to(m)
+    
+    # Display the map
     st_folium(m, width=700, height=500)
+    
+    # Write-up
+    st.write("""
+    **What this visualization shows:**  
+    This clustered heatmap visualizes complaint locations across the city.  
+    **Why it's interesting:**  
+    It highlights geographic areas with higher complaint densities, known as hotspots. These areas can be targeted for intervention and resource allocation.  
+    **Color Scheme:**  
+    The heatmap uses gradient colors, where warmer tones (red/orange) represent higher densities of complaints, providing a clear visual cue for problem areas.  
+    """)
+
 
 elif viz_type == "Resolution Status":
     st.subheader("Interactive Complaint Resolution Status")
@@ -135,10 +153,24 @@ elif viz_type == "Resolution Status":
     resolution_counts.columns = ['Disposition', 'Count']
     chart = alt.Chart(resolution_counts).mark_arc(innerRadius=50).encode(
         theta=alt.Theta(field="Count", type="quantitative"),
-        color=alt.Color(field="Disposition", type="nominal")
+        color=alt.Color(field="Disposition", type="nominal"),
+        tooltip=[
+            alt.Tooltip("Disposition", title="Resolution"),
+            alt.Tooltip("Count", title="Count")
+        ]
     )
     st.altair_chart(chart, use_container_width=True)
 
+    st.write("""
+    **What this visualization shows:**  
+    This interactive donut chart displays the distribution of complaint resolutions, such as resolved, unresolved, or escalated cases.  
+    **Why it's interesting:**  
+    By analyzing the resolution status, we can assess the effectiveness of complaint handling and identify areas for improvement.  
+    **Color Scheme:**  
+    Each resolution status is represented by a distinct color, making it easy to differentiate between categories and quickly interpret the data.  
+    """)
+
+
 elif viz_type == "Submission Methods":
     st.subheader("Submission Methods Analysis")
     submission_counts = filtered_data['Method Submitted'].value_counts()
@@ -146,6 +178,16 @@ elif viz_type == "Submission Methods":
     sns.barplot(x=submission_counts.values, y=submission_counts.index, palette='inferno', ax=ax)
     st.pyplot(fig)
 
+    st.write("""
+    **What this visualization shows:**  
+    This bar chart shows the number of complaints submitted via different methods, such as email, phone, online form, etc.  
+    **Why it's interesting:**  
+    By analyzing submission methods, we can understand how users prefer to submit complaints and focus on improving the most used channels.  
+    **Color Scheme:**  
+    The 'inferno' color palette is used to highlight differences in submission frequency, with darker shades indicating higher submission counts.  
+    """)
+
+
 elif viz_type == "Complaints by Disposition":
     st.subheader("Complaints by Disposition")
     disposition_counts = filtered_data['Disposition'].value_counts()
@@ -153,6 +195,16 @@ elif viz_type == "Complaints by Disposition":
     sns.barplot(x=disposition_counts.values, y=disposition_counts.index, palette='viridis', ax=ax)
     st.pyplot(fig)
 
+    st.write("""
+    **What this visualization shows:**  
+    This bar chart displays the distribution of complaints by their resolution status (disposition), such as 'Resolved', 'Unresolved', etc.  
+    **Why it's interesting:**  
+    By examining the disposition of complaints, organizations can assess how effectively issues are being addressed and identify any areas needing improvement.  
+    **Color Scheme:**  
+    The 'viridis' color palette highlights differences in complaint resolution status, with lighter shades indicating a higher frequency of resolved complaints.  
+    """)
+
+
 elif viz_type == "Monthly Trends by Complaint Type":
     st.subheader("Monthly Trends Grouped by Complaint Types")
     monthly_trends = filtered_data.groupby(['Month Reported', 'Type of Complaint']).size().reset_index(name='Count')
@@ -163,6 +215,18 @@ elif viz_type == "Monthly Trends by Complaint Type":
     )
     st.altair_chart(chart, use_container_width=True)
 
+    st.write("""
+    **What this visualization shows:**  
+    This line chart visualizes the monthly trends in complaint counts, grouped by complaint type. It allows tracking changes in complaint frequencies over time and identifying patterns or spikes in specific categories.
+    
+    **Why it's interesting:**  
+    By visualizing these trends, you can identify whether certain complaint types are seasonal or are influenced by specific events. This information helps prioritize resources and refine strategies for complaint management.
+    
+    **Color Scheme:**  
+    Different complaint types are represented by distinct colors, enabling easy comparison of trends across categories.
+    """)
+
+
 elif viz_type == "Top Complaint Types":
     st.subheader("Top Complaint Types")
     complaint_counts = filtered_data['Type of Complaint'].value_counts().head(10)
@@ -170,14 +234,34 @@ elif viz_type == "Top Complaint Types":
     sns.barplot(x=complaint_counts.values, y=complaint_counts.index, palette="inferno", ax=ax)
     st.pyplot(fig)
 
+    st.write("""
+    **What this visualization shows:**  
+    This bar chart displays the top 10 most common complaint types based on the number of occurrences. It provides a clear view of the most frequently reported issues.
+
+    **Why it's interesting:**  
+    By focusing on the top complaint types, organizations can identify and prioritize the issues that impact the majority of their users or customers. This can lead to targeted improvements in service or support efforts.
+
+    **Color Scheme:**  
+    The 'inferno' palette is used to emphasize the frequency of each complaint type, with darker shades representing higher frequencies.
+    """)
+
 elif viz_type == "Complaints Over Time":
     st.subheader("Complaints Over Time")
     complaints_over_time = filtered_data.groupby(filtered_data['Date Reported'].dt.date).size()
     fig, ax = plt.subplots()
-    ax.plot(complaints_over_time.index, complaints_over_time.values, marker='o')
+    
+    # Apply color scheme to the plot
+    ax.plot(complaints_over_time.index, complaints_over_time.values, marker='o', color='tab:blue')
+    
     ax.set_title("Complaints Over Time")
     st.pyplot(fig)
 
+    st.write("""
+    **Write-up:** This visualization displays the trend of complaints over time using a line chart. 
+    It shows the number of complaints reported for each day, making it easy to spot peaks or declines in complaints. 
+    The use of a blue color scheme highlights the flow and continuity of the data, providing a clear view of the patterns over time.
+    """)
+
 elif viz_type == "Complaints by Housing Block and Type":
     st.subheader("Complaints by Housing Block and Type")
     complaint_pivot = filtered_data.pivot_table(
@@ -189,6 +273,16 @@ elif viz_type == "Complaints by Housing Block and Type":
     )
     fig = complaint_pivot.plot(kind='bar', stacked=True, colormap='inferno', figsize=(10, 6)).get_figure()
     st.pyplot(fig)
+    st.write("""
+    **What this visualization shows:**  
+    This line chart shows the trend of complaints over time, displaying the number of complaints reported for each day. It helps identify patterns, peaks, and trends in the complaints data.
+
+    **Why it's interesting:**  
+    By visualizing complaints over time, organizations can track the effectiveness of their responses and interventions. It also helps identify recurring spikes or declines in complaints, which could be indicative of specific events or issues.
+
+    **Insight Potential:**  
+    This chart can be used to correlate with external factors, such as changes in policies, incidents, or other events that might lead to a sudden increase or decrease in complaints. The insights can inform better decision-making and improve the organization's complaint management strategy.
+    """)
 
 # Footer
 st.markdown("---")