Update src/streamlit_app.py

src/streamlit_app.py

@@ -131,7 +131,7 @@ col3.metric(
     value=f"{top_share:.1%}"
 )
 
-# Plotly donut chart ──
+# -------------------------------- Plot 1: Pie(Donut) Chart --------------------------------
 fig = px.pie(
     top_crimes,
     names="Crime Type",
@@ -163,8 +163,6 @@ st.markdown(""" The donut chart shows the share of the ten most frequent crime c
 
 
 # -------------------------------- Plot 2: Heat Map --------------------------------
-top_crimes = df['crm_cd_desc'].value_counts().nlargest(10).index
-df_top = df[df['crm_cd_desc'].isin(top_crimes)]
 
 # Count the crime type and list out the top 10 crime type that have the most cases.
 top_crimes = df['crm_cd_desc'].value_counts().nlargest(10).index
@@ -203,6 +201,7 @@ This heatmap shows the frequency of the top 10 crimes from 2020 to 2025. The x a
 
 
 # -------------------------------- Plot 3: Line Chart --------------------------------
+# Filter out the year 2025.
 df = df[df['year'] != 2025] # 2025 is not end, so the trend can't be see
 
 # Group the each crime type by year.
@@ -303,10 +302,12 @@ This visualization uses Folium to build an interactive map of crime distribution
 """)
 
 # -------------------------------- Plot 4: Stacked Bar Chart --------------------------------
-# Count the crime type and list out the top 10 crime type that have the most cases.
-top_crimes = df['crm_cd_desc'].value_counts().nlargest(10).index
-df = df[df['year'] != 2025]
-df_top = df[df['crm_cd_desc'].isin(top_crimes)]
+# # Filter out the year 2025.
+# df = df[df['year'] != 2025]
+
+# # Count the crime type and list out the top 10 crime type that have the most cases.
+# top_crimes = df['crm_cd_desc'].value_counts().nlargest(10).index
+# df_top = df[df['crm_cd_desc'].isin(top_crimes)]
 
 # Group by crime type and year.
 stacked_year_df = df_top.groupby(['year', 'crm_cd_desc']).size().reset_index(name='count')
@@ -334,8 +335,8 @@ By observing the plot, we can find out that 2022 had the most crimes, the year h
 """)
 
 # -------------------------------- Plot 5: Bar Chart --------------------------------
-top_crimes = df['crm_cd_desc'].value_counts().nlargest(10).index
-df_top = df[df['crm_cd_desc'].isin(top_crimes)]
+# top_crimes = df['crm_cd_desc'].value_counts().nlargest(10).index
+# df_top = df[df['crm_cd_desc'].isin(top_crimes)]
 
 # Group by crime type and year.
 heatmap1_df = df_top.groupby(['crm_cd_desc', 'year']).size().reset_index(name='count')