Update src/streamlit_app.py

src/streamlit_app.py

@@ -41,6 +41,42 @@ DATA_PATH = Path(__file__).parent / "crime_data.csv"        # /app/src/crime_dat
 def load_data():
     return pd.read_csv(DATA_PATH)
 
+# 2. Load and early‐exit if missing
+    df = load_data()
+    if df.empty:
+        st.stop()
+
+# Data processing.
+    # 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)]
+    
+    # Filter out the year 2025 since it is not the end, so that the trend can't be see.
+    df = df[df['year'] != 2025]
+    
+    # Group the each crime type by year.
+    yearly_crime_counts = (
+        df.groupby(["year", "crm_cd_desc"])
+        .size()
+        .reset_index(name="Count")
+    )
+    
+    # Filter the crime types that have the most top 5 cases.
+    top5_crimes = df["crm_cd_desc"].value_counts().nlargest(5).index
+    filtered_crimes = yearly_crime_counts[yearly_crime_counts["crm_cd_desc"].isin(top5_crimes)]
+    
+    # Identify top 10 crime types
+    top_10_crimes = df['crm_cd_desc'].value_counts().nlargest(10).index.tolist()
+    
+    # Filter the main DataFrame to include only top 10 crimes
+    df_top = df[df['crm_cd_desc'].isin(top_10_crimes)]
+    
+    # Group by crime type and year.
+    stacked_year_df = df_top.groupby(['year', 'crm_cd_desc']).size().reset_index(name='count')
+    
+    # Group by crime type and year.
+    heatmap1_df = df_top.groupby(['crm_cd_desc', 'year']).size().reset_index(name='count')
+
 # ── 0. Page configuration ──
 if page == "Pie Chart":
     st.set_page_config(
@@ -95,10 +131,10 @@ if page == "Pie Chart":
         st.cache_data.clear()  # Clear the cache
         st.toast("Data is refreshed",icon="✅")  # Reload the data
         
-    # 2. Load and early‐exit if missing
-    df = load_data()
-    if df.empty:
-        st.stop()
+    # # 2. Load and early‐exit if missing
+    # df = load_data()
+    # if df.empty:
+    #     st.stop()
         
     # 3. Data preview
     st.header("Data Preview")
@@ -187,36 +223,6 @@ if page == "Pie Chart":
     # Description.
     st.markdown(""" The donut chart shows the share of the ten most frequent crime categories in the selected year. At the center, you can see that Vehicle ­– Stolen is the single largest slice, accounting for roughly 18.7% of all incidents, The remaining five categories each represent between 3%–5% of total incidents—these include miscellaneous crimes, criminal threats, assault with a deadly weapon, burglary, and minor vandalism. By displaying both slice size and percentage labels, the chart makes it easy to compare how dominant property‐related offenses are, versus violent or lesser‐common crimes, in that year’s LAPD data. """)
 
-# Data processing.
-    # 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)]
-    
-    # Filter out the year 2025 since it is not the end, so that the trend can't be see.
-    df = df[df['year'] != 2025]
-    
-    # Group the each crime type by year.
-    yearly_crime_counts = (
-        df.groupby(["year", "crm_cd_desc"])
-        .size()
-        .reset_index(name="Count")
-    )
-    
-    # Filter the crime types that have the most top 5 cases.
-    top5_crimes = df["crm_cd_desc"].value_counts().nlargest(5).index
-    filtered_crimes = yearly_crime_counts[yearly_crime_counts["crm_cd_desc"].isin(top5_crimes)]
-    
-    # Identify top 10 crime types
-    top_10_crimes = df['crm_cd_desc'].value_counts().nlargest(10).index.tolist()
-    
-    # Filter the main DataFrame to include only top 10 crimes
-    df_top = df[df['crm_cd_desc'].isin(top_10_crimes)]
-    
-    # Group by crime type and year.
-    stacked_year_df = df_top.groupby(['year', 'crm_cd_desc']).size().reset_index(name='count')
-    
-    # Group by crime type and year.
-    heatmap1_df = df_top.groupby(['crm_cd_desc', 'year']).size().reset_index(name='count')
 
 # -------------------------------- Plot 2: Heat Map --------------------------------
 elif page == "Heat Map":