Update app.py

app.py

@@ -28,22 +28,35 @@ df['Last Modified Date Year'] = df['LastModifiedDate'].dt.year
 for col in df.select_dtypes(include='object').columns:
     df[col] = df[col].astype('category')
 
+# Debug: Check the data after preprocessing
+st.write("Data after preprocessing:")
+st.write(df.head())  # Check the first few rows
+
 # Visualization 1: Bar chart of licenses by type
 st.subheader("Licenses by Type")
 
+# Group data by License Type
 category_counts = df['License Type'].value_counts().reset_index()
 category_counts.columns = ['License Type', 'Count']
 
-chart1 = alt.Chart(category_counts).mark_bar().encode(
-    x=alt.X('License Type', sort='-y', title='License Type'),
-    y=alt.Y('Count', title='Number of Licenses'),
-    color=alt.Color('License Type', legend=None)
-).properties(
-    width=600,
-    height=400,
-    title="Number of Licenses by Type"
-)
-st.altair_chart(chart1)
+# Debug: Check the grouped data for the first chart
+st.write("Grouped data for licenses by type:")
+st.write(category_counts.head())  # Check if data is available for plotting
+
+# Ensure category_counts is not empty before plotting
+if not category_counts.empty:
+    chart1 = alt.Chart(category_counts).mark_bar().encode(
+        x=alt.X('License Type', sort='-y', title='License Type'),
+        y=alt.Y('Count', title='Number of Licenses'),
+        color=alt.Color('License Type', legend=None)
+    ).properties(
+        width=600,
+        height=400,
+        title="Number of Licenses by Type"
+    )
+    st.altair_chart(chart1)
+else:
+    st.write("No data available for the 'License Type' plot.")
 
 # Write-up for Visualization 1
 st.write("""
@@ -56,24 +69,27 @@ If I had more time, I might add interactivity to allow users to filter by other
 # Visualization 2: Line chart showing licenses issued over time
 st.subheader("Licenses Over Time")
 
-# Ensure there is no missing data for 'Original Issue Year'
-if df['Original Issue Year'].isnull().sum() == 0:
-    time_data = df.groupby('Original Issue Year').size().reset_index(name='License Count')
+# Group data by Original Issue Year
+time_data = df.groupby('Original Issue Year').size().reset_index(name='License Count')
+
+# Debug: Check the grouped data for the second chart
+st.write("Grouped data for licenses over time:")
+st.write(time_data.head())  # Check if data is available for plotting
+
+# Ensure time_data is not empty before plotting
+if not time_data.empty:
+    chart2 = alt.Chart(time_data).mark_line().encode(
+        x=alt.X('Year', title='Year'),
+        y=alt.Y('License Count', title='Number of Licenses'),
+        color=alt.value('blue')
+    ).properties(
+        width=600,
+        height=400,
+        title="Number of Licenses Issued Over Time"
+    )
+    st.altair_chart(chart2)
 else:
-    time_data = df.groupby('Original Issue Year').size().reset_index(name='License Count')
-
-time_data.columns = ['Year', 'License Count']
-
-chart2 = alt.Chart(time_data).mark_line().encode(
-    x=alt.X('Year', title='Year'),
-    y=alt.Y('License Count', title='Number of Licenses'),
-    color=alt.value('blue')
-).properties(
-    width=600,
-    height=400,
-    title="Number of Licenses Issued Over Time"
-)
-st.altair_chart(chart2)
+    st.write("No data available for the 'Licenses Over Time' plot.")
 
 # Write-up for Visualization 2
 st.write("""