Update app.py

app.py

@@ -2,87 +2,30 @@ import streamlit as st
 import pandas as pd
 import altair as alt
 
-# Load the dataset
+# Loading  the dataset
 url = 'https://github.com/UIUC-iSchool-DataViz/is445_data/raw/main/licenses_fall2022.csv'
 df = pd.read_csv(url)
 
-# Drop unnecessary columns to prevent serialization errors and reduce data size
+# Dropping unnecessary columns to prevent serialization errors and reduce data size
 df.drop(columns=['Title', 'Prefix', 'Suffix', 'BusinessDBA', '_id', 'Delegated Controlled Substance Schedule', 'Case Number'], inplace=True, errors='ignore')
 
-# Convert date columns to datetime format, handling errors
+# Converting date columns to datetime format, handling errors
 date_columns = ['Original Issue Date', 'Effective Date', 'Expiration Date', 'LastModifiedDate']
 for col in date_columns:
     df[col] = pd.to_datetime(df[col], errors='coerce')
 
-# Convert object columns to category for performance improvement
+# Converting object columns to category for performance improvement
 for col in df.select_dtypes(include='object').columns:
     df[col] = df[col].astype('category')
 
-# Drop rows with missing values in essential columns to ensure Arrow compatibility
+# Dropping rows with missing values in essential columns to ensure Arrow compatibility
 df.dropna(subset=['License Type', 'License Status', 'Original Issue Date'], inplace=True)
 
-# Add Year columns for visualizations
+# Adding Year columns for visualizations
 df['Original Issue Year'] = df['Original Issue Date'].dt.year
 
-# # Visualization 1: Bar chart of licenses by Status
-# st.subheader("Licenses by Status")
-# category_counts = df['License Status'].value_counts().reset_index()
-# category_counts.columns = ['License Status', 'Count']
-
-# if not category_counts.empty:
-#     chart1 = alt.Chart(category_counts).mark_bar().encode(
-#         x=alt.X('License Status', sort='-y', title='License Type'),
-#         y=alt.Y('Count', title='Number of Licenses',scale=alt.Scale(domain=(0, 600), nice=False)),
-#         color=alt.Color('License Status', legend=None)
-#     ).properties(
-#         width=600,
-#         height=400,
-#         title="Number of Licenses by Status"
-#     )
-#     st.altair_chart(chart1)
-# else:
-#     st.write("No data available for the 'License Status' plot.")
-
-# # Visualization 1: Pie chart of licenses by Status
-# st.subheader("Licenses by Status")
-# category_counts = df['License Status'].value_counts().reset_index()
-# category_counts.columns = ['License Status', 'Count']
-
-# if not category_counts.empty:
-#     chart1 = alt.Chart(category_counts).mark_arc().encode(
-#         theta=alt.Theta(field="Count", type="quantitative", title="Number of Licenses"),
-#         color=alt.Color(field="License Status", type="nominal", legend=None),
-#         tooltip=['License Status', 'Count']
-#     ).properties(
-#         width=400,
-#         height=400,
-#         title="Licenses by Status"
-#     )
-#     st.altair_chart(chart1)
-# else:
-#     st.write("No data available for the 'License Status' plot.")
-
-# # Visualization 1: Pie chart of licenses by Status with distinct colors and legend
-# st.subheader("Licenses by Status")
-# category_counts = df['License Status'].value_counts().reset_index()
-# category_counts.columns = ['License Status', 'Count']
-
-# if not category_counts.empty:
-#     chart1 = alt.Chart(category_counts).mark_arc().encode(
-#         theta=alt.Theta(field="Count", type="quantitative", title="Number of Licenses"),
-#         color=alt.Color(field="License Status", type="nominal", legend=alt.Legend(title="License Status"), 
-#                         scale=alt.Scale(scheme='pastel1')),  # Distinct color scheme
-#         tooltip=['License Status', 'Count']
-#     ).properties(
-#         width=400,
-#         height=400,
-#         title="Licenses by Status"
-#     )
-#     st.altair_chart(chart1)
-# else:
-#     st.write("No data available for the 'License Status' plot.")
-
-st.subheader("Licenses by Status")
+# # Visualization 1: Bar chart of licenses by Status ( Top 5)
+#st.subheader("Licenses by Status")
 category_counts = df['License Status'].value_counts().reset_index()
 category_counts.columns = ['License Status', 'Count']
 
@@ -95,22 +38,18 @@ if not category_counts_top5.empty:
                 sort='-y'),  # Sorting by count in descending order
         y=alt.Y(field="Count", type="quantitative", title="Number of Licenses"),
         color=alt.Color(field="License Status", type="nominal", legend=alt.Legend(title="License Status"),
-                        scale=alt.Scale(scheme='pastel1')),  # Pastel color scheme
+                        scale=alt.Scale(scheme='pastel1')),  
         tooltip=['License Status', 'Count']
     ).properties(
-        width=600,  # Increased width to accommodate long labels
+        width=500,
         height=400,
         title="Licenses by Status (Top 5)"
-    ).configure_axis(
-        labelAngle=45,  # Rotate labels for better visibility
-        labelPadding=10  # Add padding to avoid clipping
     )
     st.altair_chart(chart1)
 else:
     st.write("No data available for the 'License Status' plot.")
 
 
-
 # Write-up for Visualization 1
 st.write("""
 **Licenses by Status**: This visualization highlights the distribution of licenses across different statuses.