Update app.py

app.py

@@ -3,12 +3,12 @@ import pandas as pd
 import altair as alt
 
 # Title and Introduction
-st.title("Building Inventory Visualization")
+st.title("Building Inventory Analysis")
 st.markdown("""
-This app visualizes building inventory data. We explore two key visualizations:
-1. The distribution of buildings based on their acquisition year.
-2. A comparison of the square footage for buildings across different usage descriptions.
-Below, we also provide explanations for each visualization, including design choices and potential improvements.
+This application provides insights into the building inventory dataset through two visualizations:
+1. **Building Count by County**: Displays the number of buildings in each county.
+2. **Year-wise Construction of Buildings**: Shows the count of buildings constructed each year.
+Each visualization is accompanied by a brief explanation, including design choices and potential improvements.
 """)
 
 # Load Dataset
@@ -20,71 +20,68 @@ def load_data():
 data = load_data()
 
 # Data Preprocessing
-data['Year Acquired'] = pd.to_numeric(data['Year Acquired'], errors='coerce')
-data['Square Footage'] = pd.to_numeric(data['Square Footage'], errors='coerce')
+# Ensure 'Year Constructed' is numeric
+data['Year Constructed'] = pd.to_numeric(data['Year Constructed'], errors='coerce')
 
-# Data Preprocessing for New Visualization
-# Convert 'Year Acquired' and 'Square Footage' to numeric, handling errors
-data['Year Acquired'] = pd.to_numeric(data['Year Acquired'], errors='coerce')
-data['Square Footage'] = pd.to_numeric(data['Square Footage'], errors='coerce')
+# Visualization 1: Building Count by County
+st.header("1. Building Count by County")
+county_count = data['County'].value_counts().reset_index()
+county_count.columns = ['County', 'Building Count']
 
-# Remove rows with missing or invalid data in 'Year Acquired' or 'Square Footage'
-data_clean = data.dropna(subset=['Year Acquired', 'Square Footage'])
-
-# Group by 'Year Acquired' and sum 'Square Footage'
-yearly_square_footage = data_clean.groupby('Year Acquired')['Square Footage'].sum().reset_index()
-
-# Visualization: Total Square Footage Acquired Over Time
-st.header("Total Square Footage Acquired Over Time")
-line_chart = alt.Chart(yearly_square_footage).mark_line(point=True, color='seagreen').encode(
-    alt.X('Year Acquired:Q', title="Year Acquired"),
-    alt.Y('Square Footage:Q', title="Total Square Footage"),
-    tooltip=['Year Acquired', 'Square Footage']
+county_chart = alt.Chart(county_count).mark_bar(color='teal').encode(
+    alt.X('Building Count:Q', title='Number of Buildings'),
+    alt.Y('County:N', sort='-x', title='County'),
+    tooltip=['County', 'Building Count']
 ).properties(
     width=700,
     height=400,
-    title="Total Square Footage Acquired Over Time"
+    title='Number of Buildings per County'
 ).interactive()
 
-st.altair_chart(line_chart, use_container_width=True)
+st.altair_chart(county_chart, use_container_width=True)
 
 st.markdown("""
-### Explanation
-This line chart illustrates the total square footage of buildings acquired each year, highlighting trends in acquisition sizes over time.
+**Explanation**:
+This bar chart illustrates the number of buildings in each county, highlighting areas with higher concentrations of government buildings.
 - **Design Choices**:
-  - A line chart was selected to effectively display changes over time.
-  - Data points are marked to emphasize individual years.
-  - The seagreen color provides a calm and clear visual.
-  - Interactive tooltips offer precise values upon hovering.
+  - A horizontal bar chart is used to accommodate long county names and facilitate easy comparison.
+  - Counties are sorted in descending order based on building count to emphasize those with the most buildings.
+  - The teal color provides a calm and professional appearance.
+  - Interactive tooltips offer precise counts upon hovering.
 - **Potential Improvements**:
-  - Incorporating filters to view trends for specific agencies or locations.
-  - Adding a moving average line to smooth out year-to-year fluctuations.
+  - Incorporate filters to allow users to focus on specific regions or agencies.
+  - Add a map visualization to provide spatial context to the data.
 """)
 
+# Visualization 2: Year-wise Construction of Buildings
+st.header("2. Year-wise Construction of Buildings")
+yearly_construction = data['Year Constructed'].dropna().astype(int).value_counts().reset_index()
+yearly_construction.columns = ['Year Constructed', 'Building Count']
+yearly_construction = yearly_construction.sort_values('Year Constructed')
 
-# Visualization 2: Square Footage by Usage Description
-st.header("Square Footage by Usage Description")
-usage_chart = alt.Chart(data).mark_boxplot().encode(
-    alt.X('Usage Description:N', title="Usage Description"),
-    alt.Y('Square Footage:Q', title="Square Footage"),
-    color='Usage Description:N'
+year_chart = alt.Chart(yearly_construction).mark_line(point=True, color='orange').encode(
+    alt.X('Year Constructed:Q', title='Year Constructed'),
+    alt.Y('Building Count:Q', title='Number of Buildings'),
+    tooltip=['Year Constructed', 'Building Count']
 ).properties(
     width=700,
     height=400,
-    title="Square Footage by Usage Description"
-)
-st.altair_chart(usage_chart, use_container_width=True)
+    title='Number of Buildings Constructed Over Time'
+).interactive()
+
+st.altair_chart(year_chart, use_container_width=True)
 
 st.markdown("""
-### Explanation
-This visualization compares the square footage of buildings across various usage descriptions.
+**Explanation**:
+This line chart displays the number of buildings constructed each year, revealing trends and periods of increased construction activity.
 - **Design Choices**:
-  - A boxplot was selected to highlight the distribution of square footage within each usage category.
-  - Colors were added to distinguish categories visually.
-  - The plot was scaled to ensure data clarity and eliminate crowding.
+  - A line chart effectively shows changes over time and highlights trends.
+  - Data points are marked to emphasize individual years.
+  - The orange color draws attention to the trend line.
+  - Interactive tooltips provide exact counts for each year.
 - **Potential Improvements**:
-  - Adding a tooltip to show specific statistics (e.g., median, quartiles) for each category.
-  - Including an interactive filter to explore categories of interest.
+  - Implement a rolling average to smooth out year-to-year fluctuations.
+  - Allow users to filter the data by building type or agency to explore specific trends.
 """)
 
 # Footer