Update app.py

app.py

@@ -1,73 +1,80 @@
-# INSTRUCTIONS:
-# 1. Open a "Terminal" by: View --> Terminal OR just the "Terminal" through the hamburger menu
-# 2. run in terminal with: streamlit run app.py
-# 3. click the "Open in Browser" link that pops up OR click on "Ports" and copy the URL
-# 4. Open a Simple Browswer with View --> Command Palette --> Simple Browser: Show
-# 5. use the URL from prior steps as intput into this simple browser
-
-
 import streamlit as st
+import pandas as pd
 import altair as alt
-from vega_datasets import data
- 
-st.title('Streamlit App for IS445: ID16589')
 
-st.text("The URL for this app is: https://huggingface.co/spaces/msa17/is445_demo")
+# Title and Introduction
+st.title("Building Inventory Visualization")
+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.
+""")
 
-source = data.seattle_weather()
+# Load Dataset
+@st.cache
+def load_data():
+    url = "https://raw.githubusercontent.com/UIUC-iSchool-DataViz/is445_data/main/building_inventory.csv"
+    return pd.read_csv(url)
 
-scale = alt.Scale(
-    domain=["sun", "fog", "drizzle", "rain", "snow"],
-    range=["#e7ba52", "#a7a7a7", "#aec7e8", "#1f77b4", "#9467bd"],
-)
-color = alt.Color("weather:N", scale=scale)
+data = load_data()
 
-# We create two selections:
-# - a brush that is active on the top panel
-# - a multi-click that is active on the bottom panel
-brush = alt.selection_interval(encodings=["x"])
-click = alt.selection_point(encodings=["color"])
+# Data Preprocessing
+data['Year Acquired'] = pd.to_numeric(data['Year Acquired'], errors='coerce')
+data['Square Footage'] = pd.to_numeric(data['Square Footage'], errors='coerce')
 
-# Top panel is scatter plot of temperature vs time
-points = (
-    alt.Chart()
-    .mark_point()
-    .encode(
-        alt.X("monthdate(date):T", title="Date (Month Year)"),
-        alt.Y(
-            "temp_max:Q",
-            title="Maximum Daily Temperature (C)",
-            scale=alt.Scale(domain=[-5, 40]),
-        ),
-        color=alt.condition(brush, color, alt.value("lightgray")),
-        size=alt.Size("precipitation:Q", scale=alt.Scale(range=[5, 200])),
-    )
-    .properties(width=550, height=300)
-    .add_params(brush)
-    .transform_filter(click)
+# Visualization 1: Distribution of Buildings by Year Acquired
+st.header("Distribution of Buildings by Year Acquired")
+year_acquired_chart = alt.Chart(data).mark_bar(color='steelblue').encode(
+    alt.X('Year Acquired:Q', bin=alt.Bin(maxbins=20), title="Year Acquired"),
+    alt.Y('count():Q', title="Number of Buildings")
+).properties(
+    width=700,
+    height=400,
+    title="Distribution of Buildings by Year Acquired"
 )
+st.altair_chart(year_acquired_chart, use_container_width=True)
 
-# Bottom panel is a bar chart of weather type
-bars = (
-    alt.Chart()
-    .mark_bar()
-    .encode(
-        x="count()",
-        y="weather:N",
-        color=alt.condition(click, color, alt.value("lightgray")),
-    )
-    .transform_filter(brush)
-    .properties(
-        width=550,
-    )
-    .add_params(click)
-)
+st.markdown("""
+### Explanation
+This visualization highlights the distribution of buildings based on the year they were acquired. 
+- **Design Choices**:
+  - A bar chart was chosen for clarity, with years grouped into bins for better aggregation.
+  - The steel blue color provides a neutral tone and avoids distraction.
+  - Axis labels and titles were carefully chosen for readability.
+- **Potential Improvements**:
+  - If more time was available, I would add an interactive filter to explore specific years.
+  - It would also be useful to compare acquisition trends by agency or location.
+""")
 
-chart = alt.vconcat(points, bars, data=source, title="Seattle Weather - 2009 to 2016")
+# 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'
+).properties(
+    width=700,
+    height=400,
+    title="Square Footage by Usage Description"
+)
+st.altair_chart(usage_chart, use_container_width=True)
 
-tab1, tab2 = st.tabs(["Streamlit theme (default)", "Altair native theme"])
+st.markdown("""
+### Explanation
+This visualization compares the square footage of buildings across various usage descriptions.
+- **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.
+- **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.
+""")
 
-with tab1:
-    st.altair_chart(chart, theme="streamlit", use_container_width=True)
-with tab2:
-    st.altair_chart(chart, theme=None, use_container_width=True)
+# Footer
+st.markdown("""
+---
+**Data Source**: [Building Inventory Dataset](https://raw.githubusercontent.com/UIUC-iSchool-DataViz/is445_data/main/building_inventory.csv)  
+**Author**: Your Name
+""")