Update backup-app.py

backup-app.py

@@ -96,30 +96,310 @@ largest_hospitals = [
     }
 ]
 
-# Convert list of largest hospitals to a Pandas DataFrame
 largest_hospitals_df = pd.DataFrame(largest_hospitals)
 
 # Define chart functions
-def map_chart():
+def stacked_bar_chart():
+    chart = alt.Chart(largest_hospitals_df).mark_bar().encode(
+        y=alt.Y('state:N', sort='-x'),
+        x=alt.X('bed_count:Q', stack='normalize'),
+        color=alt.Color('state:N'),
+        tooltip=['state', 'bed_count']
+    ).properties(
+        width=700,
+        height=500,
+        title='Largest Hospitals by State (Stacked Bar Chart)'
+    )
+    st.altair_chart(chart)
+
+def bump_chart():
+    chart = alt.Chart(largest_hospitals_df).transform_joinaggregate(
+        max_bed_count='max(bed_count)',
+    ).transform_window(
+        rank='rank(max_bed_count)',
+        sort=[alt.SortField('max_bed_count', order='descending')]
+    ).transform_filter(
+        alt.datum.rank <= 10
+    ).mark_line().encode(
+        y=alt.Y('name:N', sort=alt.EncodingSortField('bed_count', order='descending')),
+        x=alt.X('bed_count:Q'),
+        color=alt.Color('state:N'),
+        tooltip=['name', 'bed_count', 'state']
+    ).properties(
+        width=700,
+        height=500,
+        title='Largest Hospitals by Bed Count (Bump Chart)'
+    )
+    st.altair_chart(chart)
+
+def radial_chart():
     chart = alt.Chart(largest_hospitals_df).mark_circle().encode(
-        longitude='lng:Q',
+        x='sum(bed_count)',
+        y='state',
+        size='sum(bed_count)',
+        color='state',
+        tooltip=['state', 'bed_count']
+    ).properties(
+        width=700,
+        height=500,
+        title='Largest Hospitals by State (Radial Chart)'
+    )
+    st.altair_chart(chart)
+
+def trellis_area_sort_chart():
+    chart = alt.Chart(largest_hospitals_df).mark_area().encode(
+        x=alt.X('year:O', title='Year'),
+        y=alt.Y('bed_count:Q', title='Bed Count'),
+        color=alt.Color('state:N', legend=alt.Legend(title='State')),
+        row=alt.Row('name:N', sort='-x', title='Hospital')
+    ).transform_calculate(
+        year='substring(zip_code, 0, 2) + "00"'
+    ).properties(
+        width=700,
+        height=500,
+        title='Largest Hospitals by Year (Trellis Area Sort Chart)'
+    )
+    st.altair_chart(chart)
+
+def wind_vector_map():
+    airports_df = pd.read_csv('https://raw.githubusercontent.com/hvo/datasets/master/nyc_airports.csv')
+    airports = alt.Chart(airports_df).mark_circle(size=100).encode(
+        longitude='lon:Q',
         latitude='lat:Q',
+        tooltip=['name', 'city', 'state']
+    )
+
+    wind_df = pd.read_csv('https://raw.githubusercontent.com/vega/vega/master/docs/data/wind.csv')
+    wind = alt.Chart(wind_df).mark_line().encode(
+        x='u:Q',
+        y='v:Q',
+        color=alt.Color('speed:Q', scale=alt.Scale(scheme='inferno')),
+        size='speed:Q',
+        tooltip=['u', 'v', 'speed']
+    )
+
+    chart = alt.layer(
+        alt.themes.dark(),
+        alt.repeat(row=range(4), column=range(4), layer=0, data=largest_hospitals_df),
+        airports,
+        wind.transform_filter(
+            alt.datum.zip_code == str(largest_hospitals_df.iloc[0]['zip_code'])
+        ).transform_calculate(
+            azimuth='atan2(v, u)',
+            speed='sqrt(u * u + v * v)',
+            dx='cos(azimuth * PI/180) * speed',
+            dy='sin(azimuth * PI/180) * speed'
+        ).mark_arrow().encode(
+            longitude='lng:Q',
+            latitude='lat:Q',
+            angle='azimuth:Q',
+            size=alt.Size('speed:Q', scale=alt.Scale(range=[0, 50])),
+            tooltip=['u', 'v', 'speed', 'azimuth']
+        )
+    ).properties(
+        width=700,
+        height=500,
+        title='Wind Vectors and Airports in New York City'
+    )
+    st.altair_chart(chart)
+
+def table_bubble_plot():
+    chart = alt.Chart(largest_hospitals_df).mark_circle().encode(
+        x=alt.X('bed_count:Q', title='Bed Count'),
+        y=alt.Y('state:N', sort='-x', title='State'),
         size=alt.Size('bed_count:Q', title='Bed Count'),
-        color=alt.Color('state:N', legend=alt.Legend(title='State')),
+        color=alt.Color('state:N'),
         tooltip=['name', 'bed_count', 'city', 'state']
     ).properties(
         width=700,
         height=500,
-        title='Location of Largest Hospitals in the US'
+        title='Largest Hospitals in the US (Table Bubble Plot)'
     )
     st.altair_chart(chart)
 
-# Define chart buttons
-st.sidebar.header('Select a Chart')
-chart_options = ['Map Chart']
-chart_choice = st.sidebar.selectbox('', chart_options)
+def locations_of_us_airports():
+    airports_df = pd.read_csv('https://raw.githubusercontent.com/hvo/datasets/master/nyc_airports.csv')
+    chart = alt.Chart(airports_df).mark_circle(size=100).encode(
+        longitude='lon:Q',
+        latitude='lat:Q',
+        tooltip=['name', 'city', 'state']
+    ).properties(
+        width=700,
+        height=500,
+        title='Locations of US Airports'
+    )
+    st.altair_chart(chart)
 
-# Call chart functions based on user input
-if chart_choice == 'Map Chart':
-    map_chart()
+def connections_among_us_airports_interactive():
+    airports_df = pd.read_csv('https://raw.githubusercontent.com/hvo/datasets/master/nyc_airports.csv')
+    routes_df = pd.read_csv('https://raw.githubusercontent.com/vega/vega/master/docs/data/flights-2k.csv')
+    source = alt.selection_multi(fields=['origin'])
+    chart = alt.Chart(routes_df).mark_geoshape(stroke='white', strokeWidth=0.5).encode(
+        color=alt.condition(source, alt.value('red'), alt.value('lightgray')),
+        tooltip=['origin', 'destination', 'count']
+    ).transform_lookup(
+        lookup='id',
+        from_=alt.LookupData(airports_df, 'id', ['name', 'city', 'state'])
+    ).project(
+        type='albersUsa'
+    ).properties(
+        width=700,
+        height=500,
+        title='Connections Among US Airports (Interactive)'
+    )
+    points = alt.Chart(airports_df).mark_circle(size=100).encode(
+        longitude='lon:Q',
+        latitude='lat:Q',
+        tooltip=['name', 'city', 'state', 'id']
+    ).transform_filter(
+        source
+    )
+    st.altair_chart(chart + points)
+
+def one_dot_per_zipcode():
+    chart = alt.Chart(largest_hospitals_df).mark_circle(size=50).encode(
+        longitude='lng:Q',
+        latitude='lat:Q',
+        color=alt.Color('state:N', scale=alt.Scale(scheme='category10')),
+        tooltip=['name', 'city', 'state', 'bed_count']
+    ).properties(
+        width=700,
+        height=500,
+        title='Largest Hospitals in the US (One Dot per Zip Code)'
+    )
+    st.altair_chart(chart)
+
+def isotype_visualization_with_emoji():
+    chart = alt.Chart(largest_hospitals_df).mark_image(width=50, height=50).encode(
+        x=alt.X('bed_count:Q', axis=None),
+        y=alt.Y('state:N', sort='-x', axis=None),
+        url='https://raw.githubusercontent.com/twitter/twemoji/v13.0.1/assets/svg/1f628.svg',
+        tooltip=['name', 'bed_count']
+    ).properties(
+        width=700,
+        height=500,
+        title='Largest Hospitals in the US (Isotype Visualization with Emoji)'
+    )
+    st.altair_chart(chart)
+
+def binned_heatmap():
+    chart = alt.Chart(largest_hospitals_df).mark_rect().encode(
+        x=alt.X('bed_count:Q', bin=True),
+        y=alt.Y('state:N', sort='-x'),
+        color=alt.Color('count()'),
+        tooltip=['state', 'bed_count']
+    ).properties(
+        width=700,
+        height=500,
+        title='Largest Hospitals by State (Binned Heatmap)'
+    )
+    st.altair_chart(chart)
+
+def facetted_scatterplot_with_marginal_histograms():
+    chart = alt.Chart(largest_hospitals_df).mark_circle(size=50).encode(
+        x=alt.X('bed_count:Q', title='Bed Count'),
+        y=alt.Y('state:N', sort='-x', title='State'),
+        color=alt.Color('state:N'),
+        tooltip=['name', 'bed_count', 'city', 'state']
+    ).properties(
+        width=700,
+        height=500,
+        title='Largest Hospitals in the US (Facetted Scatterplot with Marginal Histograms)'
+    ).facet(
+        column=alt.Column('state:N', sort='-y', title='State'),
+        spacing={'column': 30}
+    )
+    histogram_x = largest_hospitals_df[['bed_count']].reset_index().rename(columns={'bed_count': 'value'})
+    histogram_x['variable'] = 'bed_count'
+    histogram_y = largest_hospitals_df[['state']].reset_index().rename(columns={'state': 'value'})
+    histogram_y['variable'] = 'state'
+    chart_x = alt.Chart(histogram_x).mark_bar().encode(
+        x=alt.X('value:Q', bin=True),
+        y=alt.Y('count()'),
+        color=alt.Color('variable:N', scale=alt.Scale(range=['#675193', '#ca8861'])),
+        tooltip=['value']
+    ).properties(
+        width=700,
+        height=100
+    )
+    chart_y = alt.Chart(histogram_y).mark_bar().encode(
+        y=alt.Y('value:N', sort='-x'),
+        x=alt.X('count()'),
+        color=alt.Color('variable:N', scale=alt.Scale(range=['#675193', '#ca8861'])),
+        tooltip=['value']
+    ).properties(
+        width=100,
+        height=500
+    )
+    st.altair_chart(chart | chart_x, use_container_width=True)
+    st.altair_chart(chart_y, use_container_width=True)
+
+def ridgeline_plot():
+    chart = alt.Chart(largest_hospitals_df).transform_joinaggregate(
+        count='count()',
+        groupby=['state']
+    ).transform_window(
+        rank='rank(count)',
+        sort=[alt.SortField('count', order='descending')]
+    ).transform_filter(
+        alt.datum.rank <= 5
+    ).transform_density(
+        density='bed_count',
+        as_=['bed_count', 'density'],
+        extent=[0, 3000],
+        groupby=['state']
+    ).mark_area().encode(
+        y=alt.Y('state:N', sort='-x'),
+        x=alt.X('bed_count:Q', title='Bed Count'),
+        color=alt.Color('state:N'),
+        row=alt.Row('rank:O', sort='descending', title=None)
+    ).properties(
+        width=700,
+        height=500,
+        title='Largest Hospitals by State (Ridgeline Plot)'
+    )
+    st.altair_chart(chart)
+
+def create_sidebar():
+    chart_functions = {
+        'Stacked Bar Chart with Text Overlay': stacked_bar_chart,
+        'Bump Chart': bump_chart,
+        'Radial Chart': radial_chart,
+        'Trellis Area Sort Chart': trellis_area_sort_chart,
+        'Wind Vector Map': wind_vector_map,
+        'Table Bubble Plot': table_bubble_plot,
+        'Locations of US Airports': locations_of_us_airports,
+        'Connections Among U.S. Airports Interactive': connections_among_us_airports_interactive,
+        'One Dot Per Zipcode': one_dot_per_zipcode,
+        'Isotype Visualization with Emoji': isotype_visualization_with_emoji,
+        'Binned Heatmap': binned_heatmap,
+        'Facetted Scatterplot with Marginal Histograms': facetted_scatterplot_with_marginal_histograms,
+        'Ridgeline Plot': ridgeline_plot
+    }
+    
+    st.sidebar.title('Charts')
+    
+    for chart_name, chart_function in chart_functions.items():
+        chart_button = st.sidebar.button(f'{chart_name} {emoji(chart_name)}')
+        if chart_button:
+            chart_function()
+
+def emoji(chart_name):
+    emojis = {
+        'Stacked Bar Chart with Text Overlay': '📊',
+        'Bump Chart': '📈',
+        'Radial Chart': '🎡',
+        'Trellis Area Sort Chart': '📉',
+        'Wind Vector Map': '🌬️',
+        'Table Bubble Plot': '💬',
+        'Locations of US Airports': '✈️',
+        'Connections Among U.S. Airports Interactive': '🛫',
+        'One Dot Per Zipcode': '📍',
+        'Isotype Visualization with Emoji': '😀',
+        'Binned Heatmap': '🗺️',
+        'Facetted Scatterplot with Marginal Histograms': '🔳',
+        'Ridgeline Plot': '🏔️'
+    }
+    return emojis.get(chart_name, '')
 
+create_sidebar()