WIP. App uses new data; need to work on prompt

app/app.py

@@ -35,14 +35,14 @@ current_tables = con.list_tables()
 if "mydata" not in set(current_tables):
     tbl = con.read_parquet(ca_parquet)
     con.create_table("mydata", tbl)
+    
 ca = con.table("mydata")
 
-
+    
 for key in [
     'richness', 'rsr', 'irrecoverable_carbon', 'manageable_carbon',
     'fire', 'rxburn', 'disadvantaged_communities',
-    'svi'
-]:
+    'svi']:
     if key not in st.session_state:
         st.session_state[key] = False
     
@@ -161,12 +161,13 @@ llm = ChatOpenAI(model="gpt-4", temperature=0)
 
 managers = ca.sql("SELECT DISTINCT manager FROM mydata;").execute()
 names = ca.sql("SELECT name FROM mydata GROUP BY name HAVING SUM(acres) >10000;").execute()
+ecoregions = ca.sql("SELECT DISTINCT ecoregion FROM mydata;").execute()
 
 from langchain_core.prompts import ChatPromptTemplate
 prompt = ChatPromptTemplate.from_messages([
     ("system", template),
     ("human", "{input}")
-]).partial(dialect="duckdb", table_info = ca.schema(), managers = managers, names = names)
+]).partial(dialect="duckdb", table_info = ca.schema(), managers = managers, names = names, ecoregions = ecoregions)
 
 structured_llm = llm.with_structured_output(SQLResponse)
 few_shot_structured_llm = prompt | structured_llm
@@ -328,21 +329,21 @@ with st.sidebar:
            m.add_cog_layer(url_man_carbon, palette="purples", name="Manageable Carbon", opacity = a_climate, fit_bounds=False)
             
 
-    # Justice40 Section 
-    with st.expander("🌱 Climate & Economic Justice"):
-        a_justice = st.slider("transparency", 0.0, 1.0, 0.07, key = "social justice")
-        show_justice40 = st.toggle("Disadvantaged Communities (Justice40)", key = "disadvantaged_communities", value=chatbot_toggles['disadvantaged_communities'])
-   
-        if show_justice40:
-            m.add_pmtiles(url_justice40, style=justice40_style, name="Justice40", opacity=a_justice, tooltip=False, fit_bounds = False)
+    # # Justice40 Section 
+    # with st.expander("🌱 Climate & Economic Justice"):
+    #     a_justice = st.slider("transparency", 0.0, 1.0, 0.07, key = "social justice")
 
-    # SVI Section 
-    with st.expander("🏡 Social Vulnerability"):
-        a_svi = st.slider("transparency", 0.0, 1.0, 0.1, key = "SVI")
+    # People Section 
+    with st.expander("🏡 People"):
+        a_people = st.slider("transparency", 0.0, 1.0, 0.1, key = "SVI")
+        show_justice40 = st.toggle("Disadvantaged Communities (Justice40)", key = "disadvantaged_communities", value=chatbot_toggles['disadvantaged_communities'])
         show_sv = st.toggle("Social Vulnerability Index (SVI)", key = "svi", value=chatbot_toggles['svi'])
-
+        
+        if show_justice40:
+            m.add_pmtiles(url_justice40, style=justice40_style, name="Justice40", opacity=a_people, tooltip=False, fit_bounds = False)
+            
         if show_sv:
-            m.add_pmtiles(url_svi, style = get_sv_style("RPL_THEMES"), opacity=a_svi, tooltip=False, fit_bounds = False)
+            m.add_pmtiles(url_svi, style = svi_style, opacity=a_people, tooltip=False, fit_bounds = False)
         
     # Fire Section
     with st.expander("🔥 Fire"):
@@ -353,10 +354,10 @@ with st.sidebar:
 
 
         if show_fire_10:
-            m.add_pmtiles(url_calfire, style=fire_style("layer2"), name="CALFIRE Fire Polygons (2013-2023)", opacity=a_fire, tooltip=False, fit_bounds = True)
+            m.add_pmtiles(url_calfire, style=fire_style, name="CALFIRE Fire Polygons (2013-2023)", opacity=a_fire, tooltip=False, fit_bounds = False)
 
         if show_rx_10:
-            m.add_pmtiles(url_rxburn, style=rx_style("layer2"), name="CAL FIRE Prescribed Burns (2013-2023)", opacity=a_fire, tooltip=False, fit_bounds = True)
+            m.add_pmtiles(url_rxburn, style=rx_style, name="CAL FIRE Prescribed Burns (2013-2023)", opacity=a_fire, tooltip=False, fit_bounds = False)
                     
 
     st.divider()
@@ -388,17 +389,21 @@ with st.sidebar:
 if 'out' not in locals():
     style = get_pmtiles_style(style_options[color_choice], alpha, filter_cols, filter_vals)
     legend_d = {cat: color for cat, color in style_options[color_choice]['stops']}
+
+    # shorten legend for ecoregions 
+    if color_choice == "Ecoregion":
+        legend_d = {key.replace("California", "CA"): value for key, value in legend_d.items()} 
+        
     m.add_legend(legend_dict = legend_d, position = 'bottom-left')
     m.add_pmtiles(ca_pmtiles, style=style, name="CA", opacity=alpha, tooltip=True, fit_bounds = True)
 
 
-
 column = select_column[color_choice]
 
 select_colors = {
     "Year": year["stops"],
     "GAP Code": gap["stops"],
-    "Status": status["stops"],
+    "30x30 Status": status["stops"],
     "Ecoregion": ecoregion["stops"],
     "Manager Type": manager["stops"],
     "Easement": easement["stops"],
@@ -423,14 +428,14 @@ total_percent = df.percent_protected.sum().round(2)
 
 
 # charts displayed based on color_by variable
-richness_chart = bar_chart(df, column, 'mean_richness', "Species Richness")
-rsr_chart = bar_chart(df, column, 'mean_rsr', "Range-Size Rarity")
-irr_carbon_chart = bar_chart(df, column, 'mean_irrecoverable_carbon', "Irrecoverable Carbon")
-man_carbon_chart = bar_chart(df, column, 'mean_manageable_carbon', "Manageable Carbon")
+richness_chart = bar_chart(df, column, 'mean_richness', "Species Richness (2022)")
+rsr_chart = bar_chart(df, column, 'mean_rsr', "Range-Size Rarity (2022)")
+irr_carbon_chart = bar_chart(df, column, 'mean_irrecoverable_carbon', "Irrecoverable Carbon (2018)")
+man_carbon_chart = bar_chart(df, column, 'mean_manageable_carbon', "Manageable Carbon (2018)")
 fire_10_chart = bar_chart(df, column, 'mean_fire', "Fires (2013-2023)")
 rx_10_chart = bar_chart(df, column, 'mean_rxburn',"Prescribed Burns (2013-2023)")
-justice40_chart = bar_chart(df, column, 'mean_disadvantaged_communities', "Disadvantaged Communities (Justice40) ")
-svi_chart = bar_chart(df, column, 'mean_svi', "Social Vulnerability Index (2023)")
+justice40_chart = bar_chart(df, column, 'mean_disadvantaged', "Disadvantaged Communities (2020)")
+svi_chart = bar_chart(df, column, 'mean_svi', "Social Vulnerability Index (2022)")
 
 
 main = st.container()
@@ -441,7 +446,7 @@ with main:
     with map_col:
         m.to_streamlit(height=650)
         if 'out' not in locals():
-            st.dataframe(df_tab, use_container_width = True)
+            st.dataframe(df_tab, use_container_width = True)  
         else:
             st.dataframe(out, use_container_width = True)
 
@@ -463,18 +468,18 @@ with main:
             if show_manageable_carbon:
                 st.altair_chart(man_carbon_chart, use_container_width=True)
 
-            if show_fire_10:
-                st.altair_chart(fire_10_chart, use_container_width=True)
-                
-            if show_rx_10:
-                st.altair_chart(rx_10_chart, use_container_width=True)
-
             if show_justice40:
                 st.altair_chart(justice40_chart, use_container_width=True)
                 
             if show_sv:
                 st.altair_chart(svi_chart, use_container_width=True)
+
+            if show_fire_10:
+                st.altair_chart(fire_10_chart, use_container_width=True)
                 
+            if show_rx_10:
+                st.altair_chart(rx_10_chart, use_container_width=True)
+
  
 
 

app/system_prompt.txt

@@ -11,10 +11,12 @@ Ensure the response contains only this JSON object, with no additional text, for
 # Important Details
  
     - For map-related queries (e.g., "show me"), ALWAYS include "id," "geom", "name," and "acres" in the results, PLUS any other columns referenced in the query (e.g., in conditions, calculations, or subqueries). This output structure is MANDATORY for all map-related queries.
+    - Unless the user species to include land without a GAP code, do NOT include land where "status" is "non-conserved" in your SQL queries. 
     - ONLY use LIMIT in your SQL queries if the user specifies a quantity (e.g., 'show me 5'). Otherwise, return all matching data without a limit.
     - Wrap each column name in double quotes (") to denote them as delimited identifiers.
     - Pay attention to use only the column names you can see in the tables below. DO NOT query for columns that do not exist. 
-    If the query mentions "biodiversity" without specifying a column, default to using "richness" (species richness). Explain this choice and that they can also request "rsr" (range-size rarity). 
+    - ONLY WRITE SQL QUERIES BASED ON THE SCHEMA AND METADATA PROVIDED. DO NOT QUERY RECORDS THAT DON'T EXIST. 
+    - If the query mentions "biodiversity" without specifying a column, default to using "richness" (species richness). Explain this choice and that they can also request "rsr" (range-size rarity). 
     - If the query mentions carbon without specifying a column, use "irrecoverable carbon". Explain this choice and list the other carbon-related columns they can ask for, along with their definitions. 
     - If the query asks about the manager, use the "manager" column. You MUST ALWAYS explain the difference between manager and manager_type in your response. Clarify that "manager" refers to the name of the managing entity (e.g., an agency), while "manager_type" specifies the type of jurisdiction (e.g., Federal, State, Non Profit). Also, let the user know they can include "manager_type" in their query if they want to refine their results.
     - If the user's query is unclear, DO NOT make assumptions. Instead, ask for clarification and provide examples of similar queries you can handle, using the columns or data available. You MUST ONLY deliver accurate results.
@@ -22,6 +24,38 @@ Ensure the response contains only this JSON object, with no additional text, for
     - Users may not be familiar with this data, so your explanation should be short, clear, and easily understandable. You MUST state which column(s) you used to gather their query, along with definition(s) of the column(s). Do NOT explain SQL commands. 
     - If the prompt is unrelated to the California dataset, provide examples of relevant queries that you can answer.
 
+
+# Detailed Explanation of the Columns in the California Dataset 
+- "established": The time range which the land was acquired, either "2024" or "pre-2024". 
+- "gap_code": The GAP code; corresponds to the level of protection the area has. There are 4 gap codes and are defined as the following. 
+    GAP 1: Permanently protected to maintain a natural state, allowing natural disturbances or mimicking them through management.
+    GAP 2: Permanently protected but may allow some uses or management practices that degrade natural communities or suppress natural disturbances.
+    GAP 3: Permanently protected from major land cover conversion but allows some extractive uses (e.g., logging, mining) and protects federally listed species.
+    GAP 4: No protection mandates; land may be converted to unnatural habitat types or its management intent is unknown.
+- "name": The name of a protected area. The user may use a shortened name and/or not capitalize it. For example, "redwoods" may refer to "Redwood National Park", or "klamath" refers to "Klamath National Forest". Another example, "san diego wildlife refuge" could refer to multiple areas, so you would use "WHERE LOWER("name") LIKE '%san diego%' AND LOWER("name") LIKE '%wildlife%' AND LOWER("name") LIKE '%refuge%';" in your SQL query, to ensure that it is case-insensitive and matches any record that includes our phrases, because we don't want to overlook a match.  If the name isn't capitalized, you MUST ensure the search is case-insensitive by converting "name" to lowercase. 
+The names of the largest parks are {names}.
+- "access_type": Level of access to the land: "Unknown Access","Restricted Access","No Public Access" and "Open Access". 
+- "manager": The name of land manager for the area. Also referred to as the agency name. These are the manager names: {managers}. Users might use acronyms or could omit "United States" in the agency name, make sure to use the name used in the table. Some examples: "BLM" or "Bureau of Land Management" refers to the "United States Bureau of Land Management" or "CDFW" is "California Department of Fish and Wildlife". Similar to the "name" field, you can search for managers using "LIKE" in the SQL query. 
+- "manager_type": The jurisdiction of the land manager: "Federal","State","Non Profit","Special District","Unknown","County","City","Joint","Tribal","Private","HOA". If the user says "non-profit", do not use a hyphen in your query. 
+- "easement": Boolean value; whether or not the land is an easement. 
+- "acres": Land acreage; measures the size of the area. 
+- "id": unique id for each area. This is necessary for displaying queried results on a map. 
+- "type": Physical type of area, either "Land" or "Water". 
+- "richness": Species richness; higher values indicate better biodiversity.
+- "rsr": Range-size rarity; higher values indicate better rarity metrics.
+- "svi": Social Vulnerability Index based on 4 themes: socioeconomic status, household characteristics, racial & ethnic minority status, and housing & transportation. Higher values indicate greater vulnerability.
+- "disadvantaged_communities": Justice40-defined disadvantaged communities overburdened by climate, energy, health, housing, pollution, transportation, water, and workforce factors. Higher values indicate more disadvantage. Range is between 0 and 1. 
+- "fire": The percentage of the area burned by fires from (2013-2022). Areas can burn more than once, thus the percentage can be above 1
+- "rxburn": The percentage of the area affected by prescribed burns from (2013-2022). Areas can be burned more than once. 
+- "status": The conservation status. GAP 1 and 2 count towards 30x30, thus are "30x30-conserved", GAP 3 and 4 land are grouped into "other-conserved", and areas outside of GAP are designed "non-conserved". By default, do NOT include 'non-conserved' areas in calculations, unless the users specifically requests it. 
+- "ecoregion": Ecoregions are areas with similar ecosystems and environmental resources. The ONLY ecoregions you have access to are: {ecoregions}. Users may shorten the ecoregions. For example, "Southern CA Mountains" would refer to "Southern California Mountains and Valleys". 
+
+
+
+Only use the following table:
+{table_info}.
+
+
 # Example Questions and How to Approach Them 
 
 ## Example:
@@ -36,9 +70,9 @@ example_assistant: {{"sql_query":
 ## Example: 
 example_user: "Which gap code has been impacted the most by fire?"
 example_assistant: {{"sql_query":  
-    SELECT "reGAP", SUM("fire") AS temp
+    SELECT "gap_code", SUM("fire") AS temp
     FROM mydata
-    GROUP BY "reGAP"
+    GROUP BY "gap_code"
     ORDER BY temp ASC
     LIMIT 1;
 "explanation":"I used the `fire` column, which shows the percentage of each area burned over the past 10 years (2013–2022), summing it for each GAP code to find the one with the highest total fire impact."
@@ -49,12 +83,13 @@ example_user: "Who manages the land with the worst biodiversity and highest SVI?
 example_assistant: {{"sql_query":    
 SELECT manager,richness, svi
     FROM mydata
+    WHERE "status" != 'non-conserved'
     GROUP BY "manager"
     ORDER BY richness ASC, svi DESC
     LIMIT 1;
 "explanation": "I identified the land manager with the worst biodiversity and highest Social Vulnerability Index (SVI) by analyzing the columns: `richness`, which measures species richness, and `svi`, which represents social vulnerability based on factors like socioeconomic status, household characteristics, racial & ethnic minority status, and housing & transportation.
 
-I sorted the data by richness in ascending order (worst biodiversity first) and svi in descending order (highest vulnerability). The result provides the manager, which is the name of the entity managing the land. Note that the manager column refers to the specific agency or organization responsible for managing the land, while`manager_type` categorizes the type of jurisdiction (e.g., Federal, State, Non Profit)."
+I sorted the data by richness in ascending order (worst biodiversity first) and svi in descending order (highest vulnerability). The result provides the manager, which is the name of the entity managing the land. Note that the manager column refers to the specific agency or organization responsible for managing the land, while `manager_type` categorizes the type of jurisdiction (e.g., Federal, State, Non Profit)."
 }}
 
 
@@ -63,6 +98,7 @@ example_user: "Show me the biggest protected area"
 example_assistant: {{"sql_query":       
     SELECT "id", "geom", "name", "acres", "manager", "manager_type", "acres"
     FROM mydata
+    WHERE "status" != 'non-conserved'
     ORDER BY "acres" DESC
     LIMIT 1;
 "explanation": "I identified the biggest protected area by sorting the data in descending order based on the `acres` column, which represents the size of each area." 
@@ -72,6 +108,7 @@ example_user: "Show me the 50 most biodiverse areas found in disadvantaged commu
 example_assistant: {{"sql_query":   
     SELECT "id", "geom", "name", "acres", "richness", "disadvantaged_communities" FROM mydata 
     WHERE "disadvantaged_communities" > 0
+    WHERE "status" != 'non-conserved'
     ORDER BY "richness" DESC
     LIMIT 50;
 "explanation": "I used the `richness` column to measure biodiversity and the `disadvantaged_communities` column to identify areas located in disadvantaged communities. The `disadvantaged_communities` value is derived from the Justice40 initiative, which identifies communities burdened by systemic inequities and vulnerabilities across multiple domains, including climate resilience, energy access, health disparities, housing affordability, pollution exposure, transportation infrastructure, water quality, and workforce opportunities.
@@ -87,9 +124,9 @@ sql_query:
         SELECT PERCENTILE_CONT(0.95) WITHIN GROUP (ORDER BY "richness") AS temp
         FROM mydata
     )
-    SELECT "id", "geom", "name", "acres","richness", "reGAP"
+    SELECT "id", "geom", "name", "acres", "richness", "gap_code"
     FROM mydata
-    WHERE "reGAP" = 3
+    WHERE "gap_code" = 3
         AND "fire" >= 0.5
         and "manager_type" = "Federal"
         AND "richness" > (SELECT temp FROM temp_tab);
@@ -102,34 +139,17 @@ sql_query:
     FROM mydata
     WHERE "easement" = "True";
 
-
-# Detailed Explanation of the Columns in the California Dataset 
-- "established": The time range which the land was acquired, either "2024" or "pre-2024". 
-- "reGAP": The GAP code; corresponds to the level of protection the area has. There are 4 gap codes and are defined as the following. 
-    GAP 1: Permanently protected to maintain a natural state, allowing natural disturbances or mimicking them through management.
-    GAP 2: Permanently protected but may allow some uses or management practices that degrade natural communities or suppress natural disturbances.
-    GAP 3: Permanently protected from major land cover conversion but allows some extractive uses (e.g., logging, mining) and protects federally listed species.
-    GAP 4: No protection mandates; land may be converted to unnatural habitat types or its management intent is unknown.
-- "name": The name of a protected area. The user may use a shortened name and/or not capitalize it. For example, "redwoods" may refer to "Redwood National Park", or "klamath" refers to "Klamath National Forest". Another example, "san diego wildlife refuge" could refer to multiple areas, so you would use "WHERE LOWER("name") LIKE '%san diego%' AND LOWER("name") LIKE '%wildlife%' AND LOWER("name") LIKE '%refuge%';" in your SQL query, to ensure that it is case-insensitive and matches any record that includes our phrases, because we don't want to overlook a match.  If the name isn't capitalized, you MUST ensure the search is case-insensitive by converting "name" to lowercase. 
-The names of the largest parks are {names}.
-- "access_type": Level of access to the land: "Unknown Access","Restricted Access","No Public Access" and "Open Access". 
-- "manager": The name of land manager for the area. Also referred to as the agency name. These are the manager names: {managers}. Users might use acronyms or could omit "United States" in the agency name, make sure to use the name used in the table. Some examples: "BLM" or "Bureau of Land Management" refers to the "United States Bureau of Land Management" or "CDFW" is "California Department of Fish and Wildlife". Similar to the "name" field, you can search for managers using "LIKE" in the SQL query. 
-- "manager_type": The jurisdiction of the land manager: "Federal","State","Non Profit","Special District","Unknown","County","City","Joint","Tribal","Private","HOA". If the user says "non-profit", do not use a hyphen in your query. 
-- "easement": Boolean value; whether or not the land is an easement. 
-- "acres": Land acreage; measures the size of the area. 
-- "id": unique id for each area. This is necessary for displaying queried results on a map. 
-- "type": Physical type of area, either "Land" or "Water". 
-- "richness": Species richness; higher values indicate better biodiversity.
-- "rsr": Range-size rarity; higher values indicate better rarity metrics.
-- "svi": Social Vulnerability Index based on 4 themes: 1) socioeconomic status (e.g. poverty, unemployment, housing cost burden, education, and health insurance), 2) household characteristics (e.g. age, disability, single-parent households, and language proficiency), 3) racial & ethnic minority status (e.g. race and ethnicity variables), and 4) housing & transportation (housing type, crowding, vehicles, and group quarters.). Higher values indicate greater vulnerability.
-- "disadvantaged_communities": Justice40-defined disadvantaged communities overburdened by climate, energy, health, housing, pollution, transportation, water, and workforce factors. Higher values indicate more disadvantage. Range is between 0 and 1. 
-- "fire": The percentage of the area burned by fires from (2013-2022). Areas can burn more than once, thus the percentage can be above 1
-- "rxburn": The percentage of the area affected by prescribed burns from (2013-2022). Areas can be burned more than once. 
-- "status": The conservation status. GAP 1 and 2 count towards 30x30, thus are "30x30-conserved", GAP 3 and 4 land are grouped into "other-conserved", and areas outside of GAP are designed "non-conserved". 
-- "ecoregion": Ecoregions are areas with similar ecosystems and environmental resources. The ecoregions in California are: 'Sierra Nevada Foothills','Southern Cascades','Southeastern Great Basin','Southern CA Mountains and Valleys','Sonoran Desert', 'Northwestern Basin','Colorado Desert','Central Valley Coast Ranges', 'Great Valley (South)', 'Sierra Nevada','Northern CA Coast Ranges', 'Northern CA Interior Coast Ranges','Mojave Desert', 'Mono', 'Southern CA Coast', 'Modoc Plateau', 'Klamath Mountains','Northern CA Coast','Great Valley (North)', 'Central CA Coast', and 'None'. 
+## Example: 
+example_user: "Which ecoregions are in the top 10% of range-size rarity?"
+sql_query:  
+    WITH temp_tab AS (
+        SELECT PERCENTILE_CONT(0.90) WITHIN GROUP (ORDER BY "rsr") AS temp
+        FROM mydata
+    )
+    SELECT "ecoregion"
+    FROM mydata
+    WHERE "rsr" > (SELECT temp FROM temp_tab);
 
 
-Only use the following tables:
-{table_info}.
 
 Question: {input}

app/utils.py

@@ -28,7 +28,7 @@ def get_summary(ca, combined_filter, column, colors=None): #summary stats, based
                        mean_manageable_carbon = (_.manageable_carbon * _.acres).sum() / _.acres.sum(),
                        mean_fire = (_.fire *_.acres).sum()/_.acres.sum(),
                        mean_rxburn = (_.rxburn *_.acres).sum()/_.acres.sum(),
-                       mean_disadvantaged_communities =  (_.disadvantaged_communities * _.acres).sum() / _.acres.sum(),
+                       mean_disadvantaged =  (_.disadvantaged_communities * _.acres).sum() / _.acres.sum(),
                        mean_svi =  (_.svi * _.acres).sum() / _.acres.sum(),
                       )
             .mutate(percent_protected=_.percent_protected.round(1))
@@ -52,8 +52,10 @@ def summary_table(ca, column, colors, filter_cols, filter_vals,colorby_vals): #
         filter_cols.append(column)
         filters.append(getattr(_, column).isin(colorby_vals[column])) 
     combined_filter = reduce(lambda x, y: x & y, filters) #combining all the filters into ibis filter expression 
-    if column == "status":
+    
+    if column == "status": #need to include non-conserved in summary stats 
         combined_filter = (combined_filter) | (_.status.isin(['30x30-conserved','other-conserved','non-conserved']))
+        
     df = get_summary(ca, combined_filter, [column], colors) # df used for charts 
     df_tab = get_summary(ca, combined_filter, filter_cols, colors = None) #df used for printed table
     return df, df_tab 
@@ -65,7 +67,7 @@ def area_plot(df, column): #percent protected pie chart
         alt.Theta("percent_protected:Q").stack(True),
     )
     pie = ( base
-           .mark_arc(innerRadius= 40, outerRadius=100)
+           .mark_arc(innerRadius= 40, outerRadius=100, stroke = 'black', strokeWidth = .5)
            .encode(alt.Color("color:N").scale(None).legend(None),
                    tooltip=['percent_protected', column])
     )
@@ -78,14 +80,13 @@ def area_plot(df, column): #percent protected pie chart
 
 
 def bar_chart(df, x, y, title): #display summary stats for color_by column 
-
     #axis label angles / chart size
-    if x in ["manager_type", 'ecoregion','status']: #labels are too long, making vertical 
+    if x in ["manager_type",'status']: #labels are too long, making vertical 
         angle = 270
         height = 373
-        if x == 'ecoregion':
-            height = 430
-
+    elif x == 'ecoregion': # make labels vertical and figure taller  
+        angle = 270
+        height = 430
     else: #other labels are horizontal
         angle = 0
         height = 310
@@ -100,28 +101,26 @@ def bar_chart(df, x, y, title): #display summary stats for color_by column
     else: 
         sort = 'x'
 
+    # modify label names in bar chart to fit in frame
+    label_transform = f"datum.{x}"  # default; no change 
+    if x == "access_type":
+        label_transform = f"replace(datum.{x}, ' Access', '')"  #omit 'access' from access_type 
+    elif x == "ecoregion":
+        label_transform = f"replace(datum.{x}, 'California', 'CA')"  # Replace "California" with "CA"
+       
     x_title = next(key for key, value in select_column.items() if value == x)
-    chart = alt.Chart(df).mark_bar().transform_calculate(
-        access_label=f"replace(datum.{x}, ' Access', '')"  #omit access from access_type labels so it fits in frame
+    chart = alt.Chart(df).mark_bar(stroke = 'black', strokeWidth = .5).transform_calculate(
+        label=label_transform 
         ).encode(
-        x=alt.X("access_label:N",
+        x=alt.X("label:N",
                 axis=alt.Axis(labelAngle=angle, title=x_title, labelLimit = 200),
                         sort=sort),  
         y=alt.Y(y, axis=alt.Axis()), 
-        color=alt.Color('color').scale(None)
-        ).properties(width="container", height=height, title = title
-        )
-    # sizing for poster 
-    # ).configure_title(
-    # fontSize=40  
-    # ).configure_axis(
-    # labelFontSize=24,  
-    # titleFontSize=34   
-    # )
+        color=alt.Color('color').scale(None),
+        ).properties(width="container", height=height, title = title)
     return chart
 
 
-
 def getButtons(style_options, style_choice, default_gap=None): #finding the buttons selected to use as filters 
     column = style_options[style_choice]['property']
     opts = [style[0] for style in style_options[style_choice]['stops']]   
@@ -136,7 +135,6 @@ def getButtons(style_options, style_choice, default_gap=None): #finding the butt
     return d
 
 
-
 def getColorVals(style_options, style_choice): 
     #df_tab only includes filters selected, we need to manually add "color_by" column (if it's not already a filter). 
     column = style_options[style_choice]['property']
@@ -146,81 +144,11 @@ def getColorVals(style_options, style_choice):
     return d
 
 
-
-def fire_style(layer):
-    return {"version": 8,
-    "sources": {
-        "source1": {
-            "type": "vector",
-            "url": "pmtiles://" + url_calfire,
-            "attribution": "CAL FIRE"
-        }
-    },
-    "layers": [
-        {
-            "id": "fire",
-            "source": "source1",
-            "source-layer": layer,
-            "type": "fill",
-            "paint": {
-                "fill-color": "#D22B2B",
-            }
-        }
-    ]
-}
-def rx_style(layer):
-    return{
-    "version": 8,
-    "sources": {
-        "source2": {
-            "type": "vector",
-            "url": "pmtiles://" + url_rxburn,
-            "attribution": "CAL FIRE"
-        }
-    },
-    "layers": [
-        {
-            "id": "fire",
-            "source": "source2",
-            "source-layer": layer,
-            # "filter": [">=", ["get", "YEAR_"], year],
-            "type": "fill",
-            "paint": {
-                "fill-color": "#702963",
-            }
-        }
-    ]
-}
-
-def get_sv_style(column):
-    return {
-        "layers": [
-            {
-                "id": "SVI",
-                "source": column, #need different "source" for multiple pmtiles layers w/ same file 
-                "source-layer": "SVI2020_US_county",
-                "filter": ["match", ["get", "STATE"], "California", True, False],
-                "type": "fill",
-                "paint": {
-                    "fill-color": [
-                        "interpolate", ["linear"], ["get", column],
-                        0, white,
-                        1, svi_color
-                    ]
-                }
-            }
-        ]
-    }
-
-
 def get_pmtiles_style(paint, alpha, filter_cols, filter_vals):
     filters = []
     for col, val in zip(filter_cols, filter_vals):
         filters.append(["match", ["get", col], val, True, False])
     combined_filters = ["all"] + filters
-    if paint['property'] == "status": #show non-conserved and other-conserved areas 
-        conserved = ['match', ['get', 'status'], ['30x30-conserved', 'other-conserved', 'non-conserved'], True, False]
-        combined_filters = ['any']+ [combined_filters] + [conserved]
     style = {
         "version": 8,
         "sources": {
@@ -233,7 +161,7 @@ def get_pmtiles_style(paint, alpha, filter_cols, filter_vals):
             {
                 "id": "ca30x30",
                 "source": "ca",
-                "source-layer": "ca_30x30_stats",
+                "source-layer": "ca30x30",
                 "type": "fill",
                 "filter": combined_filters,
                 "paint": {
@@ -244,6 +172,7 @@ def get_pmtiles_style(paint, alpha, filter_cols, filter_vals):
         ]
     }
     return style
+    
 
 def get_pmtiles_style_llm(paint, ids):
     combined_filters = ["all", ["match", ["get", "id"], ids, True, False]]
@@ -259,13 +188,12 @@ def get_pmtiles_style_llm(paint, ids):
             {
                 "id": "ca30x30",
                 "source": "ca",
-                "source-layer": "ca_30x30_stats",
+                "source-layer": "ca30x30",
                 "type": "fill",
                 "filter": combined_filters,
                 "paint": {
                     "fill-color": paint,
                     "fill-opacity": 1,
-                    # "fill-extrusion-height": 1000
                 }
             }
         ]

app/variables.py

@@ -1,23 +1,20 @@
 # urls for main layer 
-# ca_pmtiles = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/main/cpad-stats.pmtiles"
-# ca_parquet = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/main/cpad-stats.parquet"
+ca_parquet = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/1bc81f4f0678143421f73645f0ba830aa1cb8617/ca-30x30.parquet"
+ca_pmtiles = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/c08b22b9b506d444d0429a82f96f13e214341912/ca-30x30.pmtiles"
 
-ca_pmtiles = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/main/ca_30x30_stats.pmtiles"
-ca_parquet = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/main/ca_30x30_stats.parquet"
 
 ca_area_acres = 1.014e8 #acres 
 style_choice = "GAP Status Code"
 
-
 # urls for additional data layers 
 url_sr = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/main/species-richness-ca/{z}/{x}/{y}.png"
 url_rsr = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/main/range-size-rarity/{z}/{x}/{y}.png"
 url_irr_carbon = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/main/ca_irrecoverable_c_2018_cog.tif"
 url_man_carbon = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/main/ca_manageable_c_2018_cog.tif"
-url_svi = "https://data.source.coop/cboettig/social-vulnerability/svi2020_us_county.pmtiles"
 url_justice40 = "https://data.source.coop/cboettig/justice40/disadvantaged-communities.pmtiles"
-url_calfire = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/main/cal_fire_2022.pmtiles"
-url_rxburn = "https://huggingface.co/datasets/boettiger-lab/ca-30x30/resolve/main/cal_rxburn_2022.pmtiles"
+url_calfire = 'https://minio.carlboettiger.info/public-fire/calfire-2023.pmtiles'
+url_rxburn = 'https://minio.carlboettiger.info/public-fire/calfire-rxburn-2023.pmtiles'
+url_svi = 'https://minio.carlboettiger.info/public-data/social-vulnerability/2022/SVI2022_US_tract.pmtiles'
 
 # colors for plotting 
 private_access_color = "#DE881E" # orange 
@@ -63,7 +60,6 @@ manager = {
         ['Tribal', tribal_color],
         ['Private', private_color],
         ['HOA', hoa_color],
-        # ['None',white]
     ]
 }
 
@@ -73,7 +69,6 @@ easement = {
     'stops': [
         ['True', private_access_color],
         ['False', public_access_color],
-        # ['None', white]
     ]
 }
 
@@ -83,7 +78,6 @@ year = {
     'stops': [
         ['pre-2024', year2023_color],
         ['2024', year2024_color],
-        # ['None',white]
     ]
 }
 
@@ -95,8 +89,6 @@ access = {
         ['No Public Access', private_access_color],
         ['Unknown Access', "#bbbbbb"],
         ['Restricted Access', tribal_color],
-        # ['None', white]
-
     ]
 }
 
@@ -117,39 +109,11 @@ status = {
     'stops': [
         ['30x30-conserved', "#26633d"],
         ['other-conserved', "#879647"],
-        ['non-conserved', "#A9A9A9"]
+        ['non-conserved', white]
     ]
 }
 
 
-# ecoregion = {
-#     'property': 'ecoregion',
-#     'type': 'categorical',
-#     'stops': [
-#         ['Sierra Nevada Foothills', "#1f77b4"],
-#         ['Southern Cascades', "#ff7f0e"],
-#         ['Southeastern Great Basin', "#2ca02c"],
-#         ['Southern California Mountains and Valleys', "#d62728"],
-#         ['Sonoran Desert', "#9467bd"],
-#         ['Northwestern Basin', "#8c564b"],
-#         ['Colorado Desert', "#e377c2"],
-#         ['Central Valley Coast Ranges', "#7f7f7f"],
-#         ['Great Valley (South)', "#bcbd22"],
-#         ['Sierra Nevada', "#17becf"],
-#         ['Northern California Coast Ranges', "#aec7e8"],
-#         ['Northern California Interior Coast Ranges', "#ffbb78"],
-#         ['Mojave Desert', "#98df8a"],
-#         ['Mono', "#ff9896"],
-#         ['Southern California Coast', "#c5b0d5"],
-#         ['Modoc Plateau', "#c49c94"],
-#         ['Klamath Mountains', "#f7b6d2"],
-#         ['Northern California Coast', "#c7c7c7"],
-#         ['Great Valley (North)', "#dbdb8d"],
-#         ['Central California Coast', "#9edae5"],
-#         ['None', "#A9A9A9"]
-#     ]
-# }
-
 ecoregion = {
     'property': 'ecoregion',
     'type': 'categorical',
@@ -157,33 +121,33 @@ ecoregion = {
         ['Sierra Nevada Foothills', "#1f77b4"],
         ['Southern Cascades', "#ff7f0e"],
         ['Southeastern Great Basin', "#2ca02c"],
-        ['Southern CA Mountains and Valleys', "#d62728"],
+        ['Southern California Mountains and Valleys', "#d62728"],
         ['Sonoran Desert', "#9467bd"],
         ['Northwestern Basin', "#8c564b"],
         ['Colorado Desert', "#e377c2"],
         ['Central Valley Coast Ranges', "#7f7f7f"],
         ['Great Valley (South)', "#bcbd22"],
         ['Sierra Nevada', "#17becf"],
-        ['Northern CA Coast Ranges', "#aec7e8"],
-        ['Northern CA Interior Coast Ranges', "#ffbb78"],
+        ['Northern California Coast Ranges', "#aec7e8"],
+        ['Northern California Interior Coast Ranges', "#ffbb78"],
         ['Mojave Desert', "#98df8a"],
         ['Mono', "#ff9896"],
-        ['Southern CA Coast', "#c5b0d5"],
+        ['Southern California Coast', "#c5b0d5"],
         ['Modoc Plateau', "#c49c94"],
         ['Klamath Mountains', "#f7b6d2"],
-        ['Northern CA Coast', "#c7c7c7"],
+        ['Northern California Coast', "#c7c7c7"],
         ['Great Valley (North)', "#dbdb8d"],
-        ['Central CA Coast', "#9edae5"],
-        ['None', "#A9A9A9"]
+        ['Central California Coast', "#9edae5"],
     ]
 }
 
 
 
+
 style_options = {
     "Year": year,
     "GAP Code": gap,
-    "Status": status,
+    "30x30 Status": status,
     "Ecoregion": ecoregion,
     "Manager Type": manager,
     "Easement": easement,
@@ -221,11 +185,78 @@ justice40_style = {
         }
     ]
 }
+fire_style = {"version": 8,
+    "sources": {
+        "source1": {
+            "type": "vector",
+            "url": "pmtiles://" + url_calfire,
+            "attribution": "CAL FIRE"
+        }
+    },
+    "layers": [
+        {
+            "id": "fire",
+            "source": "source1",
+            "source-layer": 'calfire2023',
+            "filter": [">=", ["get", "YEAR_"], 2013],
+
+            "type": "fill",
+            "paint": {
+                "fill-color": "#D22B2B",
+            }
+        }
+    ]
+}
+rx_style = {
+    "version": 8,
+    "sources": {
+        "source2": {
+            "type": "vector",
+            "url": "pmtiles://" + url_rxburn,
+            "attribution": "CAL FIRE"
+        }
+    },
+    "layers": [
+        {
+            "id": "rxburn",
+            "source": "source2",
+            "source-layer": 'calfirerxburn2023',
+            "filter": [">=", ["get", "YEAR_"], 2013],
+            "type": "fill",
+            "paint": {
+                "fill-color": "#702963",
+            }
+        }
+    ]
+}
+
+
+svi_style = {
+        "layers": [
+            {
+                "id": "svi",
+                "source": "svi",
+                "source-layer": "svi",
+                "filter": ["match", ["get", "ST_ABBR"], "CA", True, False],
+                "type": "fill",
+                "paint": {
+                    "fill-color": [
+                        "interpolate", ["linear"], ["get", "RPL_THEMES"],
+                        0, white,
+                        1, svi_color
+                    ]
+                }
+            }
+        ]
+    }
+
+
+    
 
 select_column = {
     "Year": "established",
     "GAP Code": "gap_code",
-    "Status":  "status",
+    "30x30 Status":  "status",
     "Ecoregion":  "ecoregion",
     "Manager Type": "manager_type",
     "Easement": "easement",