Add data, small improvements

data.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:367c90899c7e636c6c205f77c107fc5af245fcdc85903cc69c60308906cef2c1
+size 1303958329

fiboa/app.py

@@ -15,7 +15,7 @@ if os.path.exists("duck.db"):
 if os.path.exists("duck.db.wal"):
     os.remove("duck.db.wal")
 
-geoparquet = "https://data.source.coop/fiboa/be-vlg/be_vlg.parquet"
+geoparquet = "data.parquet"
 con = ibis.connect("duckdb://duck.db", extensions = ["spatial"])
 con.read_parquet(geoparquet, "crops").cast({"geometry": "geometry"})
 # for code, url in DATA.items():
@@ -50,6 +50,9 @@ not query for columns that do not exist. Also, pay attention to which column is
 Tables include {table_info}. The data you should use always comes from the table called "crops".
 Only use that table, do not use the "testing" table. Pay close attention to this table schema.
 
+The column area is in the unit hectares, you may need to convert it to other units, e.g. square meters.
+The column perimeter is in the unit meters, you may need to convert it to other units, e.g. kilometers.
+
 Question: {input}
 '''
 )
@@ -63,9 +66,9 @@ chain = create_sql_query_chain(llm, db, prompt=new_prompt, k=100)
 '''
 Ask me about fiboa data! Request "a map" to get map output, or table for tabular output, e.g.
 
-- "Show a map with the 10 largest fields"
-- "Show a table of the total area by crop typology"
-- "Compute the perimeters of all fields and determine which have the longest"
+- Show a map with the 10 largest fields
+- Show a table of the total area by crop type
+- Compute the total area of all fields in km² and compute the percentage the total area of the baltic states (175015 km²)
 
 '''
 
@@ -79,6 +82,7 @@ with st.container():
 st.divider()
 
 '''
-Data sources: https://beta.source.coop/fiboa/be-vlg
+Data sources: https://source.coop/fiboa
+Data License: CC-BY-SA-4.0
 Software License: BSD
 '''

fiboa/query.py

@@ -32,7 +32,7 @@ def as_geopandas(con, response):
     if 'geometry' in gdf.columns:
         gdf = (gdf
                .cast({"geometry": "geometry"})
-               .mutate(geometry = _.geometry.convert("EPSG:31370", "EPSG:4326"))
+               .mutate(geometry = _.geometry.convert("EPSG:4326", "EPSG:4326"))
                .to_pandas()
               ).set_crs(epsg=4326, inplace=True) 
     else: