testing

app.py

@@ -250,7 +250,7 @@ m.to_streamlit(height=900)
 #parquet = "https://data.source.coop/cboettig/pad-us-3/pad-mobi.parquet"
 parquet = "https://minio.carlboettiger.info/public-biodiversity/pad-us-3/pad-mobi.parquet"
 
-t = ibis.read_parquet(parquet)
+pad_data = ibis.read_parquet(parquet)
 
 
 # +
@@ -260,7 +260,7 @@ us_lower_48_area_m2 = 7.8e+12
 def summary_table():
     x = ibis.memtable({"bucket": ["public", "tribal", "mixed", "private"], 
                        "color": [public_color, tribal_color, mixed_color, private_color]})
-    df = (t.
+    df = (pad_data.
         group_by(_.bucket).
         aggregate(percent_protected =  100 * _.area.sum() / us_lower_48_area_m2,
                 mean_richness = (_.richness * _.area).sum() / _.area.sum(),
@@ -287,7 +287,7 @@ base = alt.Chart(df).encode(
 
 area_chart = (
   base.mark_arc(innerRadius=50, outerRadius=120) +
-  base.mark_text(radius=170, size=20).encode(text="bucket") +
+  base.mark_text(radius=165, size=20).encode(text="bucket") +
   base.mark_text(radius=135, size=20).encode(text="percent_protected:N")
 )
 
@@ -312,23 +312,64 @@ rsr_chart = alt.Chart(df).mark_bar().encode(
 )
 # -
 
-"## Summary Statistics"
+'''
+## Summary Statistics
+
+'''
 
 # +
 col1, col2, col3 = st.columns(3)
 
-with col1: 
+with col1:
+    "#### Percent of Continental US Area"
     st.altair_chart(area_chart, use_container_width=True)
-    "Percent of Continental US Area in each group"
+    
 # -
 
 with col2: 
+    "#### Mean Species Richness"
     st.altair_chart(richness_chart, use_container_width=True)
 
 
 with col3: 
+    "#### Mean Range-Size Rarirty"
     st.altair_chart(rsr_chart, use_container_width=True)
 
+# +
+'''
+## Custom queries
+
+Input custom python code below to interactively explore the data. 
+
+'''
+
+col2_1, col2_2 = st.columns(2)
+
+
+sample_q = '''(
+    ibis.read_parquet('https://minio.carlboettiger.info/public-biodiversity/pad-us-3/pad-mobi.parquet').
+    group_by(_.bucket).
+    aggregate(percent_protected =  100 * _.area.sum() / us_lower_48_area_m2,
+              mean_richness = (_.richness * _.area).sum() / _.area.sum(),
+              mean_rsr = (_.rsr * _.area).sum() / _.area.sum()
+              ).
+    mutate(percent_protected = _.percent_protected.round())
+)
+'''
+
+with col2_1:
+    query = st.text_area(
+        label = "Python code:",
+        value = sample_q, 
+        height = 300)
+
+with col2_2:
+    "Output table:"
+    df = eval(sample_q)
+    st.write(df.to_pandas())
+
+# -
+
 '''
 ## Technical errata
 
@@ -358,7 +399,7 @@ The 2018 version of this data product can be found on Microsoft Planetary Comput
 The original data is provided in the geotiff format (ESRI  LayerFiles) at 990 meter resolution, and includes assets subset by various taxonomic groups for three indicators: for 2,216 imperiled species (species with global conservation status of G1, G2 or listed as threatened or endagered under the United States Ednagered Species Act).
 The indicators include species richness (the number of imperiled species occurring in a given pixel),
 range-size rarity (RSR, the sum of the inverse of the range sizes of each species occurring in a given pixel),
-and protection-weighted rRSR (RSR times the perecent of the range that is unprotected in GAP 1 & Gap 2).  
+and protection-weighted RSR (RSR times the perecent of the range that is unprotected in GAP 1 & Gap 2).  
 See [geohub description](https://geohub-natureserve.opendata.arcgis.com/content/e5a6de94cc7b4d5b9204e2cc5d8b6e4e/about) for more details.
 Only data from all species for the species richness and RSR metrics is processed here (at the time of writing).