Transitional progress: 2 paths calculation working proof of concept

rdhyee · claude · rdhyee · commit b4f925cb7b7f · 2025-09-24T15:40:52.000-07:00
- pid is hardcoded for testing - working towards setting pid as the clicked id - get_samples_1 and get_samples_2 functions implemented 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
diff --git a/tutorials/parquet_cesium.qmd b/tutorials/parquet_cesium.qmd
@@ -1,15 +1,12 @@
 ---
-title: Using Cesium for geospatial visualization of remote parquet data
+title: Using Cesium for display of remote parquet.
 categories: [parquet, spatial, recipe]
 ---
 
-One key development of the iSamples project centers on the demonstration of low-cost, simplified, and more sustainable approaches to access, analyze and visualize scientific data. Rather than relying upon elaborate and costly server-side infrastructure, iSamples demonstrates how open source technologies like parquet and DuckDB-WASM can streamline cheaper and faster approaches to interacting with geospatial data.
+This page renders points from an iSamples parquet file on cesium using point primitives.
 
-This page demonstrates how geospatial data can be dynamically accessed from a remote parquet file in cloud storage. The page uses Cesium for browser visualization of these spatial data on a 3D global map. The data in this demonstration comes from [Open Context's](https://opencontext.org/) export of specimen (archaeological artifact and ecofact) records for iSamples. However, this demonstration can also work with any other iSamples compliant parquet data source made publicly accessible on the Web.
-
-
-<script src="https://cesium.com/downloads/cesiumjs/releases/1.133/Build/Cesium/Cesium.js"></script>
-<link href="https://cesium.com/downloads/cesiumjs/releases/1.133/Build/Cesium/Widgets/widgets.css" rel="stylesheet"></link>
+<script src="https://cesium.com/downloads/cesiumjs/releases/1.127/Build/Cesium/Cesium.js"></script>
+<link href="https://cesium.com/downloads/cesiumjs/releases/1.127/Build/Cesium/Widgets/widgets.css" rel="stylesheet"></link>
 <style>
     div.cesium-topleft {
         display: block;
@@ -196,6 +193,62 @@ async function getGeoRecord(pid) {
     return result;
 }
 
+async function get_samples_1(pid) {
+    if (pid === null || pid ==="" || pid == "unset") {
+        return "unset";
+    }
+    const q = `
+        SELECT DISTINCT
+            s.pid as sample_id,
+            s.label as sample_label,
+            s.name as sample_name,
+            event.pid as event_id,
+            event.label as event_label,
+            'direct_event_location' as location_path
+        FROM nodes s
+        JOIN nodes e1 ON s.row_id = e1.s AND e1.p = 'produced_by'
+        JOIN nodes event ON e1.o[1] = event.row_id
+        JOIN nodes e2 ON event.row_id = e2.s AND e2.p = 'sample_location'
+        JOIN nodes g ON e2.o[1] = g.row_id
+        WHERE s.otype = 'MaterialSampleRecord'
+          AND event.otype = 'SamplingEvent'
+          AND g.otype = 'GeospatialCoordLocation'
+          AND g.pid = ?
+    `;
+    const result = await db.queryRow(q, [pid]);
+    return result;
+}
+
+async function get_samples_2(pid) {
+    if (pid === null || pid ==="" || pid == "unset") {
+        return "unset";
+    }
+    const q = `
+        SELECT DISTINCT
+            s.pid as sample_id,
+            s.label as sample_label,
+            s.name as sample_name,
+            event.pid as event_id,
+            event.label as event_label,
+            site.label as site_name,
+            'via_site_location' as location_path
+        FROM nodes s
+        JOIN nodes e1 ON s.row_id = e1.s AND e1.p = 'produced_by'
+        JOIN nodes event ON e1.o[1] = event.row_id
+        JOIN nodes e2 ON event.row_id = e2.s AND e2.p = 'sampling_site'
+        JOIN nodes site ON e2.o[1] = site.row_id
+        JOIN nodes e3 ON site.row_id = e3.s AND e3.p = 'site_location'
+        JOIN nodes g ON e3.o[1] = g.row_id
+        WHERE s.otype = 'MaterialSampleRecord'
+          AND event.otype = 'SamplingEvent'
+          AND site.otype = 'SamplingSite'
+          AND g.otype = 'GeospatialCoordLocation'
+          AND g.pid = ?
+    `;
+    const result = await db.queryRow(q, [pid]);
+    return result; 
+}
+
 async function locationUsedBy(rowid){
     if (rowid === undefined || rowid === null) {
         return [];
@@ -238,8 +291,6 @@ viewof pointdata = {
 
 :::
 
-The number of locations in the file is: ${pointdata.length}.
-
 The click point ID is "${clickedPointId}".
 
 ```{ojs}
@@ -250,41 +301,7 @@ ${JSON.stringify(selectedGeoRecord, null, 2)}
 `
 ```
 
-## Table Structure Analysis
-
-Understanding the structure and schema of the parquet file:
-
-### Column Schema
-
-```{ojs}
-//| code-fold: true
-tableSchema = {
-    const query = `DESCRIBE nodes`;
-    const data = await loadData(query, [], "loading_schema");
-    return data;
-}
-```
-
-<div id="loading_schema">Loading table schema...</div>
-
-```{ojs}
-//| code-fold: true
-viewof schemaTable = {
-    const data_table = Inputs.table(tableSchema, {
-        header: {
-            column_name: "Column Name",
-            column_type: "Data Type",
-            null: "Nullable",
-            key: "Key",
-            default: "Default",
-            extra: "Extra"
-        }
-    });
-    return data_table;
-}
-```
-
-### Sample Data
+## Sample Data
 
 First 10 rows of the dataset to understand the data structure:
 
@@ -313,133 +330,41 @@ viewof sampleTable = {
 }
 ```
 
-### Sample Data by Object Type
-
-Examples of records for each object type to understand the data semantics:
+## getGeoRecord (harcoded)
 
 ```{ojs}
 //| code-fold: true
-sampleDataByOtype = {
-    // First get the list of unique object types
-    const otypeQuery = `SELECT DISTINCT otype FROM nodes ORDER BY otype`;
-    const otypes = await loadData(otypeQuery, [], "loading_otype_samples");
-    
-    const results = [];
-    for (const otypeRow of otypes) {
-        const otype = otypeRow.otype;
-        // Get 3 sample records for each otype
-        const sampleQuery = `SELECT * FROM nodes WHERE otype = ? LIMIT 3`;
-        const samples = await db.query(sampleQuery, [otype]);
-        
-        results.push({
-            otype: otype,
-            count: samples.length,
-            samples: samples
-        });
-    }
-    return results;
-}
-```
-
-<div id="loading_otype_samples">Loading sample data by object type...</div>
-
-```{ojs}
-//| code-fold: true
-viewof otypeSamplesDisplay = {
-    const container = html`<div></div>`;
-    
-    for (const otypeData of sampleDataByOtype) {
-        const section = html`<div style="margin-bottom: 2rem;">
-            <h4 style="color: #2563eb; margin-bottom: 0.5rem;">Object Type: ${otypeData.otype}</h4>
-            <p style="margin: 0.5rem 0; font-style: italic;">Sample records (showing up to 3):</p>
-        </div>`;
-        
-        // Create a table for this otype's samples
-        const table = Inputs.table(otypeData.samples, {
-            layout: "auto",
-            width: {
-                pid: 150,
-                otype: 120,
-                latitude: 100,
-                longitude: 100
-            }
-        });
-        
-        section.appendChild(table);
-        container.appendChild(section);
-    }
-    
-    return container;
-}
+pid = "geoloc_7ea562cce4c70e4b37f7915e8384880c86607729";
+testrecord = await getGeoRecord(pid);
 ```
 
-## Object Type Counts
-
-The distribution of object types (`otype`) in the dataset:
-
 ```{ojs}
-//| code-fold: true
-otypeCounts = {
-    const query = `SELECT otype, COUNT(*) as count FROM nodes GROUP BY otype ORDER BY count DESC`;
-    const data = await loadData(query, [], "loading_otype");
-    return data;
-}
+//| echo: false
+md`\`\`\`
+${JSON.stringify(testrecord, null, 2)}
+\`\`\`
+`
 ```
 
-<div id="loading_otype">Loading object type counts...</div>
+## Related Sample Path 1 (harcoded)
 
 ```{ojs}
-//| code-fold: true
-viewof otypeTable = {
-    const data_table = Inputs.table(otypeCounts, {
-        header: {
-            otype: "Object Type",
-            count: "Count"
-        },
-        format: {
-            count: d => d.toLocaleString()
-        }
-    });
-    return data_table;
-}
+//| echo: false
+samples_1 = await get_samples_1(pid)
+md`\`\`\`
+${JSON.stringify(samples_1, null, 2)}
+\`\`\`
+`
 ```
 
-Total records by object type: ${otypeCounts.reduce((sum, row) => sum + row.count, 0).toLocaleString()}
-
-## Property Distribution Analysis
 
-Understanding the range of properties (predicates) in this graph database structure:
+## Related Sample Path 2 (harcoded)
 
 ```{ojs}
-//| code-fold: true
-propertyDistribution = {
-    const query = `SELECT p as property, COUNT(*) as count FROM nodes WHERE p IS NOT NULL GROUP BY p ORDER BY count DESC`;
-    const data = await loadData(query, [], "loading_properties");
-    return data;
-}
-```
-
-<div id="loading_properties">Loading property distribution...</div>
-
-```{ojs}
-//| code-fold: true
-viewof propertyTable = {
-    const data_table = Inputs.table(propertyDistribution, {
-        header: {
-            property: "Property (Predicate)",
-            count: "Count"
-        },
-        format: {
-            count: d => d.toLocaleString()
-        },
-        layout: "auto"
-    });
-    return data_table;
-}
-```
-
-Total records with properties: ${propertyDistribution.reduce((sum, row) => sum + row.count, 0).toLocaleString()}
-
-Unique properties in the dataset: ${propertyDistribution.length.toLocaleString()}
-
-
+//| echo: false
+samples_2 = await get_samples_2(pid)
+md`\`\`\`
+${JSON.stringify(samples_2, null, 2)}
+\`\`\`
+`
+```
