categorical metadata performance work (#356)

* do not create unecessary option state for categories we will not display * performance improvements for categorical metadata handling
2026-09-29 16:58:11 +08:00 · 2018-10-22 09:56:41 -07:00
parent efb55a6332
commit 0c271bc815
10 changed files with 184 additions and 96 deletions
@@ -0,0 +1,94 @@
+import _ from "lodash";
+
+/*
+Build and return obs/var summary using any annotation in the schema
+
+Summary information for each annotation, keyed by annotation name.
+Value will be an object, containing summary information.
+
+For continuous annotations (int, float, etc):
+  <annotation_name>: {
+    range {
+      min: <number>,
+      max: <number>
+    }
+  }
+
+For categorical annotations (boolean, string, category):
+  <annotatoin_name>: {
+    options: {
+      <option1>: <number>,
+      ...
+    },
+    numOptions: <number>
+  }
+
+Summarize will be returned for BOTH obs and var annotations.
+
+Example:
+  {
+    "Splice_sites_Annotated": {
+      "range": {
+        "min": 26,
+        "max": 1075869
+      }
+    },
+    "Selection": {
+      numOptions, 6,
+      "options": {
+        "Astrocytes(HEPACAM)": 714,
+        "Endothelial(BSC)": 123,
+        "Oligodendrocytes(GC)": 294,
+        "Neurons(Thy1)": 685,
+        "Microglia(CD45)": 1108,
+        "Unpanned": 665
+      }
+    }
+  }
+
+NOTE: will not summarize the required 'name' annotation, as that is
+specified as unique per element.
+*/
+function summarizeDimension(schema, annotations) {
+  return _(schema)
+    .filter(v => v.name !== "name")
+    .keyBy("name")
+    .mapValues(anno => {
+      const { name, type } = anno;
+      const continuous = type === "int32" || type === "float32";
+
+      if (!continuous) {
+        const options = _.countBy(annotations, name);
+        const numOptions = _.size(options);
+        return {
+          numOptions,
+          options
+        };
+      }
+
+      if (continuous) {
+        let min = Number.POSITIVE_INFINITY;
+        let max = Number.NEGATIVE_INFINITY;
+        _.forEach(annotations, obs => {
+          const val = Number(obs[name]);
+          min = val < min ? val : min;
+          max = val > max ? val : max;
+        });
+        return { range: { min, max } };
+      }
+
+      throw new Error("incomprehensible schema");
+    })
+    .value();
+}
+
+export default function summarizeAnnotations(
+  schema,
+  obsAnnotations,
+  varAnnotations
+) {
+  return {
+    obs: summarizeDimension(schema.annotations.obs, obsAnnotations),
+    var: summarizeDimension(schema.annotations.var, varAnnotations)
+  };
+}