Dataframe (#576)

* initial dataframe commit * initial dataframe port of core app * rename variables for clarity * remove unused import * comment out unused code * fix array handling bug in crossfilter dimension creation * allow creation of empty dataframes * handle non-existent columns * handle non-existent columns * revise tests for new dataframe * comments for clarity * comments for clarity * generate bulk add placeholder with real gene names * fix bug in gene name adding * more dataframe unit tests * fix bug - subset from current world, not universe * put cut and pasted code into a single function * improve caching of crossfilter * remove cascading update bug from graph * more performance work * improve state handling for scatterplot * performance optimization of critical path * add column summarization * dataframe utils * add callOnceLazy * fix tests * minor updates found during review * fix misspelling * remove RESTv02 from function names * comment cleanup * cut/icut col parameter defaults to null * break up large test * improve tests and comments on dataframe at/has functions
2026-09-28 09:08:12 +08:00 · 2019-02-22 11:31:34 -08:00
parent 57c4e9ff33
commit 6b33315cbe
29 changed files with 1798 additions and 611 deletions
@@ -0,0 +1,57 @@
+/*
+Private dataframe support functions
+*/
+
+export function summarizeContinuous(col) {
+  let min;
+  let max;
+  let nan = 0;
+  let pinf = 0;
+  let ninf = 0;
+  if (col) {
+    for (let r = 0, l = col.length; r < l; r += 1) {
+      const val = Number(col[r]);
+      if (Number.isFinite(val)) {
+        if (min === undefined) {
+          min = val;
+          max = val;
+        } else {
+          min = val < min ? val : min;
+          max = val > max ? val : max;
+        }
+      } else if (Number.isNaN(val)) {
+        nan += 1;
+      } else if (val > 0) {
+        pinf += 1;
+      } else {
+        ninf += 1;
+      }
+    }
+  }
+  return {
+    categorical: false,
+    min,
+    max,
+    nan,
+    pinf,
+    ninf
+  };
+}
+
+export function summarizeCategorical(col) {
+  const categoryCounts = new Map();
+  if (col) {
+    for (let r = 0, l = col.length; r < l; r += 1) {
+      const val = col[r];
+      let curCount = categoryCounts.get(val);
+      if (curCount === undefined) curCount = 0;
+      categoryCounts.set(val, curCount + 1);
+    }
+  }
+  return {
+    categorical: true,
+    categories: [...categoryCounts.keys()],
+    categoryCounts,
+    numCategories: categoryCounts.size
+  };
+}