Experimental - manual annotations (#837)

* icons, partway * redux for values * onChange * cancel * annotations lifecycle for category names * copy categorical * edit category * add Dataframe.withColsFrom * render user annotations; default add/delete annotation category * add label name to actions * category name edit * error checking improvements * change schema field isUserAnnotation to writable * always have an unassigned label; implement delete label * implement add new label and edit label name * label current cell selection * fix select exact bug in crossfilter * clean up categorical reducer * fix tests * remove debugging printf * implement subset/reset for user annotations * undo redo support for user annotations * remove duplicate button from categories * add modal * remove obsolete duplicate annotation reducers * remove old debugging printf * connect modal to annotation create and dup * initial full-stack wiring * finish up end-to-end wiring * fix existing unit tests * fix pytests to match new schema API * remove debugging printfs * add label file rotation * remove obsolete comment * add fbs encode/decode tests * add tests for writable annotations * simplify code * fix hashing bug with FBS encoding * lint * fix smoke tests * improve error checking in Dataframe.withColsFrom * add unit test for Dataframe.withColsFrom * add unit test for Dataframe.columns and Dataframe.renameCol * fix bug in FBS encode, add better error checks, refactor * add FBS encode/decode test * add clarifying comment * clean up action type names; fix state inconsistency in crossfilter update * change autosave timer to 2.5sec * sort categorical metadata render order so it remains consistent * add temporary autogenerated label for add-new-label operation * fix hover-over label menu interference with cell highlighting * remove debugging code * add missing reducer cases & fix typo * make dataframe memoize more general purpose * add dev mode for annos * fix error on select duplicate * handle zero occupancy categories * correctly maintain unclipped AND clipped world * correctly handle zero length FBS matrix and label files * ensure all writable categorical schema contains an unassigned category * handle case where building occupancy stack for category with no members * dialog for creating label, disable button if duplicate or empty * visually separate writeable * edit category * fix edit category name * remove debugging code * fix edit annotation label * visually define unassigned, change options * Pull in requirements.txt from `master` * label currently selected cells * duplicate label * lint * fix pytest merge issues * rename --label-file to --experimental-label-file * remove debugging console log * spelling error fix; fix bug found in PR review. * lint
2026-10-01 07:58:12 +08:00 · 2019-09-18 07:33:41 -04:00
parent ab2c423006
commit 3660a6cc27
51 changed files with 2823 additions and 337 deletions
@@ -1,5 +1,7 @@
 import { flatbuffers } from "flatbuffers";
 import { NetEncoding } from "./matrix_generated";
+import { isTypedArray } from "../typeHelpers";
+import { IdentityInt32Index, DenseInt32Index, KeyIndex } from "../dataframe";

 const utf8Decoder = new TextDecoder("utf-8");

@@ -41,25 +43,25 @@ Returns: object containing decoded Matrix:
  colIdx: []|null
 }
 */
-function decodeMatrixFBS(arrayBuffer, inplace = false) {
+export function decodeMatrixFBS(arrayBuffer, inplace = false) {
  const bb = new flatbuffers.ByteBuffer(new Uint8Array(arrayBuffer));
-  const df = NetEncoding.Matrix.getRootAsMatrix(bb);
+  const matrix = NetEncoding.Matrix.getRootAsMatrix(bb);

-  const nRows = df.nRows();
-  const nCols = df.nCols();
+  const nRows = matrix.nRows();
+  const nCols = matrix.nCols();

  /* decode columns */
-  const columnsLength = df.columnsLength();
+  const columnsLength = matrix.columnsLength();
  const columns = Array(columnsLength).fill(null);
  for (let c = 0; c < columnsLength; c += 1) {
-    const col = df.columns(c);
+    const col = matrix.columns(c);
    columns[c] = decodeTypedArray(col.uType(), col.u.bind(col), inplace);
  }

  /* decode col_idx */
  const colIdx = decodeTypedArray(
-    df.colIndexType(),
-    df.colIndex.bind(df),
+    matrix.colIndexType(),
+    matrix.colIndex.bind(matrix),
    inplace
  );

@@ -72,4 +74,91 @@ function decodeMatrixFBS(arrayBuffer, inplace = false) {
  };
 }

-export default decodeMatrixFBS;
+function encodeTypedArray(builder, uType, uData) {
+  const uTypeName = NetEncoding.TypedArray[uType];
+  const ArrayType = NetEncoding[uTypeName];
+  const dv = ArrayType.createDataVector(builder, uData);
+  builder.startObject(1);
+  builder.addFieldOffset(0, dv, 0);
+  return builder.endObject();
+}
+
+export function encodeMatrixFBS(df) {
+  /*
+  encode the dataframe as an FBS Matrix
+  */
+
+  /* row indexing not supported currently */
+  if (df.rowIndex.constructor !== IdentityInt32Index) {
+    throw new Error("FBS does not support row index encoding at this time");
+  }
+
+  const shape = df.dims;
+  const utf8Encoder = new TextEncoder("utf-8");
+  const builder = new flatbuffers.Builder(1024);
+
+  let encColIndex;
+  let encColIndexUType;
+  let encColumns;
+
+  if (shape[0] > 0 && shape[1] > 0) {
+    const columns = df.columns().map(col => col.asArray());
+
+    const cols = columns.map(carr => {
+      let uType;
+      let tarr;
+      if (isTypedArray(carr)) {
+        uType = NetEncoding.TypedArray[carr.constructor.name];
+        tarr = encodeTypedArray(builder, uType, carr);
+      } else {
+        uType = NetEncoding.TypedArray.JSONEncodedArray;
+        const json = JSON.stringify(carr);
+        const jsonUTF8 = utf8Encoder.encode(json);
+        tarr = encodeTypedArray(builder, uType, jsonUTF8);
+      }
+      NetEncoding.Column.startColumn(builder);
+      NetEncoding.Column.addUType(builder, uType);
+      NetEncoding.Column.addU(builder, tarr);
+      return NetEncoding.Column.endColumn(builder);
+    });
+
+    encColumns = NetEncoding.Matrix.createColumnsVector(builder, cols);
+
+    if (df.colIndex && shape[1] > 0) {
+      const colIndexType = df.colIndex.constructor;
+      if (colIndexType === IdentityInt32Index) {
+        encColIndex = undefined;
+      } else if (colIndexType === DenseInt32Index) {
+        encColIndexUType = NetEncoding.TypedArray.Int32Array;
+        encColIndex = encodeTypedArray(
+          builder,
+          encColIndexUType,
+          df.colIndex.keys()
+        );
+      } else if (colIndexType === KeyIndex) {
+        encColIndexUType = NetEncoding.TypedArray.JSONEncodedArray;
+        encColIndex = encodeTypedArray(
+          builder,
+          encColIndexUType,
+          utf8Encoder.encode(JSON.stringify(df.colIndex.keys()))
+        );
+      } else {
+        throw new Error("Index type FBS encoding unsupported");
+      }
+    }
+  }
+
+  NetEncoding.Matrix.startMatrix(builder);
+  NetEncoding.Matrix.addNRows(builder, shape[0]);
+  NetEncoding.Matrix.addNCols(builder, shape[1]);
+  if (encColumns) {
+    NetEncoding.Matrix.addColumns(builder, encColumns);
+  }
+  if (encColIndexUType) {
+    NetEncoding.Matrix.addColIndexType(builder, encColIndexUType);
+    NetEncoding.Matrix.addColIndex(builder, encColIndex);
+  }
+  const root = NetEncoding.Matrix.endMatrix(builder);
+  builder.finish(root);
+  return builder.asUint8Array();
+}