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

client/src/util/dataframe/dataframe.js

@@ -345,12 +345,50 @@ class Dataframe {
     );
   }
 
+  withColsFrom(dataframe) {
+    /*
+    return a new dataframe containing all columns from both `this` and the
+    provided dataframe.
+
+    The row index from `this` will be used.  Both dataframes must have identical
+    dimensionality, and no overlapping columns labels.
+     */
+    const dims = [this.dims[0], this.dims[1] + dataframe.dims[1]];
+    const { rowIndex } = this;
+    const columns = [...this.__columns, ...dataframe.__columns];
+    const colIndex = this.colIndex.withLabels(dataframe.colIndex.keys());
+    const columnsAccessor = [
+      ...this.__columnsAccessor,
+      ...dataframe.__columnsAccessor
+    ];
+    return new this.constructor(
+      dims,
+      columns,
+      rowIndex,
+      colIndex,
+      columnsAccessor
+    );
+  }
+
   dropCol(label) {
     /*
     Create a new dataframe, omitting one columns.
 
     const newDf = df.dropCol("colors");
+
+    Corner case to manage: if dropping the last column, return an empty dataframe.
     */
+    if (!this.hasCol(label)) {
+      throw new RangeError(`unknown label: ${label}`);
+    }
+
+    /* 
+    Corner case to manage: if dropping the last column, return an empty dataframe. 
+    */
+    if (this.dims[1] === 1) {
+      return Dataframe.empty();
+    }
+
     const dims = [this.dims[0], this.dims[1] - 1];
     const coffset = this.colIndex.getOffset(label);
     const columns = [...this.__columns];
@@ -367,6 +405,50 @@ class Dataframe {
     );
   }
 
+  renameCol(oldLabel, newLabel) {
+    /*
+    Accelerator for dropping a column and then adding it again with a new label
+    */
+    const coffset = this.colIndex.getOffset(oldLabel);
+    const colIndex = this.colIndex.dropLabel(oldLabel).withLabel(newLabel);
+
+    const columns = [...this.__columns];
+    columns.push(columns[coffset]);
+    columns.splice(coffset, 1);
+
+    const columnsAccessor = [...this.__columnsAccessor];
+    columnsAccessor.push(columnsAccessor[coffset]);
+    columnsAccessor.splice(coffset, 1);
+
+    return new this.constructor(
+      this.dims,
+      columns,
+      this.rowIndex,
+      colIndex,
+      columnsAccessor
+    );
+  }
+
+  replaceColData(label, newColData) {
+    /*
+    Accelerator for dropping a column then adding it again with same
+    label and different values.
+    */
+    const coffset = this.colIndex.getOffset(label);
+    const columns = [...this.__columns];
+    columns[coffset] = newColData;
+    const columnsAccessor = [...this.__columnsAccessor];
+    columnsAccessor[coffset] = null;
+
+    return new this.constructor(
+      this.dims,
+      columns,
+      this.rowIndex,
+      this.colIndex,
+      columnsAccessor
+    );
+  }
+
   static empty(rowIndex = null, colIndex = null) {
     return new Dataframe([0, 0], [], rowIndex, colIndex);
   }
@@ -443,6 +525,8 @@ class Dataframe {
         return newCol;
       });
     }
+
+    if (dims[0] === 0 || dims[1] === 0) return Dataframe.empty();
     return new Dataframe(dims, columns, rowIndex, colIndex);
   }
 
@@ -526,6 +610,11 @@ class Dataframe {
   Data access with row/col.
   **/
 
+  columns() {
+    /* return all column accessors as an array, in offset order */
+    return [...this.__columnsAccessor];
+  }
+
   col(columnLabel) {
     /*
     Return accessor bound to a column.  Allows random row access

client/src/util/dataframe/labelIndex.js

@@ -80,6 +80,10 @@ class IdentityInt32Index {
     return this.__promote([...this.keys(), label]);
   }
 
+  withLabels(labels) {
+    return this.__promote([...this.keys(), ...labels]);
+  }
+
   dropLabel(label) {
     if (label === this.maxOffset - 1) {
       return new IdentityInt32Index(label);
@@ -163,6 +167,10 @@ class DenseInt32Index {
     return this.__promote([...this.keys(), label]);
   }
 
+  withLabels(labels) {
+    return this.__promote([...this.keys(), ...labels]);
+  }
+
   dropLabel(label) {
     const labelArray = [...this.keys()];
     labelArray.splice(labelArray.indexOf(label), 1);
@@ -187,6 +195,11 @@ class KeyIndex {
       index.set(v, i);
     });
 
+    if (index.size !== rindex.length) {
+      /* if true, there was a duplicate in the keys */
+      throw new Error("duplicate label provided to KeyIndex");
+    }
+
     this.index = index;
     this.rindex = rindex;
     this.__compile();
@@ -218,6 +231,10 @@ class KeyIndex {
     return new KeyIndex([...this.rindex, label]);
   }
 
+  withLabels(labels) {
+    return new KeyIndex([...this.rindex, ...labels]);
+  }
+
   dropLabel(label) {
     const idx = this.rindex.indexOf(label);
     const labelArray = [...this.rindex];

client/src/util/dataframe/util.js

@@ -21,7 +21,7 @@ export function callOnceLazy(f) {
   return result;
 }
 
-export function memoize(fn, hashFn) {
+export function memoize(fn, hashFn, maxResultsCached = -1) {
   /* 
   function memoization, with user-provided hash.  hashFn must return a
   key which will be unique as a Map key (ie, obeys "sameValueZero" algorithm
@@ -36,7 +36,19 @@ export function memoize(fn, hashFn) {
     }
     const result = fn(...args);
     cache.set(key, result);
+
+    if (maxResultsCached > -1 && cache.size > maxResultsCached) {
+      /* Least recent insertion deletion */
+      cache.delete(cache.keys().next().value);
+    }
+
     return result;
   };
+
+  wrap.clear = function clear() {
+    /* clear memoization cache */
+    cache.clear();
+  };
+
   return wrap;
 }