Files
cellxgene/client/__tests__/util/dataframe/summarize.test.js
Bruce Martin eaae6df5e3 TS Revert (1) (#2402)
* revert all commits to before Typescript migration

* update compat workflow to match latest deps (#2335)

* update compat workflow to match latest deps

* attempt to debug

* attempt to debug

* remove debugging code

* typo

* update deps to match desktop (#2340)

* fix: don't run lint with `--fix` on push tests (#2273)

* fix: don't run lint with `--fix` on push tests

* npx

Co-authored-by: maniarathi <mani.arathi@gmail.com>
Co-authored-by: Madison Dunitz <madison.dunitz@chanzuckerberg.com>

* rename X_approx_distribution to X_approximate_distribution (#2337)

* Correctly handle non-finite numbers in heuristic determination of X distribution (#2342)

* handle non-finites explicitly

* improve and test edge case handling for distribution estimation

* revert debugging changes

* code readability

* clean up type inferencing (#2332)

* unit tests for 64 bit conversion

* clean up type handling

* type inference tests

* more type inference fixes

* use schema to determine user intent for data typing

* stop using deprecated API

* fbs type encoding test

* add missing test

* add more tests

* correctly infer X type for CXG adaptor

* lint

* fix typo

* ts migration

* cleanup from PR review

* lint

* PR review changes

* remove unused packages from client (#2359)

* remove unused packages from client

* add missing peer dep

* fix: disable FE auth testing on compatibility tests (#2377)

* update: release process (#2277)

Co-authored-by: maniarathi <mani.arathi@gmail.com>

* fix: remove spaces in param setup (#2380)

* delete deploy workflow (#2396)

* undo reformatting which now does not pass lint

* fix snapshots which changed due to npm dep changes

* add missing quoting to snapshot

* another snapshot typo fix

* TS Revert (2) - replay PR #2347 and #2354 (#2403)

* replay edits from PR 2347

* TS Revert (3) - replay edits in PR #2327 (#2404)

* replay edits in PR 2327

* TS Revert (4) - replay PR #2355 (#2405)

* replay edits in PR 2355

* add additional babel config

* reformat with new prettier config

Co-authored-by: Severiano Badajoz <sbadajoz@chanzuckerberg.com>
Co-authored-by: maniarathi <mani.arathi@gmail.com>
Co-authored-by: Madison Dunitz <madison.dunitz@chanzuckerberg.com>
2021-08-23 15:01:36 -07:00

282 lines
6.5 KiB
JavaScript

import * as Dataframe from "../../../src/util/dataframe";
function float32Conversion(f) {
return new Float32Array([f])[0];
}
describe("Dataframe column summary", () => {
test("empty column test", () => {
const df = Dataframe.Dataframe.create([0, 1], [[]]);
const summary = df.icol(0).summarize();
expect(summary).toEqual(
expect.objectContaining({
categorical: true,
categories: [],
categoryCounts: new Map(),
numCategories: 0,
})
);
});
test("simple test", () => {
const df = new Dataframe.Dataframe(
[1, 6],
[
["n1"],
["hi"],
[true],
new Float32Array([39.3]),
new Int32Array([99]),
[1],
],
null,
new Dataframe.KeyIndex([
"name",
"nameString",
"nameBoolean",
"nameFloat32",
"nameInt32",
"nameCategorical",
])
);
expect(df.icol(0).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: ["n1"],
categoryCounts: new Map([["n1", 1]]),
numCategories: 1,
})
);
expect(df.icol(1).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: ["hi"],
categoryCounts: new Map([["hi", 1]]),
numCategories: 1,
})
);
expect(df.icol(2).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: [true],
categoryCounts: new Map([[true, 1]]),
numCategories: 1,
})
);
expect(df.icol(3).summarize()).toEqual(
expect.objectContaining({
categorical: false,
min: float32Conversion(39.3),
max: float32Conversion(39.3),
nan: 0,
ninf: 0,
pinf: 0,
})
);
expect(df.icol(4).summarize()).toEqual(
expect.objectContaining({
categorical: false,
min: 99,
max: 99,
nan: 0,
ninf: 0,
pinf: 0,
})
);
expect(df.icol(5).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: [1],
categoryCounts: new Map([[1, 1]]),
numCategories: 1,
})
);
});
test("multi test", () => {
const df = new Dataframe.Dataframe(
[3, 6],
[
["n0", "n1", "n2"],
["hi", "hi", "bye"],
[false, true, true],
new Float32Array([39.3, 39.3, 0]),
new Int32Array([99, 99, 99]),
[1, false, "0"],
],
null,
new Dataframe.KeyIndex([
"name",
"nameString",
"nameBoolean",
"nameFloat32",
"nameInt32",
"nameCategorical",
])
);
expect(df.icol(0).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: expect.arrayContaining(["n0", "n1", "n2"]),
categoryCounts: new Map([
["n0", 1],
["n1", 1],
["n2", 1],
]),
numCategories: 3,
})
);
expect(df.icol(1).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: expect.arrayContaining(["hi", "bye"]),
categoryCounts: new Map([
["hi", 2],
["bye", 1],
]),
numCategories: 2,
})
);
expect(df.icol(2).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: expect.arrayContaining([true, false]),
categoryCounts: new Map([
[true, 2],
[false, 1],
]),
numCategories: 2,
})
);
expect(df.icol(3).summarize()).toEqual(
expect.objectContaining({
categorical: false,
min: 0,
max: float32Conversion(39.3),
nan: 0,
ninf: 0,
pinf: 0,
})
);
expect(df.icol(4).summarize()).toEqual(
expect.objectContaining({
categorical: false,
min: 99,
max: 99,
nan: 0,
ninf: 0,
pinf: 0,
})
);
expect(df.icol(5).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: expect.arrayContaining([1, false, "0"]),
categoryCounts: new Map([
[1, 1],
[false, 1],
["0", 1],
]),
numCategories: 3,
})
);
});
test("non-finite numbers", () => {
const df = new Dataframe.Dataframe(
[4, 6],
[
["n0", "n1", "n2", "n2"],
["hi", "hi", "bye", "bye"],
[false, true, true, true],
new Float32Array([
39.3,
Number.NEGATIVE_INFINITY,
Number.NaN,
Number.POSITIVE_INFINITY,
]),
new Int32Array([99, 99, 99, 99]),
[1, false, "0", "0"],
],
null,
new Dataframe.KeyIndex([
"name",
"nameString",
"nameBoolean",
"nameFloat32",
"nameInt32",
"nameCategorical",
])
);
expect(df.icol(0).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: expect.arrayContaining(["n0", "n1", "n2"]),
categoryCounts: new Map([
["n0", 1],
["n1", 1],
["n2", 2],
]),
numCategories: 3,
})
);
expect(df.icol(1).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: expect.arrayContaining(["hi", "bye"]),
categoryCounts: new Map([
["hi", 2],
["bye", 1],
]),
numCategories: 2,
})
);
expect(df.icol(2).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: expect.arrayContaining([true, false]),
categoryCounts: new Map([
[true, 2],
[false, 1],
]),
numCategories: 2,
})
);
expect(df.icol(3).summarize()).toEqual(
expect.objectContaining({
categorical: false,
min: float32Conversion(39.3),
max: float32Conversion(39.3),
nan: 1,
ninf: 1,
pinf: 1,
})
);
expect(df.icol(4).summarize()).toEqual(
expect.objectContaining({
categorical: false,
min: 99,
max: 99,
nan: 0,
ninf: 0,
pinf: 0,
})
);
expect(df.icol(5).summarize()).toEqual(
expect.objectContaining({
categorical: true,
categories: expect.arrayContaining([1, false, "0"]),
categoryCounts: new Map([
[1, 1],
[false, 1],
["0", 1],
]),
numCategories: 3,
})
);
});
});