Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: generic DataFrame #293

Merged
merged 11 commits into from
Nov 21, 2024
+636 −399
Merged

feat: generic DataFrame #293

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
746f910
style: format
scarf005 Nov 13, 2024
6ae1aa7
feat: `Simplify` utility type
scarf005 Nov 14, 2024
f26f01f
fix(datatype): make `DataType` type comparable
scarf005 Nov 14, 2024
3784f87
fix(datatype): return precise DataType
scarf005 Nov 18, 2024
6fe51f5
feat(series): generic name property
scarf005 Nov 13, 2024
c73acbf
fix(series): allow nullable values
scarf005 Nov 18, 2024
5ebe299
fix: type error
scarf005 Nov 14, 2024
fef1d43
feat(dataframe): generic `DataFrame`
scarf005 Nov 14, 2024
a675894
fix(dataframe): warn type of replaceAtIdx
scarf005 Nov 18, 2024
ed11909
fix(dataframe): type fixes
scarf005 Nov 20, 2024
1cf2275
docs: type info in docstring
scarf005 Nov 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
182 changes: 95 additions & 87 deletions __tests__/dataframe.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -756,7 +756,7 @@ describe("dataframe", () => {
expect(actual.columns).toEqual(["foo_new", "bar_new", "ham_new"]);
});
test("replaceAtIdx", () => {
const actual = pl.DataFrame({
const actual: pl.DataFrame = pl.DataFrame({
foo: [1, 2, 3],
bar: [6, 7, 8],
ham: ["a", "b", "c"],
Expand Down Expand Up @@ -1315,101 +1315,109 @@ describe("dataframe", () => {
expect(actual).toFrameEqual(expected);
});
test("pivot", () => {
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Any reason for removing this? Thx

Copy link
Contributor Author

@scarf005 scarf005 Nov 18, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

gah, accidently removed when adding scopes, will amend and push again
EDIT: force-pushed on a675894 (#293)

let df = pl.DataFrame({
a: pl.Series([1, 2, 3]).cast(pl.Int32),
b: pl
.Series([
[1, 1],
[2, 2],
[3, 3],
])
.cast(pl.List(pl.Int32)),
});

let expected = pl
.DataFrame({
{
const df = pl.DataFrame({
a: pl.Series([1, 2, 3]).cast(pl.Int32),
"1": pl.Series([[1, 1], null, null]).cast(pl.List(pl.Int32)),
"2": pl.Series([null, [2, 2], null]).cast(pl.List(pl.Int32)),
"3": pl.Series([null, null, [3, 3]]).cast(pl.List(pl.Int32)),
})
.select("a", "1", "2", "3");
b: pl
.Series([
[1, 1],
[2, 2],
[3, 3],
])
.cast(pl.List(pl.Int32)),
});

let actual = df.pivot("b", {
index: "a",
on: "a",
aggregateFunc: "first",
sortColumns: true,
});
const expected = pl
.DataFrame({
a: pl.Series([1, 2, 3]).cast(pl.Int32),
"1": pl.Series([[1, 1], null, null]).cast(pl.List(pl.Int32)),
"2": pl.Series([null, [2, 2], null]).cast(pl.List(pl.Int32)),
"3": pl.Series([null, null, [3, 3]]).cast(pl.List(pl.Int32)),
})
.select("a", "1", "2", "3");

expect(actual).toFrameEqual(expected, true);
const actual = df.pivot("b", {
index: "a",
on: "a",
aggregateFunc: "first",
sortColumns: true,
});

df = pl.DataFrame({
a: ["beep", "bop"],
b: ["a", "b"],
c: ["s", "f"],
d: [7, 8],
e: ["x", "y"],
});
actual = df.pivot(["a", "e"], {
index: "b",
on: ["b"],
aggregateFunc: "first",
separator: "|",
maintainOrder: true,
});
expect(actual).toFrameEqual(expected, true);
}

expected = pl.DataFrame({
b: ["a", "b"],
"a|a": ["beep", null],
"a|b": [null, "bop"],
"e|a": ["x", null],
"e|b": [null, "y"],
});
expect(actual).toFrameEqual(expected, true);
{
const df = pl.DataFrame({
a: ["beep", "bop"],
b: ["a", "b"],
c: ["s", "f"],
d: [7, 8],
e: ["x", "y"],
});
const actual = df.pivot(["a", "e"], {
index: "b",
on: ["b"],
aggregateFunc: "first",
separator: "|",
maintainOrder: true,
});

df = pl.DataFrame({
foo: ["A", "A", "B", "B", "C"],
N: [1, 2, 2, 4, 2],
bar: ["k", "l", "m", "n", "o"],
});
actual = df.pivot(["N"], {
index: "foo",
on: "bar",
aggregateFunc: "first",
});
expected = pl.DataFrame({
foo: ["A", "B", "C"],
k: [1, null, null],
l: [2, null, null],
m: [null, 2, null],
n: [null, 4, null],
o: [null, null, 2],
});
expect(actual).toFrameEqual(expected, true);
const expected = pl.DataFrame({
b: ["a", "b"],
"a|a": ["beep", null],
"a|b": [null, "bop"],
"e|a": ["x", null],
"e|b": [null, "y"],
});
expect(actual).toFrameEqual(expected, true);
}
{
const df = pl.DataFrame({
foo: ["A", "A", "B", "B", "C"],
N: [1, 2, 2, 4, 2],
bar: ["k", "l", "m", "n", "o"],
});
const actual = df.pivot(["N"], {
index: "foo",
on: "bar",
aggregateFunc: "first",
});

df = pl.DataFrame({
ix: [1, 1, 2, 2, 1, 2],
col: ["a", "a", "a", "a", "b", "b"],
foo: [0, 1, 2, 2, 7, 1],
bar: [0, 2, 0, 0, 9, 4],
});
const expected = pl.DataFrame({
foo: ["A", "B", "C"],
k: [1, null, null],
l: [2, null, null],
m: [null, 2, null],
n: [null, 4, null],
o: [null, null, 2],
});

actual = df.pivot(["foo", "bar"], {
index: "ix",
on: "col",
aggregateFunc: "sum",
separator: "/",
});
expect(actual).toFrameEqual(expected, true);
}
{
const df = pl.DataFrame({
ix: [1, 1, 2, 2, 1, 2],
col: ["a", "a", "a", "a", "b", "b"],
foo: [0, 1, 2, 2, 7, 1],
bar: [0, 2, 0, 0, 9, 4],
});

expected = pl.DataFrame({
ix: [1, 2],
"foo/a": [1, 4],
"foo/b": [7, 1],
"bar/a": [2, 0],
"bar/b": [9, 4],
});
expect(actual).toFrameEqual(expected, true);
const actual = df.pivot(["foo", "bar"], {
index: "ix",
on: "col",
aggregateFunc: "sum",
separator: "/",
});

const expected = pl.DataFrame({
ix: [1, 2],
"foo/a": [1, 4],
"foo/b": [7, 1],
"bar/a": [2, 0],
"bar/b": [9, 4],
});
expect(actual).toFrameEqual(expected, true);
}
});
});
describe("join", () => {
Expand Down
Loading