Upgrading to rs 0.41.3 (#238)

Upgrading to rs-0.41.3
pola-rs · Jul 9, 2024 · 67285ed · 67285ed
1 parent 5e20abc
commit 67285ed
Show file tree

Hide file tree

Showing 20 changed files with 414 additions and 219 deletions.
diff --git a/.github/workflows/docs.yaml b/.github/workflows/docs.yaml
@@ -14,7 +14,7 @@ jobs:
       - name: Install latest Rust nightly
         uses: dtolnay/rust-toolchain@stable
         with:
-          toolchain: nightly-2024-05-14
+          toolchain: nightly-2024-06-23
           components: rustfmt, clippy
       - name: Install ghp-import
         uses: actions/setup-python@v5

diff --git a/.github/workflows/test-js.yaml b/.github/workflows/test-js.yaml
@@ -20,7 +20,7 @@ jobs:
       - name: Install latest Rust nightly
         uses: dtolnay/rust-toolchain@stable
         with:
-          toolchain: nightly-2024-05-14
+          toolchain: nightly-2024-06-23
           components: rustfmt, clippy
       - name: Check yarn version
         run: yarn --version
@@ -46,7 +46,7 @@ jobs:
       - name: Install latest Rust nightly
         uses: dtolnay/rust-toolchain@stable
         with:
-          toolchain: nightly-2024-05-14
+          toolchain: nightly-2024-06-23
           components: rustfmt, clippy
       - name: Bun version
         uses: oven-sh/setup-bun@v1

diff --git a/Cargo.toml b/Cargo.toml
@@ -15,18 +15,18 @@ crate-type = ["cdylib", "lib"]
 [dependencies]
 ahash = "0.8.11"
 bincode = "1.3.3"
-napi = { version = "2.16.6", default-features = false, features = [
+napi = { version = "2.16.8", default-features = false, features = [
     "napi8",
     "serde-json",
 ] }
-napi-derive = { version = "2.16.5", default-features = false }
-polars-core = { git = "https://github.com/pola-rs/polars.git", rev = "7bc70141f4dad7863a2026849522551abb274f00", default-features = false }
-polars-io = { git = "https://github.com/pola-rs/polars.git", rev = "7bc70141f4dad7863a2026849522551abb274f00", default-features = false }
-polars-lazy = { git = "https://github.com/pola-rs/polars.git", rev = "7bc70141f4dad7863a2026849522551abb274f00", default-features = false }
+napi-derive = { version = "2.16.8", default-features = false }
+polars-core = { git = "https://github.com/pola-rs/polars.git", rev = "91a423fea2dc067837db65c3608e3cbc1112a6fc", default-features = false }
+polars-io = { git = "https://github.com/pola-rs/polars.git", rev = "91a423fea2dc067837db65c3608e3cbc1112a6fc", default-features = false }
+polars-lazy = { git = "https://github.com/pola-rs/polars.git", rev = "91a423fea2dc067837db65c3608e3cbc1112a6fc", default-features = false }
 thiserror = "1"
 smartstring = { version = "1" }
 serde_json = { version = "1" }
-either = "1.11.0"
+either = "1.13.0"
 
 [dependencies.polars]
 features = [
@@ -161,7 +161,7 @@ features = [
   "azure"
 ]
 git = "https://github.com/pola-rs/polars.git"
-rev = "7bc70141f4dad7863a2026849522551abb274f00"
+rev = "91a423fea2dc067837db65c3608e3cbc1112a6fc"
 
 [build-dependencies]
 napi-build = "2.1.3"

diff --git a/__tests__/dataframe.test.ts b/__tests__/dataframe.test.ts
@@ -1324,7 +1324,7 @@ describe("dataframe", () => {
 
     let actual = df.pivot("b", {
       index: "a",
-      columns: "a",
+      on: "a",
       aggregateFunc: "first",
       sortColumns: true,
     });
@@ -1340,18 +1340,18 @@ describe("dataframe", () => {
     });
     actual = df.pivot(["a", "e"], {
       index: "b",
-      columns: ["c"],
+      on: ["b"],
       aggregateFunc: "first",
       separator: "|",
       maintainOrder: true,
     });
 
     expected = pl.DataFrame({
       b: ["a", "b"],
-      "a|c|s": ["beep", null],
-      "a|c|f": [null, "bop"],
-      "e|c|s": ["x", null],
-      "e|c|f": [null, "y"],
+      "a|a": ["beep", null],
+      "a|b": [null, "bop"],
+      "e|a": ["x", null],
+      "e|b": [null, "y"],
     });
     expect(actual).toFrameEqual(expected, true);
   });
@@ -1529,7 +1529,7 @@ describe("join", () => {
     });
     expect(actual).toFrameEqual(expected);
   });
-  test("how:outer", () => {
+  test("how:full", () => {
     const df = pl.DataFrame({
       foo: [1, 2, 3],
       bar: [6.0, 7.0, 8.0],
@@ -1542,7 +1542,7 @@ describe("join", () => {
     });
     const actual = df.join(otherDF, {
       on: "ham",
-      how: "outer",
+      how: "full",
     });
     const expected = pl.DataFrame({
       foo: [1, 2, 3, null],
@@ -2523,7 +2523,7 @@ describe("additional", () => {
       .sort("date");
 
     let actual = df
-      .upsample("date", "1mo", "0ns", "groups", true)
+      .upsample("date", "1mo", "groups", true)
       .select(pl.col("*").forwardFill());
 
     let expected = pl
@@ -2548,7 +2548,6 @@ describe("additional", () => {
       .upsample({
         timeColumn: "date",
         every: "1mo",
-        offset: "0ns",
         by: "groups",
         maintainOrder: true,
       })

diff --git a/__tests__/expr.test.ts b/__tests__/expr.test.ts
@@ -917,7 +917,7 @@ describe("expr", () => {
     const actual = df.select(col("a").tail(3).as("tail3"));
     expect(actual).toFrameEqual(expected);
   });
-  test.skip("take", () => {
+  test("take", () => {
     const df = pl.DataFrame({ a: [1, 2, 2, 3, 3, 8, null, 1] });
     const expected = pl.DataFrame({
       "take:array": [1, 2, 3, 8],
@@ -1187,7 +1187,10 @@ describe("expr.str", () => {
     });
     expect(actual).toFrameEqual(expected);
     actual = df.withColumns(
-      pl.col("a").replace([2, 3], [100, 200], -1, pl.Float64).alias("replaced"),
+      pl
+        .col("a")
+        .replaceStrict([2, 3], [100, 200], -1, pl.Float64)
+        .alias("replaced"),
     );
     expected = pl.DataFrame({
       a: [1, 2, 2, 3],
@@ -1196,7 +1199,7 @@ describe("expr.str", () => {
     });
     expect(actual).toFrameEqual(expected);
     actual = df.withColumns(
-      pl.col("b").replace("a", "c", "e", pl.Utf8).alias("replaced"),
+      pl.col("b").replaceStrict("a", "c", "e", pl.Utf8).alias("replaced"),
     );
     expected = pl.DataFrame({
       a: [1, 2, 2, 3],
@@ -1207,7 +1210,7 @@ describe("expr.str", () => {
     actual = df.withColumns(
       pl
         .col("b")
-        .replace(["a", "b"], ["c", "d"], "e", pl.Utf8)
+        .replaceStrict(["a", "b"], ["c", "d"], "e", pl.Utf8)
         .alias("replaced"),
     );
     expected = pl.DataFrame({
@@ -1220,7 +1223,7 @@ describe("expr.str", () => {
     actual = df.withColumns(
       pl
         .col("a")
-        .replace({ old: mapping, default_: -1, returnDtype: pl.Int64 })
+        .replaceStrict({ old: mapping, default_: -1, returnDtype: pl.Int64 })
         .alias("replaced"),
     );
     expected = pl.DataFrame({

diff --git a/__tests__/lazyframe.test.ts b/__tests__/lazyframe.test.ts
@@ -579,7 +579,7 @@ describe("lazyframe", () => {
       });
       expect(actual).toFrameEqualIgnoringOrder(expected);
     });
-    test("how:outer", () => {
+    test("how:full", () => {
       const df = pl.DataFrame({
         foo: [1, 2, 3],
         bar: [6.0, 7.0, 8.0],
@@ -597,7 +597,7 @@ describe("lazyframe", () => {
         .lazy()
         .join(otherDF, {
           on: "ham",
-          how: "outer",
+          how: "full",
         })
         .collectSync();
       const expected = pl.DataFrame({

diff --git a/__tests__/series.test.ts b/__tests__/series.test.ts
@@ -600,7 +600,7 @@ describe("series", () => {
     expect(actual).toFrameEqual(expected);
   });
   it("series:valueCounts", () => {
-    const actual = pl.Series("a", [1, 2, 2, 3]).valueCounts();
+    const actual = pl.Series("a", [1, 2, 2, 3]).valueCounts(true);
     const expected = pl.DataFrame({
       a: [2, 1, 3],
       count: [2, 1, 1],

diff --git a/package.json b/package.json
@@ -45,7 +45,7 @@
     "build:ts": " rm -rf bin; tsc -p tsconfig.build.json",
     "cp:bin": "cp ./polars/*.node bin/",
     "format:rs": "cargo fmt",
-    "lint:ts:fix": "biome check --apply-unsafe  {polars,__tests__} && biome format --write {polars,__tests__}",
+    "lint:ts:fix": "biome check --apply-unsafe {polars,__tests__} && biome format --write {polars,__tests__}",
     "lint:ts": "biome check {polars,__tests__} && biome format {polars,__tests__}",
     "lint": "yarn lint:ts && yarn format:rs",
     "prepublishOnly": "napi prepublish -t npm",
@@ -55,17 +55,17 @@
   },
   "devDependencies": {
     "@biomejs/biome": "=1.7.3",
-    "@napi-rs/cli": "^2.18.3",
+    "@napi-rs/cli": "^2.18.4",
     "@types/chance": "^1.1.6",
     "@types/jest": "^29.5.12",
-    "@types/node": "^20.12.12",
+    "@types/node": "^20.14.9",
     "chance": "^1.1.11",
     "jest": "^29.7.0",
     "source-map-support": "^0.5.21",
-    "ts-jest": "^29.1.3",
+    "ts-jest": "^29.1.5",
     "ts-node": "^10.9.2",
-    "typedoc": "^0.25.13",
-    "typescript": "5.4.5"
+    "typedoc": "^0.26.3",
+    "typescript": "5.5.3"
   },
   "packageManager": "[email protected]",
   "workspaces": [

diff --git a/polars/dataframe.ts b/polars/dataframe.ts
@@ -913,12 +913,21 @@ export interface DataFrame
    * ```
    */
   median(): DataFrame;
+  /**
+   * Unpivot a DataFrame from wide to long format.
+   * @deprecated *since 0.13.0* use {@link unpivot}
+   */
+  melt(idVars: ColumnSelection, valueVars: ColumnSelection): DataFrame;
   /**
    * Unpivot DataFrame to long format.
    * ___
    *
    * @param idVars - Columns to use as identifier variables.
    * @param valueVars - Values to use as value variables.
+   * @param variableName - Name to give to the `variable` column. Defaults to "variable"
+   * @param valueName - Name to give to the `value` column. Defaults to "value"
+   * @param streamable - Allow this node to run in the streaming engine.
+                         If this runs in streaming, the output of the unpivot operation will not have a stable ordering.
    * @example
    * ```
    * > const df1 = pl.DataFrame({
@@ -927,7 +936,7 @@ export interface DataFrame
    * ...   'asset_key_2': ['456'],
    * ...   'asset_key_3': ['abc'],
    * ... });
-   * > df1.melt('id', ['asset_key_1', 'asset_key_2', 'asset_key_3']);
+   * > df1.unpivot('id', ['asset_key_1', 'asset_key_2', 'asset_key_3']);
    * shape: (3, 3)
    * ┌─────┬─────────────┬───────┐
    * │ id  ┆ variable    ┆ value │
@@ -942,7 +951,7 @@ export interface DataFrame
    * └─────┴─────────────┴───────┘
    * ```
    */
-  melt(idVars: ColumnSelection, valueVars: ColumnSelection): DataFrame;
+  unpivot(idVars: ColumnSelection, valueVars: ColumnSelection): DataFrame;
   /**
    * Aggregate the columns of this DataFrame to their minimum value.
    * ___
@@ -1051,7 +1060,7 @@ export interface DataFrame
     values: string | string[],
     options: {
       index: string | string[];
-      columns: string | string[];
+      on: string | string[];
       aggregateFunc?:
         | "sum"
         | "max"
@@ -1070,7 +1079,7 @@ export interface DataFrame
   pivot(options: {
     values: string | string[];
     index: string | string[];
-    columns: string | string[];
+    on: string | string[];
     aggregateFunc?:
       | "sum"
       | "max"
@@ -1750,7 +1759,6 @@ export interface DataFrame
     @param timeColumn Time column will be used to determine a date range.
                         Note that this column has to be sorted for the output to make sense.
     @param every Interval will start 'every' duration.
-    @param offset Change the start of the date range by this offset.
     @param by First group by these columns and then upsample for every group.
     @param maintainOrder Keep the ordering predictable. This is slower.
 
@@ -1776,7 +1784,7 @@ export interface DataFrame
           .withColumn(pl.col("date").cast(pl.Date).alias("date"))
           .sort("date");
 
-    >>> df.upsample({timeColumn: "date", every: "1mo", offset: "0ns", by: "groups", maintainOrder: true})
+    >>> df.upsample({timeColumn: "date", every: "1mo", by: "groups", maintainOrder: true})
           .select(pl.col("*").forwardFill());
 shape: (7, 3)
 ┌────────────┬────────┬────────┐
@@ -1796,14 +1804,12 @@ shape: (7, 3)
   upsample(
     timeColumn: string,
     every: string,
-    offset?: string,
     by?: string | string[],
     maintainOrder?: boolean,
   ): DataFrame;
   upsample(opts: {
     timeColumn: string;
     every: string;
-    offset?: string;
     by?: string | string[];
     maintainOrder?: boolean;
   }): DataFrame;
@@ -2070,14 +2076,13 @@ export const _DataFrame = (_df: any): DataFrame => {
         by,
       );
     },
-    upsample(opts, every?, offset?, by?, maintainOrder?) {
+    upsample(opts, every?, by?, maintainOrder?) {
       let timeColumn;
       if (typeof opts === "string") {
         timeColumn = opts;
       } else {
         timeColumn = opts.timeColumn;
         by = opts.by;
-        offset = opts.offset;
         every = opts.every;
         maintainOrder = opts.maintainOrder ?? false;
       }
@@ -2088,11 +2093,7 @@ export const _DataFrame = (_df: any): DataFrame => {
         by = by ?? [];
       }
 
-      offset = offset ?? "0ns";
-
-      return _DataFrame(
-        _df.upsample(by, timeColumn, every, offset, maintainOrder),
-      );
+      return _DataFrame(_df.upsample(by, timeColumn, every, maintainOrder));
     },
     hashRows(obj: any = 0n, k1 = 1n, k2 = 2n, k3 = 3n) {
       if (typeof obj === "number" || typeof obj === "bigint") {
@@ -2174,7 +2175,10 @@ export const _DataFrame = (_df: any): DataFrame => {
       return this.lazy().median().collectSync();
     },
     melt(ids, values) {
-      return wrap("melt", columnOrColumns(ids), columnOrColumns(values));
+      return wrap("unpivot", columnOrColumns(ids), columnOrColumns(values));
+    },
+    unpivot(ids, values) {
+      return wrap("unpivot", columnOrColumns(ids), columnOrColumns(values));
     },
     min(axis = 0) {
       if (axis === 1) {
@@ -2198,7 +2202,7 @@ export const _DataFrame = (_df: any): DataFrame => {
       let {
         values: values_,
         index,
-        columns,
+        on,
         maintainOrder = true,
         sortColumns = false,
         aggregateFunc = "first",
@@ -2207,7 +2211,7 @@ export const _DataFrame = (_df: any): DataFrame => {
       values = values_ ?? values;
       values = typeof values === "string" ? [values] : values;
       index = typeof index === "string" ? [index] : index;
-      columns = typeof columns === "string" ? [columns] : columns;
+      on = typeof on === "string" ? [on] : on;
 
       let fn: Expr;
       if (Expr.isExpr(aggregateFunc)) {
@@ -2234,7 +2238,7 @@ export const _DataFrame = (_df: any): DataFrame => {
         _df.pivotExpr(
           values,
           index,
-          columns,
+          on,
           fn,
           maintainOrder,
           sortColumns,