Huge News!Announcing our $40M Series B led by Abstract Ventures.Learn More →
Socket
Sign inDemoInstall
Socket
Sign inDemoInstall

nodejs-polars

Package Overview
Dependencies
Maintainers
2
Versions
45
Alerts
File Explorer

Advanced tools

License
Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

nodejs-polars - npm Package Compare versions

Comparing version 0.8.4 to 0.9.0

41

bin/dataframe.js

@@ -224,2 +224,23 @@ "use strict";

},
upsample(opts, every, offset, 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;
}
if (typeof by === "string") {
by = [by];
}
else {
by = by ?? [];
}
offset = offset ?? "0ns";
return (0, exports._DataFrame)(_df.upsample(by, timeColumn, every, offset, maintainOrder));
},
hashRows(obj = 0n, k1 = 1n, k2 = 2n, k3 = 3n) {

@@ -281,3 +302,3 @@ if (typeof obj === "number" || typeof obj === "bigint") {

}
return wrap("max");
return this.lazy().max().collectSync();
},

@@ -288,6 +309,6 @@ mean(axis = 0, nullStrategy = "ignore") {

}
return wrap("mean");
return this.lazy().mean().collectSync();
},
median() {
return wrap("median");
return this.lazy().median().collectSync();
},

@@ -301,3 +322,3 @@ melt(ids, values) {

}
return wrap("min");
return this.lazy().min().collectSync();
},

@@ -310,3 +331,3 @@ nChunks() {

},
partitionBy(by, strict = false, includeKey, mapFn = (df) => df) {
partitionBy(by, strict = false, includeKey = true, mapFn = (df) => df) {
by = Array.isArray(by) ? by : [by];

@@ -346,4 +367,4 @@ return _df

},
quantile(quantile, interpolation = "nearest") {
return wrap("quantile", quantile, interpolation);
quantile(quantile) {
return this.lazy().quantile(quantile).collectSync();
},

@@ -432,3 +453,3 @@ rechunk() {

std() {
return wrap("std");
return this.lazy().std().collectSync();
},

@@ -439,3 +460,3 @@ sum(axis = 0, nullStrategy = "ignore") {

}
return wrap("sum");
return this.lazy().sum().collectSync();
},

@@ -612,3 +633,3 @@ tail: (length = 5) => wrap("tail", length),

var() {
return wrap("var");
return this.lazy().var().collectSync();
},

@@ -615,0 +636,0 @@ map: (fn) => map((0, exports._DataFrame)(_df), fn),

5

bin/datatypes/datatype.d.ts

@@ -62,2 +62,3 @@ import { Field } from "./field";

static get Utf8(): DataType;
static get String(): DataType;
toString(): string;

@@ -101,2 +102,4 @@ toJSON(): {

}
declare class _String extends DataType {
}
declare class _Categorical extends DataType {

@@ -178,2 +181,4 @@ }

type Utf8 = _Utf8;
/** Utf8 */
type String = _String;
/** Categorical */

@@ -180,0 +185,0 @@ type Categorical = _Categorical;

5

bin/datatypes/datatype.js

@@ -100,2 +100,5 @@ "use strict";

}
static get String() {
return new _String();
}
toString() {

@@ -160,2 +163,4 @@ if (this.inner) {

}
class _String extends DataType {
}
class _Categorical extends DataType {

@@ -162,0 +167,0 @@ }

1

bin/datatypes/index.d.ts

@@ -31,2 +31,3 @@ import { DataType, TimeUnit } from "./datatype";

Utf8: string;
String: string;
List: string;

@@ -33,0 +34,0 @@ Date: string;

4

bin/datatypes/index.js

@@ -29,2 +29,3 @@ "use strict";

Utf8: "Str",
String: "Str",
List: "List",

@@ -81,2 +82,5 @@ Date: "Date",

},
String(name, values, strict) {
return polars_internal_1.default.JsSeries.newOptStr(name, values, strict);
},
Categorical(name, values, strict) {

@@ -83,0 +87,0 @@ return polars_internal_1.default.JsSeries.newOptStr(name, values, strict);

1

bin/index.d.ts

@@ -43,2 +43,3 @@ import * as series from "./series";

export import Utf8 = DataType.Utf8;
export import String = DataType.String;
export import List = DataType.List;

@@ -45,0 +46,0 @@ export import Date = DataType.Date;

2

bin/index.js

@@ -75,2 +75,4 @@ "use strict";

pl.Utf8 = datatypes_1.DataType.Utf8;
// biome-ignore lint/suspicious/noShadowRestrictedNames: pl.String
pl.String = datatypes_1.DataType.String;
pl.List = datatypes_1.DataType.List;

@@ -77,0 +79,0 @@ // biome-ignore lint/suspicious/noShadowRestrictedNames: pl.Date

3

bin/io.d.ts

@@ -10,3 +10,2 @@ /// <reference types="node" />

nRows: number;
batchSize: number;
hasHeader: boolean;

@@ -18,2 +17,3 @@ ignoreErrors: boolean;

sep: string;
schema: Record<string, DataType>;
columns: string[];

@@ -77,2 +77,3 @@ rechunk: boolean;

* @param options.dtype -Overwrite the dtypes during inference.
* @param options.schema -Set the CSV file's schema. This only accepts datatypes that are implemented in the csv parser and expects a complete Schema.
* @param options.lowMemory - Reduce memory usage in expense of performance.

@@ -79,0 +80,0 @@ * @param options.commentChar - character that indicates the start of a comment line, for instance '#'.

102

bin/lazy/dataframe.d.ts

@@ -6,3 +6,3 @@ import { DataFrame } from "../dataframe";

import { Deserialize, GroupByOps, Serialize } from "../shared_traits";
import { LazyOptions, LazyJoinOptions } from "../types";
import { LazyOptions, LazyJoinOptions, SinkCsvOptions, SinkParquetOptions } from "../types";
import { Series } from "../series";

@@ -434,2 +434,102 @@ declare const inspect: unique symbol;

withRowCount(): any;
/***
*
* Evaluate the query in streaming mode and write to a CSV file.
.. warning::
Streaming mode is considered **unstable**. It may be changed
at any point without it being considered a breaking change.
This allows streaming results that are larger than RAM to be written to disk.
Parameters
----------
@param path - File path to which the file should be written.
@param includeBom - Whether to include UTF-8 BOM in the CSV output.
@param includeHeader - Whether to include header in the CSV output.
@param separator - Separate CSV fields with this symbol.
@param lineTerminator - String used to end each row.
@param quoteChar - Byte to use as quoting character.
@param batchSize - Number of rows that will be processed per thread. Default - 1024
@param datetimeFormat - A format string, with the specifiers defined by the
`chrono <https://docs.rs/chrono/latest/chrono/format/strftime/index.html>`_
Rust crate. If no format specified, the default fractional-second
precision is inferred from the maximum timeunit found in the frame's
Datetime cols (if any).
@param dateFormat - A format string, with the specifiers defined by the
`chrono <https://docs.rs/chrono/latest/chrono/format/strftime/index.html>`_
Rust crate.
@param timeFormat A format string, with the specifiers defined by the
`chrono <https://docs.rs/chrono/latest/chrono/format/strftime/index.html>`_
Rust crate.
@param floatPrecision - Number of decimal places to write, applied to both `Float32` and `Float64` datatypes.
@param nullValue - A string representing null values (defaulting to the empty string).
@param quoteStyle - Determines the quoting strategy used. : {'necessary', 'always', 'non_numeric', 'never'}
- necessary (default): This puts quotes around fields only when necessary.
They are necessary when fields contain a quote,
delimiter or record terminator.
Quotes are also necessary when writing an empty record
(which is indistinguishable from a record with one empty field).
This is the default.
- always: This puts quotes around every field. Always.
- never: This never puts quotes around fields, even if that results in
invalid CSV data (e.g.: by not quoting strings containing the
separator).
- non_numeric: This puts quotes around all fields that are non-numeric.
Namely, when writing a field that does not parse as a valid float
or integer, then quotes will be used even if they aren`t strictly
necessary.
@param maintainOrder - Maintain the order in which data is processed.
Setting this to `False` will be slightly faster.
Examples
--------
>>> const lf = pl.scanCsv("/path/to/my_larger_than_ram_file.csv")
>>> lf.sinkCsv("out.csv")
*/
sinkCSV(path: string, options?: SinkCsvOptions): void;
/***
*
* Evaluate the query in streaming mode and write to a Parquet file.
.. warning::
Streaming mode is considered **unstable**. It may be changed
at any point without it being considered a breaking change.
This allows streaming results that are larger than RAM to be written to disk.
Parameters
----------
@param path - File path to which the file should be written.
@param compression : {'lz4', 'uncompressed', 'snappy', 'gzip', 'lzo', 'brotli', 'zstd'}
Choose "zstd" for good compression performance. (default)
Choose "lz4" for fast compression/decompression.
Choose "snappy" for more backwards compatibility guarantees
when you deal with older parquet readers.
@param compressionLevel - The level of compression to use. Higher compression means smaller files on disk.
- "gzip" : min-level: 0, max-level: 10.
- "brotli" : min-level: 0, max-level: 11.
- "zstd" : min-level: 1, max-level: 22.
@param statistics - Write statistics to the parquet headers. This requires extra compute. Default - false
@param rowGroupSize - Size of the row groups in number of rows.
If None (default), the chunks of the `DataFrame` are
used. Writing in smaller chunks may reduce memory pressure and improve
writing speeds.
@param dataPagesizeLimit - Size limit of individual data pages.
If not set defaults to 1024 * 1024 bytes
@param maintainOrder - Maintain the order in which data is processed. Default -> true
Setting this to `False` will be slightly faster.
@param typeCoercion - Do type coercion optimization. Default -> true
@param predicatePushdown - Do predicate pushdown optimization. Default -> true
@param projectionPushdown - Do projection pushdown optimization. Default -> true
@param simplifyExpression - Run simplify expressions optimization. Default -> true
@param slicePushdown - Slice pushdown optimization. Default -> true
@param noOptimization - Turn off (certain) optimizations. Default -> false
Examples
--------
>>> const lf = pl.scanCsv("/path/to/my_larger_than_ram_file.csv") # doctest: +SKIP
>>> lf.sinkParquet("out.parquet") # doctest: +SKIP
*/
sinkParquet(path: string, options?: SinkParquetOptions): void;
}

@@ -436,0 +536,0 @@ /** @ignore */

8

bin/lazy/dataframe.js

@@ -345,2 +345,10 @@ "use strict";

},
sinkCSV(path, options = {}) {
options.maintainOrder = options.maintainOrder ?? false;
_ldf.sinkCsv(path, options);
},
sinkParquet(path, options = {}) {
options.compression = options.compression ?? "zstd";
_ldf.sinkParquet(path, options);
},
};

@@ -347,0 +355,0 @@ };

43

bin/lazy/expr/index.d.ts

@@ -49,6 +49,6 @@ import * as dt from "./datetime";

* ```
* > df = pl.DataFrame({
* > const df = pl.DataFrame({
* ... "a": [1, 2, 3],
* ... "b": ["a", "b", None],
* ... })
* ... });
* > df

@@ -136,8 +136,8 @@ * shape: (3, 2)

* ```
* >df = pl.DataFrame({
* > const df = pl.DataFrame({
* ... "a": [1, 2, 3],
* ... "b": ["a", "b", None],
* ... "c": [None, 2, 1],
* ...})
* >df
* ...});
* > df
* shape: (3, 3)

@@ -155,5 +155,5 @@ * ╭─────┬──────┬──────╮

* ╰─────┴──────┴──────╯
* >df.select(
* > df.select(
* ... pl.col("*").exclude("b"),
* ... )
* ... );
* shape: (3, 2)

@@ -249,9 +249,9 @@ * ╭─────┬──────╮

* ```
* > df = pl.DataFrame({
* > const df = pl.DataFrame({
* ... "sets": [[1, 2, 3], [1, 2], [9, 10]],
* ... "optional_members": [1, 2, 3]
* ... })
* ... });
* > df.select(
* ... pl.col("optional_members").isIn("sets").alias("contains")
* ... )
* ... );
* shape: (3, 1)

@@ -291,6 +291,6 @@ * ┌──────────┐

* ```
* > df = pl.DataFrame({
* > const df = pl.DataFrame({
* ... "a": [1, 2, 3],
* ... "b": ["a", "b", None],
* ... })
* ... });
*

@@ -300,3 +300,3 @@ * > df

* ... .agg(pl.col("b").list())
* ... .sort({by:"a"})
* ... .sort({by:"a"});
*

@@ -376,9 +376,9 @@ * shape: (3, 2)

* ```
* > df = pl.DataFrame({
* > const df = pl.DataFrame({
* ... "groups": [1, 1, 2, 2, 1, 2, 3, 3, 1],
* ... "values": [1, 2, 3, 4, 5, 6, 7, 8, 8],
* ... })
* ... });
* > df.select(
* ... pl.col("groups").sum().over("groups")
* ... )
* ... );
* ╭────────┬────────╮

@@ -421,3 +421,3 @@ * │ groups ┆ values │

* ```
* > df = pl.DataFrame({
* > const df = pl.DataFrame({
* ... "A": [1, 2, 3, 4, 5],

@@ -427,3 +427,3 @@ * ... "fruits": ["banana", "banana", "apple", "apple", "banana"],

* ... "cars": ["beetle", "audi", "beetle", "beetle", "beetle"],
* ... })
* ... });
* shape: (5, 4)

@@ -446,3 +446,3 @@ * ╭─────┬──────────┬─────┬──────────╮

* > df.select(
* ... pl.all().reverse().prefix("reverse_"),
* ... pl.col("*").reverse().prefix("reverse_"),
* ... )

@@ -544,4 +544,3 @@ * shape: (5, 8)

----------
@param by
The column(s) used for sorting.
@param by The column(s) used for sorting.
@param reverse

@@ -580,3 +579,3 @@ false -> order from small to large.

/** Take every nth value in the Series and return as a new Series. */
gatherEvery(n: number): Expr;
gatherEvery(n: number, offset?: number): Expr;
/**

@@ -583,0 +582,0 @@ * Get the unique values of this expression;

12

bin/lazy/expr/index.js

@@ -37,2 +37,3 @@ "use strict";

const series_1 = require("../../series");
const types_1 = require("util/types");
const _Expr = (_expr) => {

@@ -388,3 +389,3 @@ const unwrap = (method, ...args) => {

rollingMedian: rolling("rollingMedian"),
rollingQuantile(val, interpolation, windowSize, weights, minPeriods, center, by, closedWindow) {
rollingQuantile(val, interpolation, windowSize, weights, minPeriods, center, by, closedWindow, warnIfUnsorted) {
if (typeof val === "number") {

@@ -403,3 +404,3 @@ return wrap("rollingQuantile", {

}
return wrap("rollingQuantile", val.quantile, val.interpolation ?? "nearest", `${windowSize}i`, val?.["weights"] ?? weights ?? null, val?.["minPeriods"] ?? minPeriods ?? windowSize, val?.["center"] ?? center ?? false, val?.["by"] ?? by, val?.["closedWindow"] ?? closedWindow ?? "left");
return wrap("rollingQuantile", val.quantile, val.interpolation ?? "nearest", `${windowSize}i`, val?.["weights"] ?? weights ?? null, val?.["minPeriods"] ?? minPeriods ?? windowSize, val?.["center"] ?? center ?? false, val?.["by"] ?? by, val?.["closedWindow"] ?? closedWindow ?? "left", val?.["warnIfUnsorted"] ?? warnIfUnsorted ?? true);
},

@@ -480,4 +481,4 @@ rollingSkew(val, bias = true) {

},
gatherEvery(n) {
return (0, exports._Expr)(_expr.gatherEvery(n));
gatherEvery(n, offset = 0) {
return (0, exports._Expr)(_expr.gatherEvery(n, offset));
},

@@ -540,2 +541,5 @@ unique(opt) {

const exprToLitOrExpr = (expr, stringToLit = true) => {
if ((0, types_1.isRegExp)(expr)) {
return (0, exports._Expr)(polars_internal_1.default.lit((0, utils_1.regexToString)(expr)));
}
if (typeof expr === "string" && !stringToLit) {

@@ -542,0 +546,0 @@ return (0, exports._Expr)(polars_internal_1.default.col(expr));

13

bin/lazy/expr/list.js

@@ -66,4 +66,13 @@ "use strict";

},
join(separator = ",") {
return wrap("listJoin", (0, expr_1.exprToLitOrExpr)(separator)._expr);
join(options) {
if (typeof options === "string") {
options = { separator: options };
}
options = options ?? {};
let separator = options?.separator ?? ",";
const ignoreNulls = options?.ignoreNulls ?? false;
if (!expr_1.Expr.isExpr(separator)) {
separator = polars_internal_1.default.lit(separator);
}
return wrap("listJoin", separator, ignoreNulls);
},

@@ -70,0 +79,0 @@ last() {

31

bin/lazy/expr/string.d.ts

@@ -110,3 +110,3 @@ import { StringFunctions } from "../../shared_traits";

*/
extract(pat: string | RegExp, groupIndex: number): Expr;
extract(pat: any, groupIndex: number): Expr;
/**

@@ -117,2 +117,3 @@ * Parse string values as JSON.

* @returns DF with struct
* @deprecated @since 0.8.4 @use {@link jsonDecode}
* @example

@@ -138,2 +139,26 @@

/**
* Parse string values as JSON.
* Throw errors if encounter invalid JSON strings.
* @params Not implemented ATM
* @returns DF with struct
* @example
* >>> df = pl.DataFrame( {json: ['{"a":1, "b": true}', null, '{"a":2, "b": false}']} )
* >>> df.select(pl.col("json").str.jsonDecode())
* shape: (3, 1)
* ┌─────────────┐
* │ json │
* │ --- │
* │ struct[2] │
* ╞═════════════╡
* │ {1,true} │
* │ {null,null} │
* │ {2,false} │
* └─────────────┘
* See Also
* ----------
* jsonPathMatch : Extract the first match of json string with provided JSONPath expression.
*/
jsonDecode(dtype?: DataType, inferSchemaLength?: number): Expr;
/**
* Extract the first match of json string with provided JSONPath expression.

@@ -249,3 +274,3 @@ * Throw errors if encounter invalid json strings.

*/
zFill(length: number): Expr;
zFill(length: number | Expr): Expr;
/**

@@ -289,3 +314,3 @@ * Add a trailing fillChar to a string until string length is reached.

*/
slice(start: number, length?: number): Expr;
slice(start: number | Expr, length?: number | Expr): Expr;
/**

@@ -292,0 +317,0 @@ * Split a string into substrings using the specified separator and return them as a Series.

19

bin/lazy/expr/string.js

@@ -7,2 +7,3 @@ "use strict";

const expr_1 = require("../expr");
const functions_1 = require("../functions");
const ExprStringFunctions = (_expr) => {

@@ -46,7 +47,10 @@ const wrap = (method, ...args) => {

extract(pat, groupIndex) {
return wrap("strExtract", (0, utils_1.regexToString)(pat), groupIndex);
return wrap("strExtract", (0, expr_1.exprToLitOrExpr)(pat, true)._expr, groupIndex);
},
jsonExtract(dtype, inferSchemaLength) {
return wrap("strJsonExtract", dtype, inferSchemaLength);
return wrap("strJsonDecode", dtype, inferSchemaLength);
},
jsonDecode(dtype, inferSchemaLength) {
return wrap("strJsonDecode", dtype, inferSchemaLength);
},
jsonPathMatch(pat) {

@@ -74,3 +78,6 @@ return wrap("strJsonPathMatch", pat);

zFill(length) {
return wrap("strZFill", length);
if (!expr_1.Expr.isExpr(length)) {
length = (0, functions_1.lit)(length)._expr;
}
return wrap("zfill", length);
},

@@ -81,2 +88,8 @@ padEnd(length, fillChar) {

slice(start, length) {
if (!expr_1.Expr.isExpr(start)) {
start = (0, functions_1.lit)(start)._expr;
}
if (!expr_1.Expr.isExpr(length)) {
length = (0, functions_1.lit)(length)._expr;
}
return wrap("strSlice", start, length);

@@ -83,0 +96,0 @@ },

12

bin/lazy/functions.d.ts

@@ -124,6 +124,7 @@ import { Expr } from "./expr";

step: number;
dtype: DataType;
eager?: boolean;
}): any;
export declare function intRange(low: any, high?: any, step?: number, eager?: true): Series;
export declare function intRange(low: any, high?: any, step?: number, eager?: false): Expr;
export declare function intRange(low: any, high?: any, step?: number, dtype?: DataType, eager?: true): Series;
export declare function intRange(low: any, high?: any, step?: number, dtype?: DataType, eager?: false): Expr;
/***

@@ -142,4 +143,4 @@ * Generate a range of integers for each row of the input columns.

*/
export declare function intRanges(start: any, end: any, step?: number, eager?: false): Expr;
export declare function intRanges(start: any, end: any, step?: number, eager?: true): Series;
export declare function intRanges(start: any, end: any, step?: number, dtype?: DataType, eager?: false): Expr;
export declare function intRanges(start: any, end: any, step?: number, dtype?: DataType, eager?: true): Series;
/** Alias for `pl.col("*")` */

@@ -184,4 +185,5 @@ export declare function all(): Expr;

sep: string;
ignoreNulls?: boolean;
}): any;
export declare function concatString(exprs: ExprOrString[], sep?: string): any;
export declare function concatString(exprs: ExprOrString[], sep?: string, ignoreNulls?: boolean): any;
/** Count the number of values in this column. */

@@ -188,0 +190,0 @@ export declare function count(column: string): Expr;

20

bin/lazy/functions.js

@@ -8,2 +8,3 @@ "use strict";

const expr_1 = require("./expr");
const datatypes_1 = require("../datatypes");
const series_1 = require("../series");

@@ -133,5 +134,5 @@ const dataframe_1 = require("../dataframe");

exports.lit = lit;
function intRange(opts, high, step = 1, eager) {
function intRange(opts, high, step = 1, dtype = datatypes_1.DataType.Int64, eager) {
if (typeof opts?.low === "number") {
return intRange(opts.low, opts.high, opts.step, opts.eager);
return intRange(opts.low, opts.high, opts.step, opts.dtype, opts.eager);
}

@@ -146,15 +147,16 @@ const low = (0, expr_1.exprToLitOrExpr)(opts, false);

}
return (0, expr_1._Expr)(polars_internal_1.default.intRange(low, high, step, eager));
return (0, expr_1._Expr)(polars_internal_1.default.intRange(low, high, step, dtype));
}
exports.intRange = intRange;
function intRanges(start, end, step = 1, eager) {
function intRanges(start, end, step = 1, dtype = datatypes_1.DataType.Int64, eager) {
start = (0, expr_1.exprToLitOrExpr)(start, false);
end = (0, expr_1.exprToLitOrExpr)(end, false);
step = (0, expr_1.exprToLitOrExpr)(step, false);
if (eager) {
const df = (0, dataframe_1.DataFrame)({ a: [1] });
return df
.select(intRanges(start, end, step).alias("intRanges"))
.select(intRanges(start, end, step, dtype).alias("intRanges"))
.getColumn("intRanges");
}
return (0, expr_1._Expr)(polars_internal_1.default.intRanges(start, end, step, eager));
return (0, expr_1._Expr)(polars_internal_1.default.intRanges(start, end, step, dtype));
}

@@ -206,8 +208,8 @@ exports.intRanges = intRanges;

exports.concatList = concatList;
function concatString(opts, sep = ",") {
function concatString(opts, sep = ",", ignoreNulls = true) {
if (opts?.exprs) {
return concatString(opts.exprs, opts.sep);
return concatString(opts.exprs, opts.sep, opts.ignoreNulls);
}
const items = (0, utils_1.selectionToExprList)(opts, false);
return expr_1.Expr(polars_internal_1.default.concatStr(items, sep));
return expr_1.Expr(polars_internal_1.default.concatStr(items, sep, ignoreNulls));
}

@@ -214,0 +216,0 @@ exports.concatString = concatString;

46

bin/series/index.d.ts

@@ -455,5 +455,11 @@ import { DataType, Optional } from "../datatypes";

* Checks if this Series datatype is a Utf8.
* @deprecated *since 0.8.4*
* @see Use `Series.dtype.equals(pl.String)` instead.
*/
isUtf8(): boolean;
/**
* Checks if this Series datatype is a String.
*/
isString(): boolean;
/**
* __Compute the kurtosis (Fisher or Pearson) of a dataset.__

@@ -729,6 +735,13 @@ *

* @param value value to replace masked values with
* @deprecated @since 0.8.4 @use {@link scatter}
*/
set(filter: Series, value: any): Series;
setAtIdx(indices: number[] | Series, value: any): void;
/**
* __Set masked values__
* @param filter Boolean mask
* @param value value to replace masked values with
*/
set(filter: Series, value: any): Series;
scatter(indices: number[] | Series, value: any): void;
/**
* __Shift the values by a given period__

@@ -801,3 +814,4 @@ *

* __Sort this Series.__
* @param reverse - Reverse sort
* @param descending - Sort in descending order.
* @param nullsLast - Place nulls at the end.
* @example

@@ -815,3 +829,3 @@ * ```

* ]
* s.sort(true)
* s.sort({descending: true})
* shape: (4,)

@@ -828,5 +842,5 @@ * Series: 'a' [i64]

sort(): Series;
sort(reverse?: boolean): Series;
sort(options: {
reverse: boolean;
descending?: boolean;
nullsLast?: boolean;
}): Series;

@@ -864,3 +878,4 @@ /**

* Take every nth value in the Series and return as new Series.
* @param n - nth value to take
* @param n - Gather every *n*-th row
* @param offset - Start the row count at this offset
* @example

@@ -871,10 +886,17 @@ * ```

* shape: (2,)
* Series: '' [i64]
* Series: 'a' [i64]
* [
* 1
* 3
* 1
* 3
* ]
* s.gather_every(2, offset=1)
* shape: (2,)
* Series: 'a' [i64]
* [
* 2
* 4
* ]
* ```
*/
gatherEvery(n: number): Series;
gatherEvery(n: number, offset?: number): Series;
/**

@@ -919,2 +941,4 @@ * Take values by index.

* __Count the unique values in a Series.__
* @param sort - Sort the output by count in descending order.
* If set to `False` (default), the order of the output is random.
* ___

@@ -939,3 +963,3 @@ * @example

*/
valueCounts(): DataFrame;
valueCounts(sort?: boolean): DataFrame;
/**

@@ -942,0 +966,0 @@ * Where mask evaluates true, take values from self.

28

bin/series/index.js

@@ -187,3 +187,3 @@ "use strict";

}
else if (s.isUtf8()) {
else if (s.isString()) {
stats = {

@@ -359,2 +359,5 @@ unique: s.nUnique(),

},
isString() {
return this.dtype.equals(datatypes_1.DataType.String);
},
isUtf8() {

@@ -513,2 +516,5 @@ return this.dtype.equals(datatypes_1.DataType.Utf8);

setAtIdx(indices, value) {
_s.scatter(indices, value);
},
scatter(indices, value) {
indices = exports.Series.isSeries(indices)

@@ -526,3 +532,3 @@ ? indices.cast(datatypes_1.DataType.UInt32)

}
_s.setAtIdx(indices._s, value._s);
_s.scatter(indices._s, value._s);
},

@@ -580,7 +586,5 @@ set(mask, value) {

},
sort(reverse) {
if (typeof reverse === "boolean") {
return wrap("sort", reverse);
}
return wrap("sort", reverse?.reverse ?? false);
sort(options) {
options = { descending: false, nullsLast: false, ...(options ?? {}) };
return wrap("sort", options.descending, options.nullsLast);
},

@@ -599,4 +603,4 @@ sub(field) {

},
gatherEvery(n) {
return wrap("gatherEvery", n);
gatherEvery(n, offset) {
return wrap("gatherEvery", n, offset ?? 0);
},

@@ -637,4 +641,4 @@ multiplyBy(field) {

},
valueCounts() {
return null;
valueCounts(sorted) {
return (0, dataframe_1._DataFrame)(unwrap("valueCounts", sorted ?? false));
},

@@ -657,3 +661,3 @@ values() {

if (typeof prop !== "symbol" && !Number.isNaN(Number(prop))) {
series.setAtIdx([Number(prop)], input);
series.scatter([Number(prop)], input);
return true;

@@ -660,0 +664,0 @@ }

4

bin/series/list.js

@@ -47,4 +47,4 @@ "use strict";

},
join(separator = ",") {
return wrap("join", separator);
join(options) {
return wrap("join", options);
},

@@ -51,0 +51,0 @@ last() {

25

bin/series/string.d.ts

@@ -0,1 +1,2 @@

import { Expr } from "./../lazy/expr/index";
import { DataType } from "../datatypes";

@@ -95,9 +96,10 @@ import { Series } from ".";

*/
extract(pattern: string | RegExp, groupIndex: number): Series;
extract(pattern: any, groupIndex: number): Series;
/***
* Parse string values as JSON.
* @returns Utf8 array. Contain null if original value is null or the `jsonPath` return nothing.
* @deprecated @since 0.8.4 @use {@link jsonDecode}
* @example
* s = pl.Series("json", ['{"a":1, "b": true}', null, '{"a":2, "b": false}']);
* s.str.json_extract().as("json");
* s.str.jsonExtract().as("json");
* shape: (3,)

@@ -112,2 +114,17 @@ * Series: 'json' [struct[2]]

jsonExtract(dtype?: DataType, inferSchemaLength?: number): Series;
/***
* Parse string values as JSON.
* @returns Utf8 array. Contain null if original value is null or the `jsonPath` return nothing.
* @example
* s = pl.Series("json", ['{"a":1, "b": true}', null, '{"a":2, "b": false}']);
* s.str.jsonDecode().as("json");
* shape: (3,)
* Series: 'json' [struct[2]]
* [
* {1,true}
* {null,null}
* {2,false}
* ]
*/
jsonDecode(dtype?: DataType, inferSchemaLength?: number): Series;
/**

@@ -211,3 +228,3 @@ * Extract the first match of json string with provided JSONPath expression.

*/
zFill(length: number): Series;
zFill(length: number | Expr): Series;
/** Add trailing zeros */

@@ -240,3 +257,3 @@ padEnd(length: number, fillChar: string): Series;

*/
slice(start: number, length?: number): Series;
slice(start: number | Expr, length?: number | Expr): Series;
/**

@@ -243,0 +260,0 @@ * Split a string into substrings using the specified separator.

22

bin/series/string.js

@@ -49,7 +49,14 @@ "use strict";

extract(pat, groupIndex) {
return wrap("strExtract", (0, utils_1.regexToString)(pat), groupIndex);
const s = (0, _1._Series)(_s);
return s
.toFrame()
.select((0, functions_1.col)(s.name).str.extract(pat, groupIndex).as(s.name))
.getColumn(s.name);
},
jsonExtract(dtype, inferSchemaLength) {
return wrap("strJsonExtract", dtype, inferSchemaLength);
return wrap("strJsonDecode", dtype, inferSchemaLength);
},
jsonDecode(dtype, inferSchemaLength) {
return wrap("strJsonDecode", dtype, inferSchemaLength);
},
jsonPathMatch(pat) {

@@ -68,3 +75,6 @@ return wrap("strJsonPathMatch", pat);

zFill(length) {
return wrap("strZFill", length);
return (0, _1._Series)(_s)
.toFrame()
.select((0, functions_1.col)(_s.name).str.zFill(length).as(_s.name))
.getColumn(_s.name);
},

@@ -84,3 +94,7 @@ padEnd(length, fillChar) {

slice(start, length) {
return wrap("strSlice", start, length);
const s = (0, _1._Series)(_s);
return s
.toFrame()
.select((0, functions_1.col)(s.name).str.slice(start, length).as(s.name))
.getColumn(s.name);
},

@@ -87,0 +101,0 @@ split(by, options) {

8

bin/shared_traits.d.ts

@@ -614,5 +614,11 @@ /// <reference types="node" />

* If omitted, the list elements are separated with a comma.
* @param ignoreNulls - If true, null values will be ignored.
* @category List
*/
join(separator?: string): T;
join(): T;
join(separator: string | Expr): T;
join(options: {
separator?: string | Expr;
ignoreNulls?: boolean;
}): T;
/**

@@ -619,0 +625,0 @@ * Get the last value of the sublists.

37

bin/types.d.ts

@@ -29,2 +29,39 @@ /**

/**
* Options for @see {@link LazyDataFrame.sinkCSV}
* @category Options
*/
export interface SinkCsvOptions {
includeHeader?: boolean;
quote?: string;
includeBom?: boolean;
separator?: string;
lineTerminator?: string;
quoteChar?: string;
batchSize?: number;
datetimeFormat?: string;
dateFormat?: string;
timeFormat?: string;
floatPrecision?: number;
nullValue?: string;
maintainOrder?: boolean;
}
/**
* Options for @see {@link LazyDataFrame.sinkParquet}
* @category Options
*/
export interface SinkParquetOptions {
compression?: string;
compressionLevel?: number;
statistics?: boolean;
rowGroupSize?: number;
dataPagesizeLimit?: number;
maintainOrder?: boolean;
typeCoercion?: boolean;
predicatePushdown?: boolean;
projectionPushdown?: boolean;
simplifyExpression?: boolean;
slicePushdown?: boolean;
noOptimization?: boolean;
}
/**
* Options for {@link DataFrame.writeJSON}

@@ -31,0 +68,0 @@ * @category Options

30

package.json
{
"name": "nodejs-polars",
"version": "0.8.4",
"version": "0.9.0",
"repository": "https://github.com/pola-rs/nodejs-polars.git",

@@ -57,13 +57,13 @@ "license": "MIT",

"devDependencies": {
"@biomejs/biome": "^1.5.0",
"@napi-rs/cli": "^2.17.0",
"@biomejs/biome": "^1.5.3",
"@napi-rs/cli": "^2.18.0",
"@types/chance": "^1.1.6",
"@types/jest": "^29.5.11",
"@types/node": "^20.10.6",
"@types/jest": "^29.5.12",
"@types/node": "^20.11.17",
"chance": "^1.1.11",
"jest": "^29.7.0",
"source-map-support": "^0.5.21",
"ts-jest": "^29.1.1",
"ts-jest": "^29.1.2",
"ts-node": "^10.9.2",
"typedoc": "^0.25.6",
"typedoc": "^0.25.8",
"typescript": "5.3.3"

@@ -76,11 +76,11 @@ },

"optionalDependencies": {
"nodejs-polars-win32-x64-msvc": "0.8.4",
"nodejs-polars-darwin-x64": "0.8.4",
"nodejs-polars-linux-x64-gnu": "0.8.4",
"nodejs-polars-darwin-arm64": "0.8.4",
"nodejs-polars-linux-arm64-gnu": "0.8.4",
"nodejs-polars-linux-arm64-musl": "0.8.4",
"nodejs-polars-android-arm64": "0.8.4",
"nodejs-polars-linux-x64-musl": "0.8.4"
"nodejs-polars-win32-x64-msvc": "0.9.0",
"nodejs-polars-darwin-x64": "0.9.0",
"nodejs-polars-linux-x64-gnu": "0.9.0",
"nodejs-polars-darwin-arm64": "0.9.0",
"nodejs-polars-linux-arm64-gnu": "0.9.0",
"nodejs-polars-linux-arm64-musl": "0.9.0",
"nodejs-polars-android-arm64": "0.9.0",
"nodejs-polars-linux-x64-musl": "0.9.0"
}
}
bin/dataframe.d.ts

Sorry, the diff of this file is too big to display

SocketSocket SOC 2 Logo

Product

  • Package Alerts
  • Integrations
  • Docs
  • Pricing
  • FAQ
  • Roadmap
  • Changelog

About

Packages

npm

Go

Maven

PyPI

Rubygems

Stay in touch

Get open source security insights delivered straight into your inbox.

  • Terms
  • Privacy
  • Security

Made with ⚡️ by Socket Inc