polars-df 0.15.0 → 0.26.0

data/Cargo.toml

@@ -4,3 +4,6 @@ resolver = "2"
 
 [profile.release]
 strip = true
+
+[profile.dev]
+strip = true

data/LICENSE.txt

@@ -1,5 +1,5 @@
-Copyright (c) 2020 Ritchie Vink
-Copyright (c) 2022-2024 Andrew Kane
+Copyright (c) 2025 Ritchie Vink
+Copyright (c) 2022-2026 Andrew Kane
 Some portions Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 
 Permission is hereby granted, free of charge, to any person obtaining a copy

data/README.md

@@ -1,6 +1,6 @@
 # Ruby Polars
 
-:fire: Blazingly fast DataFrames for Ruby, powered by [Polars](https://github.com/pola-rs/polars)
+🔥 Blazingly fast DataFrames for Ruby, powered by [Polars](https://github.com/pola-rs/polars)
 
 [![Build Status](https://github.com/ankane/ruby-polars/actions/workflows/build.yml/badge.svg)](https://github.com/ankane/ruby-polars/actions)
 
@@ -14,7 +14,7 @@ gem "polars-df"
 
 ## Getting Started
 
-This library follows the [Polars Python API](https://pola-rs.github.io/polars/py-polars/html/reference/index.html).
+This library follows the [Polars Python API](https://docs.pola.rs/api/python/stable/reference/index.html).
 
 ```ruby
 Polars.scan_csv("iris.csv")
@@ -24,7 +24,7 @@ Polars.scan_csv("iris.csv")
   .collect
 ```
 
-You can follow [Polars tutorials](https://pola-rs.github.io/polars-book/user-guide/) and convert the code to Ruby in many cases. Feel free to open an issue if you run into problems.
+You can follow [Polars tutorials](https://docs.pola.rs/user-guide/getting-started/) and convert the code to Ruby in many cases. Feel free to open an issue if you run into problems.
 
 ## Reference
 
@@ -32,9 +32,7 @@ You can follow [Polars tutorials](https://pola-rs.github.io/polars-book/user-gui
 - [DataFrame](https://www.rubydoc.info/gems/polars-df/Polars/DataFrame)
 - [LazyFrame](https://www.rubydoc.info/gems/polars-df/Polars/LazyFrame)
 
-## Examples
-
-### Creating DataFrames
+## Creating DataFrames
 
 From a CSV
 
@@ -88,6 +86,21 @@ From Avro
 Polars.read_avro("file.avro")
 ```
 
+From Iceberg (experimental, requires [iceberg](https://github.com/ankane/iceberg-ruby))
+
+```ruby
+Polars.scan_iceberg(table)
+```
+
+From Delta Lake (experimental, requires [deltalake-rb](https://github.com/ankane/delta-ruby))
+
+```ruby
+Polars.read_delta("./table")
+
+# or lazily with
+Polars.scan_delta("./table")
+```
+
 From a hash
 
 ```ruby
@@ -167,20 +180,20 @@ df.tail
 Filter on a condition
 
 ```ruby
-df[Polars.col("a") == 2]
-df[Polars.col("a") != 2]
-df[Polars.col("a") > 2]
-df[Polars.col("a") >= 2]
-df[Polars.col("a") < 2]
-df[Polars.col("a") <= 2]
+df.filter(Polars.col("a") == 2)
+df.filter(Polars.col("a") != 2)
+df.filter(Polars.col("a") > 2)
+df.filter(Polars.col("a") >= 2)
+df.filter(Polars.col("a") < 2)
+df.filter(Polars.col("a") <= 2)
 ```
 
 And, or, and exclusive or
 
 ```ruby
-df[(Polars.col("a") > 1) & (Polars.col("b") == "two")] # and
-df[(Polars.col("a") > 1) | (Polars.col("b") == "two")] # or
-df[(Polars.col("a") > 1) ^ (Polars.col("b") == "two")] # xor
+df.filter((Polars.col("a") > 1) & (Polars.col("b") == "two")) # and
+df.filter((Polars.col("a") > 1) | (Polars.col("b") == "two")) # or
+df.filter((Polars.col("a") > 1) ^ (Polars.col("b") == "two")) # xor
 ```
 
 ## Operations
@@ -225,9 +238,9 @@ Trigonometric functions
 df["a"].sin
 df["a"].cos
 df["a"].tan
-df["a"].asin
-df["a"].acos
-df["a"].atan
+df["a"].arcsin
+df["a"].arccos
+df["a"].arctan
 ```
 
 Hyperbolic functions
@@ -236,9 +249,9 @@ Hyperbolic functions
 df["a"].sinh
 df["a"].cosh
 df["a"].tanh
-df["a"].asinh
-df["a"].acosh
-df["a"].atanh
+df["a"].arcsinh
+df["a"].arccosh
+df["a"].arctanh
 ```
 
 Summary statistics
@@ -313,7 +326,7 @@ df.to_dummies
 Array of hashes
 
 ```ruby
-df.rows(named: true)
+df.to_a
 ```
 
 Hash of series
@@ -336,6 +349,38 @@ Parquet
 df.write_parquet("file.parquet")
 ```
 
+JSON
+
+```ruby
+df.write_json("file.json")
+# or
+df.write_ndjson("file.ndjson")
+```
+
+Feather / Arrow IPC
+
+```ruby
+df.write_ipc("file.arrow")
+```
+
+Avro
+
+```ruby
+df.write_avro("file.avro")
+```
+
+Iceberg (experimental)
+
+```ruby
+df.write_iceberg(table, mode: "append")
+```
+
+Delta Lake (experimental)
+
+```ruby
+df.write_delta("./table")
+```
+
 Numo array
 
 ```ruby
@@ -353,13 +398,14 @@ Polars::DataFrame.new(data, schema: {"a" => Polars::Int32, "b" => Polars::Float3
 Supported types are:
 
 - boolean - `Boolean`
-- float - `Float64`, `Float32`
-- integer - `Int64`, `Int32`, `Int16`, `Int8`
-- unsigned integer - `UInt64`, `UInt32`, `UInt16`, `UInt8`
-- string - `String`, `Binary`, `Categorical`
-- temporal - `Date`, `Datetime`, `Time`, `Duration`
-- nested -  `List`, `Struct`, `Array`
-- other - `Object`, `Null`
+- decimal - `Decimal`
+- float - `Float16`, `Float32`, `Float64`
+- integer - `Int8`, `Int16`, `Int32`, `Int64`, `Int128`
+- unsigned integer - `UInt8`, `UInt16`, `UInt32`, `UInt64`, `UInt128`
+- string - `String`, `Categorical`, `Enum`
+- temporal - `Date`, `Datetime`, `Duration`, `Time`
+- nested - `Array`, `List`, `Struct`
+- other - `Binary`, `Object`, `Null`, `Unknown`
 
 Get column types
 
@@ -390,30 +436,34 @@ gem "vega"
 And use:
 
 ```ruby
-df.plot("a", "b")
+df.plot.line("a", "b")
 ```
 
-Specify the chart type (`line`, `pie`, `column`, `bar`, `area`, or `scatter`)
+Supports `line`, `pie`, `column`, `bar`, `area`, and `scatter` plots
+
+Group data
 
 ```ruby
-df.plot("a", "b", type: "pie")
+df.plot.line("a", "b", color: "c")
 ```
 
-Group data
+Stacked columns or bars
 
 ```ruby
-df.group_by("c").plot("a", "b")
+df.plot.column("a", "b", color: "c", stacked: true)
 ```
 
-Stacked columns or bars
+Plot a series
 
 ```ruby
-df.group_by("c").plot("a", "b", stacked: true)
+df["a"].plot.hist
 ```
 
+Supports `hist`, `kde`, and `line` plots
+
 ## History
 
-View the [changelog](CHANGELOG.md)
+View the [changelog](https://github.com/ankane/ruby-polars/blob/master/CHANGELOG.md)
 
 ## Contributing
 

data/ext/polars/Cargo.toml

@@ -1,42 +1,58 @@
 [package]
-name = "polars"
-version = "0.15.0"
+name = "polars-ruby"
+version = "0.26.0"
 license = "MIT"
 authors = ["Andrew Kane <andrew@ankane.org>"]
-edition = "2021"
-rust-version = "1.80.0"
+edition = "2024"
+rust-version = "1.89.0"
 publish = false
 
 [lib]
+name = "polars"
 crate-type = ["cdylib"]
 
 [dependencies]
 ahash = "0.8"
-arrow = { package = "polars-arrow", version = "=0.44.2" }
+arrow = { package = "polars-arrow", version = "=0.54.4" }
 bytes = "1"
 chrono = "0.4"
+chrono-tz = "0.10"
 either = "1.8"
-magnus = "0.7"
-polars-core = "=0.44.2"
-polars-plan = "=0.44.2"
-polars-parquet = "=0.44.2"
-polars-utils = "=0.44.2"
+magnus = { version = "0.8", features = ["chrono"] }
+num-traits = "0.2"
+parking_lot = "0.12"
+polars-buffer = "=0.54.4"
+polars-compute = "=0.54.4"
+polars-config = "=0.54.4"
+polars-core = "=0.54.4"
+polars-dtype = "=0.54.4"
+polars-error = "=0.54.4"
+polars-io = "=0.54.4"
+polars-lazy = { version = "=0.54.4", features = ["catalog"] }
+polars-ops = "=0.54.4"
+polars-plan = "=0.54.4"
+polars-parquet = "=0.54.4"
+polars-testing = "=0.54.4"
+polars-utils = "=0.54.4"
+rayon = "1.9"
+rb-sys = "0.9"
 regex = "1"
 serde_json = "1"
 
 [dependencies.polars]
-version = "=0.44.2"
+version = "=0.54.4"
 features = [
     "abs",
     "approx_unique",
     "arg_where",
-    "array_any_all",
     "array_count",
+    "array_to_struct",
     "asof_join",
     "avro",
     "aws",
     "azure",
     "binary_encoding",
+    "bitwise",
     "business",
     "cloud",
     "concat_str",
@@ -50,7 +66,9 @@ features = [
     "dataframe_arithmetic",
     "diagonal_concat",
     "diff",
+    "dot_diagram",
     "dot_product",
+    "dtype-extension",
     "dtype-full",
     "dynamic_group_by",
     "ewma",
@@ -60,23 +78,28 @@ features = [
     "find_many",
     "fmt",
     "gcp",
+    "hist",
     "http",
+    "iejoin",
+    "index_of",
     "interpolate",
+    "interpolate_by",
     "ipc",
     "ipc_streaming",
     "is_between",
+    "is_close",
     "is_first_distinct",
     "is_in",
     "is_last_distinct",
     "is_unique",
     "json",
     "lazy",
-    "list_any_all",
     "list_count",
     "list_drop_nulls",
     "list_eval",
     "list_gather",
     "list_sample",
+    "list_sets",
     "list_to_struct",
     "log",
     "merge_sorted",
@@ -107,6 +130,7 @@ features = [
     "rolling_window_by",
     "round_series",
     "row_hash",
+    "scan_lines",
     "search_sorted",
     "semi_anti_join",
     "serde-lazy",
@@ -123,8 +147,15 @@ features = [
     "unique_counts",
 ]
 
+# allocators differ from Python due to issues with cross-compilation
+# Windows cross-compilation requires libmimalloc-sys <= 0.1.38, so skip for now
+# https://github.com/purpleprotocol/mimalloc_rust/issues/125
+[target.'cfg(target_os = "macos")'.dependencies]
+mimalloc = { version = "0.1", default-features = false }
+
 [target.'cfg(target_os = "linux")'.dependencies]
-jemallocator = { version = "0.5", features = ["disable_initial_exec_tls"] }
+tikv-jemallocator = { version = "0.7", features = ["disable_initial_exec_tls"] }
 
-[target.'cfg(not(any(target_os = "linux", target_os = "windows")))'.dependencies]
-mimalloc = { version = "0.1", default-features = false }
+[features]
+default = []
+serialize_binary = []

data/ext/polars/src/c_api/allocator.rs

@@ -0,0 +1,7 @@
+#[cfg(target_os = "linux")]
+#[global_allocator]
+static ALLOC: tikv_jemallocator::Jemalloc = tikv_jemallocator::Jemalloc;
+
+#[cfg(target_os = "macos")]
+#[global_allocator]
+static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;

data/ext/polars/src/c_api/mod.rs

@@ -0,0 +1 @@
+pub mod allocator;

data/ext/polars/src/catalog/mod.rs

@@ -0,0 +1 @@
+pub mod unity;