polars-df 0.15.0-arm64-darwin → 0.16.0-arm64-darwin
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/CHANGELOG.md +10 -0
- data/Cargo.lock +588 -456
- data/LICENSE-THIRD-PARTY.txt +14994 -16055
- data/README.md +37 -2
- data/lib/polars/3.2/polars.bundle +0 -0
- data/lib/polars/3.3/polars.bundle +0 -0
- data/lib/polars/{3.1 → 3.4}/polars.bundle +0 -0
- data/lib/polars/data_frame.rb +179 -51
- data/lib/polars/data_types.rb +1 -1
- data/lib/polars/functions/aggregation/horizontal.rb +10 -4
- data/lib/polars/functions/lazy.rb +7 -3
- data/lib/polars/io/delta.rb +126 -0
- data/lib/polars/lazy_frame.rb +35 -5
- data/lib/polars/selectors.rb +85 -3
- data/lib/polars/version.rb +1 -1
- data/lib/polars.rb +15 -0
- metadata +7 -7
data/lib/polars/selectors.rb
CHANGED
@@ -372,9 +372,91 @@ module Polars
|
|
372
372
|
# def by_index
|
373
373
|
# end
|
374
374
|
|
375
|
-
#
|
376
|
-
#
|
377
|
-
#
|
375
|
+
# Select all columns matching the given names.
|
376
|
+
#
|
377
|
+
# @param names [Array]
|
378
|
+
# One or more names of columns to select.
|
379
|
+
# @param require_all [Boolean]
|
380
|
+
# Whether to match *all* names (the default) or *any* of the names.
|
381
|
+
#
|
382
|
+
# @return [SelectorProxy]
|
383
|
+
#
|
384
|
+
# @note
|
385
|
+
# Matching columns are returned in the order in which they are declared in
|
386
|
+
# the selector, not the underlying schema order.
|
387
|
+
#
|
388
|
+
# @example
|
389
|
+
# df = Polars::DataFrame.new(
|
390
|
+
# {
|
391
|
+
# "foo" => ["x", "y"],
|
392
|
+
# "bar" => [123, 456],
|
393
|
+
# "baz" => [2.0, 5.5],
|
394
|
+
# "zap" => [false, true]
|
395
|
+
# }
|
396
|
+
# )
|
397
|
+
#
|
398
|
+
# @example Select columns by name:
|
399
|
+
# df.select(Polars.cs.by_name("foo", "bar"))
|
400
|
+
# # =>
|
401
|
+
# # shape: (2, 2)
|
402
|
+
# # ┌─────┬─────┐
|
403
|
+
# # │ foo ┆ bar │
|
404
|
+
# # │ --- ┆ --- │
|
405
|
+
# # │ str ┆ i64 │
|
406
|
+
# # ╞═════╪═════╡
|
407
|
+
# # │ x ┆ 123 │
|
408
|
+
# # │ y ┆ 456 │
|
409
|
+
# # └─────┴─────┘
|
410
|
+
#
|
411
|
+
# @example Match *any* of the given columns by name:
|
412
|
+
# df.select(Polars.cs.by_name("baz", "moose", "foo", "bear", require_all: false))
|
413
|
+
# # =>
|
414
|
+
# # shape: (2, 2)
|
415
|
+
# # ┌─────┬─────┐
|
416
|
+
# # │ foo ┆ baz │
|
417
|
+
# # │ --- ┆ --- │
|
418
|
+
# # │ str ┆ f64 │
|
419
|
+
# # ╞═════╪═════╡
|
420
|
+
# # │ x ┆ 2.0 │
|
421
|
+
# # │ y ┆ 5.5 │
|
422
|
+
# # └─────┴─────┘
|
423
|
+
#
|
424
|
+
# @example Match all columns *except* for those given:
|
425
|
+
# df.select(~Polars.cs.by_name("foo", "bar"))
|
426
|
+
# # =>
|
427
|
+
# # shape: (2, 2)
|
428
|
+
# # ┌─────┬───────┐
|
429
|
+
# # │ baz ┆ zap │
|
430
|
+
# # │ --- ┆ --- │
|
431
|
+
# # │ f64 ┆ bool │
|
432
|
+
# # ╞═════╪═══════╡
|
433
|
+
# # │ 2.0 ┆ false │
|
434
|
+
# # │ 5.5 ┆ true │
|
435
|
+
# # └─────┴───────┘
|
436
|
+
def self.by_name(*names, require_all: true)
|
437
|
+
all_names = []
|
438
|
+
names.each do |nm|
|
439
|
+
if nm.is_a?(::String)
|
440
|
+
all_names << nm
|
441
|
+
else
|
442
|
+
msg = "invalid name: #{nm.inspect}"
|
443
|
+
raise TypeError, msg
|
444
|
+
end
|
445
|
+
end
|
446
|
+
|
447
|
+
selector_params = {"*names" => all_names}
|
448
|
+
match_cols = all_names
|
449
|
+
if !require_all
|
450
|
+
match_cols = "^(#{all_names.map { |nm| Utils.re_escape(nm) }.join("|")})$"
|
451
|
+
selector_params["require_all"] = require_all
|
452
|
+
end
|
453
|
+
|
454
|
+
_selector_proxy_(
|
455
|
+
F.col(match_cols),
|
456
|
+
name: "by_name",
|
457
|
+
parameters: selector_params
|
458
|
+
)
|
459
|
+
end
|
378
460
|
|
379
461
|
# Select all categorical columns.
|
380
462
|
#
|
data/lib/polars/version.rb
CHANGED
data/lib/polars.rb
CHANGED
@@ -49,6 +49,7 @@ require_relative "polars/group_by"
|
|
49
49
|
require_relative "polars/io/avro"
|
50
50
|
require_relative "polars/io/csv"
|
51
51
|
require_relative "polars/io/database"
|
52
|
+
require_relative "polars/io/delta"
|
52
53
|
require_relative "polars/io/ipc"
|
53
54
|
require_relative "polars/io/json"
|
54
55
|
require_relative "polars/io/ndjson"
|
@@ -89,4 +90,18 @@ module Polars
|
|
89
90
|
|
90
91
|
# @private
|
91
92
|
N_INFER_DEFAULT = 100
|
93
|
+
|
94
|
+
# @private
|
95
|
+
class ArrowArrayStream
|
96
|
+
def arrow_c_stream
|
97
|
+
self
|
98
|
+
end
|
99
|
+
end
|
100
|
+
|
101
|
+
# Return the number of threads in the Polars thread pool.
|
102
|
+
#
|
103
|
+
# @return [Integer]
|
104
|
+
def self.thread_pool_size
|
105
|
+
Plr.thread_pool_size
|
106
|
+
end
|
92
107
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: polars-df
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.16.0
|
5
5
|
platform: arm64-darwin
|
6
6
|
authors:
|
7
7
|
- Andrew Kane
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2024-
|
11
|
+
date: 2024-12-29 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bigdecimal
|
@@ -24,7 +24,6 @@ dependencies:
|
|
24
24
|
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '0'
|
27
|
-
force_ruby_platform: false
|
28
27
|
description:
|
29
28
|
email: andrew@ankane.org
|
30
29
|
executables: []
|
@@ -40,9 +39,9 @@ files:
|
|
40
39
|
- README.md
|
41
40
|
- lib/polars-df.rb
|
42
41
|
- lib/polars.rb
|
43
|
-
- lib/polars/3.1/polars.bundle
|
44
42
|
- lib/polars/3.2/polars.bundle
|
45
43
|
- lib/polars/3.3/polars.bundle
|
44
|
+
- lib/polars/3.4/polars.bundle
|
46
45
|
- lib/polars/array_expr.rb
|
47
46
|
- lib/polars/array_name_space.rb
|
48
47
|
- lib/polars/batched_csv_reader.rb
|
@@ -80,6 +79,7 @@ files:
|
|
80
79
|
- lib/polars/io/avro.rb
|
81
80
|
- lib/polars/io/csv.rb
|
82
81
|
- lib/polars/io/database.rb
|
82
|
+
- lib/polars/io/delta.rb
|
83
83
|
- lib/polars/io/ipc.rb
|
84
84
|
- lib/polars/io/json.rb
|
85
85
|
- lib/polars/io/ndjson.rb
|
@@ -122,17 +122,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
122
122
|
requirements:
|
123
123
|
- - ">="
|
124
124
|
- !ruby/object:Gem::Version
|
125
|
-
version: '3.
|
125
|
+
version: '3.2'
|
126
126
|
- - "<"
|
127
127
|
- !ruby/object:Gem::Version
|
128
|
-
version: 3.
|
128
|
+
version: 3.5.dev
|
129
129
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
130
130
|
requirements:
|
131
131
|
- - ">="
|
132
132
|
- !ruby/object:Gem::Version
|
133
133
|
version: '0'
|
134
134
|
requirements: []
|
135
|
-
rubygems_version: 3.
|
135
|
+
rubygems_version: 3.5.23
|
136
136
|
signing_key:
|
137
137
|
specification_version: 4
|
138
138
|
summary: Blazingly fast DataFrames for Ruby
|