polars-df 0.8.0 → 0.10.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +42 -1
- data/Cargo.lock +159 -66
- data/Cargo.toml +0 -3
- data/LICENSE.txt +1 -1
- data/README.md +3 -2
- data/ext/polars/Cargo.toml +18 -8
- data/ext/polars/src/batched_csv.rs +7 -5
- data/ext/polars/src/conversion/anyvalue.rs +186 -0
- data/ext/polars/src/conversion/chunked_array.rs +140 -0
- data/ext/polars/src/{conversion.rs → conversion/mod.rs} +273 -342
- data/ext/polars/src/dataframe.rs +108 -66
- data/ext/polars/src/expr/array.rs +78 -0
- data/ext/polars/src/expr/datetime.rs +29 -58
- data/ext/polars/src/expr/general.rs +83 -36
- data/ext/polars/src/expr/list.rs +58 -6
- data/ext/polars/src/expr/meta.rs +48 -0
- data/ext/polars/src/expr/rolling.rs +1 -0
- data/ext/polars/src/expr/string.rs +62 -11
- data/ext/polars/src/expr/struct.rs +8 -4
- data/ext/polars/src/file.rs +158 -11
- data/ext/polars/src/functions/aggregation.rs +6 -0
- data/ext/polars/src/functions/lazy.rs +120 -50
- data/ext/polars/src/functions/meta.rs +45 -1
- data/ext/polars/src/functions/string_cache.rs +14 -0
- data/ext/polars/src/functions/whenthen.rs +47 -17
- data/ext/polars/src/{lazyframe.rs → lazyframe/mod.rs} +195 -40
- data/ext/polars/src/lib.rs +246 -179
- data/ext/polars/src/map/dataframe.rs +17 -9
- data/ext/polars/src/series/aggregation.rs +20 -0
- data/ext/polars/src/series/mod.rs +35 -4
- data/lib/polars/array_expr.rb +453 -0
- data/lib/polars/array_name_space.rb +346 -0
- data/lib/polars/batched_csv_reader.rb +4 -2
- data/lib/polars/cat_expr.rb +24 -0
- data/lib/polars/cat_name_space.rb +75 -0
- data/lib/polars/config.rb +2 -2
- data/lib/polars/data_frame.rb +306 -96
- data/lib/polars/data_types.rb +191 -28
- data/lib/polars/date_time_expr.rb +41 -18
- data/lib/polars/date_time_name_space.rb +9 -3
- data/lib/polars/exceptions.rb +12 -1
- data/lib/polars/expr.rb +898 -215
- data/lib/polars/functions/aggregation/horizontal.rb +246 -0
- data/lib/polars/functions/aggregation/vertical.rb +282 -0
- data/lib/polars/functions/as_datatype.rb +248 -0
- data/lib/polars/functions/col.rb +47 -0
- data/lib/polars/functions/eager.rb +182 -0
- data/lib/polars/functions/lazy.rb +1280 -0
- data/lib/polars/functions/len.rb +49 -0
- data/lib/polars/functions/lit.rb +35 -0
- data/lib/polars/functions/random.rb +16 -0
- data/lib/polars/functions/range/date_range.rb +103 -0
- data/lib/polars/functions/range/int_range.rb +51 -0
- data/lib/polars/functions/repeat.rb +144 -0
- data/lib/polars/functions/whenthen.rb +96 -0
- data/lib/polars/functions.rb +29 -416
- data/lib/polars/group_by.rb +2 -2
- data/lib/polars/io.rb +36 -31
- data/lib/polars/lazy_frame.rb +405 -88
- data/lib/polars/list_expr.rb +158 -8
- data/lib/polars/list_name_space.rb +102 -0
- data/lib/polars/meta_expr.rb +175 -7
- data/lib/polars/series.rb +282 -41
- data/lib/polars/string_cache.rb +75 -0
- data/lib/polars/string_expr.rb +413 -96
- data/lib/polars/string_name_space.rb +4 -4
- data/lib/polars/testing.rb +507 -0
- data/lib/polars/utils.rb +106 -8
- data/lib/polars/version.rb +1 -1
- data/lib/polars/whenthen.rb +83 -0
- data/lib/polars.rb +16 -4
- metadata +37 -8
- data/lib/polars/lazy_functions.rb +0 -1181
- data/lib/polars/when.rb +0 -16
- data/lib/polars/when_then.rb +0 -19
data/ext/polars/src/dataframe.rs
CHANGED
@@ -6,16 +6,17 @@ use polars::frame::row::{rows_to_schema_supertypes, Row};
|
|
6
6
|
use polars::frame::NullStrategy;
|
7
7
|
use polars::io::avro::AvroCompression;
|
8
8
|
use polars::io::mmap::ReaderBytes;
|
9
|
-
use polars::io::
|
9
|
+
use polars::io::RowIndex;
|
10
10
|
use polars::prelude::pivot::{pivot, pivot_stable};
|
11
11
|
use polars::prelude::*;
|
12
12
|
use polars_core::utils::try_get_supertype;
|
13
13
|
use std::cell::RefCell;
|
14
14
|
use std::io::{BufWriter, Cursor};
|
15
|
+
use std::num::NonZeroUsize;
|
15
16
|
use std::ops::Deref;
|
16
17
|
|
17
18
|
use crate::conversion::*;
|
18
|
-
use crate::file::{get_file_like, get_mmap_bytes_reader};
|
19
|
+
use crate::file::{get_either_file, get_file_like, get_mmap_bytes_reader, EitherRustRubyFile};
|
19
20
|
use crate::map::dataframe::{
|
20
21
|
apply_lambda_unknown, apply_lambda_with_bool_out_type, apply_lambda_with_primitive_out_type,
|
21
22
|
apply_lambda_with_utf8_out_type,
|
@@ -45,44 +46,51 @@ impl RbDataFrame {
|
|
45
46
|
fn finish_from_rows(
|
46
47
|
rows: Vec<Row>,
|
47
48
|
infer_schema_length: Option<usize>,
|
48
|
-
|
49
|
+
schema: Option<Schema>,
|
50
|
+
schema_overrides_by_idx: Option<Vec<(usize, DataType)>>,
|
49
51
|
) -> RbResult<Self> {
|
50
|
-
//
|
52
|
+
// Object builder must be registered
|
51
53
|
crate::on_startup::register_object_builder();
|
52
54
|
|
53
|
-
let
|
55
|
+
let mut final_schema =
|
54
56
|
rows_to_schema_supertypes(&rows, infer_schema_length.map(|n| std::cmp::max(1, n)))
|
55
57
|
.map_err(RbPolarsErr::from)?;
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
}
|
62
|
-
DataType::Decimal(_, _) => {
|
63
|
-
fld.coerce(DataType::Decimal(None, None));
|
64
|
-
fld
|
58
|
+
|
59
|
+
// Erase scale from inferred decimals.
|
60
|
+
for dtype in final_schema.iter_dtypes_mut() {
|
61
|
+
if let DataType::Decimal(_, _) = dtype {
|
62
|
+
*dtype = DataType::Decimal(None, None)
|
65
63
|
}
|
66
|
-
|
67
|
-
});
|
68
|
-
let mut schema = Schema::from_iter(fields);
|
64
|
+
}
|
69
65
|
|
70
|
-
|
71
|
-
|
72
|
-
|
66
|
+
// Integrate explicit/inferred schema.
|
67
|
+
if let Some(schema) = schema {
|
68
|
+
for (i, (name, dtype)) in schema.into_iter().enumerate() {
|
69
|
+
if let Some((name_, dtype_)) = final_schema.get_at_index_mut(i) {
|
73
70
|
*name_ = name;
|
74
71
|
|
75
|
-
//
|
72
|
+
// If schema dtype is Unknown, overwrite with inferred datatype.
|
76
73
|
if !matches!(dtype, DataType::Unknown) {
|
77
74
|
*dtype_ = dtype;
|
78
75
|
}
|
79
76
|
} else {
|
80
|
-
|
77
|
+
final_schema.with_column(name, dtype);
|
81
78
|
}
|
82
79
|
}
|
83
80
|
}
|
84
81
|
|
85
|
-
|
82
|
+
// Optional per-field overrides; these supersede default/inferred dtypes.
|
83
|
+
if let Some(overrides) = schema_overrides_by_idx {
|
84
|
+
for (i, dtype) in overrides {
|
85
|
+
if let Some((_, dtype_)) = final_schema.get_at_index_mut(i) {
|
86
|
+
if !matches!(dtype, DataType::Unknown) {
|
87
|
+
*dtype_ = dtype;
|
88
|
+
}
|
89
|
+
}
|
90
|
+
}
|
91
|
+
}
|
92
|
+
let df =
|
93
|
+
DataFrame::from_rows_and_schema(&rows, &final_schema).map_err(RbPolarsErr::from)?;
|
86
94
|
Ok(df.into())
|
87
95
|
}
|
88
96
|
|
@@ -125,15 +133,16 @@ impl RbDataFrame {
|
|
125
133
|
let null_values = Option::<Wrap<NullValues>>::try_convert(arguments[19])?;
|
126
134
|
let try_parse_dates = bool::try_convert(arguments[20])?;
|
127
135
|
let skip_rows_after_header = usize::try_convert(arguments[21])?;
|
128
|
-
let
|
136
|
+
let row_index = Option::<(String, IdxSize)>::try_convert(arguments[22])?;
|
129
137
|
let sample_size = usize::try_convert(arguments[23])?;
|
130
138
|
let eol_char = String::try_convert(arguments[24])?;
|
139
|
+
let truncate_ragged_lines = bool::try_convert(arguments[25])?;
|
131
140
|
// end arguments
|
132
141
|
|
133
142
|
let null_values = null_values.map(|w| w.0);
|
134
143
|
let eol_char = eol_char.as_bytes()[0];
|
135
144
|
|
136
|
-
let
|
145
|
+
let row_index = row_index.map(|(name, offset)| RowIndex { name, offset });
|
137
146
|
|
138
147
|
let quote_char = if let Some(s) = quote_char {
|
139
148
|
if s.is_empty() {
|
@@ -186,8 +195,9 @@ impl RbDataFrame {
|
|
186
195
|
.with_quote_char(quote_char)
|
187
196
|
.with_end_of_line_char(eol_char)
|
188
197
|
.with_skip_rows_after_header(skip_rows_after_header)
|
189
|
-
.
|
198
|
+
.with_row_index(row_index)
|
190
199
|
.sample_size(sample_size)
|
200
|
+
.truncate_ragged_lines(truncate_ragged_lines)
|
191
201
|
.finish()
|
192
202
|
.map_err(RbPolarsErr::from)?;
|
193
203
|
Ok(df.into())
|
@@ -200,24 +210,39 @@ impl RbDataFrame {
|
|
200
210
|
projection: Option<Vec<usize>>,
|
201
211
|
n_rows: Option<usize>,
|
202
212
|
parallel: Wrap<ParallelStrategy>,
|
203
|
-
|
213
|
+
row_index: Option<(String, IdxSize)>,
|
204
214
|
low_memory: bool,
|
205
215
|
use_statistics: bool,
|
206
216
|
rechunk: bool,
|
207
217
|
) -> RbResult<Self> {
|
208
|
-
|
209
|
-
|
210
|
-
let
|
211
|
-
|
212
|
-
|
213
|
-
|
214
|
-
|
215
|
-
|
216
|
-
|
217
|
-
|
218
|
-
|
219
|
-
|
220
|
-
|
218
|
+
use EitherRustRubyFile::*;
|
219
|
+
|
220
|
+
let row_index = row_index.map(|(name, offset)| RowIndex { name, offset });
|
221
|
+
let result = match get_either_file(rb_f, false)? {
|
222
|
+
Rb(f) => {
|
223
|
+
let buf = f.as_buffer();
|
224
|
+
ParquetReader::new(buf)
|
225
|
+
.with_projection(projection)
|
226
|
+
.with_columns(columns)
|
227
|
+
.read_parallel(parallel.0)
|
228
|
+
.with_n_rows(n_rows)
|
229
|
+
.with_row_index(row_index)
|
230
|
+
.set_low_memory(low_memory)
|
231
|
+
.use_statistics(use_statistics)
|
232
|
+
.set_rechunk(rechunk)
|
233
|
+
.finish()
|
234
|
+
}
|
235
|
+
Rust(f) => ParquetReader::new(f.into_inner())
|
236
|
+
.with_projection(projection)
|
237
|
+
.with_columns(columns)
|
238
|
+
.read_parallel(parallel.0)
|
239
|
+
.with_n_rows(n_rows)
|
240
|
+
.with_row_index(row_index)
|
241
|
+
.use_statistics(use_statistics)
|
242
|
+
.set_rechunk(rechunk)
|
243
|
+
.finish(),
|
244
|
+
};
|
245
|
+
let df = result.map_err(RbPolarsErr::from)?;
|
221
246
|
Ok(RbDataFrame::new(df))
|
222
247
|
}
|
223
248
|
|
@@ -226,16 +251,16 @@ impl RbDataFrame {
|
|
226
251
|
columns: Option<Vec<String>>,
|
227
252
|
projection: Option<Vec<usize>>,
|
228
253
|
n_rows: Option<usize>,
|
229
|
-
|
254
|
+
row_index: Option<(String, IdxSize)>,
|
230
255
|
memory_map: bool,
|
231
256
|
) -> RbResult<Self> {
|
232
|
-
let
|
257
|
+
let row_index = row_index.map(|(name, offset)| RowIndex { name, offset });
|
233
258
|
let mmap_bytes_r = get_mmap_bytes_reader(rb_f)?;
|
234
259
|
let df = IpcReader::new(mmap_bytes_r)
|
235
260
|
.with_projection(projection)
|
236
261
|
.with_columns(columns)
|
237
262
|
.with_n_rows(n_rows)
|
238
|
-
.
|
263
|
+
.with_row_index(row_index)
|
239
264
|
.memory_mapped(memory_map)
|
240
265
|
.finish()
|
241
266
|
.map_err(RbPolarsErr::from)?;
|
@@ -352,7 +377,7 @@ impl RbDataFrame {
|
|
352
377
|
pub fn read_rows(
|
353
378
|
rb_rows: RArray,
|
354
379
|
infer_schema_length: Option<usize>,
|
355
|
-
|
380
|
+
schema: Option<Wrap<Schema>>,
|
356
381
|
) -> RbResult<Self> {
|
357
382
|
let mut rows = Vec::with_capacity(rb_rows.len());
|
358
383
|
for v in rb_rows.each() {
|
@@ -363,30 +388,34 @@ impl RbDataFrame {
|
|
363
388
|
}
|
364
389
|
rows.push(Row(row));
|
365
390
|
}
|
366
|
-
Self::finish_from_rows(
|
367
|
-
rows,
|
368
|
-
infer_schema_length,
|
369
|
-
schema_overwrite.map(|wrap| wrap.0),
|
370
|
-
)
|
391
|
+
Self::finish_from_rows(rows, infer_schema_length, schema.map(|wrap| wrap.0), None)
|
371
392
|
}
|
372
393
|
|
373
394
|
pub fn read_hashes(
|
374
395
|
dicts: Value,
|
375
396
|
infer_schema_length: Option<usize>,
|
376
|
-
|
397
|
+
schema: Option<Wrap<Schema>>,
|
398
|
+
schema_overrides: Option<Wrap<Schema>>,
|
377
399
|
) -> RbResult<Self> {
|
378
|
-
let
|
400
|
+
let mut schema_columns = PlIndexSet::new();
|
401
|
+
if let Some(s) = &schema {
|
402
|
+
schema_columns.extend(s.0.iter_names().map(|n| n.to_string()))
|
403
|
+
}
|
404
|
+
let (rows, names) = dicts_to_rows(&dicts, infer_schema_length, schema_columns)?;
|
379
405
|
|
380
|
-
|
381
|
-
if let Some(
|
382
|
-
for (
|
383
|
-
|
406
|
+
let mut schema_overrides_by_idx: Vec<(usize, DataType)> = Vec::new();
|
407
|
+
if let Some(overrides) = schema_overrides {
|
408
|
+
for (idx, name) in names.iter().enumerate() {
|
409
|
+
if let Some(dtype) = overrides.0.get(name) {
|
410
|
+
schema_overrides_by_idx.push((idx, dtype.clone()));
|
411
|
+
}
|
384
412
|
}
|
385
413
|
}
|
386
414
|
let rbdf = Self::finish_from_rows(
|
387
415
|
rows,
|
388
416
|
infer_schema_length,
|
389
|
-
|
417
|
+
schema.map(|wrap| wrap.0),
|
418
|
+
Some(schema_overrides_by_idx),
|
390
419
|
)?;
|
391
420
|
|
392
421
|
unsafe {
|
@@ -427,13 +456,14 @@ impl RbDataFrame {
|
|
427
456
|
include_header: bool,
|
428
457
|
separator: u8,
|
429
458
|
quote_char: u8,
|
430
|
-
batch_size:
|
459
|
+
batch_size: Wrap<NonZeroUsize>,
|
431
460
|
datetime_format: Option<String>,
|
432
461
|
date_format: Option<String>,
|
433
462
|
time_format: Option<String>,
|
434
463
|
float_precision: Option<usize>,
|
435
464
|
null_value: Option<String>,
|
436
465
|
) -> RbResult<()> {
|
466
|
+
let batch_size = batch_size.0;
|
437
467
|
let null = null_value.unwrap_or_default();
|
438
468
|
|
439
469
|
if let Ok(s) = String::try_convert(rb_f) {
|
@@ -563,6 +593,7 @@ impl RbDataFrame {
|
|
563
593
|
compression_level: Option<i32>,
|
564
594
|
statistics: bool,
|
565
595
|
row_group_size: Option<usize>,
|
596
|
+
data_page_size: Option<usize>,
|
566
597
|
) -> RbResult<()> {
|
567
598
|
let compression = parse_parquet_compression(&compression, compression_level)?;
|
568
599
|
|
@@ -572,10 +603,18 @@ impl RbDataFrame {
|
|
572
603
|
.with_compression(compression)
|
573
604
|
.with_statistics(statistics)
|
574
605
|
.with_row_group_size(row_group_size)
|
606
|
+
.with_data_page_size(data_page_size)
|
575
607
|
.finish(&mut self.df.borrow_mut())
|
576
608
|
.map_err(RbPolarsErr::from)?;
|
577
609
|
} else {
|
578
|
-
|
610
|
+
let buf = get_file_like(rb_f, true)?;
|
611
|
+
ParquetWriter::new(buf)
|
612
|
+
.with_compression(compression)
|
613
|
+
.with_statistics(statistics)
|
614
|
+
.with_row_group_size(row_group_size)
|
615
|
+
.with_data_page_size(data_page_size)
|
616
|
+
.finish(&mut self.df.borrow_mut())
|
617
|
+
.map_err(RbPolarsErr::from)?;
|
579
618
|
}
|
580
619
|
|
581
620
|
Ok(())
|
@@ -794,12 +833,11 @@ impl RbDataFrame {
|
|
794
833
|
self.df.borrow().get_column_index(&name)
|
795
834
|
}
|
796
835
|
|
797
|
-
|
798
|
-
pub fn column(&self, name: String) -> RbResult<RbSeries> {
|
836
|
+
pub fn get_column(&self, name: String) -> RbResult<RbSeries> {
|
799
837
|
self.df
|
800
838
|
.borrow()
|
801
839
|
.column(&name)
|
802
|
-
.map(|
|
840
|
+
.map(|s| RbSeries::new(s.clone()))
|
803
841
|
.map_err(RbPolarsErr::from)
|
804
842
|
}
|
805
843
|
|
@@ -887,11 +925,11 @@ impl RbDataFrame {
|
|
887
925
|
}
|
888
926
|
}
|
889
927
|
|
890
|
-
pub fn
|
928
|
+
pub fn with_row_index(&self, name: String, offset: Option<IdxSize>) -> RbResult<Self> {
|
891
929
|
let df = self
|
892
930
|
.df
|
893
931
|
.borrow()
|
894
|
-
.
|
932
|
+
.with_row_index(&name, offset)
|
895
933
|
.map_err(RbPolarsErr::from)?;
|
896
934
|
Ok(df.into())
|
897
935
|
}
|
@@ -922,9 +960,9 @@ impl RbDataFrame {
|
|
922
960
|
#[allow(clippy::too_many_arguments)]
|
923
961
|
pub fn pivot_expr(
|
924
962
|
&self,
|
925
|
-
values: Vec<String>,
|
926
963
|
index: Vec<String>,
|
927
964
|
columns: Vec<String>,
|
965
|
+
values: Option<Vec<String>>,
|
928
966
|
maintain_order: bool,
|
929
967
|
sort_columns: bool,
|
930
968
|
aggregate_expr: Option<&RbExpr>,
|
@@ -937,9 +975,9 @@ impl RbDataFrame {
|
|
937
975
|
let agg_expr = aggregate_expr.map(|aggregate_expr| aggregate_expr.inner.clone());
|
938
976
|
let df = fun(
|
939
977
|
&self.df.borrow(),
|
940
|
-
values,
|
941
978
|
index,
|
942
979
|
columns,
|
980
|
+
values,
|
943
981
|
sort_columns,
|
944
982
|
agg_expr,
|
945
983
|
separator.as_deref(),
|
@@ -1121,7 +1159,7 @@ impl RbDataFrame {
|
|
1121
1159
|
};
|
1122
1160
|
Ok(self
|
1123
1161
|
.df
|
1124
|
-
.
|
1162
|
+
.borrow_mut()
|
1125
1163
|
.transpose(keep_names_as.as_deref(), new_col_names)
|
1126
1164
|
.map_err(RbPolarsErr::from)?
|
1127
1165
|
.into())
|
@@ -1163,4 +1201,8 @@ impl RbDataFrame {
|
|
1163
1201
|
let df = self.df.borrow().unnest(names).map_err(RbPolarsErr::from)?;
|
1164
1202
|
Ok(df.into())
|
1165
1203
|
}
|
1204
|
+
|
1205
|
+
pub fn clear(&self) -> Self {
|
1206
|
+
self.df.borrow().clear().into()
|
1207
|
+
}
|
1166
1208
|
}
|
@@ -1,3 +1,5 @@
|
|
1
|
+
use polars::prelude::*;
|
2
|
+
|
1
3
|
use crate::RbExpr;
|
2
4
|
|
3
5
|
impl RbExpr {
|
@@ -12,4 +14,80 @@ impl RbExpr {
|
|
12
14
|
pub fn array_sum(&self) -> Self {
|
13
15
|
self.inner.clone().arr().sum().into()
|
14
16
|
}
|
17
|
+
|
18
|
+
pub fn arr_unique(&self, maintain_order: bool) -> Self {
|
19
|
+
if maintain_order {
|
20
|
+
self.inner.clone().arr().unique_stable().into()
|
21
|
+
} else {
|
22
|
+
self.inner.clone().arr().unique().into()
|
23
|
+
}
|
24
|
+
}
|
25
|
+
|
26
|
+
pub fn arr_to_list(&self) -> Self {
|
27
|
+
self.inner.clone().arr().to_list().into()
|
28
|
+
}
|
29
|
+
|
30
|
+
pub fn arr_all(&self) -> Self {
|
31
|
+
self.inner.clone().arr().all().into()
|
32
|
+
}
|
33
|
+
|
34
|
+
pub fn arr_any(&self) -> Self {
|
35
|
+
self.inner.clone().arr().any().into()
|
36
|
+
}
|
37
|
+
|
38
|
+
pub fn arr_sort(&self, descending: bool, nulls_last: bool) -> Self {
|
39
|
+
self.inner
|
40
|
+
.clone()
|
41
|
+
.arr()
|
42
|
+
.sort(SortOptions {
|
43
|
+
descending,
|
44
|
+
nulls_last,
|
45
|
+
..Default::default()
|
46
|
+
})
|
47
|
+
.into()
|
48
|
+
}
|
49
|
+
|
50
|
+
pub fn arr_reverse(&self) -> Self {
|
51
|
+
self.inner.clone().arr().reverse().into()
|
52
|
+
}
|
53
|
+
|
54
|
+
pub fn arr_arg_min(&self) -> Self {
|
55
|
+
self.inner.clone().arr().arg_min().into()
|
56
|
+
}
|
57
|
+
|
58
|
+
pub fn arr_arg_max(&self) -> Self {
|
59
|
+
self.inner.clone().arr().arg_max().into()
|
60
|
+
}
|
61
|
+
|
62
|
+
pub fn arr_get(&self, index: &RbExpr, null_on_oob: bool) -> Self {
|
63
|
+
self.inner
|
64
|
+
.clone()
|
65
|
+
.arr()
|
66
|
+
.get(index.inner.clone(), null_on_oob)
|
67
|
+
.into()
|
68
|
+
}
|
69
|
+
|
70
|
+
pub fn arr_join(&self, separator: &RbExpr, ignore_nulls: bool) -> Self {
|
71
|
+
self.inner
|
72
|
+
.clone()
|
73
|
+
.arr()
|
74
|
+
.join(separator.inner.clone(), ignore_nulls)
|
75
|
+
.into()
|
76
|
+
}
|
77
|
+
|
78
|
+
pub fn arr_contains(&self, other: &RbExpr) -> Self {
|
79
|
+
self.inner
|
80
|
+
.clone()
|
81
|
+
.arr()
|
82
|
+
.contains(other.inner.clone())
|
83
|
+
.into()
|
84
|
+
}
|
85
|
+
|
86
|
+
pub fn arr_count_matches(&self, expr: &RbExpr) -> Self {
|
87
|
+
self.inner
|
88
|
+
.clone()
|
89
|
+
.arr()
|
90
|
+
.count_matches(expr.inner.clone())
|
91
|
+
.into()
|
92
|
+
}
|
15
93
|
}
|
@@ -37,11 +37,16 @@ impl RbExpr {
|
|
37
37
|
self.inner.clone().dt().cast_time_unit(tu.0).into()
|
38
38
|
}
|
39
39
|
|
40
|
-
pub fn dt_replace_time_zone(
|
40
|
+
pub fn dt_replace_time_zone(
|
41
|
+
&self,
|
42
|
+
time_zone: Option<String>,
|
43
|
+
ambiguous: &Self,
|
44
|
+
non_existent: Wrap<NonExistent>,
|
45
|
+
) -> Self {
|
41
46
|
self.inner
|
42
47
|
.clone()
|
43
48
|
.dt()
|
44
|
-
.replace_time_zone(time_zone, ambiguous.inner.clone())
|
49
|
+
.replace_time_zone(time_zone, ambiguous.inner.clone(), non_existent.0)
|
45
50
|
.into()
|
46
51
|
}
|
47
52
|
|
@@ -61,6 +66,14 @@ impl RbExpr {
|
|
61
66
|
self.inner.clone().dt().month_end().into()
|
62
67
|
}
|
63
68
|
|
69
|
+
pub fn dt_base_utc_offset(&self) -> Self {
|
70
|
+
self.inner.clone().dt().base_utc_offset().into()
|
71
|
+
}
|
72
|
+
|
73
|
+
pub fn dt_dst_offset(&self) -> Self {
|
74
|
+
self.inner.clone().dt().dst_offset().into()
|
75
|
+
}
|
76
|
+
|
64
77
|
pub fn dt_round(&self, every: String, offset: String) -> Self {
|
65
78
|
self.inner.clone().dt().round(&every, &offset).into()
|
66
79
|
}
|
@@ -149,73 +162,31 @@ impl RbExpr {
|
|
149
162
|
self.inner.clone().dt().timestamp(tu.0).into()
|
150
163
|
}
|
151
164
|
|
152
|
-
pub fn
|
153
|
-
self.inner
|
154
|
-
.clone()
|
155
|
-
.map(
|
156
|
-
|s| Ok(Some(s.duration()?.days().into_series())),
|
157
|
-
GetOutput::from_type(DataType::Int64),
|
158
|
-
)
|
159
|
-
.into()
|
165
|
+
pub fn dt_total_days(&self) -> Self {
|
166
|
+
self.inner.clone().dt().total_days().into()
|
160
167
|
}
|
161
168
|
|
162
|
-
pub fn
|
163
|
-
self.inner
|
164
|
-
.clone()
|
165
|
-
.map(
|
166
|
-
|s| Ok(Some(s.duration()?.hours().into_series())),
|
167
|
-
GetOutput::from_type(DataType::Int64),
|
168
|
-
)
|
169
|
-
.into()
|
169
|
+
pub fn dt_total_hours(&self) -> Self {
|
170
|
+
self.inner.clone().dt().total_hours().into()
|
170
171
|
}
|
171
172
|
|
172
|
-
pub fn
|
173
|
-
self.inner
|
174
|
-
.clone()
|
175
|
-
.map(
|
176
|
-
|s| Ok(Some(s.duration()?.minutes().into_series())),
|
177
|
-
GetOutput::from_type(DataType::Int64),
|
178
|
-
)
|
179
|
-
.into()
|
173
|
+
pub fn dt_total_minutes(&self) -> Self {
|
174
|
+
self.inner.clone().dt().total_minutes().into()
|
180
175
|
}
|
181
176
|
|
182
|
-
pub fn
|
183
|
-
self.inner
|
184
|
-
.clone()
|
185
|
-
.map(
|
186
|
-
|s| Ok(Some(s.duration()?.seconds().into_series())),
|
187
|
-
GetOutput::from_type(DataType::Int64),
|
188
|
-
)
|
189
|
-
.into()
|
177
|
+
pub fn dt_total_seconds(&self) -> Self {
|
178
|
+
self.inner.clone().dt().total_seconds().into()
|
190
179
|
}
|
191
180
|
|
192
|
-
pub fn
|
193
|
-
self.inner
|
194
|
-
.clone()
|
195
|
-
.map(
|
196
|
-
|s| Ok(Some(s.duration()?.milliseconds().into_series())),
|
197
|
-
GetOutput::from_type(DataType::Int64),
|
198
|
-
)
|
199
|
-
.into()
|
181
|
+
pub fn dt_total_milliseconds(&self) -> Self {
|
182
|
+
self.inner.clone().dt().total_milliseconds().into()
|
200
183
|
}
|
201
184
|
|
202
|
-
pub fn
|
203
|
-
self.inner
|
204
|
-
.clone()
|
205
|
-
.map(
|
206
|
-
|s| Ok(Some(s.duration()?.microseconds().into_series())),
|
207
|
-
GetOutput::from_type(DataType::Int64),
|
208
|
-
)
|
209
|
-
.into()
|
185
|
+
pub fn dt_total_microseconds(&self) -> Self {
|
186
|
+
self.inner.clone().dt().total_microseconds().into()
|
210
187
|
}
|
211
188
|
|
212
|
-
pub fn
|
213
|
-
self.inner
|
214
|
-
.clone()
|
215
|
-
.map(
|
216
|
-
|s| Ok(Some(s.duration()?.nanoseconds().into_series())),
|
217
|
-
GetOutput::from_type(DataType::Int64),
|
218
|
-
)
|
219
|
-
.into()
|
189
|
+
pub fn dt_total_nanoseconds(&self) -> Self {
|
190
|
+
self.inner.clone().dt().total_nanoseconds().into()
|
220
191
|
}
|
221
192
|
}
|