polars-df 0.10.0 → 0.12.0

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.
Files changed (92) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +27 -0
  3. data/Cargo.lock +392 -351
  4. data/README.md +6 -6
  5. data/ext/polars/Cargo.toml +12 -7
  6. data/ext/polars/src/batched_csv.rs +53 -52
  7. data/ext/polars/src/conversion/any_value.rs +261 -0
  8. data/ext/polars/src/conversion/chunked_array.rs +4 -4
  9. data/ext/polars/src/conversion/mod.rs +60 -66
  10. data/ext/polars/src/dataframe/construction.rs +184 -0
  11. data/ext/polars/src/dataframe/export.rs +48 -0
  12. data/ext/polars/src/dataframe/general.rs +597 -0
  13. data/ext/polars/src/dataframe/io.rs +473 -0
  14. data/ext/polars/src/dataframe/mod.rs +26 -0
  15. data/ext/polars/src/error.rs +26 -4
  16. data/ext/polars/src/expr/categorical.rs +0 -10
  17. data/ext/polars/src/expr/datetime.rs +4 -8
  18. data/ext/polars/src/expr/general.rs +129 -94
  19. data/ext/polars/src/expr/mod.rs +2 -2
  20. data/ext/polars/src/expr/rolling.rs +201 -77
  21. data/ext/polars/src/expr/string.rs +11 -36
  22. data/ext/polars/src/functions/eager.rs +10 -10
  23. data/ext/polars/src/functions/lazy.rs +23 -21
  24. data/ext/polars/src/functions/range.rs +69 -1
  25. data/ext/polars/src/interop/mod.rs +1 -0
  26. data/ext/polars/src/interop/numo/mod.rs +2 -0
  27. data/ext/polars/src/interop/numo/to_numo_df.rs +23 -0
  28. data/ext/polars/src/interop/numo/to_numo_series.rs +61 -0
  29. data/ext/polars/src/lazyframe/mod.rs +135 -136
  30. data/ext/polars/src/lib.rs +94 -59
  31. data/ext/polars/src/map/dataframe.rs +2 -2
  32. data/ext/polars/src/map/lazy.rs +5 -25
  33. data/ext/polars/src/map/series.rs +7 -1
  34. data/ext/polars/src/rb_modules.rs +25 -1
  35. data/ext/polars/src/series/aggregation.rs +49 -30
  36. data/ext/polars/src/series/arithmetic.rs +21 -11
  37. data/ext/polars/src/series/construction.rs +56 -38
  38. data/ext/polars/src/series/export.rs +131 -49
  39. data/ext/polars/src/series/mod.rs +32 -141
  40. data/ext/polars/src/sql.rs +3 -1
  41. data/lib/polars/array_expr.rb +4 -4
  42. data/lib/polars/batched_csv_reader.rb +11 -5
  43. data/lib/polars/cat_expr.rb +0 -36
  44. data/lib/polars/cat_name_space.rb +0 -37
  45. data/lib/polars/convert.rb +6 -1
  46. data/lib/polars/data_frame.rb +176 -403
  47. data/lib/polars/data_types.rb +1 -1
  48. data/lib/polars/date_time_expr.rb +525 -572
  49. data/lib/polars/date_time_name_space.rb +263 -460
  50. data/lib/polars/dynamic_group_by.rb +5 -5
  51. data/lib/polars/exceptions.rb +7 -0
  52. data/lib/polars/expr.rb +1394 -243
  53. data/lib/polars/expr_dispatch.rb +1 -1
  54. data/lib/polars/functions/aggregation/horizontal.rb +8 -8
  55. data/lib/polars/functions/as_datatype.rb +63 -40
  56. data/lib/polars/functions/lazy.rb +63 -14
  57. data/lib/polars/functions/lit.rb +1 -1
  58. data/lib/polars/functions/range/date_range.rb +90 -57
  59. data/lib/polars/functions/range/datetime_range.rb +149 -0
  60. data/lib/polars/functions/range/int_range.rb +2 -2
  61. data/lib/polars/functions/range/time_range.rb +141 -0
  62. data/lib/polars/functions/repeat.rb +1 -1
  63. data/lib/polars/functions/whenthen.rb +1 -1
  64. data/lib/polars/group_by.rb +88 -23
  65. data/lib/polars/io/avro.rb +24 -0
  66. data/lib/polars/{io.rb → io/csv.rb} +299 -493
  67. data/lib/polars/io/database.rb +73 -0
  68. data/lib/polars/io/ipc.rb +247 -0
  69. data/lib/polars/io/json.rb +29 -0
  70. data/lib/polars/io/ndjson.rb +80 -0
  71. data/lib/polars/io/parquet.rb +227 -0
  72. data/lib/polars/lazy_frame.rb +143 -272
  73. data/lib/polars/lazy_group_by.rb +100 -3
  74. data/lib/polars/list_expr.rb +11 -11
  75. data/lib/polars/list_name_space.rb +5 -1
  76. data/lib/polars/rolling_group_by.rb +7 -9
  77. data/lib/polars/series.rb +103 -187
  78. data/lib/polars/string_expr.rb +78 -102
  79. data/lib/polars/string_name_space.rb +5 -4
  80. data/lib/polars/testing.rb +2 -2
  81. data/lib/polars/utils/constants.rb +9 -0
  82. data/lib/polars/utils/convert.rb +97 -0
  83. data/lib/polars/utils/parse.rb +89 -0
  84. data/lib/polars/utils/various.rb +76 -0
  85. data/lib/polars/utils/wrap.rb +19 -0
  86. data/lib/polars/utils.rb +8 -300
  87. data/lib/polars/version.rb +1 -1
  88. data/lib/polars/whenthen.rb +6 -6
  89. data/lib/polars.rb +20 -1
  90. metadata +28 -7
  91. data/ext/polars/src/conversion/anyvalue.rs +0 -186
  92. data/ext/polars/src/dataframe.rs +0 -1208
data/lib/polars/cat_expr.rb CHANGED
@@ -9,42 +9,6 @@ module Polars
9
9
  self._rbexpr = expr._rbexpr
10
10
  end
11
11
 
12
- # Determine how this categorical series should be sorted.
13
- #
14
- # @param ordering ["physical", "lexical"]
15
- # Ordering type:
16
- #
17
- # - 'physical' -> Use the physical representation of the categories to determine the order (default).
18
- # - 'lexical' -> Use the string values to determine the ordering.
19
- #
20
- # @return [Expr]
21
- #
22
- # @example
23
- # df = Polars::DataFrame.new(
24
- # {"cats" => ["z", "z", "k", "a", "b"], "vals" => [3, 1, 2, 2, 3]}
25
- # ).with_columns(
26
- # [
27
- # Polars.col("cats").cast(:cat).cat.set_ordering("lexical")
28
- # ]
29
- # )
30
- # df.sort(["cats", "vals"])
31
- # # =>
32
- # # shape: (5, 2)
33
- # # ┌──────┬──────┐
34
- # # │ cats ┆ vals │
35
- # # │ --- ┆ --- │
36
- # # │ cat ┆ i64 │
37
- # # ╞══════╪══════╡
38
- # # │ a ┆ 2 │
39
- # # │ b ┆ 3 │
40
- # # │ k ┆ 2 │
41
- # # │ z ┆ 1 │
42
- # # │ z ┆ 3 │
43
- # # └──────┴──────┘
44
- def set_ordering(ordering)
45
- Utils.wrap_expr(_rbexpr.cat_set_ordering(ordering))
46
- end
47
-
48
12
  # Get the categories stored in this data type.
49
13
  #
50
14
  # @return [Expr]
data/lib/polars/cat_name_space.rb CHANGED
@@ -10,43 +10,6 @@ module Polars
10
10
  self._s = series._s
11
11
  end
12
12
 
13
- # Determine how this categorical series should be sorted.
14
- #
15
- # @param ordering ["physical", "lexical"]
16
- # Ordering type:
17
- #
18
- # - 'physical' -> Use the physical representation of the categories to
19
- # determine the order (default).
20
- # - 'lexical' -> Use the string values to determine the ordering.
21
- #
22
- # @return [Series]
23
- #
24
- # @example
25
- # df = Polars::DataFrame.new(
26
- # {"cats" => ["z", "z", "k", "a", "b"], "vals" => [3, 1, 2, 2, 3]}
27
- # ).with_columns(
28
- # [
29
- # Polars.col("cats").cast(:cat).cat.set_ordering("lexical")
30
- # ]
31
- # )
32
- # df.sort(["cats", "vals"])
33
- # # =>
34
- # # shape: (5, 2)
35
- # # ┌──────┬──────┐
36
- # # │ cats ┆ vals │
37
- # # │ --- ┆ --- │
38
- # # │ cat ┆ i64 │
39
- # # ╞══════╪══════╡
40
- # # │ a ┆ 2 │
41
- # # │ b ┆ 3 │
42
- # # │ k ┆ 2 │
43
- # # │ z ┆ 1 │
44
- # # │ z ┆ 3 │
45
- # # └──────┴──────┘
46
- def set_ordering(ordering)
47
- super
48
- end
49
-
50
13
  # Get the categories stored in this data type.
51
14
  #
52
15
  # @return [Series]
data/lib/polars/convert.rb CHANGED
@@ -27,7 +27,12 @@ module Polars
27
27
  # # │ 2 ┆ 4 │
28
28
  # # └─────┴─────┘
29
29
  def from_hash(data, schema: nil, columns: nil)
30
- DataFrame._from_hash(data, schema: schema || columns)
30
+ Utils.wrap_df(
31
+ DataFrame.hash_to_rbdf(
32
+ data,
33
+ schema: schema || columns
34
+ )
35
+ )
31
36
  end
32
37
 
33
38
  # Construct a DataFrame from a sequence of dictionaries. This operation clones data.