red-arrow-activerecord 0.1.2 → 0.1.3
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/doc/text/news.md +6 -0
- data/lib/arrow-activerecord/arrowable.rb +23 -14
- data/lib/arrow-activerecord/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: e8d253180a9bf6653d4034c162efd4b092e4ea9e44f983c2f4cb8ea2aa95c8e1
|
|
4
|
+
data.tar.gz: d5d7ea4de22c17357d4eefa6518fadc8c88420e161be91df946e85dfdf7964c9
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 90502eefb44fd4d6d6ffa6e66ce9864b5c6e0b384885ff5f5512f640629b19100a3d708af5b2644711bb6a25988f26bda90ee88c3f5adaad698288bda81a2f6c
|
|
7
|
+
data.tar.gz: 38f2b95f2da0f994ee554edeedaff59d5a5ec19a344c2c0957b74647f78c0bb20538d8d0119766f728356bd9e54850c95212a13160a8a64e61c914791eb73029
|
data/doc/text/news.md
CHANGED
|
@@ -3,20 +3,15 @@ require 'arrow'
|
|
|
3
3
|
module ArrowActiveRecord
|
|
4
4
|
module Arrowable
|
|
5
5
|
def to_arrow(batch_size: 10000)
|
|
6
|
-
|
|
7
|
-
|
|
6
|
+
record_batches = each_record_batch(batch_size:).to_a
|
|
7
|
+
Arrow::Table.new(record_batches.first.schema, record_batches)
|
|
8
|
+
end
|
|
8
9
|
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
name = name.to_s
|
|
12
|
-
target_column = columns.find do |column|
|
|
13
|
-
column.name == name
|
|
14
|
-
end
|
|
15
|
-
fields << {name: name, data_type: extract_arrow_data_type(target_column)}
|
|
16
|
-
end
|
|
17
|
-
schema = Arrow::Schema.new(fields)
|
|
10
|
+
def each_record_batch(batch_size: 10000, &block)
|
|
11
|
+
return to_enum(__method__, batch_size:) unless block_given?
|
|
18
12
|
|
|
19
|
-
|
|
13
|
+
schema = build_arrow_schema
|
|
14
|
+
target_column_names = schema.fields.collect(&:name)
|
|
20
15
|
record_batch_builder = Arrow::RecordBatchBuilder.new(schema)
|
|
21
16
|
in_batches(of: batch_size).each do |relation|
|
|
22
17
|
records = relation.pluck(*target_column_names)
|
|
@@ -27,12 +22,26 @@ module ArrowActiveRecord
|
|
|
27
22
|
else
|
|
28
23
|
record_batch_builder.append(records)
|
|
29
24
|
end
|
|
30
|
-
|
|
25
|
+
yield(record_batch_builder.flush)
|
|
31
26
|
end
|
|
32
|
-
Arrow::Table.new(schema, record_batches)
|
|
33
27
|
end
|
|
34
28
|
|
|
35
29
|
private
|
|
30
|
+
def build_arrow_schema
|
|
31
|
+
target_column_names = select_values
|
|
32
|
+
target_column_names = column_names if select_values.empty?
|
|
33
|
+
|
|
34
|
+
fields = []
|
|
35
|
+
target_column_names.each do |name|
|
|
36
|
+
name = name.to_s
|
|
37
|
+
target_column = columns.find do |column|
|
|
38
|
+
column.name == name
|
|
39
|
+
end
|
|
40
|
+
fields << {name: name, data_type: extract_arrow_data_type(target_column)}
|
|
41
|
+
end
|
|
42
|
+
Arrow::Schema.new(fields)
|
|
43
|
+
end
|
|
44
|
+
|
|
36
45
|
def extract_arrow_data_type(column)
|
|
37
46
|
type = nil
|
|
38
47
|
if column
|