easy_ml 0.2.0.pre.rc77 → 0.2.0.pre.rc81
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/app/controllers/easy_ml/datasets_controller.rb +3 -3
- data/app/controllers/easy_ml/models_controller.rb +4 -3
- data/app/frontend/components/ModelForm.tsx +16 -0
- data/app/frontend/components/ScheduleModal.tsx +0 -2
- data/app/frontend/components/dataset/PreprocessingConfig.tsx +7 -6
- data/app/jobs/easy_ml/application_job.rb +1 -0
- data/app/jobs/easy_ml/batch_job.rb +47 -6
- data/app/jobs/easy_ml/compute_feature_job.rb +10 -10
- data/app/jobs/easy_ml/reaper.rb +14 -10
- data/app/jobs/easy_ml/refresh_dataset_job.rb +2 -0
- data/app/jobs/easy_ml/sync_datasource_job.rb +1 -0
- data/app/models/concerns/easy_ml/dataframe_serialization.rb +1 -17
- data/app/models/easy_ml/column/imputers/base.rb +1 -1
- data/app/models/easy_ml/column/imputers/imputer.rb +2 -0
- data/app/models/easy_ml/column/imputers/today.rb +1 -1
- data/app/models/easy_ml/column/selector.rb +0 -8
- data/app/models/easy_ml/column.rb +1 -1
- data/app/models/easy_ml/column_list.rb +2 -3
- data/app/models/easy_ml/dataset/learner/base.rb +2 -2
- data/app/models/easy_ml/dataset/learner/eager.rb +3 -1
- data/app/models/easy_ml/dataset/learner/lazy.rb +4 -1
- data/app/models/easy_ml/dataset.rb +47 -38
- data/app/models/easy_ml/datasource.rb +0 -6
- data/app/models/easy_ml/feature.rb +33 -8
- data/app/models/easy_ml/model.rb +27 -4
- data/app/models/easy_ml/models/hyperparameters/xgboost/gbtree.rb +21 -5
- data/app/models/easy_ml/models/xgboost/evals_callback.rb +9 -5
- data/app/models/easy_ml/models/xgboost.rb +58 -36
- data/app/models/easy_ml/retraining_run.rb +1 -1
- data/app/serializers/easy_ml/model_serializer.rb +1 -0
- data/lib/easy_ml/core/tuner/adapters/base_adapter.rb +16 -3
- data/lib/easy_ml/core/tuner/adapters/xgboost_adapter.rb +0 -17
- data/lib/easy_ml/core/tuner.rb +14 -5
- data/lib/easy_ml/data/dataset_manager/reader/base.rb +12 -0
- data/lib/easy_ml/data/dataset_manager/reader/data_frame.rb +8 -3
- data/lib/easy_ml/data/dataset_manager/reader/file.rb +5 -0
- data/lib/easy_ml/data/dataset_manager/reader.rb +7 -1
- data/lib/easy_ml/data/dataset_manager/writer/base.rb +26 -9
- data/lib/easy_ml/data/dataset_manager/writer.rb +5 -1
- data/lib/easy_ml/data/dataset_manager.rb +18 -4
- data/lib/easy_ml/data/embeddings/adapters.rb +56 -0
- data/lib/easy_ml/data/embeddings/compression.rb +0 -0
- data/lib/easy_ml/data/embeddings.rb +43 -0
- data/lib/easy_ml/data/polars_column.rb +19 -5
- data/lib/easy_ml/engine.rb +16 -14
- data/lib/easy_ml/feature_store.rb +19 -16
- data/lib/easy_ml/support/lockable.rb +1 -5
- data/lib/easy_ml/version.rb +1 -1
- data/public/easy_ml/assets/.vite/manifest.json +1 -1
- data/public/easy_ml/assets/assets/entrypoints/Application.tsx-Bbf3mD_b.js +522 -0
- data/public/easy_ml/assets/assets/entrypoints/{Application.tsx-B1qLZuyu.js.map → Application.tsx-Bbf3mD_b.js.map} +1 -1
- metadata +9 -7
- data/app/models/easy_ml/datasources/polars_datasource.rb +0 -69
- data/public/easy_ml/assets/assets/entrypoints/Application.tsx-B1qLZuyu.js +0 -522
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: easy_ml
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.0.pre.
|
4
|
+
version: 0.2.0.pre.rc81
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Brett Shollenberger
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2025-02-
|
11
|
+
date: 2025-02-19 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: activerecord
|
@@ -198,14 +198,14 @@ dependencies:
|
|
198
198
|
requirements:
|
199
199
|
- - "~>"
|
200
200
|
- !ruby/object:Gem::Version
|
201
|
-
version: 0.
|
201
|
+
version: 0.17.0
|
202
202
|
type: :runtime
|
203
203
|
prerelease: false
|
204
204
|
version_requirements: !ruby/object:Gem::Requirement
|
205
205
|
requirements:
|
206
206
|
- - "~>"
|
207
207
|
- !ruby/object:Gem::Version
|
208
|
-
version: 0.
|
208
|
+
version: 0.17.0
|
209
209
|
- !ruby/object:Gem::Dependency
|
210
210
|
name: pycall
|
211
211
|
requirement: !ruby/object:Gem::Requirement
|
@@ -610,7 +610,6 @@ files:
|
|
610
610
|
- app/models/easy_ml/datasource_history.rb
|
611
611
|
- app/models/easy_ml/datasources/base_datasource.rb
|
612
612
|
- app/models/easy_ml/datasources/file_datasource.rb
|
613
|
-
- app/models/easy_ml/datasources/polars_datasource.rb
|
614
613
|
- app/models/easy_ml/datasources/s3_datasource.rb
|
615
614
|
- app/models/easy_ml/deploy.rb
|
616
615
|
- app/models/easy_ml/event.rb
|
@@ -720,6 +719,9 @@ files:
|
|
720
719
|
- lib/easy_ml/data/dataset_manager/writer/partitioned.rb
|
721
720
|
- lib/easy_ml/data/dataset_manager/writer/partitioned/partition_reasons.rb
|
722
721
|
- lib/easy_ml/data/date_converter.rb
|
722
|
+
- lib/easy_ml/data/embeddings.rb
|
723
|
+
- lib/easy_ml/data/embeddings/adapters.rb
|
724
|
+
- lib/easy_ml/data/embeddings/compression.rb
|
723
725
|
- lib/easy_ml/data/partition.rb
|
724
726
|
- lib/easy_ml/data/partition/boundaries.rb
|
725
727
|
- lib/easy_ml/data/polars_column.rb
|
@@ -800,8 +802,8 @@ files:
|
|
800
802
|
- public/easy_ml/assets/.vite/manifest-assets.json
|
801
803
|
- public/easy_ml/assets/.vite/manifest.json
|
802
804
|
- public/easy_ml/assets/assets/Application-nnn_XLuL.css
|
803
|
-
- public/easy_ml/assets/assets/entrypoints/Application.tsx-
|
804
|
-
- public/easy_ml/assets/assets/entrypoints/Application.tsx-
|
805
|
+
- public/easy_ml/assets/assets/entrypoints/Application.tsx-Bbf3mD_b.js
|
806
|
+
- public/easy_ml/assets/assets/entrypoints/Application.tsx-Bbf3mD_b.js.map
|
805
807
|
homepage: https://github.com/brettshollenberger/easy_ml
|
806
808
|
licenses:
|
807
809
|
- MIT
|
@@ -1,69 +0,0 @@
|
|
1
|
-
module EasyML
|
2
|
-
module Datasources
|
3
|
-
class PolarsDatasource < BaseDatasource
|
4
|
-
include EasyML::DataframeSerialization
|
5
|
-
|
6
|
-
validates :df, presence: true
|
7
|
-
add_configuration_attributes :df
|
8
|
-
|
9
|
-
def query(**kwargs)
|
10
|
-
EasyML::Data::PolarsInMemory.query(df, **kwargs)
|
11
|
-
end
|
12
|
-
|
13
|
-
def in_batches(of: 10_000)
|
14
|
-
total_rows = df.shape[0]
|
15
|
-
(0...total_rows).step(of) do |start|
|
16
|
-
end_index = [start + of, total_rows].min
|
17
|
-
yield df.slice(start, end_index - start)
|
18
|
-
end
|
19
|
-
end
|
20
|
-
|
21
|
-
def all_files
|
22
|
-
[]
|
23
|
-
end
|
24
|
-
|
25
|
-
def files
|
26
|
-
[]
|
27
|
-
end
|
28
|
-
|
29
|
-
def last_updated_at
|
30
|
-
datasource.updated_at
|
31
|
-
end
|
32
|
-
|
33
|
-
def sha
|
34
|
-
nil
|
35
|
-
end
|
36
|
-
|
37
|
-
def data
|
38
|
-
df
|
39
|
-
end
|
40
|
-
|
41
|
-
def df
|
42
|
-
datasource.df
|
43
|
-
end
|
44
|
-
|
45
|
-
def exists?
|
46
|
-
df.present?
|
47
|
-
end
|
48
|
-
|
49
|
-
def error_not_exists
|
50
|
-
"Must have a dataframe"
|
51
|
-
end
|
52
|
-
|
53
|
-
def store_in_configuration
|
54
|
-
return unless df
|
55
|
-
|
56
|
-
datasource.configuration = (datasource.configuration || {}).merge(
|
57
|
-
"df" => serialize_dataframe(df),
|
58
|
-
)
|
59
|
-
end
|
60
|
-
|
61
|
-
def read_from_configuration
|
62
|
-
return unless datasource.configuration&.key?("df")
|
63
|
-
|
64
|
-
df_data = datasource.configuration["df"]
|
65
|
-
datasource.df = deserialize_dataframe(df_data)
|
66
|
-
end
|
67
|
-
end
|
68
|
-
end
|
69
|
-
end
|