easy_ml 0.2.0.pre.rc81 → 0.2.0.pre.rc82

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 169873e9ea5e1b00f7a4e499a2aeffc377615757cdd4b5fe6d70c8c454b9d426
-  data.tar.gz: fc1d4509606f011bd3adbdf367e767a3e9dfc4fdbb6b5cd91bb413f72da364b2
+  metadata.gz: ce245d6900c4c5c001c0de9982894ccf6b41faef31e8c958dc540ef05fe426e4
+  data.tar.gz: a120f14076a9ff83ca6afb8b0bd651b9ea9ed0185d42f23b82f5de6b2a4de831
 SHA512:
-  metadata.gz: f4ea106a66d3185f612e481b607cef21f5453a00ef6eb12558e53f43aa1d68b8f20d1e950c1840d97180ba6271db9b9b42c8a2d480c22ca8c1e33d1b768590d2
-  data.tar.gz: 24885cdecd46d612be8b8ce7d4bd9889bdf60420bc82c01993cfe0168e454ebdaaa70899f5cf9cc879ff89a895fd00b1761d01c945dafffc784f7bc1e4a2fb8e
+  metadata.gz: db2b7292bf07b5122a7949a111c56a25f8848496eaadfc94f101a271054fd4c21d401b4c941f69d7579c8cdc9887e68c4105f11720dba13aa7fd0fcdafb79b81
+  data.tar.gz: f5dc8ffee52fb67b6cda8e4462e540900d528dd9c15ff49faa8ca45f21f9e4968129b996a5018a91801aae431a65b5274d64e69045e5feeeec6f12f09900cda3

data/app/jobs/easy_ml/training_job.rb

@@ -10,13 +10,13 @@ module EasyML
 
       @last_activity = Time.current
       setup_signal_traps
-      @monitor_thread = start_monitor_thread
+      # @monitor_thread = start_monitor_thread
 
       @model.actually_train do |iteration_info|
         @last_activity = Time.current
       end
     ensure
-      @monitor_thread&.exit
+      # @monitor_thread&.exit
       @model.unlock!
     end
 

data/app/models/easy_ml/feature.rb

@@ -81,7 +81,10 @@ module EasyML
             fittable = fittable.select(&:fittable?)
             where(id: fittable.map(&:id))
           end
-    scope :needs_fit, -> { has_changes.or(never_applied).or(never_fit) }
+    scope :needs_fit, -> { has_changes.or(never_applied).or(never_fit).or(datasource_was_refreshed) }
+    scope :datasource_was_refreshed, -> do
+            where(id: all.select(&:datasource_was_refreshed?).map(&:id))
+          end
     scope :ready_to_apply, -> do
             base = where(needs_fit: false).where.not(id: has_changes.map(&:id))
             doesnt_fit = where_no_fit
@@ -144,6 +147,7 @@ module EasyML
     end
 
     def datasource_was_refreshed?
+      return false unless fittable?
       return true if fit_at.nil?
       return false if dataset.datasource.refreshed_at.nil?
 

data/app/models/easy_ml/model.rb

@@ -624,8 +624,8 @@ module EasyML
     private
 
     def default_evaluation_inputs
-      x_true, y_true = dataset.test(split_ys: true)
-      ds = dataset.test(all_columns: true)
+      x_true, y_true = dataset.processed.test(split_ys: true, all_columns: true)
+      ds = dataset.processed.test(all_columns: true)
       y_pred = predict(x_true)
       {
         x_true: x_true,

data/app/models/easy_ml/models/xgboost/evals_callback.rb

@@ -50,7 +50,7 @@ module EasyML
             x_valid = x_valid.select(model.dataset.col_order(inference: true))
             @preprocessed ||= model.preprocess(x_valid, y_valid)
             y_pred = model.predict(@preprocessed)
-            dataset = model.dataset.valid(all_columns: true)
+            dataset = model.dataset.processed.valid(all_columns: true)
 
             metrics = model.evaluate(y_pred: y_pred, y_true: y_valid, x_true: x_valid, dataset: dataset)
             Wandb.log(metrics)

data/app/models/easy_ml/models/xgboost.rb

@@ -427,11 +427,11 @@ module EasyML
       def prepare_data
         if @d_train.nil?
           col_order = dataset.col_order
-          x_sample, y_sample = dataset.train(split_ys: true, limit: 5, select: col_order, lazy: true)
+          x_sample, y_sample = dataset.processed.train(split_ys: true, limit: 5, select: col_order, lazy: true)
           preprocess(x_sample, y_sample) # Ensure we fail fast if the dataset is misconfigured
-          x_train, y_train = dataset.train(split_ys: true, select: col_order, lazy: true)
-          x_valid, y_valid = dataset.valid(split_ys: true, select: col_order, lazy: true)
-          x_test, y_test = dataset.test(split_ys: true, select: col_order, lazy: true)
+          x_train, y_train = dataset.processed.train(split_ys: true, select: col_order, lazy: true)
+          x_valid, y_valid = dataset.processed.valid(split_ys: true, select: col_order, lazy: true)
+          x_test, y_test = dataset.processed.test(split_ys: true, select: col_order, lazy: true)
           @d_train = preprocess(x_train, y_train)
           @d_valid = preprocess(x_valid, y_valid)
           @d_test = preprocess(x_test, y_test)
@@ -457,7 +457,7 @@ module EasyML
         lazy = xs.is_a?(Polars::LazyFrame)
         return xs if (lazy ? xs.limit(1).collect : xs).shape[0] == 0
 
-        weights_col = model.weights_column || nil
+        weights_col = (model.weights_column.nil? || model.weights_column.blank?) ? nil : model.weights_column
 
         if weights_col == model.dataset.target
           raise ArgumentError, "Weight column cannot be the target column"
@@ -468,11 +468,7 @@ module EasyML
         feature_cols -= [weights_col] if weights_col
 
         # Get features, labels and weights
-        begin
-          features = lazy ? xs.select(feature_cols).collect.to_numo : xs.select(feature_cols).to_numo
-        rescue => e
-          binding.pry
-        end
+        features = lazy ? xs.select(feature_cols).collect.to_numo : xs.select(feature_cols).to_numo
         weights = weights_col ? (lazy ? xs.select(weights_col).collect.to_numo : xs.select(weights_col).to_numo) : nil
         weights = weights.flatten if weights
         if ys.present?

data/lib/easy_ml/core/tuner.rb

@@ -73,13 +73,13 @@ module EasyML
         model.task = task
 
         model.dataset.refresh if model.dataset.needs_refresh?
-        x_valid, y_valid = model.dataset.valid(split_ys: true, all_columns: true)
+        x_valid, y_valid = model.dataset.processed.valid(split_ys: true, all_columns: true)
         x_normalized = model.dataset.normalize(x_valid, inference: true)
         x_normalized = model.preprocess(x_normalized)
         self.x_valid = x_valid
         self.y_valid = y_valid
         self.x_normalized = x_normalized
-        self.dataset = model.dataset.valid(all_columns: true)
+        self.dataset = model.dataset.processed.valid(all_columns: true)
         adapter.tune_started_at = tune_started_at
         adapter.x_valid = x_valid
         adapter.y_valid = y_valid

data/lib/easy_ml/data/dataset_manager/writer/base.rb

@@ -95,7 +95,7 @@ module EasyML
             keylist = unique_id_key(subdir: "keylist")
 
             acquire_lock(keylist) do |suo|
-              suo.client.sadd(keylist, key)
+              suo.client.sadd?(keylist, key)
             end
           end
 

data/lib/easy_ml/data/embeddings/compression.rb

@@ -0,0 +1 @@
+

data/lib/easy_ml/version.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 module EasyML
-  VERSION = "0.2.0-rc81"
+  VERSION = "0.2.0-rc82"
 
   module Version
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: easy_ml
 version: !ruby/object:Gem::Version
-  version: 0.2.0.pre.rc81
+  version: 0.2.0.pre.rc82
 platform: ruby
 authors:
 - Brett Shollenberger
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-02-19 00:00:00.000000000 Z
+date: 2025-02-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activerecord