easy_ml 0.1.1 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7a959176791dac2307979438ad0f9a9319b4295fe25e489214df5f3b4c908466
-  data.tar.gz: c665ef3c19fda35197be653d9c14a34e9b2256d3c1b7387be4313086ba5d2c11
+  metadata.gz: c68319b0bcca7b83e1fb4a539a15b42ced62475f8c8ab7f6b9a7a164c3b02cea
+  data.tar.gz: 1a6a83e77ff7723c590ab1238ce12d80aa6aa15bb5897b95a738c0a00760fb48
 SHA512:
-  metadata.gz: bda834230add0f3de2b57d8df4abde48f79f64275946b372d5069b49c610ab09c8cc1117a89a2d9206100b19b30c8f30bbfbe2d8973ce5db551626bfb612949d
-  data.tar.gz: 3d80ffc4930323f3b8cff51ef2e3475f557589e96d54717c750a63507c3c3ab682650c7ccb4daf2bd1168cb35627c0101579e8bd26b310e86906e134c6626249
+  metadata.gz: 8e1e3fdcbae41205892d47be90407b982efdce329b54b635ea2870d141297780ce6f166ab1769f3d531bf51906ff25c17a2d1b8d6a8aed0ea4e1e12052ff8eec
+  data.tar.gz: 31b5b12f27734f44fa92015feb8e4ac5c868f38090c3244a90f15b83327427fc05f3d2a34446d1b64f11ba10903bb1b989e890b8a63381c3da2e5a1330b5f778

data/app/models/easy_ml/model.rb

@@ -1,9 +1,18 @@
 require_relative "../../../lib/easy_ml/core/model"
 module EasyML
   class Model < ActiveRecord::Base
-    include EasyML::Core::ModelCore
+    if ActiveRecord::Base.connection.data_source_exists?("easy_ml_models")
+      include EasyML::Core::ModelCore
 
-    self.table_name = "easy_ml_models"
+      self.table_name = "easy_ml_models"
+    else
+      # Placeholder if the table doesn't exist (keeps the file quiet)
+      def self.table_ready?
+        false
+      end
+
+      Rails.logger.info("Skipping EasyML::Model definition as the 'easy_ml_models' table doesn't exist.")
+    end
 
     scope :live, -> { where(is_live: true) }
     attribute :root_dir, :string

data/lib/easy_ml/core/model.rb

@@ -9,6 +9,7 @@ module EasyML
 
       attribute :name, :string
       attribute :version, :string
+      attribute :verbose, :boolean, default: false
       attribute :task, :string, default: "regression"
       attribute :metrics, :array
       attribute :ml_model, :string

data/lib/easy_ml/core/model_core.rb

@@ -21,30 +21,6 @@ module EasyML
         end
       end
 
-      def dataset_is_a_dataset?
-        return if dataset.nil?
-        return if dataset.class.ancestors.include?(EasyML::Data::Dataset)
-
-        errors.add(:dataset, "Must be a subclass of EasyML::Dataset")
-      end
-
-      def validate_any_metrics?
-        return if metrics.any?
-
-        errors.add(:metrics, "Must include at least one metric. Allowed metrics are #{allowed_metrics.join(", ")}")
-      end
-
-      def validate_metrics_for_task
-        nonsensical_metrics = metrics.select do |metric|
-          allowed_metrics.exclude?(metric)
-        end
-
-        return unless nonsensical_metrics.any?
-
-        errors.add(:metrics,
-                   "cannot use metrics: #{nonsensical_metrics.join(", ")} for task #{task}. Allowed metrics are: #{allowed_metrics.join(", ")}")
-      end
-
       def fit(x_train: nil, y_train: nil, x_valid: nil, y_valid: nil)
         if x_train.nil?
           dataset.refresh!
@@ -55,16 +31,6 @@ module EasyML
         @is_fit = true
       end
 
-      def decode_labels(ys, col: nil)
-        dataset.decode_labels(ys, col: col)
-      end
-
-      def evaluate(y_pred: nil, y_true: nil, x_true: nil, evaluator: nil)
-        evaluator ||= self.evaluator
-        EasyML::Core::ModelEvaluator.evaluate(model: self, y_pred: y_pred, y_true: y_true, x_true: x_true,
-                                              evaluator: evaluator)
-      end
-
       def predict(xs)
         raise NotImplementedError, "Subclasses must implement predict method"
       end
@@ -82,6 +48,16 @@ module EasyML
         save_model_file
       end
 
+      def decode_labels(ys, col: nil)
+        dataset.decode_labels(ys, col: col)
+      end
+
+      def evaluate(y_pred: nil, y_true: nil, x_true: nil, evaluator: nil)
+        evaluator ||= self.evaluator
+        EasyML::Core::ModelEvaluator.evaluate(model: self, y_pred: y_pred, y_true: y_true, x_true: x_true,
+                                              evaluator: evaluator)
+      end
+
       def save_model_file
         raise "No trained model! Need to train model before saving (call model.fit)" unless fit?
 
@@ -116,13 +92,13 @@ module EasyML
       end
 
       def cleanup!
-        [file_dir, model_dir].each do |dir|
+        [carrierwave_dir, model_dir].each do |dir|
           EasyML::FileRotate.new(dir, []).cleanup(extension_allowlist)
         end
       end
 
       def cleanup
-        [file_dir, model_dir].each do |dir|
+        [carrierwave_dir, model_dir].each do |dir|
           EasyML::FileRotate.new(dir, files_to_keep).cleanup(extension_allowlist)
         end
       end
@@ -133,7 +109,7 @@ module EasyML
 
       private
 
-      def file_dir
+      def carrierwave_dir
         return unless file.path.present?
 
         File.dirname(file.path).split("/")[0..-2].join("/")
@@ -172,10 +148,34 @@ module EasyML
       end
 
       def files_to_keep
-        Dir.glob(File.join(file_dir, "*")).select { |f| File.file?(f) }.sort_by do |filename|
+        Dir.glob(File.join(carrierwave_dir, "**/*")).select { |f| File.file?(f) }.sort_by do |filename|
           Time.parse(filename.split("/").last.gsub(/\D/, ""))
         end.reverse.take(5)
       end
+
+      def dataset_is_a_dataset?
+        return if dataset.nil?
+        return if dataset.class.ancestors.include?(EasyML::Data::Dataset)
+
+        errors.add(:dataset, "Must be a subclass of EasyML::Dataset")
+      end
+
+      def validate_any_metrics?
+        return if metrics.any?
+
+        errors.add(:metrics, "Must include at least one metric. Allowed metrics are #{allowed_metrics.join(", ")}")
+      end
+
+      def validate_metrics_for_task
+        nonsensical_metrics = metrics.select do |metric|
+          allowed_metrics.exclude?(metric)
+        end
+
+        return unless nonsensical_metrics.any?
+
+        errors.add(:metrics,
+                   "cannot use metrics: #{nonsensical_metrics.join(", ")} for task #{task}. Allowed metrics are: #{allowed_metrics.join(", ")}")
+      end
     end
   end
 end

data/lib/easy_ml/core/models/xgboost_core.rb

@@ -155,7 +155,7 @@ module EasyML
           ys = ys.nil? ? nil : _preprocess(ys).flatten
           kwargs = { label: ys }.compact
           ::XGBoost::DMatrix.new(xs, **kwargs).tap do |dmat|
-            dmat.instance_variable_set(:@feature_names, column_names)
+            dmat.feature_names = column_names
           end
         end
 

data/lib/easy_ml/data/preprocessor/simple_imputer.rb

@@ -179,7 +179,6 @@ module EasyML
           min_ct = options[:categorical_min] || 25
           allowed_values = values.select { |_v, c| c >= min_ct }.keys.map(&:to_s)
 
-          binding.pry
           allowed_values.include?(val.to_s) ? val.to_s : "other"
         end
 

data/lib/easy_ml/railtie/generators/migration/migration_generator.rb

@@ -1,4 +1,3 @@
-# lib/railtie/generators/migration/migration_generator.rb
 require "rails/generators"
 require "rails/generators/active_record/migration"
 
@@ -13,12 +12,7 @@ module EasyML
         source_root File.expand_path("../../templates/migration", __dir__)
 
         # Define the migration name
-        desc "Generates a migration for EasyMLModel with version and file for remote storage"
-
-        # Define the migration name; can be customized if needed
-        def self.migration_name
-          "create_easy_ml_models"
-        end
+        desc "Generates migrations for EasyMLModel, Dataset, and TunerRun"
 
         # Specify the next migration number
         def self.next_migration_number(dirname)
@@ -31,10 +25,24 @@ module EasyML
           end
         end
 
-        # Generate the migration file using the template
-        def create_migration_file
-          migration_template "create_easy_ml_models.rb.tt",
-                             "db/migrate/#{self.class.migration_name}.rb"
+        # Generate the migration files using the templates
+        def create_migration_files
+          create_easy_ml_models_migration
+        end
+
+        private
+
+        # Generate the migration file for EasyMLModel using the template
+        def create_easy_ml_models_migration
+          migration_template(
+            "create_easy_ml_models.rb.tt",
+            "db/migrate/create_easy_ml_models.rb"
+          )
+        end
+
+        # Get the next migration number
+        def next_migration_number
+          self.class.next_migration_number(Rails.root.join("db/migrate"))
         end
       end
     end

data/lib/easy_ml/support/file_rotate.rb

@@ -16,7 +16,7 @@ module EasyML
       files_to_check.each do |file|
         FileUtils.chown_R(`whoami`.chomp, "staff", file)
         FileUtils.chmod_R(0o777, file)
-        File.delete(file) unless @files_to_keep.include?(file)
+        File.delete(file) if @files_to_keep.exclude?(file) && File.exist?(file)
       end
     end
   end

data/lib/easy_ml/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module EasyML
-  VERSION = "0.1.1"
+  VERSION = "0.1.3"
 end

data/lib/easy_ml.rb

@@ -19,5 +19,4 @@ module EasyML
   require_relative "easy_ml/data"
   require_relative "easy_ml/transforms"
   require_relative "easy_ml/core"
-  require_relative "easy_ml/trainer"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: easy_ml
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.3
 platform: ruby
 authors:
 - Brett Shollenberger
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-10-17 00:00:00.000000000 Z
+date: 2024-10-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activerecord
@@ -58,20 +58,34 @@ dependencies:
     - - "<"
       - !ruby/object:Gem::Version
         version: '4'
+- !ruby/object:Gem::Dependency
+  name: fog
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.42'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.42'
 - !ruby/object:Gem::Dependency
   name: fog-aws
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '2.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '2.0'
 - !ruby/object:Gem::Dependency
   name: glue_gun_dsl
   requirement: !ruby/object:Gem::Requirement
@@ -156,6 +170,34 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: wandb
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.1.6
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.1.6
+- !ruby/object:Gem::Dependency
+  name: xgb
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: annotate
   requirement: !ruby/object:Gem::Requirement
@@ -321,7 +363,6 @@ files:
 - lib/easy_ml/support/git_ignorable.rb
 - lib/easy_ml/support/synced_directory.rb
 - lib/easy_ml/support/utc.rb
-- lib/easy_ml/trainer.rb
 - lib/easy_ml/transforms.rb
 - lib/easy_ml/version.rb
 homepage: https://github.com/brettshollenberger/easy_ml

data/lib/easy_ml/trainer.rb

@@ -1,92 +0,0 @@
-module EasyML
-  class Trainer
-    # include GlueGun::DSL
-    # include EasyML::Logging
-
-    # define_attr :verbose, default: false
-    # define_attr :root_dir do |root_dir|
-    #   File.join(root_dir, "trainer")
-    # end
-
-    # define_config :dataset do |config|
-    #   config.define_option :default do |option|
-    #     option.set_class EasyML::Data::Dataset
-    #     option.define_attr :root_dir
-    #     option.define_attr :target
-    #     option.define_attr :batch_size
-    #   end
-    # end
-
-    # define_config :model do |config|
-    #   config.define_option :default do |option|
-    #     option.set_class EasyML::Model
-    #     option.define_attr :root_dir
-    #     option.define_attr :name
-    #     option.define_attr :hyperparameters
-    #   end
-    # end
-
-    # def train
-    #   log_info("Starting training process") if verbose
-
-    #   dataset.refresh!
-
-    #   log_info("Fitting model") if verbose
-    #   dataset.train(split_ys: true) do |xs, ys|
-    #     model.fit(xs, ys)
-    #   end
-
-    #   log_info("Saving model") if verbose
-    #   model.save
-
-    #   log_info("Training completed") if verbose
-    # end
-
-    # def evaluate
-    #   log_info("Starting evaluation process") if verbose
-
-    #   results = {}
-
-    #   %i[train test valid].each do |split|
-    #     log_info("Evaluating on #{split} set") if verbose
-    #     predictions = []
-    #     actuals = []
-
-    #     dataset.send(split, split_ys: true) do |xs, ys|
-    #       batch_predictions = model.predict(xs)
-    #       predictions.concat(batch_predictions.to_a)
-    #       actuals.concat(ys.to_a)
-    #     end
-
-    #     results[split] = calculate_metrics(predictions, actuals)
-    #   end
-
-    #   log_info("Evaluation completed") if verbose
-    #   results
-    # end
-
-    # private
-
-    # def calculate_metrics(predictions, actuals)
-    #   # Implement your metric calculations here
-    #   # This is a placeholder and should be replaced with actual metric calculations
-    #   {
-    #     mse: mean_squared_error(predictions, actuals),
-    #     mae: mean_absolute_error(predictions, actuals),
-    #     r2: r_squared(predictions, actuals)
-    #   }
-    # end
-
-    # def mean_squared_error(predictions, actuals)
-    #   # Implement MSE calculation
-    # end
-
-    # def mean_absolute_error(predictions, actuals)
-    #   # Implement MAE calculation
-    # end
-
-    # def r_squared(predictions, actuals)
-    #   # Implement R-squared calculation
-    # end
-  end
-end