easy_ml 0.2.0.pre.rc9 → 0.2.0.pre.rc10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 27e223058d1e119b3f70e39fee2425e50e3d94780fbf9a54ea496e0d713f2492
-  data.tar.gz: 42b8ffa08fe474412946628bfb7de71d83bccc4195a779db4fafd87002799c42
+  metadata.gz: 798cbe6a945c8321a2289622602ff4a0c71b6f3558eff1523a0352107cd41473
+  data.tar.gz: 4795d77060af37384555cea4e2a3c2c6c0f4ce9577d3fdc91b73b6aca0f864d3
 SHA512:
-  metadata.gz: e448d3ed98f5a3b96893115865d37a3890684de543e3a7746b11c43c184d568d775c3a38c0b06fae34b00aeaa1eb76c012f3becc91e7637aeacf85ec902ec64f
-  data.tar.gz: 83f5d575fe8ff06d3d57ac287faacf820905313ac16d6e36bf8d54f672363a62043c078ca9121cd8e7d10b2eab08125c53e005474ca17f543e429a6feb96f79e
+  metadata.gz: 921c16d1d885c441eee2b5249d4eb4eb8fa988d7ef5768579bc76c1784cef55f4cc40b0ad2c2c81fd28fb66f246a8f67b89637e48a05b4abcf6454ede516383a
+  data.tar.gz: '0039a45b69bfe5c7e306305e980784b509e4721e04a2775209a6200155fa407e58fb2efb058fb3dffde725a74c51555493f4337df67c6793a356dba31b286128'

data/app/.vite/manifest-assets.json

@@ -0,0 +1 @@
+{}

data/app/.vite/manifest.json

@@ -0,0 +1,17 @@
+{
+  "entrypoints/Application.tsx": {
+    "file": "assets/Application-GDgZ4vVt.js",
+    "name": "entrypoints/Application.tsx",
+    "src": "entrypoints/Application.tsx",
+    "isEntry": true,
+    "css": [
+      "assets/Application-tsa3Id3n.css"
+    ]
+  },
+  "entrypoints/application.js": {
+    "file": "assets/application-DBfCPIOZ.js",
+    "name": "entrypoints/application.js",
+    "src": "entrypoints/application.js",
+    "isEntry": true
+  }
+}

data/app/easy_ml/.vite/manifest-assets.json

@@ -0,0 +1 @@
+{}

data/app/easy_ml/.vite/manifest.json

@@ -0,0 +1,11 @@
+{
+  "entrypoints/Application.tsx": {
+    "file": "assets/Application-GDgZ4vVt.js",
+    "name": "entrypoints/Application.tsx",
+    "src": "entrypoints/Application.tsx",
+    "isEntry": true,
+    "css": [
+      "assets/Application-tsa3Id3n.css"
+    ]
+  }
+}

data/bin/build

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+set -e
+
+bin/build_vite
+gem build easy_ml.gemspec

data/bin/build_vite

@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+set -e
+
+echo "Building production assets for EasyML gem..."
+# Run the Vite production build
+bundle exec vite build
+echo "Production assets built successfully."

data/bin/console

@@ -0,0 +1,11 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require "bundler/setup"
+require "easy_ml"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+require "irb"
+IRB.start(__FILE__)

data/bin/rspec

@@ -0,0 +1,28 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+#
+# This file was generated by Bundler.
+#
+# The application 'rspec' is installed as part of a gem, and
+# this file is here to facilitate running it.
+#
+
+ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../Gemfile", __dir__)
+ENV['SPRING_APPLICATION_ROOT'] = './spec/internal'
+
+bundle_binstub = File.expand_path("bundle", __dir__)
+
+if File.file?(bundle_binstub)
+  if File.read(bundle_binstub, 300).include?("This file was generated by Bundler")
+    load(bundle_binstub)
+  else
+    abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
+Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
+  end
+end
+
+require "rubygems"
+require "bundler/setup"
+
+load Gem.bin_path("rspec-core", "rspec")

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/bin/vite

@@ -0,0 +1,27 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+#
+# This file was generated by Bundler.
+#
+# The application 'vite' is installed as part of a gem, and
+# this file is here to facilitate running it.
+#
+
+ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../Gemfile", __dir__)
+
+bundle_binstub = File.expand_path("bundle", __dir__)
+
+if File.file?(bundle_binstub)
+  if File.read(bundle_binstub, 300).include?("This file was generated by Bundler")
+    load(bundle_binstub)
+  else
+    abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
+Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
+  end
+end
+
+require "rubygems"
+require "bundler/setup"
+
+load Gem.bin_path("vite_ruby", "vite")

data/lib/easy_ml/version.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 module EasyML
-  VERSION = "0.2.0-rc9"
+  VERSION = "0.2.0-rc10"
 
   module Version
   end

data/public/easy_ml/assets/.vite/manifest-assets.json

@@ -0,0 +1 @@
+{}

data/public/easy_ml/assets/.vite/manifest.json

@@ -0,0 +1,11 @@
+{
+  "entrypoints/Application.tsx": {
+    "file": "assets/entrypoints/Application.tsx-GDgZ4vVt.js",
+    "name": "entrypoints/Application.tsx",
+    "src": "entrypoints/Application.tsx",
+    "isEntry": true,
+    "css": [
+      "assets/Application-tsa3Id3n.css"
+    ]
+  }
+}

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: easy_ml
 version: !ruby/object:Gem::Version
-  version: 0.2.0.pre.rc9
+  version: 0.2.0.pre.rc10
 platform: ruby
 authors:
 - Brett Shollenberger
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-01-07 00:00:00.000000000 Z
+date: 2025-01-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activerecord
@@ -437,8 +437,8 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- README.md
-- Rakefile
+- app/.vite/manifest-assets.json
+- app/.vite/manifest.json
 - app/controllers/easy_ml/application_controller.rb
 - app/controllers/easy_ml/columns_controller.rb
 - app/controllers/easy_ml/datasets_controller.rb
@@ -447,6 +447,8 @@ files:
 - app/controllers/easy_ml/models_controller.rb
 - app/controllers/easy_ml/retraining_runs_controller.rb
 - app/controllers/easy_ml/settings_controller.rb
+- app/easy_ml/.vite/manifest-assets.json
+- app/easy_ml/.vite/manifest.json
 - app/easy_ml/assets/Application-GDgZ4vVt.js
 - app/easy_ml/assets/Application-GDgZ4vVt.js.map
 - app/easy_ml/assets/Application-tsa3Id3n.css
@@ -578,6 +580,12 @@ files:
 - app/serializers/easy_ml/retraining_run_serializer.rb
 - app/serializers/easy_ml/settings_serializer.rb
 - app/views/layouts/easy_ml/application.html.erb
+- bin/build
+- bin/build_vite
+- bin/console
+- bin/rspec
+- bin/setup
+- bin/vite
 - config/initializers/resque.rb
 - config/resque-pool.yml
 - config/routes.rb
@@ -651,6 +659,8 @@ files:
 - lib/easy_ml/support/utc.rb
 - lib/easy_ml/version.rb
 - lib/tasks/vite.rake
+- public/easy_ml/assets/.vite/manifest-assets.json
+- public/easy_ml/assets/.vite/manifest.json
 - public/easy_ml/assets/assets/Application-tsa3Id3n.css
 - public/easy_ml/assets/assets/entrypoints/Application.tsx-GDgZ4vVt.js
 homepage: https://github.com/brettshollenberger/easy_ml

data/README.md

@@ -1,497 +0,0 @@
-<img src="easy_ml.svg" alt="EasyML Logo" style="width: 310px; height: 300px;">
-
-# EasyML
-
-~~You can't do machine learning in Ruby.~~
-
-Deploy models in minutes.
-
-## What is EasyML?
-
-EasyML is a **low code/no code**, end-to-end machine learning framework for Ruby on Rails.
-
-**Get productionized models in minutes.** It takes the guesswork out of:
-
-- Preprocessing data
-- Storing and batch computing features
-- Training models
-- Metric visualization
-- Deployment and versioning
-- Evaluating model performance
-
-With a dead-simple point-and-click interface, EasyML makes it stupid easy to train and deploy.
-
-Oh yeah, and it's open source!
-
-## Features
-
-- **No Code (if you want)**: EasyML ships as a Rails engine. Just mount it in your app and get started.
-- **Opinionated Framework**: Provides a structured approach to data and model management, ensuring best practices are followed.
-- **Model Lifecycle On Rails**: Want predictions directly from your Rails app? You can do that.
-- **Easily Extensible**: Want a model that's not supported? Send a pull request!
-
-## Current and Planned Features
-
-### Models Available
-
-| XGBoost | LightGBM | TensorFlow | PyTorch |
-| ------- | -------- | ---------- | ------- |
-| ✅      | ❌       | ❌         | ❌      |
-
-### Datasources Available
-
-| S3  | File | Polars | SQL Databases | REST APIs |
-| --- | ---- | ------ | ------------- | --------- |
-| ✅  | ✅   | ✅     | ❌            | ❌        |
-
-_Note: Features marked with ❌ are part of the roadmap and are not yet implemented._
-
-## Quick Start:
-
-Building a Production pipeline is as easy as 1,2,3!
-
-### 1. Create Your Dataset
-
-```ruby
-class MyDataset < EasyML::Data::Dataset
-  datasource :s3, s3_bucket: "my-bucket" # Every time the data changes, we'll pull new data
-  target "revenue" # What are we trying to predict?
-  splitter :date, date_column: "created_at" # How should we partition data into training, test, and validation datasets?
-  transforms DataPipeline # Class that manages data transformation, adding new columns, etc.
-  preprocessing_steps({
-    training: {
-      annual_revenue: { median: true, clip: { min: 0, max: 500_000 } }
-    }
-  }) # If annual revenue is missing, use the median value, after clipping the values into the approved list
-end
-```
-
-### 2. Create a Model
-
-```ruby
-class MyModel < EasyML::Models::XGBoost
-  dataset MyDataset
-  task :regression # Or classification
-  hyperparameters({
-    max_depth: 5,
-    learning_rate: 0.1,
-    objective: "reg:squarederror"
-  })
-end
-```
-
-### 3. Create a Trainer
-
-```ruby
-class MyTrainer < EasyML::Trainer
-  model MyModel
-  evaluator MyMetrics
-end
-
-class MyMetrics
-  def metric_we_make_money(y_pred, y_true)
-    return true if model_makes_money?
-    return false if model_lose_money?
-  end
-
-  def metric_sales_team_has_enough_leads(y_pred, y_true)
-    return false if sales_will_be_sitting_on_their_hands?
-  end
-end
-```
-
-Now you're ready to predict in production!
-
-```ruby
-MyTrainer.train # Yay, we did it!
-MyTrainer.deploy # Let the production hosts know it's live!
-MyTrainer.predict(customer_data: "I am worth a lot of money")
-# prediction: true!
-```
-
-## Mount The Engine
-
-```ruby
-Rails.application.routes.draw do
-  mount EasyML::Engine, at: "easy_ml"
-end
-```
-
-## Data Management
-
-EasyML provides a comprehensive data management system that handles all preprocessing tasks, including splitting data into train, test, and validation sets, and avoiding data leakage. The primary abstraction for data handling is the `Dataset` class, which ensures data is properly managed and prepared for machine learning tasks.
-
-### Preprocessing Features
-
-EasyML offers a variety of preprocessing features to prepare your data for machine learning models. Here's a complete list of available preprocessing steps and examples of when to use them:
-
-- **Mean Imputation**: Replace missing values with the mean of the feature. Use this when you want to maintain the average value of the data.
-
-  ```ruby
-  annual_revenue: {
-    mean: true
-  }
-  ```
-
-- **Median Imputation**: Replace missing values with the median of the feature. This is useful when you want to maintain the central tendency of the data without being affected by outliers.
-
-  ```ruby
-  annual_revenue: {
-    median: true
-  }
-  ```
-
-- **Forward Fill (ffill)**: Fill missing values with the last observed value. Use this for time series data where the last known value is a reasonable estimate for missing values.
-
-  ```ruby
-  created_date: {
-    ffill: true
-  }
-  ```
-
-- **Most Frequent Imputation**: Replace missing values with the most frequently occurring value. This is useful for categorical data where the mode is a reasonable estimate for missing values.
-
-  ```ruby
-  loan_purpose: {
-    most_frequent: true
-  }
-  ```
-
-- **Constant Imputation**: Replace missing values with a constant value. Use this when you have a specific value that should be used for missing data.
-
-  ```ruby
-  loan_purpose: {
-    constant: { fill_value: 'unknown' }
-  }
-  ```
-
-- **Today Imputation**: Fill missing date values with the current date. Use this for features that should default to the current date.
-
-  ```ruby
-  created_date: {
-    today: true
-  }
-  ```
-
-- **One-Hot Encoding**: Convert categorical variables into a set of binary variables. Use this when you have categorical data that needs to be converted into a numerical format for model training.
-
-  ```ruby
-  loan_purpose: {
-    one_hot: true
-  }
-  ```
-
-- **Ordinal Encoding**: Convert categorical variables into integer labels. Use this when you have categorical data that can be ordinally encoded.
-
-  ```ruby
-  loan_purpose: {
-    categorical: {
-      ordinal_encoding: true
-    }
-  }
-  ```
-
-### Other Dataset Features
-
-- **Data Splitting**: Automatically split data into train, test, and validation sets using various strategies, such as date-based splitting.
-- **Data Synchronization**: Ensure data is synced from its source, such as S3 or local files.
-- **Batch Processing**: Process data in batches to handle large datasets efficiently.
-- **Null Handling**: Alert and handle null values in datasets to ensure data quality.
-
-## Feature Store
-
-The Feature Store is a powerful component of EasyML that helps you manage, compute, and serve features for your machine learning models. Here's how to use it effectively:
-
-### Setting Up Features
-
-1. Create a `features` directory in your application:
-
-```bash
-mkdir app/features
-```
-
-2. Create feature classes in this directory. Each feature should include the `EasyML::Features` module:
-
-```ruby
-class MyFeature
-  include EasyML::Features
-
-  def transform(df, feature)
-    # Your feature transformation logic here
-  end
-
-  feature name: "My Feature",
-          description: "Description of what this feature does"
-end
-```
-
-### Feature Types and Configurations
-
-#### Simple Transform-Only Features
-
-For features that can be computed using only the input columns:
-
-```ruby
-class DidConvert
-  include EasyML::Features
-
-  def transform(df, feature)
-    df.with_column(
-      (Polars.col("rev") > 0).alias("did_convert")
-    )
-  end
-
-  feature name: "did_convert",
-          description: "Boolean indicating if conversion occurred"
-end
-```
-
-#### Batch Processing Features
-
-For features that require processing large datasets in chunks:
-
-```ruby
-class LastConversionTimeFeature
-  include EasyML::Features
-
-  def batch(reader, feature)
-    # Efficiently query only the company_id column for batching
-    # This will create batches of batch_size records (default 1000)
-    reader.query(select: ["company_id"], unique: true)["company_id"]
-  end
-
-  def fit(reader, feature, options = {})
-    batch_start = options.dig(:batch_start)
-    batch_end = options.dig(:batch_end)
-
-    # More efficient than is_in for continuous ranges
-    df = reader.query(
-      filter: Polars.col("company_id").is_between(batch_start, batch_end),
-      select: ["id", "company_id", "converted_at", "created_at"],
-      sort: ["company_id", "created_at"]
-    )
-
-    # For each company, find the last time they converted before each application
-    #
-    # This value will be cached in the feature store for fast inference retrieval
-    df.with_columns([
-      Polars.col("converted_at")
-        .shift(1)
-        .filter(Polars.col("converted_at").is_not_null())
-        .over("company_id")
-        .alias("last_conversion_time"),
-
-      # Also compute days since last conversion
-      (Polars.col("created_at") - Polars.col("last_conversion_time"))
-        .dt.days()
-        .alias("days_since_last_conversion")
-    ])[["id", "last_conversion_time", "days_since_last_conversion"]]
-  end
-
-  def transform(df, feature)
-    # Pull the pre-computed values from the feature store
-    stored_df = feature.query(filter: Polars.col("id").is_in(df["id"]))
-    return df if stored_df.empty?
-
-    df.join(stored_df, on: "id", how: "left")
-  end
-
-  feature name: "Last Conversion Time",
-          description: "Computes the last time a company converted before each application",
-          batch_size: 1000,  # Process 1000 companies at a time
-          primary_key: "id",
-          cache_for: 24.hours  # Cache feature values for 24 hours after running fit
-end
-```
-
-This example demonstrates several key concepts:
-
-1. **Efficient Batching**: The `batch` method uses the reader to lazily query only the necessary column for batching
-1. **Batches Groups Together**: All records with the same `company_id` need to be in the same batch to properly compute the feature, so we create a custom batch (instead of using the primary key `id` column, which would split up companies into different batches)
-1. **Column Selection**: Only selects required columns in the reader query
-1. **Feature Computation**: Computes multiple related features (last conversion time and days since) in a single pass.
-1. **Automatic Feature Store Caching**: The feature store automatically caches feature values returned from the `fit` method
-
-### Performance Optimization
-
-#### Caching During Development
-
-Use `cache_for` to save processing time during development:
-
-```ruby
-feature name: "My Feature",
-        cache_for: 24.hours # After running fit, this feature will be cached for 24 hours (unless new data is read from datasource, like S3)
-```
-
-#### Early Returns
-
-Always implement early returns in your transform method to avoid unnecessary reprocessing:
-
-```ruby
-def transform(df, feature)
-  return df if df["required_column"].nil?
-  # Feature computation logic
-end
-```
-
-#### Using Reader vs DataFrame
-
-- The Polars `reader` is a lazy reader that allows you to query data incrementally.
-- If your feature includes a `batch` method or uses the `batch_size` variable, you will receive a reader instead of a dataframe in the `fit` method
-
-```ruby
-def fit(reader, feature)
-  df = reader.query(select: ["column1", "column2"])
-  # Process only needed columns
-end
-```
-
-- If you don't have a `batch` method or don't use the `batch_size` variable, you will receive a dataframe in the `fit` method
-
-````ruby
-def fit(df, feature)
-  # process directly on dataframe
-end
-
-- To ensure you get a reader instead of a dataframe, include the `batch` method
-
-```ruby
-def batch(reader, feature)
-  reader.query(select: ["column1"])["column1"]
-end
-
-feature name: "My Feature", batch_size: 1_000
-````
-
-### Production Considerations
-
-#### Handling Missing Data
-
-When processing historical data:
-
-1. Check for missing dates:
-
-```ruby
-def transform(df, feature)
-  missing_dates = feature.store.missing_dates(start_date, end_date)
-  return df if missing_dates.empty?
-
-  # Process only missing dates
-  process_dates(df, missing_dates)
-end
-```
-
-### Best Practices
-
-1. Always specify a `primary_key` to allow the feature store to partition your data
-1. Use `batch/fit` to process large datasets in batches
-1. Use `batch/fit` to allow faster inference feature computation
-1. Use transform-only features when all required columns will be available on the inference dataset
-1. Use `cache_for` to save processing time during development
-1. Only query necessary columns using the reader
-
-## Installation
-
-Install necessary Python dependencies
-
-1. **Install Python dependencies (don't worry, all code is in Ruby, we just call through to Python)**
-
-```bash
-pip install wandb optuna
-```
-
-1. **Install the gem**:
-
-   ```bash
-   gem install easy_ml
-   ```
-
-2. **Run the generator to store model versions**:
-
-   ```bash
-   rails generate easy_ml:migration
-   rails db:create # If this is a new app
-   rails db:migrate
-   ```
-
-3. Add the `easy_ml` dir to your `.gitignore` — This is where datasets and model files will be downloaded
-
-```
-# .gitignore
-easy_ml/
-```
-
-## Usage
-
-To use EasyML in your Rails application, follow these steps:
-
-1. **Define your preprocessing steps** in a configuration hash. For example:
-
-   ```ruby
-   preprocessing_steps = {
-     training: {
-       annual_revenue: {
-         median: true,
-         clip: { min: 0, max: 1_000_000 }
-       },
-       loan_purpose: {
-         categorical: {
-           categorical_min: 2,
-           one_hot: true
-         }
-       }
-     }
-   }
-   ```
-
-2. **Create a dataset** using the `EasyML::Data::Dataset` class, providing necessary configurations such as data source, target, and preprocessing steps.
-
-3. **Train a model** using the `EasyML::Models` module, specifying the model class and configuration.
-
-4. **Deploy the model** by marking it as live and storing it in the configured S3 bucket.
-
-## Development
-
-After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
-
-To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
-
-## Contributing
-
-1. Install Appraisals gemfiles:
-
-```bash
-bundle exec appraisal install
-```
-
-1. Creating a test app:
-
-a. Follow the typical steps
-b. Declare an environment variable: `EASY_ML_DEV=true`, using Figaro, dotenv, or similar to load develoment assets
-c. Run `yarn vite dev` in both the `easy_ml` gem and test app directories
-
-1. Building production assets
-
-```bash
-bin/vite_build
-```
-
-1. Ensure you run tests against all supported Rails versions
-
-Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/easy_ml. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/[USERNAME]/easy_ml/blob/main/CODE_OF_CONDUCT.md).
-
-## License
-
-The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
-
-## Code of Conduct
-
-Everyone interacting in the EasyML project's codebases, issue trackers, chat rooms, and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/easy_ml/blob/main/CODE_OF_CONDUCT.md).
-
-## Expected Future Enhancements
-
-- **Support for Additional Models**: Integration with LightGBM, TensorFlow, and PyTorch.
-- **Expanded Data Source Support**: Ability to pull data from SQL databases and REST APIs.
-- **Enhanced Deployment Options**: More flexible deployment strategies and integration with CI/CD pipelines.
-- **Advanced Monitoring and Logging**: Improved tools for monitoring model performance and logging.
-- **User Interface Improvements**: Enhanced UI components for managing models and datasets.

data/Rakefile

@@ -1,57 +0,0 @@
-# frozen_string_literal: true
-
-require "sprockets/railtie"
-require "bundler/gem_tasks"
-require "rspec/core/rake_task"
-
-RSpec::Core::RakeTask.new(:spec)
-
-require "rubocop/rake_task"
-
-RuboCop::RakeTask.new
-
-task default: %i[spec rubocop]
-
-Bundler.require(:default)
-
-# Load your gem's code
-require_relative "lib/easy_ml"
-
-# Load the annotate tasks
-require "annotate/annotate_models"
-
-task :environment do
-  require "combustion"
-  require "sprockets"
-  Combustion.path = "spec/internal"
-  Combustion.initialize! :active_record do |config|
-    config.assets = ActiveSupport::OrderedOptions.new # Stub to avoid errors
-    config.assets.enabled = false # Set false since assets are handled by Vite
-  end
-  EasyML::Engine.eager_load!
-end
-
-namespace :easy_ml do
-  task annotate_models: :environment do
-    model_dir = File.expand_path("app/models", EasyML::Engine.root)
-    $LOAD_PATH.unshift(model_dir) unless $LOAD_PATH.include?(model_dir)
-
-    AnnotateModels.do_annotations(
-      is_rake: true,
-      model_dir: [EasyML::Engine.root.join("app/models/easy_ml").to_s],
-      root_dir: [EasyML::Engine.root.join("app/models/easy_ml").to_s],
-      include_modules: true, # Include modules/namespaces in the annotation
-    )
-  end
-
-  task :create_test_migrations do
-    require "combustion"
-    require "rails/generators"
-    require_relative "lib/easy_ml/railtie/generators/migration/migration_generator"
-
-    db_files = Dir.glob(EasyML::Engine.root.join("spec/internal/db/migrate/**/*"))
-
-    FileUtils.rm(db_files)
-    Rails::Generators.invoke("easy_ml:migration", [], { destination_root: EasyML::Engine.root.join("spec/internal") })
-  end
-end