Doc examples

.github/workflows/Documenter.yml

@@ -2,7 +2,7 @@ name: Documenter
 on:
   push:
     branches:
-      - main
+      - Doc-Examples
     tags: '*'
   pull_request:
 jobs:
@@ -19,4 +19,4 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}           # For authentication with GitHub Actions token
           DOCUMENTER_KEY: ${{ secrets.DOCUMENTER_KEY }}       # For authentication with SSH deploy key
-        run: julia --project=docs/ docs/make.jl
+        run: julia --project=docs/ docs/make.jl

.github/workflows/codecov.yml

@@ -0,0 +1,4 @@
+- name: Upload coverage reports to Codecov
+  uses: codecov/codecov-action@v3
+  env:
+    CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

Project.toml

@@ -6,20 +6,13 @@ version = "0.1.0"
 [deps]
 CategoricalArrays = "324d7699-5711-5eae-9e2f-1d82baa6b597"
 CategoricalDistributions = "af321ab8-2d2e-40a6-b165-3d674595d28e"
-Conda = "8f4d0f93-b110-5947-807f-2305c1781a2d"
-DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 Distances = "b4f34e82-e78d-54a5-968a-f98e89d6e8f7"
-DocumenterTools = "35a29f4d-8980-5a13-9543-d66fff28ecb8"
-JuliaFormatter = "98e50ef6-434e-11e9-1051-2b60c6c9e899"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 MLJModelInterface = "e80e1ace-859a-464e-9ed9-23947d8ae3ea"
 MLJTestInterface = "72560011-54dd-4dc2-94f3-c5de45b75ecd"
 Memoization = "6fafb56a-5788-4b4e-91ca-c0cea6611c73"
 NearestNeighbors = "b8a86587-4115-5ab1-83bc-aa920d37bbce"
-OneRule = "90484964-6d6a-4979-af09-8657dbed84ff"
 OrderedCollections = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
-Parameters = "d96e819e-fc66-5662-9728-84c9c7592b0a"
-Pkg = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
 ProgressMeter = "92933f4c-e287-5a05-a399-4b506db050ca"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 ScientificTypes = "321657f4-b219-11e9-178b-2701a2544e81"
@@ -46,6 +39,9 @@ PyCall = "438e738f-606a-5dbb-bf0a-cddfbfd45ab0"
 StableRNGs = "860ef19b-820b-49d6-a774-d7a799459cd3"
 TableTransforms = "0d432bfd-3ee1-4ac1-886a-39f05cc69a3e"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+Pkg = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
+Conda = "8f4d0f93-b110-5947-807f-2305c1781a2d"
+
 
 [targets]
-test = ["Test", "DataFrames", "MLJBase", "TableTransforms", "StableRNGs", "PyCall"]
+test = ["Test", "DataFrames", "MLJBase", "TableTransforms", "StableRNGs", "PyCall", "Pkg", "Conda"]

README.md

@@ -4,8 +4,8 @@
 
 A Julia package with resampling methods to correct for class imbalance in a wide variety of classification settings.
 
-[![](https://img.shields.io/badge/docs-dev-blue.svg)](https://essamwisam.github.io/Imbalance.jl/dev/)
-[![Tests](https://github.com/EssamWisam/Imbalance.jl/actions/workflows/Runtests.yml/badge.svg)](https://github.com/EssamWisam/Imbalance.jl/actions/workflows/Runtests.yml)
+[![](https://img.shields.io/badge/docs-dev-blue.svg)](https://juliaai.github.io/Imbalance.jl/dev/)
+[![Tests](https://github.com/JuliaAI/Imbalance.jl/actions/workflows/Runtests.yml/badge.svg)](https://github.com/JuliaAI/Imbalance.jl/actions/workflows/Runtests.yml)
 
 ## ⏬ Installation
 ```julia
@@ -24,8 +24,8 @@ using Imbalance
 
 # Set dataset properties then generate imbalanced data
 probs = [0.5, 0.2, 0.3]                  # probability of each class      
-num_rows, num_cont_feats = 100, 5
-X, y = generate_imbalanced_data(num_rows, num_cont_feats; probs, rng=42)      
+num_rows, num_continuous_feats = 100, 5
+X, y = generate_imbalanced_data(num_rows, num_continuous_feats; probs, rng=42)      
 
 # Apply SMOTE to oversample the classes
 Xover, yover = smote(X, y; k=5, ratios=Dict(0=>1.0, 1=> 0.9, 2=>0.8), rng=42)
@@ -55,7 +55,7 @@ All implemented oversampling methods are considered static transforms and hence,
 This interface operates on single tables; it assumes that `y` is one of the columns of the given table. Thus, it follows a similar pattern to the `MLJ` interface except that the index of `y` is a required argument while instantiating the model and the data to be transformed via `apply` is only one table `Xy`.
 ```julia
 using Imbalance
-using TableTransforms
+using Imbalance.TableTransforms
 
 # Generate imbalanced data
 num_rows = 200
@@ -65,7 +65,7 @@ Xy, _ = generate_imbalanced_data(num_rows, num_features;
                                  probs=[0.5, 0.2, 0.3], insert_y=y_ind, rng=42)
 
 # Initiate SMOTE model
-oversampler = SMOTE_t(y_ind; k=5, ratios=Dict(0=>1.0, 1=> 0.9, 2=>0.8), rng=42)
+oversampler = SMOTE(y_ind; k=5, ratios=Dict(0=>1.0, 1=> 0.9, 2=>0.8), rng=42)
 Xyover = Xy |> oversampler       # can chain with other table transforms                  
 Xyover, cache = TableTransforms.apply(oversampler, Xy)    # equivalently
 ```
@@ -110,4 +110,4 @@ One obvious possible remedy is to weight the smaller sums so that a learning alg
 To our knowledge, there are no existing maintained Julia packages that implement oversampling algorithms for multi-class classification problems or that handle both nominal and continuous features. This has served as a primary motivation for the creation of this package.
 
 ## 👥 Credits
-This package was created by [Essam Wisam](https://github.com/EssamWisam) under supervision and expert guidance from his mentor [Dr. Anthony Blaom](https://github.com/ablaom). The binary `SMOTE` implementation by [Dr. Rik Huijzer](https://github.com/rikhuijzer) in `Resample.jl` has also been ultimately helpful while starting this project.
+This package was created by [Essam Wisam](https://github.com/JuliaAI) as a Google Summer of Code project, under the mentorship of [Anthony Blaom](https://ablaom.github.io). Additionally, [Rik Huijzer](https://github.com/rikhuijzer) and his binary `SMOTE` implementation in `Resample.jl` have also been helpful.

docs/Project.toml

@@ -1,3 +1,7 @@
 [deps]
+CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
+DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
 DocumenterTools = "35a29f4d-8980-5a13-9543-d66fff28ecb8"
+MLJ = "add582a8-e3ab-11e8-2d5e-e98b27df1bc7"
+ScientificTypes = "321657f4-b219-11e9-178b-2701a2544e81"

docs/examples.jl

@@ -1,43 +1,46 @@
+"""
+This file automatically generates the grid in examples.md from a given Julia dictionary.
+"""
 
 data = [
     Dict(
     "title" => "Effect of Ratios Hyperparameter", 
     "description" => "In this tutorial we use an SVM and SMOTE and the Iris data to study 
                       how the decision regions change with the amount of oversampling", 
-    "image" => "/examples/assets/iris smote.jpeg",
-    "link" => "/examples/effect_of_ratios",
-    "colab_link" => "https://colab.research.google.com/github/JuliaAI/Imbalance.jl/blob/main/examples/effect_of_ratios.ipynb"
+    "image" => "./assets/iris smote.jpeg",
+    "link" => "./effect_of_ratios",
+    "colab_link" => "https://colab.research.google.com/github/JuliaAI/Imbalance.jl/blob/Doc-Examples/examples/effect_of_ratios.ipynb"
     ), 
     Dict(
       "title" => "From Random Oversampling to ROSE", 
       "description" => "In this tutorial we study the `s` parameter in rose and the effect
                         of increasing it.", 
-      "image" => "/examples/assets/iris rose.jpeg",
-      "link" => "/examples/effect_of_s",
-      "colab_link" => "https://colab.research.google.com/github/JuliaAI/Imbalance.jl/blob/main/examples/effect_of_s.ipynb"
+      "image" => "./assets/iris rose.jpeg",
+      "link" => "./effect_of_s",
+      "colab_link" => "https://colab.research.google.com/github/JuliaAI/Imbalance.jl/blob/Doc-Examples/examples/effect_of_s.ipynb"
     ), 
     Dict(
       "title" => "SMOTE on Customer Churn Data", 
       "description" => "In this tutorial we apply SMOTE and random forest to predict customer churn based 
                         on continuous attributes.", 
-      "image" => "/examples/assets/churn smote.jpeg",
-      "link" => "/examples/smote_churn_dataset",
-      "colab_link" => "https://colab.research.google.com/github/JuliaAI/Imbalance.jl/blob/main/examples/smote_churn_dataset.ipynb"
+      "image" => "./assets/churn smote.jpeg",
+      "link" => "./smote_churn_dataset",
+      "colab_link" => "https://colab.research.google.com/github/JuliaAI/Imbalance.jl/blob/Doc-Examples/examples/smote_churn_dataset.ipynb"
     ), 
     Dict(
       "title" => "SMOTEN on Mushroom Data", 
       "description" => "In this tutorial we use a purely categorical dataset to predict mushroom odour.", 
-      "image" => "/examples/assets/mushy.jpeg",
-      "link" => "/examples/smoten_mushroom",
-      "colab_link" => "https://colab.research.google.com/github/JuliaAI/Imbalance.jl/blob/main/examples/smoten_mushroom.ipynb"
+      "image" => "./assets/mushy.jpeg",
+      "link" => "./smoten_mushroom",
+      "colab_link" => "https://colab.research.google.com/github/JuliaAI/Imbalance.jl/blob/Doc-Examples/examples/smoten_mushroom.ipynb"
     ), 
     Dict(
       "title" => "SMOTENC on Customer Churn Data", 
       "description" => "In this tutorial we extend the SMOTE tutorial to include both categorical and continuous
                         data for churn prediction", 
-      "image" => "/examples/assets/churn smoten.jpeg",
-      "link" => "/examples/smotenc_churn_dataset",
-      "colab_link" => "https://colab.research.google.com/github/JuliaAI/Imbalance.jl/blob/main/examples/smotenc_churn_dataset.ipynb"
+      "image" => "./assets/churn smoten.jpeg",
+      "link" => "./smotenc_churn_dataset",
+      "colab_link" => "https://colab.research.google.com/github/JuliaAI/Imbalance.jl/blob/Doc-Examples/examples/smotenc_churn_dataset.ipynb"
     )
 ]
 
@@ -51,10 +54,10 @@ for item in data
   colab_link = item["colab_link"]
     grid_item = """
       <div class="grid-item">
-      <a href="$colab_link"><img id="colab" src="/examples/assets/colab.png"/></a>
+      <a href="$colab_link"><img id="colab" src="./assets/colab.png"/></a>
       <a href="$link">
       <img src="$img_src" alt="Image">
-      <div class="title">$title
+      <div class="item-title">$title
       <p>$description</p>
       </div>
       </a>
@@ -66,81 +69,11 @@ end
 template = """
 ```@raw html
 
-<!DOCTYPE html>
-<html lang="en">
-<head>
-<meta charset="UTF-8">
-<meta name="viewport" content="width=device-width, initial-scale=1.0">
-<style>
-
-  .grid {
-    display: grid;
-    grid-template-columns: repeat(auto-fit, minmax(250px, 1fr));
-    gap: 20px;
-    max-width: 1200px;
-    padding: 20px;
-  }
-
-  .grid-item {
-    position: relative;
-    overflow: hidden;
-    border-radius: 15px;
-    transition: transform 0.3s ease;
-    cursor: pointer;
-  }
-
-  .grid-item img {
-    max-width: 100%;
-    height: auto;
-    display: block;
-  }
-
-  .grid-item .title {
-    position: absolute;
-    bottom: 0;
-    left: 0;
-    width: 100%;
-    background-color: rgba(0, 0, 0, 0.9);
-    color: #fff;
-    padding: 8px 15px;
-    font-size: 16px;
-  }
-
-  .title p {
-    font-weight: normal !important;
-    display: none;
-  }
-
-
-
-  .grid-item:hover p {
-    display: block;
-  }
-
-  .grid-item:hover #colab {
-    display: block;
-  }
-
-  #colab {
-    border-radius: 25%;
-    position: absolute;
-    top: 3px;
-    right: 3px;
-    width: 11%;
-    display: none;
-  }
-</style>
-
-</head>
-<body>
 
   <div class="grid">
   $grid_items
   </div>
 
-<script>
-</body>
-</html>
 
 ```"""
 

docs/make.jl

@@ -21,9 +21,10 @@ include("examples.jl")
 
 
 makedocs(
-    sitename = "Imbalance.jl", 
-    authors = "Essam Wisam, mentored by Dr. Anthony Blaom", 
-    repo="https://github.com/JuliaAI/TableTransforms.jl/", 
+
+    sitename = "Imbalance.jl",
+    authors = "Essam Wisam, mentored by Dr. Anthony Blaom",
+    repo="https://github.com/JuliaAI/Imbalance.jl/",
     format = Documenter.HTML(;
     assets=[
         "assets/favicon.ico", 
@@ -44,6 +45,4 @@ makedocs(
 # Documenter can also automatically deploy documentation to gh-pages.
 # See "Hosting Documentation" and deploydocs() in the Documenter manual
 # for more information.
-deploydocs(repo = "github.com/EssamWisam/Imbalance.jl.git")
-
-
+deploydocs(repo = "github.com/JuliaAI/Imbalance.jl.git", devbranch="Doc-Examples")

docs/src/about.md

@@ -1,2 +1,3 @@
 # Credits
-This package was created by [Essam Wisam](https://github.com/EssamWisam) under supervision and expert guidance from his mentor [Dr. Anthony Blaom](https://github.com/ablaom). The binary `SMOTE` implementation by [Dr. Rik Huijzer](https://github.com/rikhuijzer) in `Resample.jl` has also been ultimately helpful while starting this project.
+This package was created by [Essam Wisam](https://github.com/JuliaAI) as a Google Summer of Code project, under the mentorship of [Anthony Blaom](https://ablaom.github.io). Additionally, [Rik Huijzer](https://github.com/rikhuijzer) and his binary `SMOTE` implementation in `Resample.jl` have also been helpful.
+