diff --git a/applications/machine_learning/scikit_learn.ipynb b/applications/machine_learning/scikit_learn.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..23f2e146ee5ca4db6e0a0dce1d76f19bd82300c1
--- /dev/null
+++ b/applications/machine_learning/scikit_learn.ipynb
@@ -0,0 +1,268 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# scikit-learn\n",
+ "\n",
+ "Machine learning in python.\n",
+ "\n",
+ "- Simple and efficient tools for predictive data analysis\n",
+ "- Built on `numpy`, `scipy`, and `matplotlib`\n",
+ "- Open source, commercially usable - BSD license\n",
+ "\n",
+ "Some useful links are:\n",
+ "- [Main website](https://scikit-learn.org/stable/index.html)\n",
+ "- [User guide](https://scikit-learn.org/stable/user_guide.html)\n",
+ "- [API](https://scikit-learn.org/stable/modules/classes.html)\n",
+ "- [GitHub](https://github.com/scikit-learn/scikit-learn)\n",
+ "\n",
+ "## Project Overview:\n",
+ "\n",
+ "- \\> 2.1k contributers, 22.5k forks, 48.5k \"stars\"\n",
+ "- Current version: 1.0.2\n",
+ "- Powerful generic API\n",
+ "- Very well documented\n",
+ "- Core techniques, hundreds of options for:\n",
+ " - Classification \n",
+ " - Regression \n",
+ " - Clustering \n",
+ " - Dimensionality Reduction \n",
+ " - Model Selection \n",
+ " - Preprocessing\n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Getting Started\n",
+ "\n",
+ "Adapted from the `scikit-learn` \"Getting Started\" documetation: https://scikit-learn.org/stable/getting_started.html"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Fitting and predicting: estimator basics\n",
+ "\n",
+ "Each machine learning model in `scikit-learn` is implemented as an [`estimator`](https://scikit-learn.org/stable/glossary.html#term-estimators) object. Here we instantiate [Random Forest](https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html#sklearn.ensemble.RandomForestClassifier) `estimator`:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "RandomForestClassifier(random_state=0)\n"
+ ]
+ }
+ ],
+ "source": [
+ "# import RF estimator\n",
+ "from sklearn.ensemble import RandomForestClassifier\n",
+ "\n",
+ "# instantiate RF estimator\n",
+ "clf = RandomForestClassifier(random_state=0)\n",
+ "\n",
+ "print(clf)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "After creation, the `estimator` can be **fit** to the training data using the `fit` method.\n",
+ "\n",
+ "The fit method accepts 2 inputs:\n",
+ "\n",
+ "1. `X` is training input samples of shape (`n_samples`, `n_features`). Thus, rows=samples and columns=features\n",
+ "2. `y` is the target values (class labels in classification, real numbers in regression) of shape (`n_samples`,) for one output, or (`n_samples`, `n_outputs`) for multiple outputs. \n",
+ "\n",
+ "\n",
+ "> Note: Both `X` and `y` are usually are numpy arrays or equivalent array-like data types."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "RandomForestClassifier(random_state=0)"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# create some toy data\n",
+ "X = [[ 1, 2, 3], # 2 samples, 3 features\n",
+ " [11, 12, 13]]\n",
+ "y = [0, 1] # classes of each sample\n",
+ "\n",
+ "# fit the model to the data\n",
+ "clf.fit(X, y)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Once trained, the `estimator` can make predictions on new data using the `predict` method."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([0, 1])"
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# predict classes of new data\n",
+ "clf.predict([[4, 5, 6], [14, 15, 16]]) "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "\n",
+ "Importantly, this `fit` and `predict` interface is consistent across different estimators making it very easy to change estimators within your code. For example, here we swap the Random Forest `estimator` for a Support Vector Machine `estimator`:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([0, 1])"
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# import an SVM estimator\n",
+ "from sklearn.svm import SVC\n",
+ "\n",
+ "# instantiate SVM estimator\n",
+ "clf = SVC(random_state=0)\n",
+ "\n",
+ "# fit and predict\n",
+ "clf.fit(X, y)\n",
+ "clf.predict([[4, 5, 6], [14, 15, 16]]) "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Transformers and pre-processors\n",
+ "\n",
+ "The `transformer` is a special object that follows the same API as an `estimator` and allows you to apply pre-processing and/or post-procssing transform to the data in your machine learning pipeline."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Pipelines: chaining pre-processors and estimators\n",
+ "\n",
+ "TBD"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Model evaluation\n",
+ "\n",
+ "TBD"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Automatic parameter searches\n",
+ "\n",
+ "TBD"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Classification\n",
+ "\n",
+ "TBD"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Regression\n",
+ "\n",
+ "TBD"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": []
+ }
+ ],
+ "metadata": {
+ "interpreter": {
+ "hash": "8f33debd3f7a540b5e7318765d3a2e4659a97370cb154e29f8abf55d879f5f56"
+ },
+ "kernelspec": {
+ "display_name": "Python 3.7.6 64-bit ('fslpython604': conda)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.7.6"
+ },
+ "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}