Unsupervised Learning Algorithm Practice
K-means clustering - Using features of seed varieties to practice this model

Supervised Learning Algorithm Practice
K Nearest Neighbour (Regression) - Using house rental data to calculate a suitable rental price for my flat in Manhattan

K Nearest Neighbour (Classification) - Using one of the datasets built in to SKLearn (Breast Cancer) to classify if a new patient may have breast cancer

Decision Tree Classification - Using patient dataset to classify if a future patient may be diabetic

SVM Introduction - From sets of data points (linear and non-linear), create decision boundaries separating the classifications

SVM Classification - Using one of the datasets built in to SKLearn to classify if a new patient may have breast cancer

Logistic Classification - Using patient dataset to classify if a future patient may be diabetic

Multiple Linear Regresssion Model - Using property features of houses in Manhattan to calculate rental prices

Simple Linear Regresssion Model - Using a dataset comparing a cars horsepower against its retail price

Feature Engineering Methods
Wrapper Method Comparison - Comparing wrapper methods (Sequential Forward Selection, Sequential Backward Selection and Recursive Feature Elimination)

Feature Importance Practice - Assessing the feature importance of a dataset by building a decision tree and comparing gini gain.

Lasso and Ridge Regression Practice - To prevent overfitting the complexity of a model was reduced by removing/reducing the coefficients of less important features.

Hyperparameter Tuning Practice - Copying a CodeCademy project tutorial to practice hyperparameter tuning - using various techniques to classify types of raisins.

Neutral Networks
Perceptron Logic Gates - A followed tutorial, starting to learn about perceptrons - in this case representing AND and OR Logic Gates.