Machine Learning Algorithms

Aim

To practice machine learning algorithms.

Algorithms

The following algorithms have been implemented by me.

1. Simple Linear Regression.
2. Multi-variate Linear Regression.
3. L1 Regularisation Regression.
4. L2 Regularisation Regression.
5. Gradient Descent for linear and logistic regression.
6. Logistic Regression
7. Naive Bayes Algorithm
8. K-Nearest Neighbors Algorithm.
9. Decision Trees
10. Perceptrons

Installation

1. Git clone this repository or download as zip or download selected files.
2. Note : you should have jupyter notebook installed for this or you can also use google colab.
   Google Colab - https://colab.research.google.com/
   Jupyter Notebook Download - https://www.anaconda.com/products/individual#:~:text=Anaconda%20Navigator%20is%20a%20desktop,without%20using%20command%2Dline%20commands.
3. Python ^3.6 is expected to be installed and the corresponding valid versions for numpy, scikit-learn and matplotlib libraries needs to be installed.

Data

The data is easily available on kaggle and UCI repository. For reference:

Linear Regression

1. Moore's Law Dataset -- Already present in the repository (Moore's.txt)
2. Predicting Systole BP -- Present in the repository (mlr02.xls)

Logistic Regression

1. Ecommerce Dataset -- ecommerce_data.xlsx present in the folder where Logistic regression folder.

KNN, Naive Bayes, Decision Trees and Perceptron

1. train.csv --- shorturl.at/arKY0
2. mnist dataset --- https://www.kaggle.com/oddrationale/mnist-in-csv