Machine-Learning-from-Scrach

This repository contains and learnings of the topics and there documentation for future reference.

In future I will also add my ML projects in this repository. Language used: Python

Library used:

1. Numpy: pip install numpy
2. Pandas: pip install pandas
3. Matplotlib: python -m pip install -U matplotlib
4. Seaborn: pip install seaborn

Modules:

1. Exploratory Data Analysis(EDA): This is a very useful technique to find very interesting insights from the data done in the early stage to summarize main characteristics of the data in visual form using various graphs

   a. Iris dataset

2. Statistics: In this module I would try to implement some statistical tests that can be performed on the datasets a. Q-Q plot- this is a graphical method to find out distribution(Guassian, Uniform, etc.) b. Bootrapping technique- for calculating confidence Interval of our statistic, uses the computation power to compute the confidence Interval.

3. Dimensionality Reduction: Dimension reduction is the process of reducing the number of random variables under consideration by obtaining a set of principal variables. There are several techniques to do it:

   1. PCA(Principal Component Analysis)
   2. T-SNE