/All-stats-and-DS-on-iris

A collection of ALL POSSIBLE statistical and data science models on the iris data set in R. Let us make a comparision between ALL invented approaches to crunch the data!

Primary LanguageHTMLMIT LicenseMIT

All-stats-and-DS-on-iris

A collection of ALL POSSIBLE statistical and data science models on the iris data set in R. Let us make a comparision between ALL invented approaches to crunch the data!

README

This is a repository to store and share ALL THINGS that can be done with the famous iris dataset in R. Most code blocks are included in the .RMD files (can be used to generate documents).

In the discriptions I will not only compare and contrast R func & packages usages but also comment on their intended scenarios. [It is important why,how, and when we SHOULD use certain models, rather than simply knowing that we CAN use them.]

It is not fully written yet, but I would appreciate R users to push to this repo. Also plz point out typos and mistakes.

Follow this project to see how one (non-time-serial) dataset can be explored, analyzed, visualized and explained in a number of ways.

There is no one way to 'correctly' help us understand data. Understand different method can be inspirational. Also, the use of R and a variety of R packages can be demonstrated in this way.

The different perspectives may include:

0 Before you start

1 Basic statistics

2 Data Science techniques

  • Data Engineering
  • Advanced Data Visualization and Analysis
  • Reducing the Dimension

2 Numerical Experiments

  • Bootstrapping
  • Fractal Dimension of the Scatters

3 Regression

  • Linear Regression
  • Non-linear Regression

4 Classification

  • Clustering
  • Binary Trees
  • Support Vector Machine

5 Data Presentation

  • Making Interactive UI
  • Making Interactive Plots