The assignment guides you through the feature selection techniques.
data mining
Description
The Third Part of the Assignment of DM 2020-2021
Introduction
The assignment guides you through the feature selection techniques. It is recommended to follow the assignment in the given order since the result of some questions might depend on answers to previous steps. The questions are detailed in the provided Jupyter notebook.
The Dataset Dataset: First, visit UCI machine learning repository. The link is provided here: https://archive.ics.uci.edu/ml/index.php. Choose any dataset from the newest list (2018-2020). In this part of the assignment, you have to apply and compare the performance of used DM technique when different feature selection methods are applied.
o There are three major FS methods: o Filter-based FS
o Wrapper-based FS
o Embedded-based FS
o Apply at least 3 methods of each category.
o Summarize and visualize the results.
You should pass some steps before starting the assignment as preprocessing steps. The details of
preprocessing steps are given in the Jupyter notebook file. After passing these preprocessing steps,
export your final dataset as 'air_pollution_2.csv' dataset and use that for the corresponding
questions of the assignment. Make sure that you submit this extracted dataset with your results
