This is a SteamLit Web-App which delves in Exploratory Data Analysis with Iris, Breast-Cancer and Wine datasets using ML models like KNN's, SVM's and Random Forests StreamLit is a Python based open-source library that allows you to create stunning data based web-apps. It also allows you to deploy these apps as well.
KNN or KNearestNeighbours is a supervised machine learning algorithm which is used in classification and regression problems.During training, KNN just stores the data that comes to it, but on recieving the new data, it tries to classify it based on the previous data.
SVM or SupportVectorMachines is a machine learning algorithm which could be used both in classification and regression(particularly logistic regression) problems but it is mostly used in classification sectors. The main idea of SVM is to create a hyperplane(i.e. which is a generalization of plane) of the data and seperating the available classes of the data as far from the plane as possible.
Random Forests work on the principle of Decision Trees. These trees help in classifying data based on their features. When multiple trees combine and work as an ensemble , it is called a Random Forest. Each tree in the Forest works individually to give out a class prediction and the prediction with heighest frequency is considered as the model's prediction.
Find my Web-App here : https://share.streamlit.io/parthrangarajan/wib-eda_streamlit/main/main.py