KNN Classification Models

01. Breast Cancer Classification

In this project, I have build a K-Nearest Neighbor classifier that is trained to predict whether a patient has benign or malignant breast cancer.

Project Goals:

• My model would classify Benign & Malignant Breast Cancer with highest accuracy.

👈🏻 Click Here

Decision Trees and Random Forest

01. Predicting Income with Random Forest

In this project, I will be using a dataset containing census information from UCI’s Machine Learning Repository. By using this census data with a random forest, I will try to predict whether or not a person makes more than 50,000 Dollar.

👈🏻 Click here

02. Guessing Continent From Flag Color

What are some of the features that would provide clue for defining Continent of a country from just their flag? Maybe some of the colors are good indicators. The presence or absence of certain shapes could provide a hint.

In this project, I’ve used decision trees to try to predict the continent of flags based on several of these features.The Flag Attribute Information for this dataset is from UCI’s Machine Learning Repository.

Project Goals:

• From which Continent the Flag☝🏻 is from ?

👈🏻 Click here

Neural Networks

01. Perceptron Implementation in Logic Gates

In this project, I’ve used building blocks of Neural Network: perceptrons to model the fundamental building blocks of computers — logic gates.

1. AND gate - The table below shows the results of an AND gate. Given two inputs, an AND gate will output a 1 only if both inputs are a 1.
2. XOR gate — a gate that outputs a 1 only if one of the inputs is a 1.

Project Goals:

• AND gate can be thought of as linearly separable data and Perceptron can be trained to perform AND.
• XOR gate isn’t linearly separable and a Perceptron fails to learn XOR.

👈🏻 Click Here

Regression Models

01. Feature Engineering

Here I’ve deployed single, double and multiple features linear regression models, for feature selection and model tuning.

Project Goals:

tennis_stats.csv is data from the men’s professional tennis league, which is called the ATP (Association of Tennis Professionals). Data from the top 1500 ranked players in the ATP over the span of 2009 to 2017 are provided in file. The statistics recorded for each player in each year include service game (offensive) statistics, return game (defensive) statistics and outcomes.

• To determine what it takes to be one of the best tennis players in the world.

👈🏻 Click Here

02. Titanic Survival Prediction

In this project I’ve build Regression model that predicts which passengers survived the sinking of the Titanic, based on features.The data I’ll be using for training the model is provided by Kaggle Titanic competition!

Project Goals:

Predicting what happened to:

• 3rd class passenger Jack,
• 1st class passenger Rose and
• 3rd class youngest passenger onboard Millvina Dean

👈🏻 Click Here

03. Prediction of Future Production

The Honeybees are in a precarious state right now. There have been articles about the decline of the honeybee population for various reasons. This project is to investigate this decline and how the trends of the past predict the future for the honeybees.

DataFrame about honey production in the United States is collected from Kaggle.

👈🏻 Click Here