This repository is a collection of some data science related projects I have done during my master’s and while attending a data science bootcamp by datarockie. It involves data querrying with SQL and programming in python and R.

During my master’s

During my master’s in Biorobotics, I took Introduction to Artificial Intelligence as a mandatory course from which I learned machine learning with python. Below are some of applications I learned from the course.

Machine Learning with Python

• K Nearest Neighbors Classifier from Scratch

  Building my own version of KNeighbors Classifier.

• Gaussian Naive Bayes Classifier from Scratch

  Building my own version of Gaussian Naive Bayes Classifier

• DecisionTreeRegressor tuning with GridSearchCV

  Fitting DecisionTreeRegressor with the best criterion and max depth to predict Seoul Bike Sharing Demand Data

Datarockie bootcamp

In this bootcamp, I learned essential data science skills covering spreadsheets, statistics, data transformation, data visualisation and programming skills including:

• SQL
• Python
• R

SQL

Restaurant Database

Mockup relational database for a restaurant created using SQLite. Please checkout how the queries run on my replit

Python

Please check out my python notebooks here

Essential python for data science

• Sales Data Analysis and Visualisation

  Use of pandas library to import a dataframe for analysis and visualisation

  

• Cleaning COVID-19 Data for Looker Studio Report

  Clean raw data and prepare a dataset for COVID-19 Report on Looker Studio

  
  

• Top 50 movies by IMDb ratings

  Web scraping on IMDb

• Naruto characters’ info

  Use of a public API to get data from the Naruto universe

Object Oriented Programming and User-defined Functions

• Running an ATM

  A class of python with a few class methods for mimicking the operation of an ATM and logging all transactions

• Rock Paper Scissors game

  A mini game built from user-defined functions with a result summary plot using pandas

  

R

Data Visualisation

Some charts plot of built-in diamond dataset using ggplot2

Data Transformation

code snippets I used for transforming tables in nycflights13 package

Machine Learning

Comparing 2 regression models created with caret package for predicting house price in India