anamakarevich/dand

DAND projects, selected lecture notes and cheatsheets

Data Analyst Nanodegree Projects and Lecture Notes

This repository is for lecture notes, projects and cheatsheets for Udacity's Data Analyst Nanodegree.

Program review can be found here. Certificate can be found here.

Projects Overview

Note about formats: .MD is a natural format for GitHub and it's lighter. However, LaTeX expressions are not rendered in .MD format - see original .ipynb versions for these projects.

Project ID	Project Folder	MD Version	Original Format	Description
8	Chytridiomycosis in Australia	.MD (cleaning phase only)	Tableau Story	The goal of the project was to learn how to convey the findings discovered during EDA with focus on explanatory part rather than exploratory. For this project I took the dataset that contains aggregate data on Chytridiomycosis in amphibia in Australia over several decades. Initial dataset contained about 10K observations, but was reduced during cleaning
7	WeRateDogs Tweets	.MD	.ibynb	The goal of the project was to gather Twitter data from different sources, including loading tweets via Twitter API, assess quality and tidiness of this data and clean it up. The short write-up of the cleaning process is available here. The short write-up of the EDA is available here
6	Online News Popularity	.MD	.Rmd	The goal of the project is to analyze if we can find any factors that influence news popularity measured in the number of shares. For this project I took a dataset from UCI that contains about 39K records from Mashable.com
5	The Stroop Effect	.MD	.ipynb	The goal of this project is to analyse the results of the experiment that tested the Stroop effect - i.e. whether it really takes longer to read the name of the colour if the colour of the words is incongruent with the word itself.
4	A/B Testing	.MD	.ipynb	The goal of the project is to perform an A/B test in order to understand whether the new landing page leads to better conversion rate.
3	No Show Appointments	.MD	.ipynb	The goal of the project is to explore what factors influence if the patient shows up for their appointment. The dataset contains the data about 110,527 appointments and indicates whether the patient showed up.
2	Bikeshare Analysis	.MD	.ipynb	This is guided analysis implemented in a question-answer format. The questions were provided by Udacity. The goal of the project is to perform EDA on the bikeshare data provided by bike-share system provider Motivate, specifically: compare system usage in New York City, Chicago, and Washington, DC
*	Wikipedia Lab	.MD	.ipynb	This project is inspired by one of the Udacity's lectures where the instructor shared an observation that if we keep clicking the first link on any Wikipedia page, we will end up at an article about Philosophy. I tried to reproduce that result.
1	Weather Trends	.MD	.ipynb	Introductory project. The dataset contains global and local average temerature by year. The goal of the project was to compare local weather trends (in Kiev and in Moscow) and global weather trends and provide appropriate visualisations.