The dataset we will analyze is from TidyTuesday about movie profits for a slew of movie distributors with various genres. Data Introduction Let’s load the libraries and set the theme as theme_bw(). library(tidyverse) library(lubridate) library(scales) library(tidytext) theme_set(theme_bw()) Load the dataset below and some regular data processing steps are needed after exploring it. Read more

R is a nice tool I use everyday for my data analysis work, especially those data science libraries such as tidyverse that have made my work productive. In this blog, we analyze R and R package downloads, and here is the dataset download link. Read more

In this blog post, we will analyze a horror movie dataset from TidyTuesday by visualizing some interesting metrics and by using text mining and applying LASSO model on predicting movie ratings. Data Introduction and Processing First, load the necessary libraries we need for the analysis. Read more

In this project, we analyze the relations between college major and income after graduation. The dataset is from the link. To explore which majors are the most popular ones and which ones can help graduates land a high paying job is interesting. Let’s load the libraries we need for this project. Read more

COVID vaccination has been a trending topic around the world in the last a few months. In this project, we use a vaccination dataset from Kaggle (here is the download link) about the vaccination status around the world. Since every country is presented in the dataset, it would be riveting to use a global map to visualize some metrics, and to see if we would encounter some technical issues along the way. Read more

Keeping car accidents at bay is every driver’s hope, and all of us want to have a safe road trip. Accidents, however, do happen. Few days ago, I came across a dataset from data.gov about the state of Maryland car crash reports from year of 2015 to the first two quarters of 2021 (as the year has not finished) and the download link is here. Read more

The New York Times has released data related to mask-wearing (link is here), and in this dataset, it provides the estimated prevalence of the frequency of people wearing mask in each county of every state. County residents are divided into 5 categories in terms of mask-wearing frequency: never, rarely, sometimes, frequently, always. Read more

Fast food chains are ubiquitous. In this Kaggle dataset, it has records of 10000 fast food restaurants here in the U.S. across 50 states and Washington D.C. In this project, we would like to explore this dataset to see which fast food chains are among the most popular ones nationwide and each statewide. Read more

In this project, we analyze Facebook stock dataset found on Kaggle, which is time-series related. There is a wonderful R package lubridate, which has made any work dealing with date handy and less miserable. Besides few time-series data visualizations we will make, changepoint detection will also be carried out on a number of key indexes of the stock. Read more

When we encounter any technical issues in our everyday work, one of the ways to get the issue addressed is Stack Overflow, where some users might have posted similar questions and useful solutions we can borrow for solving the problems we have at the moment. Read more