Titanic's passengers survivability with random forest machine learning algorithm

R Markdown file

The US Census Bureau collects and shares immense amounts of data on the US population to better inform policy decisions and ensure equal representation when drawing legislative districts. Much of the data is collected through the American Community Survey (ACS), which surveys households across the country on everything from demographics to home characteristics. Using those survey answers, the Census Bureau creates estimates for the various enumeration areas, e.g., block groups, tracts, counties, states. While the estimates are open to the public, navigating through the Census Bureau’s website or using the API can be tricky. However, the tidycensus package in R makes it easy to retrieve census data in a tidy format, making it ready for many forms of analysis. In this report, I’ll explore how tidycensus can be used to create informative visuals out of ACS data. Part A will explore the percentage of people with graduate degrees for each Tennessee county. Part B will map the median year structures were built by census block groups in Davidson County.

Build a linear (or generalized linear) model - Response variable and explanatory variables. Test the model and Interpret at least one of the coefficients