We will use the profiles data set in the okcupiddata package and the Titanic (note the capital T) data set in the datasets package. datasets comes automatically loaded with R.

library(dplyr)
library(okcupiddata)
data(profiles)
View(profiles)
Titanic <- data.frame(Titanic)
View(Titanic)

How many of those identified as Male survived the Titanic crash, broken down by Child/Adult?

• filter to focus only on Sex == "Male"
• filter to focus only on Survived == "Yes"
• group_by to break down by Age
• summarize to sum together the remaining counts of Freq

What's another dplyr-type question you can answer from the Titanic data set?

What is the mean age of OKCupid profiles corresponding to levels of drugs and drinks?

• group_by to break down by drugs and drinks
• summarize to calculate mean age

Produce an appropriate plot relating age to the levels of drugs and drinks.

What are the top 2 heights of those identifying as female entered based on pets?

• filter to only choose sex == "f"
• select to only choose height and pets
• group_by to break down by pets
• top_n to determine top 2 heights

Identify two new dplyr questions to answer based on the profiles data frame.

• Find a sociology related data set, download it to your computer, and upload it to the RStudio Server. The best file formats are CSVs (comma-separated) files, but other file formats will work as well.
• Make a note about the "tidy"-ness of the data and how easy it is to understand the names of the variables.
• Find an article/data journalism piece related to sociology that uses data visualization to convey a message. Write a two paragraph summary of the article and how data visualization is used.
• You can work in partners (2 per group) on this lab.

• Read over Chapter 6 in MODERN DIVE
• Read the article from Lifehacker published yesterday entitled How to Lie to Yourself and Others With Statistics
• We will go over the Learning Checks for Sections 6.1 and 6.2 on Monday. Try them for practice before then.