1. Learn
    2. /
  2. Courses
    3. /
  3. Effective Data Storytelling using the tidyverse
  • 1

    Applying R Basics

    Exploring the basics of R on a data set based on the fivethirtyeight.com "Most Police Don’t Live In The Cities They Serve" article.

  • 2

    Tidy Data

    Look into tidy data properties on data sets used in articles from fivethirtyeight.com in the fivethirtyeight R package

  • 3

    Scatter-plots & Line-graphs

    Create and analyze different plots relating two numerical variables via the ggplot2 package using datasets in and derived from the fivethirtyeight R package

  • 4

    Histograms & Boxplots

    Make and interpret different plots relating one categorical variable to one numerical variable via the ggplot2 package using datasets in and derived from the fivethirtyeight R package

  • 5

    Barplots

    Generate and examine barplots displaying one categorical variable or relationships between multiple categorical variables via the ggplot2 package using datasets in and derived from the fivethirtyeight R package

  • 6

    ggplot2 Review

    Identifying and creating the appropriate plot based on different types of variables using the ggplot2 package

  • 7

    Filtering, Grouping, & Summarizing

    Choose a subset of rows and summarize a data frame in total and across different levels of other variables using the dplyr package

  • 8

    dplyr Review

    Create a new column in a data frame, modify an existing column, and sort by one or more columns using the dplyr package. Review the main ideas of the Five Main Verbs of dplyr - filter, summarize, group_by, mutate, and arrange.

  • 9

    Supplement to ModernDive textbook

    To supplement learning of the material covered at http://moderndive.com, this chapter provides a playground for you to work with the code and better understand what each of the gray chunks of R code throughout the book does.

Initializing

Exercise

Joining data frames

Recall the police_locals data frame you worked with in Applying R Basics as an interactive table here.

There has been much discussion about the political divide that exists in the US. A separate data frame has been loaded with the name ideology that lists cities, their state, and the political ideology of the state. Created somewhat naively, a description of this state_ideology variable follows.

state_ideology: For each city in the dataset, a look-up of the state the city resides in and the results of the 2016 Presidential election were given. If Clinton won the state in 2016, "Liberal" is the value for state_ideology. If Trump won the state in 2016, "Conservative" is the value for state_ideology.

An interactive table of the ideology data frame is here.

Instructions

100 XP
  • Use the inner_join function in the dplyr package to add the state and state_ideology columns to the police_locals data frame where the key variable is city in both data frames. (Note the use of library(dplyr) here. You will always need to load the package first if you would like to use the functions inside it.)
  • Recall that the main arguments to inner_join are x, y, and by. x corresponds to the data frame you would like to add columns to. y corresponds to the data frame you'd like to add columns from. by corresponds to the name (or names) of the key vectors that you'd like to join the two data frames together by. Note that the names of the variables for by must be inside quotation marks.
  • Assign the name police_join to this expanded data frame.