--- title: "Lab 16: Filtering Data" output: html_document --- ```{r setup, include=FALSE} knitr::opts_chunk\$set(echo = TRUE) library(readr) library(ggplot2) library(dplyr) library(smodels) theme_set(theme_minimal()) ``` ## Pick a dataset For the remainder of this lab, you choice of three datasets to work with. You can choose either to investigate the daily team ELO ratings in the NBA: ```{r} nba <- read_csv("https://statsmaths.github.io/stat_data/nba_elo_daily.csv") ``` Metadata from US senator's tweets: ```{r} tweets <- read_csv("https://statsmaths.github.io/stat_data/senator_tweets_meta.csv") ``` Or swear words given in the movies of Quentin Tarantino: ```{r} tarantino <- read_csv("https://statsmaths.github.io/stat_data/tarantino.csv") ``` Pick a dataset and work on the instructions in the next section. If you have time before we come back together, try to use a second dataset as well. We will talk about all of the plots in the last 15 minutes of class. ## Instructions This lab is similar to the last. You'll pick a dataset and then generate an analysis of that data using data visualizations. The difference here is that instead of a single plot, I would like you to construct 3-4 plots that together tell a linear story. Each plot should be separated by a sentence or two describing what the viewer should take away from the plot. Try to keep the plots similar in some way; perhaps each simply highlights a different subset of the data but has the same underlying layers. Notice that each of the datasets for today are larger than you will probably be able to use. You will need to filter the data to a particular team, year, subset of curse words. You may further filter the data to highlight an even smaller subset of the data within each plot. ## Analysis