Agenda


January 15-17, 2019

R for Environmental Data Analysis

Fond du Lac Tribal and Community College
2101 14th Street
Cloquet, MN 55720

Day 1

Planets visited: Endor and Jakku

Morning | 8:30-11:45am

Begin Jedi training
 

  1. Power on your droid
    • Install and update R
  2. Project launch
    • Start a new R project
    • Create an R script
  3. Tour and customize RStudio
  4. Invent new/fake data
    • Variables, names, and lists
  5. Make a data table / dataframe
  6. Upgrade your droid
    • Add new R packages
  7. Read real data into R
    • readr for text files
    • readxl for Excel files
  8. Get visual with ggplot2
    • Plot the data, plot the data, plot the data!
    • Look for errors and outliers

Packages: readr, ggplot2

Afternoon | 1:15-5:00pm

Get scrappy and solve a junk-data mystery

  1. Explore data
    • Column names, rows, observations, value types
    • Missing values
    • Mean, max, min, quantile
  2. Data transformations with dplyr
    • Arrange, sort, and filter data
  3. Summarize data
  4. Find the most profitable scrap
  5. Summarize each group, site, or category within the data
    • Summarize by location
    • Check for the number of data points in a group (you can use this to check for completeness!)

Travel to Endor to investigate magnetic storms

  1. Introduction to data with dates
  2. Plot time series

Packages: dplyr, lubridate

Day 2

Planets visited: Endor and Jakku

Morning | 8:30-11:45am

Questions and Review

  1. Calendar Plots 📅
    • Plot data by day of the week
  2. Intermediate data manipulation
    • Join tables together
    • Adding and calculating new columns
    • Unit conversions
    • Add new columns based on a condition
  3. Learn summary functions: mean, median, max, min, nth
  4. Use the with pipe %>% to string your functions together for less typing
  5. Save files
  6. Working with difficult data
    • Replacing NULL values, -999
    • Missing values NA

Packages: openair

Afternoon | 1:15-5:00pm

Star Wars - Guess Who

  1. Plot like a Jedi!
    • Scatter plots and boxplots
    • Add titles, colors, and labels
    • Histograms
    • Reference lines
    • Add trend lines 📈
  2. Save charts to different formats
  3. Plot pollution vs. meteorology
    • Scatter plots
      • Conc vs. Temp
      • Conc vs. Hour of day
      • Temp vs. Hour of day
  4. More plots
    • Log transform
    • Reference lines
  5. Time series plots with regression line and detection limits

Day 3

Planets visited: Ahch-To, Earth

Your turn!

Morning | 8:30-11:45am

  1. Join GitHub
  2. Share your data, code, and plots

Questions / Review

  1. Choose your own adventure!
    • Select your own or Star Wars data
  2. PATHS
    • Wind and Pollution roses
    • Messy data
      • Gather a wide table with hundreds of columns into 1 column
      • Read an entire folder of files and combine into 1 table
    • More maps and shapefiles
      • Read and save shapefiles
      • Convert coordinate projections (ex. Lat/Long to UTM)
      • Load reference maps (Tribal boundaries, States, Counties)
      • Build interactive maps

Packages: tidycensus, tigris, sf, leaflet

Afternoon | 1:15-5:00pm

  1. Select your own or Star Wars data
  2. Build a report
    • Clean the data
    • Create a summary table
    • Compare years or sites
    • Chart & map the data
    • Multiple paths to choose from
  3. Put script and results in Rmarkdown
  4. Share with the world
    • Generate Web, Word and PDF documents

🐈🐈 Concatulations!! 🐱🐱

Receive your well deserved accolades and certificates


agenda