Week 07

Review / Projects

Data scientist(s) / Statistician(s) of the Week

Erin Hartman

Wendy Cho

Thursday announcements

  • Offering another round of quiz corrections (1/2 points back).
    • quiz4.csv is available in the data folder on Github
    • write code to read it in
    • use glimpse() to show the data types for each variable
    • try to create a bar plot of Measurement Time, see what happens
    • try to create a scatterplot with Date on x-axis and Diastolic BP on y-axis, see what happens.
    • conduct necessary cleaning steps so that you can produce appropriate versions of the two plots above
  • What have we done so far?
    • Data visualization w/ ggplot()
    • Data wrangling w/ tidyverse
    • Data summarization
    • Data importing & cleaning
  • What’s coming after the break?
    • Data ethics
    • Working with strings
    • Web scraping
    • Communicating results
    • Miscellaneous topics - anything you want to cover?? Put it on your notecard and/or come talk to me
    • PROJECTS!
    • 8 weeks left, but only 3 more labs
  • Today: work on data cleaning & EDA for your project
    • Recommend creating a new R project with a data subfolder
    • create cleaning.qmd file
    • load packages + read in data (pipe into clean_names() immediately)
    • glimpse() the data
    • plot each variable one-by-one (categorical variable = bar plot, numeric variable = histogram)
      • if you have a lot, ask AI to write you a function that will loop through and create a bar-plot/histogram for each categorical/numeric variable
    • Plotting will illuminate data cleaning needs

Tuesday announcements

  • Quiz corrections due now (email or hard copy)

  • Fill out extra credit survey if you haven’t already (link sent in email via Piazza on Monday)

  • Quiz to start class today

  • This week:

    • Lab 07 (midterm / reivew)
    • Project work session(s)

  • Project EDA & data cleaning due Thursday after spring break

Questions?