Community Data Science Course (Spring 2017)/Day 5 Notes

From CommunityData
< Community Data Science Course (Spring 2017)
Revision as of 00:28, 3 May 2017 by Guyrt (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Today we'll take a partial digression from python to talk about Pivot Tables in Excel.

Outline:

  • Load the SDOT data from last time
  • Creating basic pivot tables
  • Rows, columns, values, filters
  • Aggregation functions
  • Common tricks
    • Percentiles
    • Visualizations
    • Filters
    • Sorting
  • Stats! Let's talk about the Odds Ratio

Let's use what we learned to answer some questions

  • What kinds of accidents are more likely to occur at Intersections than in a Block?
  • Do accidents with speeding involved result in a higher chance of injury? (Hint: use an odds ratio)
  • Look at columns HITPARKEDCAR and COLLISIONS. What do you notice about HITPARKEDCAR
  • Is speeding more likely to result in injuries or death?
  • what is the most dangerous corner in Seattle?
  • What do JunctionType and AddrType tell you about this data set?