Data Wrangling, Analyze Messy Data and Nick's Experiences

  |   Source
Data Wrangling, Analyze Messy Data and Nick's Experiences

  • This is the data of baseball player team
  • If we look into the data, there's something missing out
  • Average bat can't be more than one thousand, and there's missing left-or-hand by Ichiro SUzuki.
  • Data Wrangling is an art of gathering, fixing, and cleaning up the data that we have.
  • There's 3 part to gather data, files, databases, and Web APIS
  • At some point of our lifes, there's gotta be an experience when we have mesy data
  • Like how we have to find personal budget in our projects,
  • Or there's too many catalog menu in Bake sales.
  • We should be realize by now that cleaning the data will need much work
  • It's important to visualize the data, find out the structure to really understand the what data that we have.
Nick Gustafson said:
  • About average projects, spent time about 50% to gather the data.
  • If the data can't be used by our algorithm, then we have to reiterate the process.