Jeremy-big-data

From Earlham CS Department
Jump to navigation Jump to search
Project Tasks
  1. Identifying and downloading the target data set
  2. Data cleaning and pre-processing
  3. Load the data into your Postgres instance
  4. Develop queries to explore your ideas in the data
  5. Develop and document the model function you are exploring in the data
  6. Develop a visualization to show the model/patterns in the data
Tech Details
  • Node: as4
  • Path to storage space: /scratch/big-data/jeremy
Results
  • The visualization(s)
  • Frequency of Tornadoes with respect to month
  • Total Number of Killer tornadoes per category (F1, F2.. etc)
  • The Maximum Number of Deaths Caused by an Individual Tornado with respect to category
  • Where Tornado Victims are Found
  • The Percentage of the Population Killed per State
  • 1 in How Many Were Killed
  • A Graphic Visualization of the US with color coded states
  • The Number of Tornadoes per year
  • The Number of deaths per year
  • The story
  • Tornadoes are most frequent during change in seasons
  • People are most frequently killed by F3 tornadoes
  • Bigger Tornadoes Kill more People
  • Most victims are found in mobile homes
  • 1 in 10,000 people in Alabama are killed by tornadoes
  • Killer Tornadoes are becoming more frequent

All files can be grabbed from ~jrhurst08/public/big_data