/Oil_Pipelines

Primary LanguageJupyter Notebook

Oil Pipelines Accidents Analysis

Data PreProcessing Steps

  1. Renaming of Features for simplicity
  2. Using geopy to replace missing addresses
  3. Replacing other missing values for other features with zero or Not Stated (where appropriate)
  4. Feature Creation - Shutdown_Days (Gives the shutdown time for each oil pipeline facility in Days)

Further Preprocessing Steps

I realized that four locations were incorrect.

  • Three in China and one off the Iberian coast

I did further investigations on these four addresses:

  1. FROST, TX
  2. MOBILE, AL
  3. YODER, WY
  4. LINDEN, NJ

Made the following amendments.

Map with Time Slider

Next steps...creating map with Time Slider Also, I want to create dropdown for the following features:

  1. Total Costs
  2. Liquid Recovery
  3. (Net) Loss of Barrels