This repo includes all the files for farm equipment car following behaviour project.

Description

• add description.

How to run:

1. Clone the repo and cd to the :
   • mkdir myproject
   • cd myproject
   • git clone https://github.com/saeedarabi92/Farm-equipment-following-behaviour.git
2. Run pip install -e .

TODO list:

• Convert UTC time to local " US/Central "
• VAN category excluded
• Day of week rearranged based on the UTC conversion
• Plotting CDFs of trajectories in python
• Plotting CDFs of each trajectory in Tableau (It was too hard! I could not figure it out! Officially gave up)
• Meeting with Ashirwad about the model.
  • Meeting summery:
    • Do not shrink your dataset to mean and std. One outlier will have a great influence on the results.
    • One option could finding the outliers and remove them from the dataset. There is something called Cook's distance which can be used to identify the outliers.
• Finding appropriate statistical models. The response variables are mean and std of following distances. Also, random variable should be involved.
• Schedule appointment with stat department to go over the available options of stat model.

---

Update on 01/22/2021

• Validity check of the fall 2018 . (Pictures and initial validation check)
  • location in box: SaferTrek/Fall 2018 SaferTrek Roadway Data/Chunks based on Frame Missing from Koray Hard Drive
• Tableau visualization of medians and CDFs.
  • I set meeting with Archana.

---

Update on 01/29/2021

• Include only one following phase per trajectory. The one which is closest to the end of trajectory.
• Use median instead of mean and std for the model.
• [ ]

---

Update on 02/05/2021

• Consider only the last following phase for each trajectory.
• Use two different distance estimation model for car and pickup truck.
• Put SUV in the pickup truck category.
• marginal effects ---> effect of one variable on the model
• Add more data.
• Use spline information for model fitting.