Hands-On Data Analysis with Pandas

Assumptions

Before we jump into the code that handles the simulation, we need to understand the assumptions. It is impossible to control for every possible variable when we make a simulation, so we must identify some simplifying assumptions to get started.

The simulator makes the following assumptions about valid users of the website:

• Valid users come according to a Poisson process at an hourly rate that depends on the day of the week and the time of day. A Poisson process models arrivals per unit of time (our simulation will use an hour) as a Poisson distribution with mean λ (lambda). The interarrival times are exponentially distributed with mean 1/λ.
• Valid users connect from 1-3 IP addresses (a unique identifier for each device using ...