1. Learn
    2. /
  2. Courses
    3. /
  3. Monitoring Machine Learning in Python
Connected

Exercise

Summary statistics

Recall from the previous lesson that NannyML provides five methods for tracking statistical changes in your features.

In this exercise, you will focus on examining the lead_time feature from the Hotel Booking dataset, which indicates how many days in advance a booking was made. By using summation, median, and standard deviation statistics, you can gain valuable insights into how customer booking behavior has evolved over time.

It's important to note that both the reference and analysis sets, as well as the nannyml library, are already pre-loaded and ready for use.

Instructions 1/3

undefined XP
  • 1
    • Define analyzed column to lead time, initialize SummaryStatsSumCalculator, Pass analyzed_column to the column names parameter.
  • 2
    • Initialize SummaryStatsMedianCalculator, pass analyzed_column to the column names parameter, filter results for the only analysis period.
  • 3
    • Initialize SummaryStatsStdCalculator.