datacamp-logo
Session Ready
Exercise

Setting dependencies for Netflix

Netflix has compiled a forecast up to the 2019 financial year netflix_f_is, and has based the sales figures in 2019 on the following dependency:

  • Number of active subscriptions, which are based on the success of Netflix original shows.

For 2019, the success of original shows (critical and commercial acclaim) are estimated at 78%. The total amount of subscribers per percentage point is 500, and set to the variable n_subscribers_per_pp (i.e there is a calculated correlation between show success and number of subscribers).

In this exercise, we will calculate how dependent sales are on the number of subscribers in the forecast, which we will use in the next exercise.

The Netflix forecast, netflix_f_iscan be printed in the shell.

Instructions 1/3
XP
  • 1
  • 2
  • 3
  • Print netflix_f_is in the shell and choose the metric that represents the sales row for the sales_metric filter list.
  • Filter the data for rows using the using the .isin() method where metric is in sales_metric and assign the result to filtered_netflix_f_is.
  • Select the 2019 forecast column, "2019 fc", from filtered_netflix_f_is, and use iloc[0] to extract the zeroth value, and assign the result to forecast1
  • Print forecast1.