1. Learn
    2. /
  2. Courses
    3. /
  3. Designing Forecasting Pipelines for Production
Connected

Exercise

Preparing and visualizing the data

Accurate data preparation is key to building effective machine learning models. Now it's time to apply the skills you've learned.

Your data needs three columns for the statsforecast library:

  • unique_id: series ID
  • ds: series timestamp
  • y: series values

Apply the necessary steps to clean and reformat your data for time series forecasting. The dataset has been preloaded as ts, and pandas is imported as pd.

Instructions 1/3

undefined XP
    1
    2
    3
  • Convert the "period" column to a datetime format and sort the DataFrame by "period" in ascending order.