Changed dataset and model to make example easier to follow

[MMenchero]

No description provided.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

mergenthaler commented on 2022-12-01T00:26:03Z
----------------------------------------------------------------

In this example, we'll implement time series cross-validation to evaluate model's performance.

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

mergenthaler commented on 2022-12-01T00:26:04Z
----------------------------------------------------------------

Include a text justifiyng the imports of the libraries. These import statements are lost in this part of the text.

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

mergenthaler commented on 2022-12-01T00:26:05Z
----------------------------------------------------------------

Here would be a better example to import pandas. Something like, we will use M4.... first we will read the library from an URL using pandas.

import pandas as pd
Y_df = pd.read_parquet('https://datasets-nixtla.s3.amazonaws.com/m4-hourly.parquet') # load the data 

Y_df.head() 

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

mergenthaler commented on 2022-12-01T00:26:06Z
----------------------------------------------------------------

In the next step, you are not instantiating the StatsForecast class. Just calling a .plot method. The plot method does not take all of those parameters.

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

mergenthaler commented on 2022-12-01T00:26:07Z
----------------------------------------------------------------

Here is a good place to talk about the StatsForecast class and its inputs.

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

mergenthaler commented on 2022-12-01T00:26:08Z
----------------------------------------------------------------

You did not install datasetsforecast or mention what it is. (This will break for a user)