Commit cff563c3 authored by Florent Chatelain's avatar Florent Chatelain
Browse files

fix typo

parent b6b5a9ad
......@@ -104,17 +104,17 @@
![](data:image/png;base64,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)
%% Cell type:markdown id: tags:
## Questions 4
- How many different prediction values are defined by a tree of depth N?
- What is the average number of samples from the training set in each leave? (let N be the size of the training set)
- How many different prediction values are defined by a tree of depth $d$?
- What is the average number of samples from the training set in each leave? (let $N$ be the size of the training set)
%% Cell type:markdown id: tags:
## Setting the depth by using cross validation
https://scikit-learn.org/stable/modules/model_evaluation.html
Recall the sklearn documention to assess the [performance of a model (`model_evaluation` module)](https://scikit-learn.org/stable/modules/model_evaluation.html).
%% Cell type:code id: tags:
``` python
from sklearn.model_selection import ShuffleSplit
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment