Unnecessary call to `fit()` before `cross_validate`

lukas / ml-class

Machine learning lessons and teaching projects designed for engineers

https://www.youtube.com/channel/UCBp3w4DCEC64FZr4k9ROxig

GNU General Public License v2.0

2.34k stars 1.17k forks source link

Unnecessary call to `fit()` before `cross_validate` #30

Closed rcrowell closed 4 years ago

rcrowell commented 6 years ago

https://github.com/lukas/ml-class/blob/e50faa312d70d409b1618f31386cc905172d9f17/scikit/pipeline-bigrams-cross-validate.py#L19

this confused me for a while, re: my question about whether when we do cross-validation do we start with a new model each iteration or do we improve an existing model.