Timeline for Why would my additional information harm my prediction score but improve ROC and F-1?
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 18, 2020 at 22:41 | comment | added | Dave | Let us continue this discussion in chat. | |
| Apr 18, 2020 at 22:25 | history | edited | TomSelleck | CC BY-SA 4.0 |
deleted 9 characters in body
|
| Apr 18, 2020 at 22:21 | comment | added | TomSelleck | crap sorry that's a typo - both scores are coming out around 75% | |
| Apr 18, 2020 at 22:15 | comment | added | Dave | But then what’s the 65% that you mentioned? | |
| Apr 18, 2020 at 22:09 | comment | added | TomSelleck |
See the values for DecisionTreeClassifier Score: 0.747892534416884? That's the output from model.score(X_test, y_test) - it's nearly the same when including or excluding the cluster information. Is there a reason why the model accuracy wouldn't have increased to 0.80 for example?
|
|
| Apr 18, 2020 at 22:02 | comment | added | Dave | I don’t follow what you’re doing. Which numbers confuse you. | |
| Apr 18, 2020 at 22:01 | comment | added | TomSelleck |
I'm confused why model.score(X_test, y_test) is outputting (ever so slightly) lower scores, I would have expected some improvement rather than consistently a tiny bit lower...
|
|
| Apr 18, 2020 at 21:59 | history | edited | TomSelleck | CC BY-SA 4.0 |
added 130 characters in body
|
| Apr 18, 2020 at 21:51 | comment | added | Dave | It sure looks like the situation where you’ve got the higher AUC also has the higher accuracy. Please explain why you think your model with higher accuracy has lower AUC. | |
| Apr 18, 2020 at 21:41 | history | asked | TomSelleck | CC BY-SA 4.0 |