Closed theiman112860 closed 4 years ago
Below is a subset of the data
Hi @theiman112860
Thanks for getting in touch and reporting your issue. I've added a small peace of code that should fix this error. Please, run updateLares()
to update the library, close RStudio, open it, and try again! Let me know how it goes.
BTW: No need to run h2o.init()
before you call the function ;)
Hi laresbernardo,
Now I am getting another error:
"In error/tag : longer object length is not a multiple of shorter object length"
Weird isn't it? Any ideas on what is going on? Thank you again!
Sincerely,
tom
Let's check what's wrong here. Try renaming your data3 tag column to something like "tag" (data3<-data.frame(data2[,feat_imp_df], tag = data2$tag)
)
Please, run these 3 examples to see if it's the library or something with your data. These 3 cases should work!
library(lares)
library(dplyr)
data(dft)
dft <- dft %>% select(-Ticket, -PassengerId, -Cabin)
# Classification: 2 class
r <- h2o_automl(dft, y = "Survived", max_models = 1, target = "TRUE")
# Classification: 3 classes
r <- dft %>% select(-Fare) %>% h2o_automl(y = "Pclass", impute = TRUE, max_models = 1)
# Regression
r <- dft %>% h2o_automl(y = "Fare", ignore = c("Pclass","Cabin"), max_models = 1)
Hi Laresbernardo,
Thank you for the quick response!!!!! All of your examples worked. I renamed tag like you said i.e. data3<-data.frame(data2[,feat_imp_df], tag = data2$tag)) .. It worked i.e. no errors. However, it did not generate any results.. It also mentioned generating plots.. I cant find those either.. Any ideas? Thank you again!! Sorry to be a pain in the neck..
Sincerely,
tom
The output is: Check results in H2O Flow's nice interface: http://localhost:54321/flow/index.html Model selected: GBM_1_AutoML_20191031_075159 NOTE: The following variables were NOT important: "VEHICLE_LICENSE_STATE_OTHER", "REPORT_STATE_OTHER", "ACCESS_CONTROL_DESC_Full.Control", "ACCESS_CONTROL_DESC_No.Control"
Running predictions for tag... Generating plots... Process duration: 55.77s rmse mae mape mse rsq rsqa 1 0.1907409 0.05760291 0.9113939 0.03638208 0.01379 0.01375 Error in beep() : could not find function "beep" results Error: object 'results' not found
I installed beepr and that fixed it!!!!!
Great! That shouldn't happen. If you don't have beepr
library installed, the function should skip the alarm. You could set the alarm
parameter to FALSE
or if it's TRUE
and you don't have it installed, nothing should happen. I'll check why that didn't happen to you.
The graphics are really nice!! Thank you again!!
Thanks! Hope they are useful as well! xD
Hi Bernardo, They are very useful!! Thank you!! Sincerely, tom
-----Original Message----- From: laresbernardo notifications@github.com To: laresbernardo/lares lares@noreply.github.com Cc: theiman112860 theiman@verizon.net; Mention mention@noreply.github.com Sent: Thu, Oct 31, 2019 9:04 am Subject: Re: [laresbernardo/lares] object 'cats' not found (#18)
Thanks! Hope they are useful as well! xD— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.
Hi,
Great package! Thank you!! After I run the H20 autoML I get the following error:
Check results in H2O Flow's nice interface: http://localhost:54321/flow/index.html Model selected: GBM_1_AutoML_20191030_214222 NOTE: The following variables were NOT important: "VEHICLE_LICENSE_STATE_OTHER", "REPORT_STATE_OTHER", "ACCESS_CONTROL_DESC_Full.Control", "ACCESS_CONTROL_DESC_No.Control"
ART.txt
Any ideas on what object "cats" is or how I can get it to work? Thank you!!
Sincerely,
tom