Getting error while dealing with large dataset

[saleharashid01]

[Muhammad-Ali-Butt]

From the looks of it , seems like you're trying to get the best model based upon recall score?
can you explain what exactly you're trying to do ?

[Muhammad-Ali-Butt]

also the error you are encountering is due to presence of continuous variables which the model cannot deal with so you have to convert the continuous to numerical either by label encoding , onehot encoding and @AammarTufail taught us about it in machine learning videos you can check them out to refresh the concept or find another way based upon your data

[saleharashid01]

ok great, it worked (Jazak Allah) with label encoding,
(I was trying best score, parameter(grid search)

Scikit learn label encoding

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
le.fit(dataset['New_deaths'])
dataset['New_deaths'] =le.transform(dataset['New_deaths'])

[saleharashid01]

@Muhammad-Ali-Butt

when i run Best Score model, it worked for linear in my case and give value in negative, but i move towards KNN, Decision tree, randomforest,,.. it shows me warnings and say that best score (nan, nan, nan...as shown in fig)... what does it mean,?

[Muhammad-Ali-Butt]

you have nan values in your data try checking them by df.isnull().sum() * 100 / len(df) and then filling them or completely dropping the column if it has more than 70% nan values. the other error is that you are using binary classification for multiclass classification hence you should change average='macro' or 'weighted' and then try again.

[Muhammad-Ali-Butt]

ok great, it worked (Jazak Allah) with label encoding, (I was trying best score, parameter(grid search)

wa iyyakum glad it helped 😊

[nouman073]

apply the label encoding on y

…

On Tue, Feb 7, 2023 at 1:41 PM Saleha Rashid ***@***.***> wrote: [image: getting error in model training] <https://user-images.githubusercontent.com/121869148/217193024-6d3c5207-98a8-4125-9532-2b3cb858df1a.jpg> [image: train] <https://user-images.githubusercontent.com/121869148/217194721-fe097d1d-a5ca-43ba-8208-9e6b66ca69ad.jpg> — Reply to this email directly, view it on GitHub <#103>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ASKOYX23ORP4AT3VE74D5QDWWIDDPANCNFSM6AAAAAAUTVGLAA> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[nouman073]

same issue i faced i applied this methed then my issue solved

from sklearn import preprocessing
from sklearn import utils

label_encoder = preprocessing.LabelEncoder()
y_train = label_encoder.fit_transform(y_train

[AzamBukhari]