Help Center> ModelArts> Troubleshooting> Training Jobs> Service Code Issues> Error Message "DataFrame.dtypes for data must be int, float or bool" Displayed in Logs
Updated on 2024-06-11 GMT+08:00
View PDF

Error Message "DataFrame.dtypes for data must be int, float or bool" Displayed in Logs

Symptom

The following error message is displayed during training: 
DataFrame.dtypes for data must be int, float or bool

Possible Causes

The training data is not of the int, float, or bool type.

Solution

Run the following commands to convert the error column: 
from sklearn import preprocessing 
lbl = preprocessing.LabelEncoder() 
train_x['acc_id1'] = lbl.fit_transform(train_x['acc_id1'].astype(str)

Summary and Suggestions

Before creating a training job, use the ModelArts development environment to debug the training code to maximally eliminate errors in code migration.

Parent topic: Service Code Issues