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 2024-04-11 GMT+08:00

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 possible cause is as follows:

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.