# Multi class classification Not able to tokenize using map on custom datset

**URL:** <https://discuss.huggingface.co/t/multi-class-classification-not-able-to-tokenize-using-map-on-custom-datset/9591>\
**Category:** Beginners\
**Created:** [August 30, 2021, 11:27am UTC](https://discuss.huggingface.co/t/multi-class-classification-not-able-to-tokenize-using-map-on-custom-datset/9591 "2021-08-30T11:27:48Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Sravan](https://avatars.discourse-cdn.com/v4/letter/s/51bf81/32.png) [@Sravan](https://discuss.huggingface.co/u/Sravan)\
**Post date:** [August 30, 2021, 11:27am UTC](https://discuss.huggingface.co/t/multi-class-classification-not-able-to-tokenize-using-map-on-custom-datset/9591/1 "2021-08-30T11:27:48Z")

</div>

i’m trying to load the data using the pandas dataframe and loaded bert based tokenizer  
bert-base-cased.

I am trying to tokenize using below code.

def tokenize\_function(examples):  
return tokenizer(examples[“text”], padding=“max\_length”, truncation=True)

dataset\_df.map(tokenize\_function, batched=True)

**and it throws error saying dataframe has no attribute map.**

How can map those using pandas dataframe?