# How to use dataset with costume function?
**URL:**
**Author:**  [@laro1](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Flaro1)%5C
**Post date:** [August 8, 2022, 12:45pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-use-dataset-with-costume-function%2F21382%2F1 "2022-08-08T12:45:43Z")
I want to call `DatasetDict` `map` function with parameters, and I dont know how to do it.
I have function with the following API:
```auto
def tokenize_function(tokenizer, examples):
s1 = examples["premise"]
s2 = examples["hypothesis"]
args = (s1, s2)
return tokenizer(*args, padding="max_length", truncation=True)
```
And when I’m trying to use in this way:
```auto
dataset = load_dataset("json", data_files=data_files)
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenized_datasets = dataset.map(tokenize_function, tokenizer, batched=True)
```
I’m getting error:
`TypeError: list indices must be integers or slices, not str`
How can I call `map` function in my example ?
---
**Author:**  [@nielsr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnielsr)%5C
**Post date:** [August 8, 2022, 5:03pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-use-dataset-with-costume-function%2F21382%2F2 "2022-08-08T17:03:16Z")
The function shouldn’t take the tokenizer as input, only the examples. You can add additional arguments to the function, which can then be passed as fn\_kwargs in the map method.
Option 1: define tokenizer outside the function
```auto
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
dataset = load_dataset("json", data_files=data_files)
def tokenize_function(examples):
s1 = examples["premise"]
s2 = examples["hypothesis"]
args = (s1, s2)
return tokenizer(*args, padding="max_length", truncation=True)
tokenized_datasets = dataset.map(tokenize_function, tokenizer, batched=True)
```
Option 2: use `fn_kwargs` to pass the tokenizer to the function
```auto
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
dataset = load_dataset("json", data_files=data_files)
def tokenize_function(examples, tokenizer):
s1 = examples["premise"]
s2 = examples["hypothesis"]
args = (s1, s2)
return tokenizer(*args, padding="max_length", truncation=True)
tokenized_datasets = dataset.map(tokenize_function, fn_kwargs={"tokenizer":tokenizer}, batched=True)
```
---
**Author:**  [@meti007](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmeti007)%5C
**Post date:** [June 19, 2023, 2:14am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-use-dataset-with-costume-function%2F21382%2F3 "2023-06-19T02:14:18Z")
how can i do a function on Dataset as batch here my code:
def get\_sent(examples):
sents =sentiment\_classifier(examples[‘text’])
labels=[sent[0][‘label’] for sent in sents]
examples[‘label’]=labels
return examples
to\_label1 = to\_label1.map(get\_sent,batched=True)
when i run the code i got error and cant run function as batch.
---
**Author:**  [@mariosasko](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmariosasko)%5C
**Post date:** [June 19, 2023, 3:53pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-use-dataset-with-costume-function%2F21382%2F4 "2023-06-19T15:53:17Z")
Can you paste the error message?