ValueError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]] - Tokenizing BERT / Distilbert Error

Question

def split_data(path):
  df = pd.read_csv(path)
  return train_test_split(df , test_size=0.1, random_state=100)

train, test = split_data(DATA_DIR)
train_texts, train_labels = train['text'].to_list(), train['sentiment'].to_list() 
test_texts, test_labels = test['text'].to_list(), test['sentiment'].to_list() 

train_texts, val_texts, train_labels, val_labels = train_test_split(train_texts, train_labels, test_size=0.1, random_state=100)

from transformers import DistilBertTokenizerFast
tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-uncased

train_encodings = tokenizer(train_texts, truncation=True, padding=True)
valid_encodings = tokenizer(valid_texts, truncation=True, padding=True)
test_encodings = tokenizer(test_texts, truncation=True, padding=True)

When I tried to split from the dataframe using BERT tokenizers I got an error us such.

Answer 1

I had the same error. The problem was that I had None in my list, e.g:

from transformers import DistilBertTokenizerFast

tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-german-cased')

# create test dataframe
texts = ['Vero Moda Damen Übergangsmantel Kurzmantel Chic Business Coatigan SALE',
         'Neu Herren Damen Sportschuhe Sneaker Turnschuhe Freizeit 1975 Schuhe Gr. 36-46',
         'KOMBI-ANGEBOT Zuckerpaste STRONG / SOFT / ZUBEHÖR -Sugaring Wachs Haarentfernung',
         None]

labels = [1, 2, 3, 1]

d = {'texts': texts, 'labels': labels} 
test_df = pd.DataFrame(d)

So, before I converted the Dataframe columns to list I remove all None rows.

test_df = test_df.dropna()
texts = test_df["texts"].tolist()
texts_encodings = tokenizer(texts, truncation=True, padding=True)

This worked for me.

Answer 2

In my case I had to set is_split_into_words=True

https://huggingface.co/transformers/main_classes/tokenizer.html

The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set is_split_into_words=True (to lift the ambiguity with a batch of sequences).

Answer 3

Similar to MarkusOdenthal I had a non string type in my list. I fixed it by converting the column to string, then converting it to a list, before splitting it into train and test segments. So you would do

train_texts = train['text'].astype(str).values.to_list()

Answer 4

def split_data(path):
  df = pd.read_csv(path)
  return train_test_split(df , test_size=0.2, random_state=100)

train, test = split_data(DATA_DIR)
train_texts, train_labels = train['text'].to_list(), train['sentiment'].to_list() 
test_texts, test_labels = test['text'].to_list(), test['sentiment'].to_list() 

train_texts, val_texts, train_labels, val_labels = train_test_split(train_texts, train_labels, test_size=0.2, random_state=100)

from transformers import DistilBertTokenizerFast
tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-uncased

train_encodings = tokenizer(train_texts, truncation=True, padding=True)
valid_encodings = tokenizer(valid_texts, truncation=True, padding=True)
test_encodings = tokenizer(test_texts, truncation=True, padding=True)

Try changing the size of the split. It will work. Which means that the split data wasn't enough for tokenizer to tokenize

Answer 5

in tokenizer first text must be STR for exaample: train_encodings = tokenizer(str(train_texts), truncation=True, padding=True)