nielsr/

tapex-large-finetuned-tabfact

from transformers import BartTokenizer, BartForSequenceClassification
import pandas as pd

tokenizer = BartTokenizer.from_pretrained("nielsr/tapex-large-finetuned-tabfact")
model = BartForSequenceClassification.from_pretrained("nielsr/tapex-large-finetuned-tabfact")

# create table
data = {'Actors': ["Brad Pitt", "Leonardo Di Caprio", "George Clooney"], 'Number of movies': ["87", "53", "69"]}
table = pd.DataFrame.from_dict(data)

# turn into dict
table_dict = {"header": list(table.columns), "rows": [list(row.values) for i,row in table.iterrows()]}

# turn into format TAPEX expects
# define the linearizer based on this code: https://github.com/microsoft/Table-Pretraining/blob/main/tapex/processor/table_linearize.py
linearizer = IndexedRowTableLinearize()
linear_table = linearizer.process_table(table_dict)

# add sentence
sentence = "George Clooney has 69 movies"
joint_input = sentence + " " + linear_table

# encode 
encoding = tokenizer(joint_input, return_tensors="pt")

# forward pass
outputs = model(**encoding)

# print prediction
logits = outputs.logits
print(logits.argmax(-1))