def test_table_question_answering_model_from_pretrained(self):
for model_name in TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST[5:6]:
config = AutoConfig.from_pretrained(model_name)
self.assertIsNotNone(config)
self.assertIsInstance(config, TapasConfig)
model = AutoModelForTableQuestionAnswering.from_pretrained(model_name)
model, loading_info = AutoModelForTableQuestionAnswering.from_pretrained(
model_name, output_loading_info=True
)
self.assertIsNotNone(model)
self.assertIsInstance(model, TapasForQuestionAnswering)
def __init__(self):
self.tokenizer = AutoTokenizer.from_pretrained(
"google/tapas-base-finetuned-wtq")
self.model = AutoModelForTableQuestionAnswering.from_pretrained(
"google/tapas-base-finetuned-wtq")
self.tableQA = TableQuestionAnsweringPipeline(
model=self.model, tokenizer=self.tokenizer)
def test_slow_tokenizer_sqa_pt(self):
model_id = "lysandre/tiny-tapas-random-sqa"
model = AutoModelForTableQuestionAnswering.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
table_querier = TableQuestionAnsweringPipeline(model=model,
tokenizer=tokenizer)
inputs = {
"table": {
"actors":
["brad pitt", "leonardo di caprio", "george clooney"],
"age": ["56", "45", "59"],
"number of movies": ["87", "53", "69"],
"date of birth":
["7 february 1967", "10 june 1996", "28 november 1967"],
},
"query": [
"how many movies has george clooney played in?",
"how old is he?", "what's his date of birth?"
],
}
sequential_outputs = table_querier(**inputs, sequential=True)
batch_outputs = table_querier(**inputs, sequential=False)
self.assertEqual(len(sequential_outputs), 3)
self.assertEqual(len(batch_outputs), 3)
self.assertEqual(sequential_outputs[0], batch_outputs[0])
self.assertNotEqual(sequential_outputs[1], batch_outputs[1])
# self.assertNotEqual(sequential_outputs[2], batch_outputs[2])
table_querier = TableQuestionAnsweringPipeline(model=model,
tokenizer=tokenizer)
outputs = table_querier(
table={
"actors":
["brad pitt", "leonardo di caprio", "george clooney"],
"age": ["56", "45", "59"],
"number of movies": ["87", "53", "69"],
"date of birth":
["7 february 1967", "10 june 1996", "28 november 1967"],
},
query="how many movies has george clooney played in?",
)
self.assertEqual(
outputs,
{
"answer": "7 february 1967",
"coordinates": [(0, 3)],
"cells": ["7 february 1967"]
},
)
outputs = table_querier(
table={
"actors":
["brad pitt", "leonardo di caprio", "george clooney"],
"age": ["56", "45", "59"],
"number of movies": ["87", "53", "69"],
"date of birth":
["7 february 1967", "10 june 1996", "28 november 1967"],
},
query=[
"how many movies has george clooney played in?",
"how old is he?", "what's his date of birth?"
],
)
self.assertEqual(
outputs,
[
{
"answer": "7 february 1967",
"coordinates": [(0, 3)],
"cells": ["7 february 1967"]
},
{
"answer": "7 february 1967",
"coordinates": [(0, 3)],
"cells": ["7 february 1967"]
},
{
"answer": "7 february 1967",
"coordinates": [(0, 3)],
"cells": ["7 february 1967"]
},
],
)
outputs = table_querier(
table={
"Repository": ["Transformers", "Datasets", "Tokenizers"],
"Stars": ["36542", "4512", "3934"],
"Contributors": ["651", "77", "34"],
"Programming language":
["Python", "Python", "Rust, Python and NodeJS"],
},
query=[
"What repository has the largest number of stars?",
"Given that the numbers of stars defines if a repository is active, what repository is the most active?",
"What is the number of repositories?",
"What is the average number of stars?",
"What is the total amount of stars?",
],
)
self.assertEqual(
outputs,
[
{
"answer": "Python, Python",
"coordinates": [(0, 3), (1, 3)],
"cells": ["Python", "Python"]
},
{
"answer": "Python, Python",
"coordinates": [(0, 3), (1, 3)],
"cells": ["Python", "Python"]
},
{
"answer": "Python, Python",
"coordinates": [(0, 3), (1, 3)],
"cells": ["Python", "Python"]
},
{
"answer": "Python, Python",
"coordinates": [(0, 3), (1, 3)],
"cells": ["Python", "Python"]
},
{
"answer": "Python, Python",
"coordinates": [(0, 3), (1, 3)],
"cells": ["Python", "Python"]
},
],
)
with self.assertRaises(ValueError):
table_querier(query="What does it do with empty context ?",
table=None)
with self.assertRaises(ValueError):
table_querier(query="What does it do with empty context ?",
table="")
with self.assertRaises(ValueError):
table_querier(query="What does it do with empty context ?",
table={})
with self.assertRaises(ValueError):
table_querier(
table={
"Repository": ["Transformers", "Datasets", "Tokenizers"],
"Stars": ["36542", "4512", "3934"],
"Contributors": ["651", "77", "34"],
"Programming language":
["Python", "Python", "Rust, Python and NodeJS"],
})
with self.assertRaises(ValueError):
table_querier(
query="",
table={
"Repository": ["Transformers", "Datasets", "Tokenizers"],
"Stars": ["36542", "4512", "3934"],
"Contributors": ["651", "77", "34"],
"Programming language":
["Python", "Python", "Rust, Python and NodeJS"],
},
)
with self.assertRaises(ValueError):
table_querier(
query=None,
table={
"Repository": ["Transformers", "Datasets", "Tokenizers"],
"Stars": ["36542", "4512", "3934"],
"Contributors": ["651", "77", "34"],
"Programming language":
["Python", "Python", "Rust, Python and NodeJS"],
},
)
def test_small_model_pt(self):
model_id = "lysandre/tiny-tapas-random-wtq"
model = AutoModelForTableQuestionAnswering.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
self.assertIsInstance(model.config.aggregation_labels, dict)
self.assertIsInstance(model.config.no_aggregation_label_index, int)
table_querier = TableQuestionAnsweringPipeline(model=model,
tokenizer=tokenizer)
outputs = table_querier(
table={
"actors":
["brad pitt", "leonardo di caprio", "george clooney"],
"age": ["56", "45", "59"],
"number of movies": ["87", "53", "69"],
"date of birth":
["7 february 1967", "10 june 1996", "28 november 1967"],
},
query="how many movies has george clooney played in?",
)
self.assertEqual(
outputs,
{
"answer": "AVERAGE > ",
"coordinates": [],
"cells": [],
"aggregator": "AVERAGE"
},
)
outputs = table_querier(
table={
"actors":
["brad pitt", "leonardo di caprio", "george clooney"],
"age": ["56", "45", "59"],
"number of movies": ["87", "53", "69"],
"date of birth":
["7 february 1967", "10 june 1996", "28 november 1967"],
},
query=[
"how many movies has george clooney played in?",
"how old is he?", "what's his date of birth?"
],
)
self.assertEqual(
outputs,
[
{
"answer": "AVERAGE > ",
"coordinates": [],
"cells": [],
"aggregator": "AVERAGE"
},
{
"answer": "AVERAGE > ",
"coordinates": [],
"cells": [],
"aggregator": "AVERAGE"
},
{
"answer": "AVERAGE > ",
"coordinates": [],
"cells": [],
"aggregator": "AVERAGE"
},
],
)
outputs = table_querier(
table={
"Repository": ["Transformers", "Datasets", "Tokenizers"],
"Stars": ["36542", "4512", "3934"],
"Contributors": ["651", "77", "34"],
"Programming language":
["Python", "Python", "Rust, Python and NodeJS"],
},
query=[
"What repository has the largest number of stars?",
"Given that the numbers of stars defines if a repository is active, what repository is the most active?",
"What is the number of repositories?",
"What is the average number of stars?",
"What is the total amount of stars?",
],
)
self.assertEqual(
outputs,
[
{
"answer": "AVERAGE > ",
"coordinates": [],
"cells": [],
"aggregator": "AVERAGE"
},
{
"answer": "AVERAGE > ",
"coordinates": [],
"cells": [],
"aggregator": "AVERAGE"
},
{
"answer": "AVERAGE > ",
"coordinates": [],
"cells": [],
"aggregator": "AVERAGE"
},
{
"answer": "AVERAGE > ",
"coordinates": [],
"cells": [],
"aggregator": "AVERAGE"
},
{
"answer": "AVERAGE > ",
"coordinates": [],
"cells": [],
"aggregator": "AVERAGE"
},
],
)
with self.assertRaises(ValueError):
table_querier(query="What does it do with empty context ?",
table=None)
with self.assertRaises(ValueError):
table_querier(query="What does it do with empty context ?",
table="")
with self.assertRaises(ValueError):
table_querier(query="What does it do with empty context ?",
table={})
with self.assertRaises(ValueError):
table_querier(
table={
"Repository": ["Transformers", "Datasets", "Tokenizers"],
"Stars": ["36542", "4512", "3934"],
"Contributors": ["651", "77", "34"],
"Programming language":
["Python", "Python", "Rust, Python and NodeJS"],
})
with self.assertRaises(ValueError):
table_querier(
query="",
table={
"Repository": ["Transformers", "Datasets", "Tokenizers"],
"Stars": ["36542", "4512", "3934"],
"Contributors": ["651", "77", "34"],
"Programming language":
["Python", "Python", "Rust, Python and NodeJS"],
},
)
with self.assertRaises(ValueError):
table_querier(
query=None,
table={
"Repository": ["Transformers", "Datasets", "Tokenizers"],
"Stars": ["36542", "4512", "3934"],
"Contributors": ["651", "77", "34"],
"Programming language":
["Python", "Python", "Rust, Python and NodeJS"],
},
)