haystack/test/test_table_reader.py
Sara Zan a59bca3661
Apply black formatting (#2115)
* Testing black on ui/

* Applying black on docstores

* Add latest docstring and tutorial changes

* Create a single GH action for Black and docs to reduce commit noise to the minimum, slightly refactor the OpenAPI action too

* Remove comments

* Relax constraints on pydoc-markdown

* Split temporary black from the docs. Pydoc-markdown was obsolete and needs a separate PR to upgrade

* Fix a couple of bugs

* Add a type: ignore that was missing somehow

* Give path to black

* Apply Black

* Apply Black

* Relocate a couple of type: ignore

* Update documentation

* Make Linux CI run after applying Black

* Triggering Black

* Apply Black

* Remove dependency, does not work well

* Remove manually double trailing commas

* Update documentation

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2022-02-03 13:43:18 +01:00

63 lines
2.6 KiB
Python

import pandas as pd
import pytest
from haystack.schema import Document
from haystack.pipelines.base import Pipeline
def test_table_reader(table_reader):
data = {
"actors": ["brad pitt", "leonardo di caprio", "george clooney"],
"age": ["58", "47", "60"],
"number of movies": ["87", "53", "69"],
"date of birth": ["18 december 1963", "11 november 1974", "6 may 1961"],
}
table = pd.DataFrame(data)
query = "When was Di Caprio born?"
prediction = table_reader.predict(query=query, documents=[Document(content=table, content_type="table")])
assert prediction["answers"][0].answer == "11 november 1974"
assert prediction["answers"][0].offsets_in_context[0].start == 7
assert prediction["answers"][0].offsets_in_context[0].end == 8
def test_table_reader_in_pipeline(table_reader):
pipeline = Pipeline()
pipeline.add_node(table_reader, "TableReader", ["Query"])
data = {
"actors": ["brad pitt", "leonardo di caprio", "george clooney"],
"age": ["58", "47", "60"],
"number of movies": ["87", "53", "69"],
"date of birth": ["18 december 1963", "11 november 1974", "6 may 1961"],
}
table = pd.DataFrame(data)
query = "When was Di Caprio born?"
prediction = pipeline.run(query=query, documents=[Document(content=table, content_type="table")])
assert prediction["answers"][0].answer == "11 november 1974"
assert prediction["answers"][0].offsets_in_context[0].start == 7
assert prediction["answers"][0].offsets_in_context[0].end == 8
@pytest.mark.parametrize("table_reader", ["tapas"], indirect=True)
def test_table_reader_aggregation(table_reader):
data = {
"Mountain": ["Mount Everest", "K2", "Kangchenjunga", "Lhotse", "Makalu"],
"Height": ["8848m", "8,611 m", "8 586m", "8 516 m", "8,485m"],
}
table = pd.DataFrame(data)
query = "How tall are all mountains on average?"
prediction = table_reader.predict(query=query, documents=[Document(content=table, content_type="table")])
assert prediction["answers"][0].answer == "8609.2 m"
assert prediction["answers"][0].meta["aggregation_operator"] == "AVERAGE"
assert prediction["answers"][0].meta["answer_cells"] == ["8848m", "8,611 m", "8 586m", "8 516 m", "8,485m"]
query = "How tall are all mountains together?"
prediction = table_reader.predict(query=query, documents=[Document(content=table, content_type="table")])
assert prediction["answers"][0].answer == "43046.0 m"
assert prediction["answers"][0].meta["aggregation_operator"] == "SUM"
assert prediction["answers"][0].meta["answer_cells"] == ["8848m", "8,611 m", "8 586m", "8 516 m", "8,485m"]