some helpers for working with pandas data frames in a conda environment
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

48 lines
1.1 KiB

import pandas as pd
import pytest
@pytest.fixture()
def example_data():
return pd.DataFrame({"A": [1, 2, 2], "B": [3, 4, 3], "C": ["x", "y", "z"]})
def test_split_uniques_one_column(example_data):
from conda_helpers import iter_uniques
result = list(iter_uniques(example_data, "A"))
assert len(result) == 2
assert isinstance(result[0], tuple)
a_value, data = result[0]
assert a_value == 1
assert list(data["C"]) == ["x"]
a_value, data = result[1]
assert a_value == 2
assert list(data["C"]) == ["y", "z"]
def test_split_uniques_multiple_columns(example_data):
from conda_helpers import iter_uniques
result = list(iter_uniques(example_data, "B", "A"))
assert len(result) == 3
assert isinstance(result[0], tuple)
b_value, a_value, data = result[0]
assert b_value == 3
assert a_value == 1
assert list(data["C"]) == ["x"]
b_value, a_value, data = result[1]
assert b_value == 3
assert a_value == 2
assert list(data["C"]) == ["z"]
b_value, a_value, data = result[2]
assert b_value == 4
assert a_value == 2
assert list(data["C"]) == ["y"]