def test_step_row_ungroup_max():
source = Resource(path="data/transform-groups.csv")
source.infer()
target = transform(
source,
steps=[
steps.row_ungroup(group_name="name",
selection="max",
value_name="population"),
],
)
assert target.schema == source.schema
assert target.read_rows() == [
{
"id": 3,
"name": "france",
"population": 66,
"year": 2020
},
{
"id": 1,
"name": "germany",
"population": 83,
"year": 2020
},
{
"id": 5,
"name": "spain",
"population": 47,
"year": 2020
},
]
def test_step_row_ungroup_last():
source = Resource(path="data/transform-groups.csv")
source.infer()
target = transform(
source,
steps=[
steps.row_ungroup(group_name="name", selection="last"),
],
)
assert target.schema == source.schema
assert target.read_rows() == [
{
"id": 4,
"name": "france",
"population": 54,
"year": 1920
},
{
"id": 2,
"name": "germany",
"population": 77,
"year": 1920
},
{
"id": 6,
"name": "spain",
"population": 33,
"year": 1920
},
]
def test_step_row_ungroup_max():
source = Resource("data/transform-groups.csv")
target = transform(
source,
steps=[
steps.row_ungroup(group_name="name",
selection="max",
value_name="population"),
],
)
assert target.schema == {
"fields": [
{
"name": "id",
"type": "integer"
},
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
{
"name": "year",
"type": "integer"
},
]
}
assert target.read_rows() == [
{
"id": 3,
"name": "france",
"population": 66,
"year": 2020
},
{
"id": 1,
"name": "germany",
"population": 83,
"year": 2020
},
{
"id": 5,
"name": "spain",
"population": 47,
"year": 2020
},
]