],
],
*[
_boolean_update_column_case(bool_kwarg) for bool_kwarg in [
"nullable",
"allow_duplicates",
"coerce",
"required",
"regex",
]
],
[
Column(Int, checks=Check.greater_than(0)),
"col",
{
"checks": Check.less_than(10)
},
lambda old, new: [
old.columns["col"].checks == [Check.greater_than(0)],
new.columns["col"].checks == [Check.less_than(10)],
],
],
# error cases
[Column(Int), "col", {
"name": "renamed_col"
}, ValueError],
[Column(Int), "foobar", {}, ValueError],
],
)
def test_dataframe_schema_update_column(column, column_to_update, update,
assertion_fn):
def test_lazy_dataframe_validation_error():
"""Test exceptions on lazy dataframe validation."""
schema = DataFrameSchema(
columns={
"int_col": Column(Int, Check.greater_than(5)),
"int_col2": Column(Int),
"float_col": Column(Float, Check.less_than(0)),
"str_col": Column(String, Check.isin(["foo", "bar"])),
"not_in_dataframe": Column(Int),
},
checks=Check(lambda df: df != 1,
error="dataframe_not_equal_1",
ignore_na=False),
index=Index(String, name="str_index"),
strict=True,
)
dataframe = pd.DataFrame(
data={
"int_col": [1, 2, 6],
"int_col2": ["a", "b", "c"],
"float_col": [1.0, -2.0, 3.0],
"str_col": ["foo", "b", "c"],
"unknown_col": [None, None, None],
},
index=pd.Index(["index0", "index1", "index2"], name="str_index"),
)
expectation = {
# schema object context -> check failure cases
"DataFrameSchema": {
# check name -> failure cases
"column_in_schema": ["unknown_col"],
"dataframe_not_equal_1": [1],
"column_in_dataframe": ["not_in_dataframe"],
},
"Column": {
"greater_than(5)": [1, 2],
"pandas_dtype('int64')": ["object"],
"less_than(0)": [1, 3],
},
}
with pytest.raises(errors.SchemaErrors,
match="^A total of .+ schema errors were found"):
schema.validate(dataframe, lazy=True)
try:
schema.validate(dataframe, lazy=True)
except errors.SchemaErrors as err:
# data in the caught exception should be equal to the dataframe
# passed into validate
assert err.data.equals(dataframe)
# make sure all expected check errors are in schema errors
for schema_context, check_failure_cases in expectation.items():
err_df = err.failure_cases.loc[err.failure_cases.schema_context ==
schema_context]
for check, failure_cases in check_failure_cases.items():
assert check in err_df.check.values
assert (err_df.loc[err_df.check == check].failure_case.isin(
failure_cases).all())
],
],
*[
_boolean_update_column_case(bool_kwarg)
for bool_kwarg in [
"nullable",
"allow_duplicates",
"coerce",
"required",
"regex",
]
],
[
Column(Int, checks=Check.greater_than(0)),
"col",
{"checks": Check.less_than(10)},
lambda old, new: [
old.columns["col"].checks == [Check.greater_than(0)],
new.columns["col"].checks == [Check.less_than(10)],
],
],
# error cases
[Column(Int), "col", {"name": "renamed_col"}, ValueError],
[Column(Int), "foobar", {}, ValueError],
],
)
def test_dataframe_schema_update_column(
column, column_to_update, update, assertion_fn
):
"""Test that DataFrameSchema columns create updated copies."""
schema = DataFrameSchema({"col": column})