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., -2., 3.],
"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.schema_errors.loc[
err.schema_errors.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()
)
def test_index_schema_coerce():
"""Test that index can be type-coerced."""
schema = DataFrameSchema(index=Index(Float, coerce=True))
df = pd.DataFrame(index=pd.Index([1, 2, 3, 4], dtype="int64"))
validated_df = schema(df)
assert validated_df.index.dtype == Float.value
],
[
Column(
Int, checks=[Check.greater_than(1), Check.less_than(3)],
name="column"
),
pd.DataFrame({"column": [1, 2, 3]}),
{
"data": pd.DataFrame({"column": [1, 2, 3]}),
"schema_errors": {
"Column": {"greater_than(1)": [1], "less_than(3)": [3]},
},
},
],
[
Index(String, checks=Check.isin(["a", "b", "c"])),
pd.DataFrame({"col": [1, 2, 3]}, index=["a", "b", "d"]),
{
# expect that the data in the SchemaError is the pd.Index cast
# into a Series
"data": pd.Series(["a", "b", "d"]),
"schema_errors": {
"Index": {"isin(%s)" % {'a', 'b', 'c'}: ["d"]},
}
},
],
[
MultiIndex(
indexes=[
Index(Int, checks=Check.greater_than(0), name="index0"),
Index(Int, checks=Check.less_than(0), name="index1"),