def test_required_column_failure():
df = _get_test_dataframe()
# drop a column
df = df[["primary_key", "letter"]]
with pytest.raises(ValueError):
dataframe.validate(
df, require_present_columns=["primary_key", "letter", "produce"])
def test_failure_dict_return():
df = _get_test_dataframe()
df = df[["primary_key", "letter"]]
result = dataframe.validate(df,
raise_error=False,
require_present_columns=["produce"])
assert not result.passed
assert "produce" in result.details["failed_present_columns"]
def test_successful_validation():
df = _get_test_dataframe()
result = dataframe.validate(
df,
require_present_columns=["primary_key", "letter", "produce"],
require_unique_columns=["primary_key"],
require_nonnull_columns=["primary_key", "letter", "produce"],
)
assert result.passed
assert len(result.details) == 0
def main() -> ValidationCheck:
"""Checks the columns of a DataFrame
Returns: ValidationCheck object consisting of Pass/Fail and dict of failed columns
"""
df1 = pd.DataFrame({
"a": [1, 1, 1, 1],
"b": [1, 1, 2, 2],
"c": [2, 2, 2, 2],
"d": [3, 3, 3, 3]
})
failed_checks_dict = dataframe.validate(
df1,
require_present_columns=["a", "b"],
require_unique_columns=["d"],
require_nonnull_columns=["b", "c"],
custom_checks=((ensure_not_2, ["a", "b"]), (ensure_not_3, ["a", "d"])),
)
return failed_checks_dict
def test_check_custom():
def ensure_not_2(value):
return value != 2
def ensure_3(value):
return value == 3
df_check = pd.DataFrame({
"a": [1, 1, 1, 1],
"b": [2, 2, 2, 2],
"c": [3, 3, 3, 3]
})
dataframe.validate(df_check,
custom_checks=((ensure_not_2, ["a"]), (ensure_3, ["c"
])))
with pytest.raises(ValueError):
dataframe.validate(df_check,
custom_checks=((ensure_3, ["c"]), (ensure_not_2,
["b"])))
with pytest.raises(ValueError):
dataframe.validate(df_check, custom_checks=((ensure_not_2, ["b"]), ))
def test_nonnull_column_failure():
df = _get_test_dataframe()
# introduce an empty value
df.loc[0, "produce"] = None
with pytest.raises(ValueError):
dataframe.validate(df, require_nonnull_columns=["produce"])
def test_unique_column_failure():
df = _get_test_dataframe()
# introduce a repeated value
df.loc[1, "primary_key"] = "1"
with pytest.raises(ValueError):
dataframe.validate(df, require_unique_columns=["primary_key"])