def test_default_data_checks_regression(input_type):
X = pd.DataFrame({
'lots_of_null': [None, None, None, None, "some data"],
'all_null': [None, None, None, None, None],
'also_all_null': [None, None, None, None, None],
'no_null': [1, 2, 3, 5, 5],
'id': [0, 1, 2, 3, 4],
'has_label_leakage': [100, 200, 100, 200, 100]
})
y = pd.Series([0.3, 100.0, np.nan, 1.0, 0.2])
y_no_variance = pd.Series([5] * 5)
if input_type == "ww":
X = ww.DataTable(X)
y = ww.DataColumn(y)
y_no_variance = ww.DataColumn(y_no_variance)
null_leakage = [
DataCheckWarning(
message=
"Column 'lots_of_null' is 95.0% or more correlated with the target",
data_check_name="TargetLeakageDataCheck",
message_code=DataCheckMessageCode.TARGET_LEAKAGE,
details={
"column": "lots_of_null"
}).to_dict()
]
data_checks = DefaultDataChecks(
"regression", get_default_primary_search_objective("regression"))
assert data_checks.validate(X, y) == {
"warnings": messages[:3],
"errors": messages[3:]
}
# Skip Invalid Target
assert data_checks.validate(X, y_no_variance) == {
"warnings":
messages[:3] + null_leakage,
"errors":
messages[4:] + [
DataCheckError(message="Y has 1 unique value.",
data_check_name="NoVarianceDataCheck",
message_code=DataCheckMessageCode.NO_VARIANCE,
details={
"column": "Y"
}).to_dict()
]
}
data_checks = DataChecks(
DefaultDataChecks._DEFAULT_DATA_CHECK_CLASSES, {
"InvalidTargetDataCheck": {
"problem_type": "regression",
"objective": get_default_primary_search_objective("regression")
}
})
assert data_checks.validate(X, y) == {
"warnings": messages[:3],
"errors": messages[3:]
}
def test_default_data_checks_regression(input_type):
X = pd.DataFrame({'lots_of_null': [None, None, None, None, "some data"],
'all_null': [None, None, None, None, None],
'also_all_null': [None, None, None, None, None],
'no_null': [1, 2, 3, 5, 5],
'id': [0, 1, 2, 3, 4],
'has_label_leakage': [100, 200, 100, 200, 100],
'natural_language_nan': [None,
"string_that_is_long_enough_for_natural_language_1",
"string_that_is_long_enough_for_natural_language_2",
"string_that_is_long_enough_for_natural_language_3",
"string_that_is_long_enough_for_natural_language_4"],
'nan_dt_col': pd.Series(pd.date_range('20200101', periods=5))})
X['nan_dt_col'][0] = None
y = pd.Series([0.3, 100.0, np.nan, 1.0, 0.2])
y_no_variance = pd.Series([5] * 5)
if input_type == "ww":
X = ww.DataTable(X)
y = ww.DataColumn(y)
y_no_variance = ww.DataColumn(y_no_variance)
null_leakage = [DataCheckWarning(message="Column 'lots_of_null' is 95.0% or more correlated with the target",
data_check_name="TargetLeakageDataCheck",
message_code=DataCheckMessageCode.TARGET_LEAKAGE,
details={"column": "lots_of_null"}).to_dict()]
data_checks = DefaultDataChecks("regression", get_default_primary_search_objective("regression"))
id_leakage_warning = [DataCheckWarning(message="Column 'id' is 95.0% or more correlated with the target",
data_check_name="TargetLeakageDataCheck",
message_code=DataCheckMessageCode.TARGET_LEAKAGE,
details={"column": "id"}).to_dict()]
nan_dt_leakage_warning = [DataCheckWarning(message="Column 'nan_dt_col' is 95.0% or more correlated with the target",
data_check_name="TargetLeakageDataCheck",
message_code=DataCheckMessageCode.TARGET_LEAKAGE,
details={"column": "nan_dt_col"}).to_dict()]
impute_action = DataCheckAction(DataCheckActionCode.IMPUTE_COL, metadata={"column": None, "is_target": True, 'impute_strategy': 'mean'}).to_dict()
nan_dt_action = DataCheckAction(DataCheckActionCode.DROP_COL, metadata={"column": 'nan_dt_col'}).to_dict()
expected_actions_with_drop_and_impute = expected_actions[:3] + [nan_dt_action, impute_action] + expected_actions[4:]
assert data_checks.validate(X, y) == {"warnings": messages[:3] + id_leakage_warning + nan_dt_leakage_warning,
"errors": messages[3:],
"actions": expected_actions_with_drop_and_impute}
# Skip Invalid Target
assert data_checks.validate(X, y_no_variance) == {
"warnings": messages[:3] + null_leakage,
"errors": messages[4:7] + [DataCheckError(message="Y has 1 unique value.",
data_check_name="NoVarianceDataCheck",
message_code=DataCheckMessageCode.NO_VARIANCE,
details={"column": "Y"}).to_dict()] + messages[7:],
"actions": expected_actions[:3] + expected_actions[4:]
}
data_checks = DataChecks(DefaultDataChecks._DEFAULT_DATA_CHECK_CLASSES,
{"InvalidTargetDataCheck": {"problem_type": "regression",
"objective": get_default_primary_search_objective("regression")}})
assert data_checks.validate(X, y) == {"warnings": messages[:3] + id_leakage_warning + nan_dt_leakage_warning,
"errors": messages[3:],
"actions": expected_actions_with_drop_and_impute}
def test_default_data_checks_null_rows():
class SeriesWrap():
def __init__(self, series):
self.series = series
def __eq__(self, series_2):
return all(self.series.eq(series_2.series))
X = pd.DataFrame({'all_null': [None, None, None, None, None],
'also_all_null': [None, None, None, None, None]})
y = pd.Series([0, 1, np.nan, 1, 0])
data_checks = DefaultDataChecks("regression", get_default_primary_search_objective("regression"))
highly_null_rows = SeriesWrap(pd.Series([1.0, 1.0, 1.0, 1.0, 1.0]))
expected = {
"warnings": [DataCheckWarning(message="5 out of 5 rows are more than 95.0% null",
data_check_name="HighlyNullDataCheck",
message_code=DataCheckMessageCode.HIGHLY_NULL_ROWS,
details={"pct_null_cols": highly_null_rows}).to_dict(),
DataCheckWarning(message="Column 'all_null' is 95.0% or more null",
data_check_name="HighlyNullDataCheck",
message_code=DataCheckMessageCode.HIGHLY_NULL_COLS,
details={"column": 'all_null', "pct_null_rows": 1.0}).to_dict(),
DataCheckWarning(message="Column 'also_all_null' is 95.0% or more null",
data_check_name="HighlyNullDataCheck",
message_code=DataCheckMessageCode.HIGHLY_NULL_COLS,
details={"column": 'also_all_null', "pct_null_rows": 1.0}).to_dict()],
"errors": [DataCheckError(message="1 row(s) (20.0%) of target values are null",
data_check_name="InvalidTargetDataCheck",
message_code=DataCheckMessageCode.TARGET_HAS_NULL,
details={"num_null_rows": 1, "pct_null_rows": 20.0}).to_dict(),
DataCheckError(message="all_null has 0 unique value.",
data_check_name="NoVarianceDataCheck",
message_code=DataCheckMessageCode.NO_VARIANCE,
details={"column": "all_null"}).to_dict(),
DataCheckError(message="also_all_null has 0 unique value.",
data_check_name="NoVarianceDataCheck",
message_code=DataCheckMessageCode.NO_VARIANCE,
details={"column": "also_all_null"}).to_dict()],
"actions": [DataCheckAction(DataCheckActionCode.DROP_ROWS, metadata={"rows": [0, 1, 2, 3, 4]}).to_dict(),
DataCheckAction(DataCheckActionCode.DROP_COL, metadata={"column": 'all_null'}).to_dict(),
DataCheckAction(DataCheckActionCode.DROP_COL, metadata={"column": 'also_all_null'}).to_dict(),
DataCheckAction(DataCheckActionCode.IMPUTE_COL, metadata={"column": None, "is_target": True, "impute_strategy": "mean"}).to_dict()]}
validation_results = data_checks.validate(X, y)
validation_results['warnings'][0]['details']['pct_null_cols'] = SeriesWrap(validation_results['warnings'][0]['details']['pct_null_cols'])
assert validation_results == expected
def test_default_data_checks_classification(input_type):
X = pd.DataFrame({
'lots_of_null': [None, None, None, None, "some data"],
'all_null': [None, None, None, None, None],
'also_all_null': [None, None, None, None, None],
'no_null': [1, 2, 3, 4, 5],
'id': [0, 1, 2, 3, 4],
'has_label_leakage': [100, 200, 100, 200, 100],
'natural_language_nan': [
None, "string_that_is_long_enough_for_natural_language_1",
"string_that_is_long_enough_for_natural_language_2",
"string_that_is_long_enough_for_natural_language_3",
"string_that_is_long_enough_for_natural_language_4"
],
'nan_dt_col':
pd.Series(pd.date_range('20200101', periods=5))
})
X['nan_dt_col'][0] = None
y = pd.Series([0, 1, np.nan, 1, 0])
y_multiclass = pd.Series([0, 1, np.nan, 2, 0])
if input_type == "ww":
X = ww.DataTable(X)
y = ww.DataColumn(y)
y_multiclass = ww.DataColumn(y_multiclass)
data_checks = DefaultDataChecks(
"binary", get_default_primary_search_objective("binary"))
imbalance = [
DataCheckError(
message=
"The number of instances of these targets is less than 2 * the number of cross folds = 6 instances: [0.0, 1.0]",
data_check_name="ClassImbalanceDataCheck",
message_code=DataCheckMessageCode.CLASS_IMBALANCE_BELOW_FOLDS,
details={
"target_values": [0.0, 1.0]
}).to_dict()
]
assert data_checks.validate(X, y) == {
"warnings": messages[:3],
"errors": messages[3:] + imbalance,
"actions": expected_actions
}
data_checks = DataChecks(
DefaultDataChecks._DEFAULT_DATA_CHECK_CLASSES, {
"InvalidTargetDataCheck": {
"problem_type": "binary",
"objective": get_default_primary_search_objective("binary")
}
})
assert data_checks.validate(X, y) == {
"warnings": messages[:3],
"errors": messages[3:],
"actions": expected_actions
}
# multiclass
imbalance = [
DataCheckError(
message=
"The number of instances of these targets is less than 2 * the number of cross folds = 6 instances: [0.0, 2.0, 1.0]",
data_check_name="ClassImbalanceDataCheck",
message_code=DataCheckMessageCode.CLASS_IMBALANCE_BELOW_FOLDS,
details={
"target_values": [0.0, 2.0, 1.0]
}).to_dict()
]
min_2_class_count = [
DataCheckError(
message=
"Target does not have at least two instances per class which is required for multiclass classification",
data_check_name="InvalidTargetDataCheck",
message_code=DataCheckMessageCode.
TARGET_MULTICLASS_NOT_TWO_EXAMPLES_PER_CLASS,
details={
"least_populated_class_labels": [2.0, 1.0]
}).to_dict()
]
high_class_to_sample_ratio = [
DataCheckWarning(
message=
"Target has a large number of unique values, could be regression type problem.",
data_check_name="InvalidTargetDataCheck",
message_code=DataCheckMessageCode.
TARGET_MULTICLASS_HIGH_UNIQUE_CLASS,
details={
'class_to_value_ratio': 0.6
}).to_dict()
]
# multiclass
data_checks = DefaultDataChecks(
"multiclass", get_default_primary_search_objective("multiclass"))
assert data_checks.validate(X, y_multiclass) == {
"warnings": messages[:3] + high_class_to_sample_ratio,
"errors": [messages[3]] + min_2_class_count + messages[4:] + imbalance,
"actions": expected_actions
}
data_checks = DataChecks(
DefaultDataChecks._DEFAULT_DATA_CHECK_CLASSES, {
"InvalidTargetDataCheck": {
"problem_type": "multiclass",
"objective": get_default_primary_search_objective("multiclass")
}
})
assert data_checks.validate(X, y_multiclass) == {
"warnings": messages[:3] + high_class_to_sample_ratio,
"errors": [messages[3]] + min_2_class_count + messages[4:],
"actions": expected_actions
}