def test_valid_percentages():
# these are valid:
assert_valid_percent(0.5)
assert_valid_percent(0.9)
assert_valid_percent(0.1)
# these will fail:
assert_raises(ValueError, assert_valid_percent, x=0.0)
assert_raises(ValueError, assert_valid_percent, x=1.0)
# these will pass:
assert_valid_percent(x=1.0, eq_upper=True)
assert_valid_percent(x=0.0, eq_lower=True)
def insert_missing_values(df, percent_rows, random_state=None):
"""
Inserts missing values into a data frame.
:param df: data frame we're operating on
:param percent_rows: the percentage of rows that should have a missing value.
:param random_state: the numpy RandomState
:return: a df with missing values
"""
# get the initialized random_state (if not already initialized)
random_state = get_random_state(random_state)
df = df.copy()
def _insert_random_null(x):
"""
Chose a random column in a df row to null. This
operates in-place. But it's on the copy, so it should be OK.
:param x: the data frame
"""
# -1 because last col will always be y
x[random_state.randint(0, len(x) - 1)] = np.nan
return x
# this is a "truthy" check. If it's zero or False, this will work.
if not percent_rows:
return df
else:
# otherwise validate that it's a float
percent_rows = assert_valid_percent(percent_rows, eq_upper=True) # eq_lower not necessary because != 0.
sample_index = df.sample(frac=percent_rows, random_state=random_state).index # random sample of rows to null
df.loc[sample_index] = df.loc[sample_index].apply(_insert_random_null, axis=1)
return df
def test_score_dataset_multiclass():
results = score_dataset(y_file="y_test.csv", y_hat_file="y_hat_test.csv")
assert_valid_percent(results[0], "Not a valid percent for Accuracy")
def test_score_datasetclassification():
results = score_dataset(y_file="y_test.csv", y_hat_file="y_hat_test.csv")
assert_valid_percent(results[0], "Not a valid percent for AUC")
def test_invalid_percetages(pct):
with pytest.raises(ValueError):
assert_valid_percent(x=pct)
def test_valid_percentages(pct, kwargs):
assert_valid_percent(pct, **kwargs)