def test_simple_preprocessor_dirty_float():
dirty = pd.DataFrame(make_dirty_float())
fp = EasyPreprocessor()
fp.fit(dirty)
res = fp.transform(dirty)
assert res.shape == (100, 3)
rowsum = res.sum(axis=0)
# count of "garbage"
assert rowsum[1] == 1
# count of "missing"
assert rowsum[2] == 9
# make sure we can transform a clean column
fp.transform(pd.DataFrame(['0', '1', '2'], columns=['a_column']))
def test_simple_preprocessor():
sp = EasyPreprocessor()
sp.fit(X_cat)
trans = sp.transform(X_cat)
assert trans.shape == (3, 7) # FIXME should be 6?
iris = load_iris()
sp = EasyPreprocessor()
sp.fit(iris.data)