def test_sdg_likelihood_categorical():
sdg = DataGenerator(10, ['categorical']*2, view_weights=1)
x = [0, 1, 2]
lls = sdg.log_likelihood(x, 0)
assert len(lls) == 3
assert lls.shape == (3,)
def test_sdg_likelihood_categorical():
sdg = DataGenerator(10, ['categorical'] * 2, view_weights=1)
x = [0, 1, 2]
lls = sdg.log_likelihood(x, 0)
assert len(lls) == 3
assert lls.shape == (3, )
def test_sdg_likelihood_continuous():
sdg = DataGenerator(10, ['continuous']*2, view_weights=1)
x = np.linspace(0, 6, 10)
lls = sdg.log_likelihood(x, 0)
assert len(lls) == 10
assert lls.shape == (10,)
def test_sdg_likelihood_continuous():
sdg = DataGenerator(10, ['continuous'] * 2, view_weights=1)
x = np.linspace(0, 6, 10)
lls = sdg.log_likelihood(x, 0)
assert len(lls) == 10
assert lls.shape == (10, )
def test_sdg_init_dual_mixed_two_view(dtype):
sdg = DataGenerator(10, [dtype] * 3, view_weights=2)
assert sdg.df.shape == (
10,
3,
)
assert min(sdg._colpart) == 0
assert max(sdg._colpart) == 1
def gen_data_and_engine(n_rows, n_cols, n_cats, cat_sep, n_models, n_iter):
dg = DataGenerator(n_rows, ['continuous'] * n_cols,
cat_weights=n_cats,
cat_sep=cat_sep,
seed=1337)
engine = Engine(dg.df, use_mp=False)
engine.init_models(n_models)
engine.run(n_iter)
return dg, engine
def test_sdg_init_single_categorical():
sdg = DataGenerator(10, ['categorical'])
assert sdg.df.shape == (
10,
1,
)
assert sdg.df[0].dtype == 'int'
assert len(sdg._params) == 1
assert len(sdg._params[0]) == 2
def test_sdg_init_single_continuous():
sdg = DataGenerator(10, ['continuous'])
assert sdg.df.shape == (
10,
1,
)
assert sdg.df[0].dtype == 'float'
assert len(sdg._params) == 1
assert len(sdg._params[0]) == 2
def test_sdg_init_dual_mixed():
sdg = DataGenerator(10, ['continuous', 'categorical'])
assert sdg.df.shape == (
10,
2,
)
assert sdg.df[0].dtype == 'float'
assert sdg.df[1].dtype == 'int'
assert len(sdg._params) == 2
assert len(sdg._params[0]) == 2
assert len(sdg._params[1]) == 2
def test_sdg_init_dual_continuous():
sdg = DataGenerator(10, ['continuous'] * 2)
assert sdg.df.shape == (
10,
2,
)
assert sdg.df[0].dtype == 'float'
assert sdg.df[1].dtype == 'float'
assert len(sdg._params) == 2
assert len(sdg._params[0]) == 2
assert len(sdg._params[1]) == 2
def test_sdg_init_dual_categorical():
sdg = DataGenerator(10, ['categorical'] * 2)
assert sdg.df.shape == (
10,
2,
)
assert sdg.df[0].dtype == 'int'
assert sdg.df[1].dtype == 'int'
assert len(sdg._params) == 2
assert len(sdg._params[0]) == 2
assert len(sdg._params[1]) == 2
def gen_data_and_engine(n_rows, n_cols, n_cats, cat_sep, n_models, n_iter):
dg = DataGenerator(n_rows, ['categorical'] * n_cols,
cat_weights=n_cats,
cat_sep=cat_sep,
seed=1337)
col_md = {'dtype': 'categorical', 'values': [0, 1, 2, 3, 4]}
md = dict((
col,
col_md,
) for col in range(n_cols))
engine = Engine(dg.df, metadata=md, use_mp=False)
engine.init_models(n_models)
engine.run(n_iter)
return dg, engine
