def test_factor_type():
lg1 = pbn.LinearGaussianCPD("a", [])
lg2 = pbn.LinearGaussianCPD("b", ["a"])
lg3 = pbn.LinearGaussianCPD("c", ["b", "a"])
assert lg1.type() == pbn.LinearGaussianCPDType()
assert lg1.type() == lg2.type()
assert lg1.type() == lg3.type()
assert lg2.type() == lg3.type()
c1 = pbn.CKDE("a", [])
c2 = pbn.CKDE("b", ["a"])
c3 = pbn.CKDE("c", ["b", "a"])
assert c1.type() == pbn.CKDEType()
assert c1.type() == c2.type()
assert c1.type() == c3.type()
assert c2.type() == c3.type()
d1 = pbn.DiscreteFactor("a", [])
d2 = pbn.DiscreteFactor("b", ["a"])
d3 = pbn.DiscreteFactor("c", ["b", "a"])
assert d1.type() == pbn.DiscreteFactorType()
assert d1.type() == d2.type()
assert d1.type() == d3.type()
assert d2.type() == d3.type()
assert lg1.type() != c1.type()
assert lg1.type() != d1.type()
assert c1.type() != d1.type()
def test_lg_sample():
SAMPLE_SIZE = 1000
cpd = pbn.LinearGaussianCPD('a', [])
cpd.fit(df)
sampled = cpd.sample(SAMPLE_SIZE, None, 0)
assert sampled.type == pa.float64()
assert int(sampled.nbytes / (sampled.type.bit_width / 8)) == SAMPLE_SIZE
cpd = pbn.LinearGaussianCPD('b', ['a'])
cpd.fit(df)
sampling_df = pd.DataFrame({'a': np.full((SAMPLE_SIZE,), 3.0)})
sampled = cpd.sample(SAMPLE_SIZE, sampling_df, 0)
assert sampled.type == pa.float64()
assert int(sampled.nbytes / (sampled.type.bit_width / 8)) == SAMPLE_SIZE
cpd = pbn.LinearGaussianCPD('c', ['a', 'b'])
cpd.fit(df)
sampling_df = pd.DataFrame({'a': np.full((SAMPLE_SIZE,), 3.0),
'b': np.full((SAMPLE_SIZE,), 7.45)})
sampled = cpd.sample(SAMPLE_SIZE, sampling_df, 0)
assert sampled.type == pa.float64()
assert int(sampled.nbytes / (sampled.type.bit_width / 8)) == SAMPLE_SIZE
def test_lg_slogl_null():
test_df = util_test.generate_normal_data(5000)
np.random.seed(0)
a_null = np.random.randint(0, 5000, size=100)
b_null = np.random.randint(0, 5000, size=100)
c_null = np.random.randint(0, 5000, size=100)
d_null = np.random.randint(0, 5000, size=100)
df_null = test_df.copy()
df_null.loc[df_null.index[a_null], 'a'] = np.nan
df_null.loc[df_null.index[b_null], 'b'] = np.nan
df_null.loc[df_null.index[c_null], 'c'] = np.nan
df_null.loc[df_null.index[d_null], 'd'] = np.nan
for variable, evidence in [('a', []), ('b', ['a']), ('c', ['a', 'b']), ('d', ['a', 'b', 'c'])]:
cpd = pbn.LinearGaussianCPD(variable, evidence)
cpd.fit(df)
beta = cpd.beta
variance = cpd.variance
assert np.all(np.isclose(cpd.slogl(df_null), np.nansum(numpy_logpdf(df_null, variable, evidence, beta, variance)))),\
"Wrong slogl for LinearGaussianCPD(" + str(variable) + " | " + str(evidence) + ") with null values."
cpd = pbn.LinearGaussianCPD('d', ['a', 'b', 'c'])
cpd.fit(df)
cpd2 = pbn.LinearGaussianCPD('d', ['c', 'a', 'b'])
cpd2.fit(df)
assert np.all(np.isclose(cpd.slogl(df_null), cpd2.slogl(df_null))), "The order of the evidence changes the slogl() result."
def test_lg_slogl():
test_df = util_test.generate_normal_data(5000)
for variable, evidence in [('a', []), ('b', ['a']), ('c', ['a', 'b']), ('d', ['a', 'b', 'c'])]:
cpd = pbn.LinearGaussianCPD(variable, evidence)
cpd.fit(df)
beta = cpd.beta
variance = cpd.variance
assert np.all(np.isclose(cpd.slogl(test_df), np.sum(numpy_logpdf(test_df, variable, evidence, beta, variance)))),\
"Wrong slogl for LinearGaussianCPD(" + str(variable) + " | " + str(evidence) + ")"
cpd = pbn.LinearGaussianCPD('d', ['a', 'b', 'c'])
cpd.fit(df)
cpd2 = pbn.LinearGaussianCPD('d', ['c', 'a', 'b'])
cpd2.fit(df)
assert np.all(np.isclose(cpd.slogl(test_df), cpd2.slogl(test_df))), "The order of the evidence changes the slogl() result."
def test_lg_fit():
for variable, evidence in [("a", []), ("b", ["a"]), ("c", ["a", "b"]), ("d", ["a", "b", "c"])]:
cpd = pbn.LinearGaussianCPD(variable, evidence)
assert not cpd.fitted()
cpd.fit(df)
assert cpd.fitted()
npbeta, npvar = fit_numpy(df, variable, evidence)
assert np.all(np.isclose(npbeta, cpd.beta)), "Wrong beta vector."
assert np.all(np.isclose(npvar, cpd.variance)), "Wrong variance."
def test_lg_fit_null():
np.random.seed(0)
a_null = np.random.randint(0, SIZE, size=100)
b_null = np.random.randint(0, SIZE, size=100)
c_null = np.random.randint(0, SIZE, size=100)
d_null = np.random.randint(0, SIZE, size=100)
df_null = df.copy()
df_null.loc[df_null.index[a_null], 'a'] = np.nan
df_null.loc[df_null.index[b_null], 'b'] = np.nan
df_null.loc[df_null.index[c_null], 'c'] = np.nan
df_null.loc[df_null.index[d_null], 'd'] = np.nan
for variable, evidence in [("a", []), ("b", ["a"]), ("c", ["a", "b"]), ("d", ["a", "b", "c"])]:
cpd = pbn.LinearGaussianCPD(variable, evidence)
assert not cpd.fitted()
cpd.fit(df_null)
assert cpd.fitted()
npbeta, npvar = fit_numpy(df_null, variable, evidence)
assert np.all(np.isclose(npbeta, cpd.beta)), "Wrong beta vector."
assert np.all(np.isclose(npvar, cpd.variance)), "Wrong variance."
def gaussian_partial_fit_bytes():
gaussian = GaussianNetwork(["a", "b", "c", "d"], [("a", "b")])
lg = pbn.LinearGaussianCPD("b", ["a"], [1, 2], 2)
gaussian.add_cpds([lg])
gaussian.include_cpd = True
return pickle.dumps(gaussian)
def test_lg_data_type():
cpd = pbn.LinearGaussianCPD("a", [])
assert cpd.data_type() == pa.float64()
def test_lg_evidence():
for variable, evidence in [('a', []), ('b', ['a']), ('c', ['a', 'b']), ('d', ['a', 'b', 'c'])]:
cpd = pbn.LinearGaussianCPD(variable, evidence)
assert cpd.evidence() == evidence