def test_marg():
spn = example_spns.get_gender_spn()
spn1 = fn.marg(spn, [2])
fn.plot_spn(spn1, "marg1.pdf")
spn2 = fn.marg(spn, [0])
fn.plot_spn(spn2, "marg2.pdf")
spn3 = fn.marg(spn, [1])
fn.plot_spn(spn3, "marg3.pdf")
spn4 = fn.marg(spn, [1, 2])
fn.plot_spn(spn4, "marg4.pdf")
rang = [None, NominalRange([1]), None]
prob, spn5 = fn.marg_rang(spn, rang)
fn.plot_spn(spn5, "marg5.pdf")
rang = [None, NominalRange([1]), NumericRange([[10, 12]])]
prob, spn6 = fn.marg_rang(spn, rang)
fn.plot_spn(spn6, "marg6.pdf")
rang = [NominalRange([0]), NominalRange([1]), None]
prob = fn.prob(spn, rang)
print(prob)
prob = fn.prob(spn6, rang)
print(prob)
def test_plot():
spn = example_spns.get_gender_spn()
fn.plot_spn(spn, "sample_spn.pdf")
spn = example_spns.get_credit_spn()()
fn.plot_spn(spn, "sample_spn2.pdf")
df = pd.DataFrame(data, columns=[value_dict[i][1] for i in range(num_vars)])
print(df.corr())
# parameters for the construction
rdc_threshold = 0.1
min_instances_slice = 0.1
if not spn_handler.exist_spn(dataset_name, rdc_threshold, min_instances_slice):
print("Creating SPN ...")
# get data
# df, value_dict, parametric_types = real_data.get_titanic()
spn, value_dict, _ = spn_handler.create_parametric_spns(
data,
data_types,
dataset_name, [rdc_threshold], [min_instances_slice],
value_dict,
save=False)
# # Load SPN
# spn, value_dict, _ = spn_handler.load_spn(dataset_name, rdc_threshold, min_instances_slice)
# Print some statistics
fn.print_statistics(spn)
visualize_expected_sub_populations(spn, value_dict, 10)
visualize_sub_populations(spn, value_dict, 10)
subpops = fn.get_sub_populations(spn, )
print(subpops)
print('============')
pprint(subpops)
fn.plot_spn(spn, "icecream_spn.pdf", value_dict)
bbox_inches='tight',
dpi=400)
plt.show()
from spn.structure.leaves.parametric.Parametric import Poisson
# Z plot
fig, ax = plt.subplots(figsize=(size[0] / 2.5, size[1]))
currp = p[4]
ticks = list(range(len(currp)))
labels = ['{}{}'.format('Z', i) for i, _ in enumerate(currp)]
ax.bar(
ticks,
currp,
)
ax.set_xticks(ticks, )
ax.set_xticklabels(labels)
ax.set_ylim([0., 1.05])
ax.set_ylabel('probability')
ax.yaxis.set_label_position("right")
ax.yaxis.tick_right()
plt.savefig('../../_figures/rule_extraction/leaf5.png',
bbox_inches='tight',
dpi=400)
plt.show()
fn.plot_spn(spn)
df, _, _ = get_titanic_bins()
c = df.Pclass.astype(int).value_counts()
r = c / c.sum()
r.index = pd.Index(['1st Class', '2nd Class', '3rd Class'])
r.plot('bar')
pass
df = df[["Survived", "Sex", "Age", "Fare", "Pclass"]]
df, val_dict, param_types = fn.transform_dataset(df)
#print data after transformation (top 5 rows)
io.print_pretty_table(df.head(5))
''''
SPN functions
'''
#Load synthetic example SPN (very simple SPN)
from simple_spn.example import example_spns
spn = example_spns.get_gender_spn()
#plot spn
fn.plot_spn(spn, "sample_spn.pdf", value_dict)
#generate samples
samples = fn.sampling(spn, n_samples=10, random_seed=1)
print(samples)
samples = fn.sampling_rang(spn,
rang=[None, None, None, None],
n_samples=10,
random_seed=1)
print(samples)
samples = fn.sampling_rang(
spn,
rang=[None, None, NumericRange([[10, 11], [29, 30]])],
n_samples=10,