def explore_1():
dataset_name = "rki_ed_1"
rdc_threshold = 0.3
min_instances_slice = 0.01
if not spn_handler.exist_spn(dataset_name, rdc_threshold, min_instances_slice):
df, value_dict, parametric_types = ed_data.get_rki_ed_1()
spn_handler.create_parametric_spns(df.values, parametric_types, dataset_name, [rdc_threshold], [min_instances_slice], value_dict)
spn, value_dict, _ = spn_handler.load_spn(dataset_name, rdc_threshold, min_instances_slice)
spn = fn.marg(spn, keep=[0,2,3,4,5])
fn.print_statistics(spn)
p = io.get_path("_results/ed_data_explore")
#vz.visualize_overall_distribution(spn, value_dict)
from spn.experiments.AQP.Ranges import NominalRange
target_conds = [{0 : NominalRange([5,6])}, {0 : NominalRange([0,1,2,3,4])}]
#target_conds = [{0 : NominalRange([5,6]), 1 : NominalRange([0,1,2,3,4,5,6,7,8,9,10,11])}, {0 : NominalRange([0,1,2,3,4]), 1 : NominalRange([0,1,2,3,4,5,6,7,8,9,10,11])}]
vz.visualize_target_based_conds_overall_distribution_compact(spn, target_conds, value_dict, target_names=["Wochenende", "Unter der Woche"], save_path=p+dataset_name+"_weekend_measures.pdf")
def test_rule_clustering(
): #todo spflow automatically summarizes chains of sums
dataset_name = 'gender'
recalc_SPN = True
rdc_threshold, min_instances_slice = 0.2, 0.1
if not spn_handler.exist_spn(dataset_name, rdc_threshold,
min_instances_slice) or recalc_SPN:
print("Creating SPN ...")
# get data
df, value_dict, parametric_types = synthetic_data.get_synthetic_data(
dataset_name)
# Creates the SPN and saves to a file
spn_handler.create_parametric_spns(df.values,
parametric_types,
dataset_name, [rdc_threshold],
[min_instances_slice],
clustering='rule_clustering')
# Load SPN
spn, value_dict, _ = spn_handler.load_spn(dataset_name, rdc_threshold,
min_instances_slice)
fn.print_statistics(spn)
pass
def explore_2():
dataset_name = "rki_ed_2"
rdc_threshold = 0.3
min_instances_slice = 0.01
if not spn_handler.exist_spn(dataset_name, rdc_threshold, min_instances_slice):
df, value_dict, parametric_types = ed_data.get_rki_ed_2()
spn_handler.create_parametric_spns(df.values, parametric_types, dataset_name, [rdc_threshold], [min_instances_slice], value_dict)
spn, value_dict, _ = spn_handler.load_spn(dataset_name, rdc_threshold, min_instances_slice)
fn.print_statistics(spn)
vz.visualize_overall_distribution(spn, value_dict)
def explore_3():
dataset_name = "rki_ed_3"
rdc_threshold = 0.3
min_instances_slice = 0.01
if not spn_handler.exist_spn(dataset_name, rdc_threshold, min_instances_slice):
df, value_dict, parametric_types = ed_data.get_rki_ed_3()
spn_handler.create_parametric_spns(df.values, parametric_types, dataset_name, [rdc_threshold], [min_instances_slice], value_dict)
spn, value_dict, _ = spn_handler.load_spn(dataset_name, rdc_threshold, min_instances_slice)
fn.print_statistics(spn)
print(value_dict)
p = io.get_path("_results/ed_data_explore")
vz.visualize_likeliness_heatmap(spn, target_id_x=0, target_id_y=1, value_dict=value_dict, save_path=p+dataset_name+"_hour_dep.pdf")
vz.visualize_likeliness_heatmap(spn, target_id_x=0, target_id_y=5, value_dict=value_dict, save_path=p+dataset_name+"_hour_day.pdf")
vz.visualize_likeliness_heatmap(spn, target_id_x=0, target_id_y=6, value_dict=value_dict, save_path=p+dataset_name+"_hour_month.pdf")
print('Data not compatible for topdown')
# labeled = rule_ex.df2labeled(intra_df, value_dict)
rules_intra = intra_df.head(len(topdown_rules))
metrics = ['sup', 'conf', 'conviction', 'F']
eval_intra = evaluate_rules(df,
rules_intra,
value_dict,
metrics=metrics,
beta=beta)
eval_top = evaluate_rules(onehot_df,
topdown_rules,
vd_onehot,
metrics=metrics,
beta=beta)
eval_intra['method'] = 'IntraNode'
eval_top['method'] = 'Topdown'
comp = pd.concat([eval_intra, eval_top], )
comp.drop_duplicates(['head', 'body'], inplace=True)
comp = comp.sort_values('F', ascending=False)
comp.to_csv(res_path + 'comparison_{}.csv'.format(dataset_name))
# mean F of first N rules
print(comp.groupby('method').mean())
hyperparam_grid_search(df, spn, value_dict)
fn.print_statistics(spn)