columns = ['clump_thickness', 'cell_size_uniformity', 'cell_shape_uniformity', 'marginal_adhesion',
'single_epi_cell_size', 'bare_nuclei', 'bland_chromatin', 'normal_nucleoli', 'mitoses']
nums = columns
data, num_idx, columns = load_data('data/breastw/breastw.csv', attrs=columns, label=['label'], numerics=nums, pos='benign')

X_train, Y_train = split_xy(data_train)
X_pos, X_neg = split_X_by_Y(X_train, Y_train)
rules1 = foldrpp(X_pos, X_neg, [])

fr1 = flatten(rules1)
rule_set = decode_rules(fr1, attrs)
for r in rule_set:
    print(r)

% breastw dataset (699, 10).
% the answer set program generated by foldr++:

label(X,'benign'):- bare_nuclei(X,'?').
label(X,'benign'):- bland_chromatin(X,N6), N6=<4.0,
		    clump_thickness(X,N0), N0=<6.0,  
                    bare_nuclei(X,N5), N5=<1.0, not ab7(X).   
label(X,'benign'):- cell_size_uniformity(X,N1), N1=<2.0,
		    not ab3(X), not ab5(X), not ab6(X).  
label(X,'benign'):- cell_size_uniformity(X,N1), N1=<4.0,
		    bare_nuclei(X,N5), N5=<3.0,
		    clump_thickness(X,N0), N0=<3.0, not ab8(X).  
ab2(X):- clump_thickness(X,N0), N0=<1.0.  
ab3(X):- bare_nuclei(X,N5), N5>5.0, not ab2(X).  
ab4(X):- cell_shape_uniformity(X,N2), N2=<1.0.  
ab5(X):- clump_thickness(X,N0), N0>7.0, not ab4(X).  
ab6(X):- bare_nuclei(X,N5), N5>4.0, single_epi_cell_size(X,N4), N4=<1.0.  
ab7(X):- marginal_adhesion(X,N3), N3>4.0.  
ab8(X):- marginal_adhesion(X,N3), N3>6.0.  

% foldr++ costs:  0:00:00.027710  post: 0:00:00.000127
% acc 0.95 p 0.96 r 0.9697 f1 0.9648 

data_pred = decode_test_data(data_test, attrs)
for p in data_pred:
    print(p)

% acute dataset (120, 7) 
% the answer set program generated by foldr++:

ab2(X):- a5(X,'no'), a1(X,N0), N0>37.9.
label(X,'yes'):- not a4(X,'no'), not ab2(X).

% foldr++ costs:  0:00:00.001990  post: 0:00:00.000040
% acc 1.0 p 1.0 r 1.0 f1 1.0 

id(1).
a1(1,37.2).
a2(1,'no').
a3(1,'yes').
a4(1,'no').
a5(1,'no').
a6(1,'no').

id(2).
a1(2,38.1).
a2(2,'no').
a3(2,'yes').
a4(2,'yes').
a5(2,'no').
a6(2,'yes').

id(3).
a1(3,37.5).
a2(3,'no').
a3(3,'no').
a4(3,'yes').
a5(3,'yes').
a6(3,'yes').

@misc{wang2021foldr,
      title={FOLD-R++: A Toolset for Automated Inductive Learning of Default Theories from Mixed Data}, 
      author={Huaduo Wang and Gopal Gupta},
      year={2021},
      eprint={2110.07843},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}