Animal example

1_Model/ILP_model_learner.py

+# -*- coding: utf-8 -*-
+"""
+Created on Thu Apr 01 14:28:02 2021
+
+@author: Bettina Finzel
+"""
+
+import pexpect
+import os
+
+data_set = "semanticnet"
+
+aleph_path = os.getcwd()
+
+aleph_call = "yap -l aleph.pl -g 'read_all(" + data_set + ").'"
+
+child_process = pexpect.spawn(aleph_call, timeout = 500, maxread = 200000)
+
+child_process.sendline('induce.')
+
+index = child_process.expect(["[total clauses constructed]", pexpect.TIMEOUT])
+
+if index == 0:
+    child_process.sendline('write_rules.')
+    index2 = child_process.expect(["yes",  pexpect.TIMEOUT])
+    if index2 == 0:
+        child_process.sendline('halt.')
+        index3 = child_process.expect(["yes",  pexpect.TIMEOUT])
+        if index3 == 0:
+            child_process.terminate()
+        else:
+            child_process.terminate()
+    else:
+        child_process.terminate()
+else:
+    child_process.terminate()

1_Model/README.txt

+### You can adapt the files in this repository with respect to your use case. ###
+
+In ILP_model_learner.py change the data_set field according to the name of your Aleph input files,
+written in Prolog. Per default it is set to "semanticnet". The script loads all Aleph files,
+which are located in the same directory as the aleph.pl file and induces a model.
+
+Aleph needs three input files: the background file *.b, the file with positive example *.f,
+and the file with negative examples *.n.
+Check out the Aleph manual for more information about how to set up the files:
+https://www.cs.ox.ac.uk/activities/programinduction/Aleph/aleph.html
+
+In our code, Aleph is setup such that it produces output files for each run ("Record.txt"),
+and for the learned model ("Result.txt"). The result file is stored by using the command "write_rules.".
+
+### In order to run the aleph.pl file with our code, you will need an installation of Yap ###
+
+The installation is currently only available for Linux operating systems and can be simply downloaded
+using the command "apt-get install yap".
\ No newline at end of file

1_Model/Record

+
+[settings]
+        abduce=false
+        cache_clauselength=3
+        caching=false
+        check_good=false
+        check_redundant=false
+        check_useless=false
+        clauselength=10
+        condition=false
+        confidence=0.95
+        construct_bottom=saturation
+        depth=10
+        evalfn=coverage
+        explore=false
+        good=false
+        greedy=true
+        gsamplesize=100
+        i=10
+        interactive=false
+        language=(+inf)
+        lazy_negs=false
+        lazy_on_contradiction=false
+        lazy_on_cost=false
+        lookahead=1
+        max_abducibles=2
+        max_features=(+inf)
+        minacc=0.0
+        mingain=0.05
+        minpos=2
+        minposfrac=0
+        minscore=0
+        moves=5
+        newvars=(+inf)
+        nodes=180000
+        noise=0
+        nreduce_bottom=false
+        openlist=(+inf)
+        optimise_clauses=false
+        permute_bottom=false
+        portray_examples=false
+        portray_hypothesis=false
+        portray_literals=false
+        portray_search=false
+        print=4
+        prior=[0.5-pos,0.5-neg]
+        proof_strategy=restricted_sld
+        prooftime=(+inf)
+        prune_tree=false
+        record=true
+        recordfile=Record
+        recordfile_stream=$stream(4)
+        refine=false
+        refineop=false
+        resample=1
+        rls_type=gsat
+        rulefile=Result
+        samplesize=0
+        search=bf
+        searchstrat=bf
+        searchtime=(+inf)
+        skolemvars=10000
+        splitvars=false
+        stage=command
+        store_bottom=false
+        subsample=false
+        subsamplesize=(+inf)
+        threads=1
+        train_neg=semanticnet.n
+        train_pos=semanticnet.f
+        tries=10
+        typeoverlap=0.95
+        uniform_sample=false
+        updateback=true
+        verbosity=2
+        version=5
+[sat] [1]
+[clauses constructed] [180000]
+[search time] [19.261]
+[best clause]
+tracks_down(A,B) :-
+   is_(B,plant), is_(A,herbivore).
+[positive examples left] [3]
+[estimated time to finish (secs)] [11.5566]
+[sat] [3]
+[clauses constructed] [598]
+[search time] [0.0210000000000008]
+[best clause]
+tracks_down(A,B) :-
+   is_(B,herbivore), is_(A,carnivore).
+[positive examples left] [0]
+[estimated time to finish (secs)] [0.0]
+
+[theory]
+
+[Rule 1] [Pos cover = 5 Neg cover = 0]
+tracks_down(A,B) :-
+   is_(B,plant), is_(A,herbivore).
+[positive examples covered]
+tracks_down(bobby,dandelion).
+tracks_down(fluffy,clover).
+tracks_down(bobby,parsley).
+tracks_down(fluffy,rosemary).
+tracks_down(tipsie,rosemary).
+[negative examples covered]
+
+[Rule 2] [Pos cover = 3 Neg cover = 0]
+tracks_down(A,B) :-
+   is_(B,herbivore), is_(A,carnivore).
+[positive examples covered]
+tracks_down(samson,fluffy).
+tracks_down(bella,bobby).
+tracks_down(bella,tipsie).
+[negative examples covered]
+
+[Training set performance]
+          Actual
+       +        - 
+     + 8        0        8 
+Pred 
+     - 0        8        8 
+
+       8        8        16 
+
+Accuracy = 1.0
+[Training set summary] [[8,0,0,8]]
+[time taken] [20.522]
+
+[total clauses constructed] [180598]

1_Model/Result

+tracks_down(A,B) :-
+   is_(B,plant), is_(A,herbivore).
+tracks_down(A,B) :-
+   is_(B,herbivore), is_(A,carnivore).

1_Model/colon.b

+% Head declaration for target class
+:- modeh(1, stage_t2(+tissue,+tissue)).
+
+% Body declarations for relations
+:- modeb(*, is_(+tissue,+tissue)).
+:- modeb(*, is_(+tissue,-tissue)).
+:- modeb(*, is_(-tissue,+tissue)).
+:- modeb(*, is_(+tissue,#tissue)).
+:- modeb(*, is_(#tissue,+tissue)).
+:- modeb(*, is_(-tissue,#tissue)).
+:- modeb(*, is_(#tissue,-tissue)).
+:- modeb(*, is_(#tissue,#tissue)).
+
+%:- modeb(*, has(+tissue,+tissue)).
+%:- modeb(*, has(+tissue,-tissue)).
+%:- modeb(*, has(-tissue,+tissue)).
+%:- modeb(*, has(+tissue,#tissue)).
+%:- modeb(*, has(#tissue,+tissue)).
+%:- modeb(*, has(-tissue,#tissue)).
+%:- modeb(*, has(#tissue,-tissue)).
+%:- modeb(*, has(#tissue,#tissue)).
+
+:- modeb(*, contains(+tissue,+tissue)).
+:- modeb(*, contains(+tissue,-tissue)).
+:- modeb(*, contains(-tissue,+tissue)).
+:- modeb(*, contains(+tissue,#tissue)).
+:- modeb(*, contains(#tissue,+tissue)).
+:- modeb(*, contains(-tissue,#tissue)).
+:- modeb(*, contains(#tissue,-tissue)).
+:- modeb(*, contains(#tissue,#tissue)).
+
+:- modeb(*, invades(+tissue,+tissue)).
+:- modeb(*, invades(+tissue,-tissue)).
+:- modeb(*, invades(-tissue,+tissue)).
+:- modeb(*, invades(+tissue,#tissue)).
+:- modeb(*, invades(#tissue,+tissue)).
+:- modeb(*, invades(-tissue,#tissue)).
+:- modeb(*, invades(#tissue,-tissue)).
+:- modeb(*, invades(#tissue,#tissue)).
+
+:- modeb(*, intersects(+tissue,+tissue)).
+:- modeb(*, intersects(+tissue,-tissue)).
+:- modeb(*, intersects(-tissue,+tissue)).
+:- modeb(*, intersects(+tissue,#tissue)).
+:- modeb(*, intersects(#tissue,+tissue)).
+:- modeb(*, intersects(-tissue,#tissue)).
+:- modeb(*, intersects(#tissue,-tissue)).
+:- modeb(*, intersects(#tissue,#tissue)).
+
+% Determinations
+:- determination(stage_t2/2, is_/2).
+:- determination(stage_t2/2, contains/2).
+:- determination(stage_t2/2, invades/2).
+%:- determination(stage_t2/2, has/2).
+
+% Aleph settings
+:- set(i, 10).
+:- set(clauselength, 10).
+:- set(minpos, 2).
+:- set(minscore, 0).
+:- set(verbosity, 2).
+:- set(noise, 0).
+:- set(nodes, 180000).
+:- set(rulefile,'Result').
+:- set(record, true).
+:- set(recordfile, 'Record').
+
+% semantic concepts
+is_a(mucosa,tissue).
+is_a(submucosa,tissue).
+is_a(muscle,tissue).
+is_a(fat,tissue).
+
+% background of examples
+% T2
+contains(scan_0708,tissue_1718).
+contains(scan_0708,tissue_1818).
+contains(scan_0708,tissue_1918).
+contains(scan_0708,tissue_1118).
+
+contains(scan_0001,tissue_1615).
+contains(scan_0001,tissue_1715).
+contains(scan_0001,tissue_1815).
+contains(scan_0001,tissue_1115).
+
+contains(scan_0002,tissue_1413).
+contains(scan_0002,tissue_1513).
+contains(scan_0002,tissue_1613).
+contains(scan_0002,tissue_1113).
+
+is_a(tissue_1718,tumor).
+is_a(tissue_1615,tumor).
+is_a(tissue_1413,tumor).
+
+is_a(tissue_1818,muscle).
+is_a(tissue_1715,muscle).
+is_a(tissue_1513,muscle).
+
+is_a(tissue_1918,submucosa).
+is_a(tissue_1815,submucosa).
+is_a(tissue_1613,submucosa).
+
+is_a(tissue_1118,mucosa).
+is_a(tissue_1115,mucosa).
+is_a(tissue_1113,mucosa).
+
+intersects(tissue_1718,tissue_1818).
+intersects(tissue_1615,tissue_1715).
+intersects(tissue_1413,tissue_1513).
+
+intersects(tissue_1718,tissue_1918).
+intersects(tissue_1615,tissue_1815).
+intersects(tissue_1413,tissue_1613).
+
+% Contrast class
+contains(scan_2728,tissue_2718).
+contains(scan_2728,tissue_2818).
+contains(scan_2728,tissue_2918).
+contains(scan_2728,tissue_2118).
+
+contains(scan_0003,tissue_2615).
+contains(scan_0003,tissue_2715).
+contains(scan_0003,tissue_2815).
+contains(scan_0003,tissue_2115).
+
+contains(scan_0004,tissue_2413).
+contains(scan_0004,tissue_2513).
+contains(scan_0004,tissue_2613).
+contains(scan_0004,tissue_2113).
+
+is_a(tissue_2718,tumor).
+is_a(tissue_2615,tumor).
+is_a(tissue_2413,tumor).
+
+is_a(tissue_2818,muscle).
+is_a(tissue_2715,muscle).
+is_a(tissue_2513,muscle).
+
+is_a(tissue_2918,submucosa).
+is_a(tissue_2815,submucosa).
+is_a(tissue_2613,submucosa).
+
+is_a(tissue_2118,mucosa).
+is_a(tissue_2115,mucosa).
+is_a(tissue_2113,mucosa).
+
+intersects(tissue_2718,tissue_2918).
+intersects(tissue_2615,tissue_2815).
+intersects(tissue_2413,tissue_2613).
+
+intersects(tissue_2718,tissue_2118).
+intersects(tissue_2615,tissue_2115).
+intersects(tissue_2413,tissue_2113).
+
+% reasoning rules
+is_(A,B) :- is_a(A,B).
+is_(A,B) :- is_a(A,C), is_(C,B).
+
+invades(A,B) :- intersects(A,B).
+
+%has(A,X) :- has_p(A,X).
+%has(X,Z) :- has_p(X,Y), has(Y,Z).
+
+%has(A,X) :- is_(A,B), has(B,X).
+%has(A,X) :- has_p(A,Y), is_(Y,X).

1_Model/colon.f

+stage_t2(scan_0708).
+stage_t2(scan_0001).
+stage_t2(scan_0002).

1_Model/colon.n

+stage_t2(scan_2728).
+stage_t2(scan_0003).
+stage_t2(scan_0004).
+

1_Model/semanticnet.b

+% Head declaration for target class
+:- modeh(1, tracks_down(+being,+being)).
+
+% Body declarations for relations
+:- modeb(*, is_(+being,+being)).
+:- modeb(*, is_(+being,-being)).
+:- modeb(*, is_(-being,+being)).
+:- modeb(*, is_(+being,#being)).
+:- modeb(*, is_(#being,+being)).
+:- modeb(*, is_(-being,#being)).
+:- modeb(*, is_(#being,-being)).
+:- modeb(*, is_(#being,#being)).
+
+:- modeb(*, has(+being,+being)).
+:- modeb(*, has(+being,-being)).
+:- modeb(*, has(-being,+being)).
+:- modeb(*, has(+being,#being)).
+:- modeb(*, has(#being,+being)).
+:- modeb(*, has(-being,#being)).
+:- modeb(*, has(#being,-being)).
+:- modeb(*, has(#being,#being)).
+
+%:- modeb(*, is_a(+being,+being)).
+%:- modeb(*, is_a(+being,-being)).
+%:- modeb(*, is_a(-being,+being)).
+%:- modeb(*, is_a(+being,#being)).
+%:- modeb(*, is_a(#being,+being)).
+%:- modeb(*, is_a(-being,#being)).
+%:- modeb(*, is_a(#being,-being)).
+%:- modeb(*, is_a(#being,#being)).
+
+%:- modeb(*, has_p(+being,+being)).
+%:- modeb(*, has_p(+being,-being)).
+%:- modeb(*, has_p(-being,+being)).
+%:- modeb(*, has_p(+being,#being)).
+%:- modeb(*, has_p(#being,+being)).
+%:- modeb(*, has_p(-being,#being)).
+%:- modeb(*, has_p(#being,-being)).
+%:- modeb(*, has_p(#being,#being)).
+
+% Determinations
+:- determination(tracks_down/2, is_/2).
+:- determination(tracks_down/2, has/2).
+%:- determination(tracks_down/2, is_a/2).
+%:- determination(tracks_down/2, has_p/2).
+
+% Aleph settings
+:- set(i, 10).
+:- set(clauselength, 10).
+:- set(minpos, 2).
+:- set(minscore, 0).
+:- set(verbosity, 2).
+:- set(noise, 0).
+:- set(nodes, 180000).
+:- set(rulefile,'Result').
+:- set(record, true).
+:- set(recordfile, 'Record').
+
+% semantic concepts
+is_a(plant,being).
+is_a(animal,being).
+is_a(flower,plant).
+is_a(clover,flower).
+is_a(dandelion,flower).
+is_a(fish,animal).
+is_a(bird,animal).
+is_a(mammal,animal).
+is_a(herbivore,mammal).
+is_a(carnivore,mammal).
+is_a(rabbit,herbivore).
+is_a(fox,carnivore).
+is_a(dog,carnivore).
+is_a(stomach,organ).
+has_p(being,metabolism).
+has_p(animal,stomach).
+has_p(fish,gills).
+has_p(bird,feathers).
+has_p(mammal,fur).
+
+is_a(herb,plant).
+is_a(parsley,herb).
+is_a(rosemary,herb).
+is_a(mouse,herbivore).
+
+% background of examples
+is_a(bobby,rabbit).
+is_a(fluffy,rabbit).
+is_a(tweety,bird).
+is_a(blubbly,fish).
+is_a(bello,dog).
+is_a(samson,dog).
+is_a(argo,dog).
+is_a(bella,fox).
+
+is_a(tipsie,mouse).
+
+% reasoning rules
+is_(A,B) :- is_a(A,B).
+is_(A,B) :- is_a(A,C), is_(C,B).
+
+has(A,X) :- has_p(A,X).
+has(X,Z) :- has_p(X,Y), has(Y,Z).
+
+has(A,X) :- is_(A,B), has(B,X).
+has(A,X) :- has_p(A,Y), is_(Y,X).

1_Model/semanticnet.f

+tracks_down(bobby,dandelion).
+tracks_down(fluffy,clover).
+tracks_down(samson,fluffy).
+tracks_down(bella,bobby).
+tracks_down(bella,tipsie).
+tracks_down(bobby,parsley).
+tracks_down(fluffy,rosemary).
+tracks_down(tipsie,rosemary).

1_Model/semanticnet.n

+tracks_down(argo,argo).
+tracks_down(dandelion,bobby).
+tracks_down(bobby,bobby).
+tracks_down(blubbly,samson).
+tracks_down(fluffy,argo).
+tracks_down(clover,clover).
+tracks_down(tipsie,bella).
+tracks_down(rosemary,tipsie).

2_Tree/ILP_rule_prover.py

+# -*- coding: utf-8 -*-
+"""
+Created on Sat Feb 20 12:26:27 2021
+
+@author: Bettina Finzel
+"""
+
+# Imports
+import os
+from os import path
+import pexpect
+from shutil import *
+import regex as re
+
+data_set = "semanticnet"
+
+target_class = "tracks_down"
+
+# Create a rule file for every rule from the learned model
+
+print(os.getcwd())
+
+tree_path = os.getcwd()
+path_parent = os.path.dirname(tree_path)
+os.chdir(path_parent)
+model_path = os.getcwd() + "/1_Model"
+model_file = model_path + "/Result"
+
+# record the lines of the model file
+count = len(open(model_file).readlines())
+print("The file has " + str(count) + " lines.")
+
+list_of_rules = []
+
+lines = open(model_file).readlines()
+     
+line_index = 0
+while line_index < count:
+    head_check = lines[line_index]
+    if ":-" in head_check:
+        # add the head to the rule
+        concatenated_rule = head_check
+        # skip the head and iterate over lines to check, when the fullstop comes.
+        index = line_index + 1
+        while index < count:
+            if ")." in lines[index]:
+                concatenated_rule = concatenated_rule + lines[index]
+                index = index + 1
+                list_of_rules.append(concatenated_rule)
+                break
+            else:
+                concatenated_rule = concatenated_rule + lines[index]
+                index = index + 1
+        line_index = index
+    # if a rule has no body, add it directly
+    else:
+        rule = lines[line_index]
+        line_index = line_index + 1
+        list_of_rules.append(rule)
+        
+# write the rule files
+file_index = 1
+for rule in list_of_rules:
+    print("Rule: " + rule)
+    rule_file = tree_path + "/Rule" + str(file_index) + ".pl"
+    with open(rule_file, 'w') as outfile:
+        outfile.write(rule)
+    file_index = file_index + 1
+    
+
+# Proof each rule and save the proof
+
+print("RULES: " + str(len(list_of_rules)))
+file_index = len(list_of_rules)
+while file_index > 0:
+
+    proof_files = []
+
+    background = tree_path + "/background_without_settings.pl"
+
+    # rest of the files
+    prover = tree_path + "/prover.pl"
+    rule = tree_path + "/Rule" + str(file_index) + ".pl"
+
+    print("Rule File")
+    print(rule)
+
+    proof_files.append(background)
+    proof_files.append(prover)
+    proof_files.append(rule)
+
+    ### folder for output
+    ##if not os.path.exists("Proves"):
+    ##     os.mkdir("Proves")
+             
+    # create a big proof and proof file
+    proof_writer_input = tree_path + "/proof_writer_input.pl"
+    print(proof_writer_input)
+    with open(proof_writer_input, 'w') as outfile:
+         for file_name in proof_files:
+             with open(file_name) as infile:
+                 outfile.write(infile.read())
+                         
+    selected_examples_pos = []
+    pos_examples = open(model_path + "/" + data_set + ".f", "rt")
+    lines = pos_examples.readlines()
+    print("POS")
+    print(lines)
+    for line in lines:
+         example_predicate = line
+         print(example_predicate)
+         result = re.findall(r"\((.*?)\)", example_predicate)
+         print(result)
+         selected_examples_pos.append(result[0])
+         print(selected_examples_pos)
+         
+    print("NEG")
+    selected_examples_neg = []
+    neg_examples = open(model_path + "/" + data_set + ".n", "rt")
+    lines = neg_examples.readlines()
+    print(lines)
+    for line in lines:
+         example_predicate = line
+         print(example_predicate)
+         result = re.findall(r"\((.*?)\)", example_predicate)
+         print(result)
+