diff options
Diffstat (limited to 'abml')
| -rw-r--r-- | abml/evaluate.py | 22 | ||||
| -rw-r--r-- | abml/learn_dist.py | 11 | ||||
| -rw-r--r-- | abml/rules_prolog.py | 14 |
3 files changed, 24 insertions, 23 deletions
diff --git a/abml/evaluate.py b/abml/evaluate.py index 2e318fb..cb959ed 100644 --- a/abml/evaluate.py +++ b/abml/evaluate.py @@ -1,4 +1,4 @@ -import pickle +import os.path import argparse import Orange from Orange.evaluation import TestOnTestData, CA, AUC, LogLoss @@ -8,30 +8,28 @@ import orangecontrib.evcrules.logistic as logistic import orangecontrib.abml.abrules as rules import orangecontrib.abml.argumentation as arg -parser = argparse.ArgumentParser(description='Learn and test rules for prolog programs.') -parser.add_argument('Name', type=str, help='Predicate name.') +parser = argparse.ArgumentParser(description='Learn and evaluate rules for Prolog programs.') +parser.add_argument('path', help='path to data directory') args = parser.parse_args() -name = args.Name +path = args.path # load data -data = Orange.data.Table('data/{}/programs-train'.format(name)) +data = Orange.data.Table(os.path.join(path, 'programs-train')) # create learner -rule_learner = rp.Rules4Prolog(name, 0.9) - - +rule_learner = rp.Rules4Prolog(path, 0.9) # learn a classifier classifier = rule_learner(data) # save model -fmodel = open("data/{}/model.txt".format(name), "wt") +fmodel = open(os.path.join(path, 'model.txt'), "wt") for r in classifier.rule_list: print(r, r.curr_class_dist, r.quality) fmodel.write("{} dist={} quality={}\n".format(str(r), str(r.curr_class_dist), r.quality)) # accuracy of model -testdata = Orange.data.Table('data/{}/programs-test'.format(name)) +testdata = Orange.data.Table(os.path.join(path, 'programs-test')) predictions = classifier(testdata) acc = 0 for i, p in enumerate(predictions): @@ -64,12 +62,12 @@ scores += "CA\tAUC\tLogLoss\tMethod\n" for ni, n in enumerate(names): scores += "{}\t{}\t{}\t{}\n".format(ca[ni], auc[ni], ll[ni], n) print(scores) -fscores = open("data/{}/scores.txt".format(name), "wt") +fscores = open(os.path.join(path, 'scores.txt'), 'wt') fscores.write(scores) all_rules = classifier.rule_list all_rules.sort(key = lambda r: r.quality, reverse=True) -rfile = open("data/{}/rules.txt".format(name), "wt") +rfile = open(os.path.join(path, 'rules.txt'), 'wt') for r in all_rules: print(r, r.curr_class_dist, r.quality) rfile.write("{} {} {}\n".format(r, r.curr_class_dist, r.quality)) diff --git a/abml/learn_dist.py b/abml/learn_dist.py index 58e4968..44e19c3 100644 --- a/abml/learn_dist.py +++ b/abml/learn_dist.py @@ -1,15 +1,16 @@ +import os.path import pickle import argparse from Orange.data import Table import abml.rules_prolog as rp parser = argparse.ArgumentParser(description='Learn and test rules for prolog programs.') -parser.add_argument('Name', type=str, help='Predicate name.') +parser.add_argument('path', help='path to data directory') args = parser.parse_args() -name = args.Name +path = args.path -data = Table('data/{}/programs-train'.format(name)) +data = Table(os.path.join(path, 'programs-train')) -rule_learner = rp.create_learner(name, evds=False) +rule_learner = rp.create_learner(path, evds=False) rule_learner.calculate_evds(data) -pickle.dump(rule_learner.evds, open("data/{}/evds.pickle".format(name), "wb")) +pickle.dump(rule_learner.evds, open(os.path.join(path, 'evds.pickle'), "wb")) diff --git a/abml/rules_prolog.py b/abml/rules_prolog.py index 9edd674..f67ba93 100644 --- a/abml/rules_prolog.py +++ b/abml/rules_prolog.py @@ -1,6 +1,8 @@ -import numpy as np -import pickle import itertools +import os.path +import pickle + +import numpy as np from Orange.classification.rules import _RuleClassifier, GuardianValidator import orangecontrib.abml.abrules as rules from Orange.classification.rules import Rule @@ -92,14 +94,14 @@ class NegativeFirstClassifier(_RuleClassifier): return probabilities class Rules4Prolog: - def __init__(self, name, threshold): + def __init__(self, path, threshold): self.threshold = threshold self.learner = rules.ABRuleLearner(width=50, parent_alpha=0.05) self.learner.rule_finder.general_validator = TrueCondValidator(self.learner.rule_finder.general_validator.max_rule_length, self.learner.rule_finder.general_validator.min_covered_examples) self.learner.rule_validator = PureAccuracyValidator(0, self.threshold) self.learner.classifier = NegativeFirstClassifier - self.learner.evds = pickle.load(open("data/{}/evds.pickle".format(name), "rb")) + self.learner.evds = pickle.load(open(os.path.join(path, 'evds.pickle'), 'rb')) def __call__(self, data): # first learn rules for negative class (quality should be higher than @@ -161,13 +163,13 @@ class Rules4Prolog: -def create_learner(name, evds=True): +def create_learner(path, evds=True): rule_learner = rules.ABRuleLearner(width=50, parent_alpha=0.05) rule_learner.rule_finder.general_validator = TrueCondValidator(rule_learner.rule_finder.general_validator.max_rule_length, rule_learner.rule_finder.general_validator.min_covered_examples) rule_learner.rule_validator = PureAccuracyValidator(0, 0.8) rule_learner.classifier = NegativeFirstClassifier if evds: - rule_learner.evds = pickle.load(open("data/{}/evds.pickle".format(name), "rb")) + rule_learner.evds = pickle.load(open(os.path.join(path, 'evds.pickle'), 'rb')) return rule_learner |