weka_classifiers.py 8.71 KB
Newer Older
1 2 3 4 5 6
#!/usr/bin/python
# -*- coding: utf-8 -*-
#
"""
    Runs collection of machine learning algorithms for data mining tasks available in Weka.
    
7 8
    Hall, Mark, et al, The WEKA data mining software: an update, ACM SIGKDD explorations newsletter, 2009.
    
9 10 11 12
    Name: weka_classifiers.py
    Author: Alessandro dos Santos Ferreira ( santosferreira.alessandro@gmail.com )
"""

13 14
import weka.core.jvm as jvm

15 16 17 18 19 20 21 22 23
from weka.core.converters import Loader as WLoader
from weka.classifiers import Classifier as WClassifier
from weka.classifiers import Evaluation as WEvaluation
from weka.core.classes import Random as WRandom

from collections import OrderedDict

from util.config import Config
from util.file_utils import File
24
from util.utils import TimeUtils
25

26
from weka_alias import WekaAlias
27 28 29
from classifier import Classifier

class WekaClassifiers(Classifier):
30
    """Class for all classifiers available in python-weka-wrapper"""
31 32

    def __init__(self, classname="weka.classifiers.functions.SMO", options='default'):
33 34 35 36 37 38 39 40 41
        """Constructor.
        
        Parameters
        ----------
        classname : string, optional, default = 'weka.classifiers.functions.SMO'
            Classifier initialized as default.
        options : string, optional, default = 'default'
            Classifier options initialized as default. Use the string 'default' to default options.
        """
42 43 44 45
        if not jvm.started:
            jvm.start()

        self.classname = Config("ClassName", classname, str)
46 47
        self.options = Config("Options", options, str)
        
48 49
        self.reset()

50 51
    
    def get_config(self):
52 53 54 55 56 57 58
        """Return configuration of classifier. 
        
        Returns
        -------
        config : OrderedDict
            Current configs of classifier.
        """
59 60 61
        weka_config = OrderedDict()
        
        weka_config["classname"] = self.classname
62 63
        weka_config["classname"].value = weka_config["classname"].value.split('.')[-1]

64 65 66 67 68
        weka_config["options"] = self.options
        
        return weka_config
        
    def set_config(self, configs):
69 70 71 72 73 74 75
        """Update configuration of classifier. 
        
        Parameters
        ----------
        configs : OrderedDict
            New configs of classifier.
        """
76 77
        configs["classname"].value = WekaAlias.get_classifier(configs["classname"].value)
        
78 79 80 81
        self.classname = Config.nvl_config(configs["classname"], self.classname)
        self.options = Config.nvl_config(configs["options"], self.options)

    def get_summary_config(self):
82 83 84 85 86 87 88
        """Return fomatted summary of configuration. 
        
        Returns
        -------
        summary : string
            Formatted string with summary of configuration.
        """
89 90 91
        weka_config = OrderedDict()
        
        weka_config[self.classname.label] = self.classname.value
92
        weka_config[self.options.label] = self.options.value
93 94 95 96 97 98 99 100 101

        summary = ''
        for config in weka_config:
            summary += "%s: %s\n" % (config, str(weka_config[config]))
        
        return summary


    def must_train(self):
102 103 104 105 106 107
        """Return if classifier must be trained. 
        
        Returns
        -------
        True
        """
108 109
        return True

110
    def train(self, dataset, training_data, force = False):
111 112 113 114 115 116 117 118 119 120 121
        """Perform the training of classifier.
        
        Parameters
        ----------
        dataset : string
            Path to image dataset.
        training_data : string
            Name of ARFF training file.
        force : boolean, optional, default = False
            If False don't perform new training if there is trained data.
        """
122 123 124 125 126 127
        if self.data is not None and not force:
            return 
        
        if self.data is not None:
            self.reset()
        
128 129 130 131 132 133 134 135 136 137 138
        loader = WLoader(classname="weka.core.converters.ArffLoader")
        
        training_file = File.make_path(dataset, training_data + ".arff")
        self.data = loader.load_file(training_file)
        self.data.class_is_last()
        
        options = None if self.options.value == 'default' else self.options.value.split()
        self.classifier = WClassifier(classname=self.classname.value, options=options)
        self.classifier.build_classifier(self.data)

    
139
    def classify(self, dataset, test_dir, test_data):
140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
        """Perform the classification. 
        
        Parameters
        ----------
        dataset : string
            Path to image dataset.
        test_dir : string
            Not used.
        test_data : string
            Name of test data file.
            
        Returns
        -------
        summary : list of string
            List of predicted classes for each instance in test data in ordered way.
        """
156 157
        loader = WLoader(classname="weka.core.converters.ArffLoader")
        
158
        test_file = File.make_path(dataset, test_data)
159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177
        predict_data = loader.load_file(test_file)
        predict_data.class_is_last()
        
        #values = str(predict_data.class_attribute)[19:-1].split(',')
        values = [str(predict_data.class_attribute.value(i)) for i in range(0, predict_data.class_attribute.num_values)]
        
        classes = []
        
        for index, inst in enumerate(predict_data):
            #pred = self.classifier.classify_instance(inst)
            prediction = self.classifier.distribution_for_instance(inst)
            #cl = int(values[prediction.argmax()][7:])
            cl = values[prediction.argmax()]
            
            #print 'Classe:', cl
            classes.append(cl)

        return classes

178 179

    def cross_validate(self, detail = True):
180 181 182 183 184 185 186 187 188 189 190 191
        """Perform cross validation using trained data. 
        
        Parameters
        ----------
        detail : boolean, optional, default = True
            If true return a detailed information of cross validation.
            
        Returns
        -------
        info : string
            Info with results of cross validation.
        """
192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222
        start_time = TimeUtils.get_time()
        
        info =  "Scheme:\t%s %s\n" % (str(self.classifier.classname) , " ".join([str(option) for option in self.classifier.options]))
        
        if detail == True:
            info += "Relation:\t%s\n" % (self.data.relationname)
            info += "Instances:\t%d\n" % (self.data.num_instances)
            info += "Attributes:\t%d\n\n" % (self.data.num_attributes)
        
        evl = WEvaluation(self.data)
        evl.crossvalidate_model(self.classifier, self.data, 10, WRandom(1))
        
        if detail == False:
            info += "Correctly Classified Instances: %0.4f%%\n" % (evl.percent_correct)

        info += "Time taken to build model: %0.5f seconds\n\n" % (TimeUtils.get_time() - start_time)
        #info += str(evl.percent_correct) + "\n\n"
        
        if detail == True:
            info += "=== Stratified cross-validation ===\n"
            info += evl.summary() + "\n\n"
            
            info += str(evl.class_details()) + "\n\n"
            
            classes = [str(self.data.class_attribute.value(i)) for i in range(0, self.data.class_attribute.num_values)]
            cm = evl.confusion_matrix
            info += Classifier.confusion_matrix(classes, cm)

        return info


223
    def experimenter(self):
224 225 226 227 228 229 230
        """Perform a test using all classifiers available. 
        
        Returns
        -------
        info : string
            Info with results of experimenter.
        """
231 232 233 234 235
        info = ""
        
        aliases = sorted(WekaAlias.get_aliases())
        for alias in aliases:
            try:
236
                # Ignore very slow classifiers.
237
                if alias == 'KStar' or alias == 'LWL' or alias == 'MultilayerPerceptron':
238 239 240 241 242 243 244 245 246
                    continue 
                    
                start_time = TimeUtils.get_time()
                
                classifier = WClassifier(classname=WekaAlias.get_classifier(alias))
        
                info +=  "Scheme:\t%s %s\n" % (str(classifier.classname) , " ".join([str(option) for option in classifier.options]))
                
                evl = WEvaluation(self.data)
247
                evl.evaluate_train_test_split(classifier, self.data, 66, WRandom(1))
248 249 250 251 252 253 254 255 256 257 258
        
                info += "Correctly Classified Instances: %0.4f%%\n" % (evl.percent_correct)
                info += "Time taken to build model: %0.5f seconds\n\n" % (TimeUtils.get_time() - start_time)

            except Exception as e:
                if str(e) != 'Object does not implement or subclass weka.classifiers.Classifier: __builtin__.NoneType':
                    info += "Exception in %s: %s\n\n" % (WekaAlias.get_aliases()[alias], str(e))
        
        return info
        

259
    def reset(self):
260 261
        """Clean all data of classification. 
        """
262 263
        self.data = None
        self.classifier = None