def __init__(self):
self.savedCategories = None
self._corpus = ""
self._features = []
self._classifierIndex = None
self._mins = {}
self.__featureExtractor = FeatureExtractor()
class Classifier(object):
def __init__(self):
self.savedCategories = None
self._corpus = ""
self._features = []
self._classifierIndex = None
self._mins = {}
self.__featureExtractor = FeatureExtractor()
def _getCorpusShort(self):
return self._corpus[:50] if self._corpus else ""
def _getGroupedCategories(self, categories):
groupedCategories = {}
for category in categories :
if not groupedCategories.get(category.categoryName) :
groupedCategories[category.categoryName] = {}
groupedCategories[category.categoryName][category.yes] = category
return groupedCategories
def setFeatureExtractor(self, featureExtractor):
self.__featureExtractor = featureExtractor
def setMinThreshold(self, categoryName, yes, value):
if not self._mins.get(categoryName) :
self._mins[categoryName] = {}
self._mins[categoryName][yes] = value
def getMinThreshold(self, categoryName, yes):
return self._mins.get(categoryName, {}).get(yes, .6)
'''
Classification of text corpus
'''
def classify(self, corpus):
self._corpus = corpus
self._features = self.__featureExtractor.getFeatures(corpus)
self._classifierIndex = ClassifierIndex(self._features)
# Find the category with the highest probability
logger = logging.getLogger("Classifier.classify")
categories = ClassifierCategory.getAllCategories()
groupedCategories = self._getGroupedCategories(categories)
probableTags = []
try :
probableTags = self._getProbableTags(groupedCategories)
except Exception, ex :
logger.exception("classification failure: " + str(ex))
return probableTags
