Python PassiveAggressiveClassifier.partial_fit方法代码示例

# 需要导入模块: from sklearn.linear_model import PassiveAggressiveClassifier [as 别名]
# 或者: from sklearn.linear_model.PassiveAggressiveClassifier import partial_fit [as 别名]
def test_classifier_partial_fit():
    classes = np.unique(y)
    for data in (X, X_csr):
            clf = PassiveAggressiveClassifier(C=1.0,
                                              fit_intercept=True,
                                              random_state=0)
            for t in range(30):
                clf.partial_fit(data, y, classes)
            score = clf.score(data, y)
            assert_greater(score, 0.79)

# 需要导入模块: from sklearn.linear_model import PassiveAggressiveClassifier [as 别名]
# 或者: from sklearn.linear_model.PassiveAggressiveClassifier import partial_fit [as 别名]
def train_online_model(xtr, ytr, model=None):
    # Train classifier
    t0 = time.time()
    if model is None:
        model = PassiveAggressiveClassifier()
        model.fit(xtr, ytr)
    else:
        model.partial_fit(xtr, ytr)
    print "Training took %.2f seconds" % (time.time()-t0)
    return model

# 需要导入模块: from sklearn.linear_model import PassiveAggressiveClassifier [as 别名]
# 或者: from sklearn.linear_model.PassiveAggressiveClassifier import partial_fit [as 别名]
def test_classifier_partial_fit():
    classes = np.unique(y)
    for data in (X, X_csr):
        for average in (False, True):
            clf = PassiveAggressiveClassifier(
                C=1.0, fit_intercept=True, random_state=0,
                average=average, max_iter=5)
            for t in range(30):
                clf.partial_fit(data, y, classes)
            score = clf.score(data, y)
            assert_greater(score, 0.79)
            if average:
                assert hasattr(clf, 'average_coef_')
                assert hasattr(clf, 'average_intercept_')
                assert hasattr(clf, 'standard_intercept_')
                assert hasattr(clf, 'standard_coef_')

# 需要导入模块: from sklearn.linear_model import PassiveAggressiveClassifier [as 别名]
# 或者: from sklearn.linear_model.PassiveAggressiveClassifier import partial_fit [as 别名]

#.........这里部分代码省略.........
      random = RandomFeatureExtractor()
      lengthBaseline = LenFeatureExtractor()
      fullRST = FullPickledRSTFeatureExtractor(nums)  if newData else FullTextRSTFeatureExtractor(nums)
      limitedRST = LimitedPickledRSTFeatureExtractor(nums)  if newData else LimitedTextRSTFeatureExtractor(nums)
      vectorizer =  FeatureUnion([('extra',limitedRST),('tfid',tfidvec)])

      print 'Fitting random features baseline'
      random.fit(texts)
      print 'Fitting text length baseline'
      lengthBaseline.fit(texts)
      print 'Fitting full RST features'
      fullRST.fit(texts)
      print 'Fitting limited RST features'
      limitedRST.fit(texts)
      print 'Fitting limited RST with tfidvec features'
      vectorizer.fit(texts)
      print 'Fitting tfidvec features'
      tfidvec.fit(texts)

      split = int(0.8*len(ilabels))
      trainData = (texts[:split],ilabels[:split])
      testData = (texts[split:],ilabels[split:])      

      X,y = getAsSciKit(trainData[0],trainData[1],random,encoder,selector)
      learner.fit(X,y)
      X,y = getAsSciKit(trainData[0],trainData[1],random,encoder,selector)
      print 'random features baseline trained on %d instances has accuracy %f'%(len(trainData[0]),learner.score(X,y))

      dummy = DummyClassifier()
      X,y = getAsSciKit(trainData[0],trainData[1],random,encoder,selector)
      dummy.fit(X,y)
      X,y = getAsSciKit(testData[0],testData[1],random,encoder,selector)
      print 'Dummy label distribution baseline trained on %d instances has accuracy %f'%(len(trainData[0]),dummy.score(X,y))

      X,y = getAsSciKit(trainData[0],trainData[1],lengthBaseline,encoder,selector)
      learner.fit(X,y)
      X,y = getAsSciKit(testData[0],testData[1],lengthBaseline,encoder,selector)
      print 'text length baseline trained on %d instances has accuracy %f'%(len(trainData[0]),learner.score(X,y))

      X,y = getAsSciKit(trainData[0],trainData[1],fullRST,encoder,selector)
      learner.fit(X,y)
      X,y = getAsSciKit(testData[0],testData[1],fullRST,encoder,selector)
      print 'Full RST learner trained on %d instances has accuracy %f'%(len(trainData[0]),learner.score(X,y))

      X,y = getAsSciKit(trainData[0],trainData[1],limitedRST,encoder,selector)
      learner.fit(X,y)
      X,y = getAsSciKit(testData[0],testData[1],limitedRST,encoder,selector)
      print 'Limited RST learner trained on %d instances has accuracy %f'%(len(trainData[0]),learner.score(X,y))

      X,y = getAsSciKit(trainData[0],trainData[1],vectorizer,encoder,selector)
      learner.fit(X,y)
      X,y = getAsSciKit(testData[0],testData[1],vectorizer,encoder,selector)
      print 'Limited RST with ngram learner trained on %d instances has accuracy %f'%(len(trainData[0]),learner.score(X,y))

      X,y = getAsSciKit(trainData[0],trainData[1],tfidvec,encoder,selector)
      learner = learner.fit(X,y)
      X,y = getAsSciKit(testData[0],testData[1],tfidvec,encoder,selector)
      print 'ngram learner trained on %d instances has accuracy %f'%(len(trainData[0]),learner.score(X,y))


    else:
      vectorizer = tfidvec
      testData = None
      vocabGotten = False
      instances = ([],[])
      numVocab = 50000
      numTest = 50000
      numTrain = 100000
      maxTrainStages = 20
      for text,label in getSciKitData(stateProgress = False, discreteLabels=discreteHelpfulness):
          if label!='few' or useFew:
            instances[0].append(text)
            instances[1].append(label)
            if not vocabGotten and len(instances[0]) == numVocab:
                if printStages:
                    print 'Fitting vocabulary with %d instances'%numVocab
                vectorizer.fit(instances[0],None)
                if selector is not None:
                    X,y = getSciKitInstance(instances[0],instances[1],vectorizer,encoder,None)
                    selector.fit(X,y)
                vocabGotten = True
                instances = ([],[])
            elif vocabGotten and testData is None and len(instances[0]) == numTest:
                if printStages:
                    print 'Getting test data with %d instances'%numTest
                testData = getSciKitInstance(instances[0],instances[1],vectorizer,encoder,selector)
                instances = ([],[])
            elif vocabGotten and testData is not None and len(instances[0]) == numTrain:
                X,y = getSciKitInstance(instances[0],instances[1],vectorizer,encoder,selector)
                if discreteHelpfulness:
                    learner = learner.partial_fit(X,y, classes = classlabels)
                else:
                    learner = learner.partial_fit(X,y)
                instances = ([],[])
                count = count + 1
                if printStages:
                    print 'Baseline trained on %d instances has accuracy %f'%(count*numTrain,learner.score(testData[0],testData[1]))
            elif count == maxTrainStages:
                break
      print 'Final learner trained on %d instances has accuracy %f'%(maxTrainStages*numTrain,learner.score(testData[0],testData[1]))