training.py 文件源码

def splitValidateModel(self, visualizePredictions = False):
    (label_vector, input_vector) = loadData(self.featureFile)

    indexArray = range(0, len(input_vector))
    trainData, testData, trainLabels, expectedLabels, trainIndices, testIndices = \
      cross_validation.train_test_split(input_vector, label_vector, indexArray, test_size=(1.0 - self.percentSplit))

    kNNClassifier = neighbors.KNeighborsClassifier(self.n_neighbors, weights='distance')
    kNNClassifier.fit(trainData, trainLabels) 
    predictedLabels = kNNClassifier.predict(testData)

    print("Classification report for classifier %s:\n%s\n"
          % ('k-NearestNeighbour', metrics.classification_report(expectedLabels, predictedLabels)))
    print("Confusion matrix:\n%s" % metrics.confusion_matrix(expectedLabels, predictedLabels))
    print('Split Validation training :: Done.\n')

    if visualizePredictions:
      self.__visualizePredictedDataset__(input_vector, testIndices, predictedLabels, expectedLabels)