def handwritingClassTest(train_X, train_y, test_X, test_y):
clf = knn.KNNClassifier(k=3)
len_test = len(test_y)
error_count = 0.0
results = clf.classify(test_X, train_X, train_y)
arr_res = np.array(results) - np.array(test_y)
for elem in arr_res:
error_count += np.abs(elem)
error_rate = error_count / len_test
print error_rate
return error_rate
def __init__(self, norm_type="Normalization", iterations=5, base_classifier="SVM"):
self.iterations = iterations
self.norm_type = norm_type
self.prediction = None
self.probability = None
self.classifier_set = None
if base_classifier == "SVM":
self.base_classifier = SVM.SVMClassifier()
elif base_classifier == "KNN":
self.base_classifier = KNN.KNNClassifier()
elif base_classifier == "DecisionTree":
self.base_classifier = DecisionTree.DecisionTreeClassifier()
elif base_classifier == "Logistic":
self.base_classifier = Logistic.LogisticRegressionClassifier()
elif base_classifier == "Perceptron":
self.base_classifier = Perceptron.PerceptronClassifier()
[float(param1),
float(param2),
float(param3),
float(param4)])
xTest = np.vstack([xTest, newRow])
newTrue = np.array([classification])
trues = np.vstack([trues, newTrue])
count = count + 1
k = int(sys.argv[1])
timingFile = open(r"KNN/KNNTiming.txt", "a")
# Call our python KNN implementation and time classification
ourClass = KNN.KNNClassifier(xTrain, yTrain, k)
ourStart = time.time()
ourPred = ourClass.classify(xTest)
ourEnd = time.time()
ourTime = (ourEnd - ourStart) * 1000000
# Call the scikit KNN implementation and time classification
scikitImp = neighbors.KNeighborsClassifier(k)
sciStart = time.time()
scikitImp.fit(xTrain, yTrain)