def kNN_model():
# Init kNN's weights
X, Y = [], []
cset = [str(i) for i in range(10)]
for c in cset[:]:
image_paths = glob.glob('./train/{}/*.*'.format(c))
# cells_list = [ path2cells(p) for p in image_paths ]
for p in image_paths:
x = path2cells(p)
X.append(x)
Y.append(int(c))
X = np.array(X)
Y = np.array(Y)
# np.save('X.npy', X)
# np.save('Y.npy', Y)
model = kNNClassifier(1)
model.fit(X, Y)
# %%
# Test kNN model
X_test = []
Y_test = []
for root_dir, sub_dir, files in os.walk('./test'):
for i, f in enumerate(files):
fpath = os.path.join(root_dir, f)
image = cv2.imread(fpath, cv2.IMREAD_GRAYSCALE)
image = 255 -image
cells = calc_cells(image,thresh=10 )
X_test.append(cells)
Y_test.append(int(root_dir[-1].lower()))
X_test = np.array(X_test)
Y_test = np.array(Y_test)
pred = model.predict(X_test)
acc = np.sum( Y_test == pred ) / Y_test.shape[0]
print(f"Accuracy: {acc} on {n_test} images")
# -*- coding: utf-8 -*- """ @Project = KNN @File = main.py @Author = FengQi @Mail = [email protected] @Time = 2019/11/7 10:21 上午 @Software: PyCharm """ from kNN import kNNClassifier import numpy as np raw_data_X = [[3.393533211, 2.331273381], [3.110073483, 1.781539638], [1.343853454, 3.368312451], [3.582294121, 4.679917921], [2.280362211, 2.866990212], [7.423436752, 4.685324231], [5.745231231, 3.532131321], [9.172112222, 2.511113104], [7.927841231, 3.421455345], [7.939831414, 0.791631213]] raw_data_y = [0, 0, 0, 0, 0, 1, 1, 1, 1, 1] # 设置训练组 X_train = np.array(raw_data_X) y_train = np.array(raw_data_y) x = np.array([[8.90933607318, 3.365731514]]) knn_clf = kNNClassifier(k=6) knn_clf.fit(X_train, y_train) X_predict = x.reshape(1, -1) y_predict = knn_clf.predict(X_predict) print(y_predict)
#导入iris数据
iris = datasets.load_iris()
X = iris.data
y = iris.target
standardScaler = StandardScaler()
standardScaler.fit
#将数据集拆分为train、test数据
X_train, X_test, y_train, y_test = train_test_split(X, y, 0.2)
#数据的归一化（训练数据集、测试数据集的归一化）
standardScaler = StandardScaler()
standardScaler.fit(X_train)
X_train = standardScaler.transform(X_train)
X_test = standardScaler.transform(X_test)
print(X_test)
#使用上述数据进行训练和预测
kcf = kNNClassifier(3)
kcf.fit(X_train, y_train)
y_predict = kcf.predict(X_test)
#计算预测准确度
accuracy = accuracy_score(y_test, y_predict)
print('Origin: ', y_test)
print('Predict:', y_predict)
print('Accuracy:', accuracy)
print(kcf.score(X_test, y_test))
def readCommand( argv ):
"Processes the command used to run from the command line."
from optparse import OptionParser
parser = OptionParser(USAGE_STRING)
parser.add_option('-c', '--classifier', help=default('The type of classifier'), choices=['naiveBayes', 'perceptron', 'kNN'], default='naiveBayes')
parser.add_option('-d', '--data', help=default('Dataset to use'), choices=['digits', 'faces'], default='digits')
parser.add_option('-t', '--training', help=default('The size of the training set'), default=100, type="int")
parser.add_option('-w', '--weights', help=default('Whether to print weights'), default=False, action="store_true")
parser.add_option('-k', '--neighbors', help=default("Numbers of neighbors in k-Nearest Neighbors"), type="int", default=3)
parser.add_option('-i', '--iterations', help=default("Maximum iterations to run training"), default=3, type="int")
parser.add_option('-s', '--test', help=default("Amount of test data to use"), default=TEST_SET_SIZE, type="int")
options, otherjunk = parser.parse_args(argv)
if len(otherjunk) != 0: raise Exception('Command line input not understood: ' + str(otherjunk))
args = {}
# Set up variables according to the command line input.
print "Doing classification"
print "--------------------"
print "data:\t\t" + options.data
print "classifier:\t\t" + options.classifier
print "training set size:\t" + str(options.training)
if(options.data=="digits"):
printImage = ImagePrinter(DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT).printImage
featureFunction = basicFeatureExtractorDigit
elif(options.data=="faces"):
printImage = ImagePrinter(FACE_DATUM_WIDTH, FACE_DATUM_HEIGHT).printImage
featureFunction = basicFeatureExtractorFace
else:
print "Unknown dataset", options.data
print USAGE_STRING
sys.exit(2)
if(options.data=="digits"):
legalLabels = range(10)
else:
legalLabels = range(2)
if options.training <= 0:
print "Training set size should be a positive integer (you provided: %d)" % options.training
print USAGE_STRING
sys.exit(2)
if options.neighbors <= 0:
print "Neighbors for kNN should be a positive integer (you provided: %d)" % options.neighbors
print USAGE_STRING
sys.exit(2)
if(options.classifier == "naiveBayes"):
classifier = naiveBayes.NaiveBayesClassifier(legalLabels)
elif(options.classifier == "perceptron"):
classifier = perceptron.PerceptronClassifier(legalLabels,options.iterations)
elif(options.classifier == "kNN"):
classifier = kNN.kNNClassifier(legalLabels,options.neighbors)
else:
print "Unknown classifier:", options.classifier
print USAGE_STRING
sys.exit(2)
args['classifier'] = classifier
args['featureFunction'] = featureFunction
args['printImage'] = printImage
return args, options
print(targets_train)
print("\n\nPreparing classifier...")
classifier = GaussianNB()
print("Training classifier...")
model = classifier.fit(data_train, targets_train)
print(
"\nRunning test --- sending 30% data for testing and predicting targets..."
)
targets_predicted = model.predict(data_test)
print("\nComparing targets tested to the targets trained...")
print("Accuracy Score:")
percent = accuracy_score(targets_test, targets_predicted)
print("{:.0%}".format(percent))
print("\n\nPreparing k-Nearest Neighbors classifier...")
k = int(input("Enter the number of neighbors to check (k):"))
classifier = kNNClassifier(k)
print("Training classifier...")
model = classifier.fit(data_train, targets_train)
print(
"\nRunning test --- sending 30% data for testing and predicting targets..."
)
targets_predicted = model.predict(data_train, targets_train, data_test, k)
print("\nComparing targets tested to the targets trained...")
print("Accuracy Score:")
# percent = accuracy_score(targets_test, targets_predicted)
# print("{:.0%}".format(percent))
print(targets_predicted)