KNN

# coding:utf-8
import sklearn.datasets
import sklearn.neighbors
import numpy.random
import matplotlib.pyplot
import matplotlib.colors

if __name__ == "__main__":
    # Load iris dataset
    iris = sklearn.datasets.load_iris()

    # Split the dataset with sampleRatio
    sampleRatio = 0.2
    n_samples = len(iris.target)

    sampleBoundary = int(n_samples * sampleRatio)

    # Shuffle the whole data
    shuffleIdx = range(n_samples)
    numpy.random.shuffle(shuffleIdx)

    # Make the training data
    train_features = iris.data[shuffleIdx[:sampleBoundary]]
    train_targets = iris.target[shuffleIdx[:sampleBoundary]]

    # Make the testing data
    test_features = iris.data[shuffleIdx[sampleBoundary:]]
    test_targets = iris.target[shuffleIdx[sampleBoundary:]]

    # Train
    n_neighbors = 5 # 選5個最近鄰

    for weights in ['uniform', 'distance']: # 這個地方採用兩種加權方式
        kNeighborsClassifier = sklearn.neighbors.KNeighborsClassifier(n_neighbors, weights = weights)
        kNeighborsClassifier.fit(train_features, train_targets)

    # Test
    predict_targets = kNeighborsClassifier.predict(test_features)

    # Evaluation
    n_test_samples = len(test_targets)
    X = range(n_test_samples)
    correctNum = 0
    for i in X:
        if(predict_targets[i] == test_targets[i]):
            correctNum += 1
    accuracy = correctNum * 1.0 / n_test_samples
    print("K Neighbors Classifier (Iris) Accuracy [weight = '%s']:%.2f" %(weights, accuracy))

    # Draw
    cmap_bold = matplotlib.colors.ListedColormap(['red', 'blue', 'green'])
    X_test = test_features[:, 2:4]
    X_train = train_features[:, 2:4]
    matplotlib.pyplot.scatter(X_train[:, 0], X_train[:, 1], label = 'train samples', marker='o', c = train_targets, cmap=cmap_bold,)
    matplotlib.pyplot.scatter(X_test[:,0], X_test[:, 1], label = 'test samples', marker='+', c = predict_targets, cmap=cmap_bold)
    legend = matplotlib.pyplot.legend()
    matplotlib.pyplot.title("K Neighbors Classifier (Iris) [weight = %s]" %(weights))
    matplotlib.pyplot.savefig("K Neighbors Classifier (Iris) [weight = %s].png" %(weights), format='png')
    matplotlib.pyplot.show()