sitc/ml1/util_knn.py

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn import neighbors, datasets
import seaborn as sns
from sklearn.neighbors import KNeighborsClassifier

# Taken from http://scikit-learn.org/stable/auto_examples/neighbors/plot_classification.html
def plot_classification_iris():
    """
     Plot knn classification of the iris dataset
    """
    # import some data to play with
    iris = datasets.load_iris()
    
    X = iris.data[:, :2]  # we only take the first two features. We could
                      # avoid this ugly slicing by using a two-dim dataset
    y = iris.target

    h = .02  # step size in the mesh
    n_neighbors = 15

  # Create color maps
    cmap_light = ListedColormap(['orange', 'cyan', 'cornflowerblue'])
    cmap_bold = ['darkorange', 'c', 'darkblue']

    for weights in ['uniform', 'distance']:
        # we create an instance of Neighbours Classifier and fit the data.
        clf = KNeighborsClassifier(n_neighbors, weights=weights)
        clf.fit(X, y)

        # Plot the decision boundary. For that, we will assign a color to each
        # point in the mesh [x_min, x_max]x[y_min, y_max].
        x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
        y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
        xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                             np.arange(y_min, y_max, h))
        Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])

        # Put the result into a color plot
        Z = Z.reshape(xx.shape)
        plt.figure(figsize=(8, 6))
        plt.contourf(xx, yy, Z, cmap=cmap_light)

        # Plot also the training points
        sns.scatterplot(x=X[:, 0], y=X[:, 1], hue=iris.target_names[y],
                        palette=cmap_bold, alpha=1.0, edgecolor="black")
        plt.xlim(xx.min(), xx.max())
        plt.ylim(yy.min(), yy.max())
        plt.title("3-Class classification (k = %i, weights = '%s')"
                  % (n_neighbors, weights))
        plt.xlabel(iris.feature_names[0])
        plt.ylabel(iris.feature_names[1])

plt.show()