K Nearest Neighbors: Effect of parameters

K Nearest Neighbors-Effect of parameters on output 

 K Nearest Neighbors Analyses technique is tested here to see their accuracy in terms of output.

Python program:

>>> import numpy as np

>>> import matplotlib.pyplot as plt

>>> from matplotlib.colors import ListedColormap

>>> from sklearn import neighbors, datasets

>>> n_neighbors = 24

>>> iris = datasets.load_iris()

>>> x = iris.data[:, :2]

>>> y = iris.target

>>> h = .02

>>> cmap_bold = ListedColormap(['firebrick', 'lime', 'blue'])

>>> cmap_light = ListedColormap(['pink', 'lightgreen', 'paleturquoise'])

//Plotting the analysis//

a) Effect of weights: 
>>> for weights in ['uniform', 'distance']:
...     clf = neighbors.KNeighborsClassifier(n_neighbors, weights=weights)
...     clf.fit(x, y)
...     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()])
...     z = z.reshape(xx.shape)
...     plt.figure()
...     plt.pcolormesh(xx, yy, z, cmap=cmap_light)
...     plt.scatter(x[:, 0], x[:, 1], c=y, cmap=cmap_bold, edgecolor='k', s=24)
...     plt.xlim(xx.min(), xx.max())
...     plt.ylim(yy.min(), yy.max())
...     plt.titles("3-class classification (k = %i, weights ='%s')" %(n_neighbors, weights))


b) Effect of number of neighbors (n_neighbors):
>>> for n_neighbors in [1, 2, 5, 25, 100, 150]:
...     clf = neighbors.KNeighborsClassifier(n_neighbors=n_neighbors)
...     clf.fit(x, y)
...     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()])
...     z = z.reshape(xx.shape)
...     plt.figure()
...     plt.pcolormesh(xx, yy, z, cmap=cmap_light)
...     plt.scatter(x[:, 0], x[:, 1], c=y, cmap=cmap_bold, edgecolor='k', s=24)
...     plt.xlim(xx.min(), xx.max())
...     plt.ylim(yy.min(), yy.max())
...     plt.title("3-class classification (neighbors='%s')" %(n_neighbors))
...

c) Number of jobs (n_jobs):

>>> for n_jobs in [1, 2, 5, 25, 100, 150]:
...     clf = neighbors.KNeighborsClassifier(n_jobs=n_jobs)
...     clf.fit(x, y)
...     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()])
...     z = z.reshape(xx.shape)
...     plt.figure()
...     plt.pcolormesh(xx, yy, z, cmap=cmap_light)
...     plt.scatter(x[:, 0], x[:, 1], c=y, cmap=cmap_bold, edgecolor='k', s=24)
...     plt.xlim(xx.min(), xx.max())
...     plt.ylim(yy.min(), yy.max())
...     plt.title("3-class classification (jobs='%s')" %(n_jobs))
...

d) Effect of leaf size (leaf_size):

>>> for leaf_size in [1, 2, 5, 25, 100, 150]:
...     clf = neighbors.KNeighborsClassifier(leaf_size=leaf_size)
...     clf.fit(x, y)
...     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()])
...     z = z.reshape(xx.shape)
...     plt.figure()
...     plt.pcolormesh(xx, yy, z, cmap=cmap_light)
...     plt.scatter(x[:, 0], x[:, 1], c=y, cmap=cmap_bold, edgecolor='k', s=24)
...     plt.xlim(xx.min(), xx.max())
...     plt.ylim(yy.min(), yy.max())
...     plt.title("3-class classification (leaf_size='%s')" %(leaf_size))
...