Bagging Classifier: Effect of parameters

Bagging Classifier

Bagging Classifier 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 ensemble, datasets
>>> iris = datasets.load_iris()
>>> x = iris.data[:, :2]
>>> y = iris.target
>>> h = .02
>>> cmap_bold = ListedColormap(['firebrick', 'lawngreen', 'b'])
>>> cmap_light = ListedColormap(['pink', 'palegreen', 'lightcyan'])


//Plotting the analysis//

a) Effect of maximum samples (max_samples):

>>> for max_samples in [2, 5, 10, 25, 50, 100, 125]:

...     clf = ensemble.BaggingClassifier(max_samples=max_samples)

...     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("Bagging Classifier (max_samples='%s')" %(max_samples))

...

Increase in maximum samples value (max_samples) result in increased output accuracy.

b) Effect of number of jobs (n_jobs):

>>> for n_jobs in [150, 250, 500, 2500, 5000, 10000, 13500]:

...     clf = ensemble.BaggingClassifier(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("Bagging Classifier (n_jobs='%s')" %(n_jobs))

...

Increased number of jobs result in decreased output accuracy.

c) Effect of random state (random_state):

>>> for random_state in [250,500, 1250, 3500, 5700, 12500]:

...     clf = ensemble.BaggingClassifier(random_state=random_state)

...     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("Bagging Classifier (random_state='%s')" %(random_state))

...

Increased number of estimators result in decreased output accuracy.

d) Effect of number of estimators (n_estimators):

>>> for n_estimators in [1, 2, 5, 25, 50, 100, 150, 250, 500, 1250]:

...     clf = ensemble.BaggingClassifier(n_estimators=n_estimators)

...     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("Bagging Classifier (n_estimators='%s')" %(n_estimators))

...

Increased number of estimators result in improved output accuracy.