Decision Tree Classifier-Effect of parameters

Decision Tree Classifier-Effect of parameters on output 

Decision Tree 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 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) Maximum leaf nodes (max_leaf_nodes):

>>> for max_leaf_nodes in [2, 10, 50, 100]:
...         clf = tree.DecisionTreeClassifier(max_leaf_nodes=max_leaf_nodes)
...         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("DecisionTreeClassifier (max_leaf_nodes='%s')" %(max_leaf_nodes))
...

b) Maximum depth (max_depth):

>>> for max_depth in [2, 10, 50, 100, 500]:
...         clf = tree.DecisionTreeClassifier(max_depth=max_depth)
...         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("DecisionTreeClassifier (max_depth='%s')" %(max_depth))
...

c) Maximum features (max_features):

>>> for max_features in [1, 2, None]:
...         clf = tree.DecisionTreeClassifier(max_features=max_features)
...         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("DecisionTreeClassifier (max_features='%s')" %(max_features))
...

d) Minimum samples split(min_samples_split):

>>> for min_samples_split in [2, 10, 100, 500]:
...         clf = tree.DecisionTreeClassifier(min_samples_split=min_samples_split)
...         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("DecisionTreeClassifier (min_samples_split='%s')" %(min_samples_split))
...

e)Minimum weight fraction per leaf(min_weight_fraction_leaf):

>>> for min_weight_fraction_leaf in [0.001, 0.005, 0.01, 0.05, 0.1, 0.2, 0.4, 0.5]:
...         clf = tree.DecisionTreeClassifier(min_weight_fraction_leaf=min_weight_fraction_leaf)
...         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("DecisionTreeClassifier (min_weight_fraction_leaf='%s')" %(min_weight_fraction_leaf))
...