def test_trees_classify_lenses(self):
matrix, labels = data.create_contacts_set()
lens_tree = trees.create_tree(matrix, labels)
filename = "save_lens_tree.txt"
trees.save_tree(lens_tree, filename)
self.failUnless(True)
def create_digit_tree():
digits = datasets.load_digits()
d_data = digits.data
d_target = digits.target
labels = [i for i in range(len(d_target))]
data_set = np.append(d_data, np.array([d_target]).T, axis=1).tolist()
tree = trees.create_tree(data_set, labels)
print(tree)
# treePlotter.createPlot(tree)
trees.store_tree(tree, "digit_tree.txt")
def test_create_tree(self):
"""Unittest for create tree.
:return:
"""
data, feat_names = trees.create_dataset()
decision_tree = {
'no surfacing': {
0: 'no',
1: {
'flippers': {
0: 'no',
1: 'yes'
}
}
}
}
self.assertEqual(decision_tree, trees.create_tree(data, feat_names))
data = [[1, 2, 'yes'], [1, 3, 'yes'], [2, 3, 'no']]
feat_names = ['no surfacing', 'flippers']
decision_tree = {'no surfacing': {1: 'yes', 2: 'no'}}
self.assertEqual(decision_tree, trees.create_tree(data, feat_names))
def test_create_tree(self):
data_set, labels = trees.load_simple_data()
my_tree = trees.create_tree(data_set, labels)
res_exp = {
'no surfacing': {
0: 'no',
1: {
'flippers': {
0: 'no',
1: 'yes'
}
}
}
}
self.assertEqual(res_exp, my_tree)
def test_trees_classify(self):
matrix = [[1, 1, 'yes'],
[1, 1, 'yes'],
[1, 0, 'no'],
[0, 1, 'no'],
[0, 1, 'no']]
labels = ['no surfacing', 'flippers']
tree = trees.create_tree(matrix, labels)
prediction = trees.classify([1, 1], tree, labels)
self.failUnless(prediction == 'yes')
prediction = trees.classify([1, 0], tree, labels)
self.failUnless(prediction == 'no')
prediction = trees.classify([0, 1], tree, labels)
self.failUnless(prediction == 'no')
prediction = trees.classify([0, 0], tree, labels)
self.failUnless(prediction == 'no')
#!/usr/bin/env python
import trees as trees
import tree_plotter as tree_plotter
def parse_data(filename):
with open(filename) as f:
lenses = [x.strip().split('\t') for x in f.readlines()]
lense_labels = ['age', 'prescript', 'astigmatic', 'tearRate']
return lenses, lense_labels
if __name__ == '__main__':
lenses, lense_labels = parse_data('../../data/ch3/lenses.txt')
lenses_tree = trees.create_tree(lenses, lense_labels)
tree_plotter.create_plot(lenses_tree)
import trees import tree_plotter my_data, _ = trees.create_dataset() print(trees.cal_shannon_ent(my_data)) my_data[0][-1] = 'maybe' print(trees.cal_shannon_ent(my_data)) my_data, _ = trees.create_dataset() trees.split_dataset(my_data, 0, 1) trees.split_dataset(my_data, 0, 0) trees.choose_best_feature_to_split(my_data) my_data, labels = trees.create_dataset() trees.create_tree(my_data, labels) tree_plotter.create_plot()
fig = fig.clf()
axprops = dict(xticks=[], yticks=[])
create_plot.ax1 = plt.subplot(111, frameon=False, **axprops)
plot_tree.totalW = float(get_tree_leafs(my_tree))
plot_tree.totalD = float(get_tree_depth(my_tree))
plot_tree.xOff = -0.5 / plot_tree.totalW
plot_tree.yOff = 1.0
plot_tree(my_tree, (0.5, 1.0), '')
plt.show()
if __name__ == "__main__":
# from create_data_set import creat_data_set
# data_set, data_tag, labels = creat_data_set()
# tree_node = []
# my_tree = create_tree(data_set, labels, data_tag, tree_node)
# print(my_tree)
# create_plot(my_tree)
# 测试隐形眼镜数据
with open('lenses.txt', 'r') as fr:
lenses = [inst.strip().split('\t') for inst in fr.readlines()]
lense_set, labels = [lense[:-1]
for lense in lenses], [lense[-1] for lense in lenses]
lense_tag = ['age', 'prescript', 'astigmatic', 'tearRate']
tree_node = []
lenses_tree = create_tree(lense_set, labels, lense_tag, tree_node)
create_plot(lenses_tree)
secondDict = myTree[firstStr]
plotTree.yOff = plotTree.yOff - 1.0 / plotTree.totalD
for key in secondDict.keys():
if type(secondDict[key]).__name__ == 'dict':
plotTree(secondDict[key], cntrPt, str(key))
else:
plotTree.xOff = plotTree.xOff + 1.0 / plotTree.totalW
plotNode(secondDict[key], (plotTree.xOff, plotTree.yOff), cntrPt,
leaf_node)
plotMidText((plotTree.xOff, plotTree.yOff), cntrPt, str(key))
plotTree.yOff = plotTree.yOff + 1.0 / plotTree.totalD
def createPlot(inTree):
fig = plt.figure(1, facecolor='white')
fig.clf()
axprops = dict(xticks=[], yticks=[])
createPlot.ax1 = plt.subplot(111, frameon=False, **axprops)
plotTree.totalW = float(get_leaf_num(inTree))
plotTree.totalD = float(get_tree_depth(inTree))
plotTree.xOff = -0.5 / plotTree.totalW
plotTree.yOff = 1.0
plotTree(inTree, (0.5, 1.0), '')
plt.show()
if __name__ == '__main__':
data_set, labels = trees.create_test_data_set()
tree = trees.create_tree(data_set, labels)
createPlot(tree)
def test_tree_traversal(self):
tree = trees.create_tree("html", [("html", "body"), ("html", "head"), ("head", "meta"), ("body", "block"), ("head", "link"), ("block", "div")])
tree_content = trees.bfs_content(tree)
self.assertEqual(tree_content, ["html", "body", "head", "block", "meta", "link", "div"])
def test_glass():
fr = open('lenses.txt')
lenses = [line.strip().split('\t') for line in fr.readlines()]
lense_labels = ['age', 'precript', 'astigmatic', 'tearRate']
lense_tree = trees.create_tree(lenses, lense_labels)
treePlotter.create_plot(lense_tree)
def test_base():
data_set, labels = trees.create_data_set()
my_tree = trees.create_tree(data_set, labels)
trees.store_tree(my_tree, 'classifierStorage.txt')
load_tree = trees.load_tree('classifierStorage.txt')
print load_tree
#!usr/bin/env python
# -*- coding:utf-8 -*-
import tree_plotter
import trees
fr = open('lenses.txt')
lenses = [inst.strip().split('\t') for inst in fr.readlines()]
lensesLabels = ['age', 'prescript', 'astigmatic', 'tearRate']
lensesTree = trees.create_tree(lenses, lensesLabels)
print(lenses)
print(lensesTree)
tree_plotter.create_plot(lensesTree) # 由ID3算法产生的决策树
import trees
if __name__ == '__main__':
lenses_dataset, lenses_labels = trees.get_training_lenses_data(
'./data/lenses.txt')
tree = trees.create_tree(lenses_dataset, lenses_labels)
trees.store_tree(tree, './data/lenses_tree.txt')
Author: [email protected] Date: 2018/03/05 16:53:54 ''' import trees import tree_plotter import random fr = open('car.data') lenses = [line.strip().split(',') for line in fr] labels = ['buying', 'maint', 'doors', 'doors', 'persons', 'safety'] fr.close() random.shuffle(lenses) train = lenses[:1000] test = lenses[1000:] lenses_tree = trees.create_tree(train, labels) #print lenses_tree #tree_plotter.create_plot(lenses_tree) err = 0 total = 0 call = 0 for vec in test: real = vec[-1] test_vec = vec[:-1] ret = trees.classify(lenses_tree, labels, test_vec) total += 1 if ret == '-': continue call += 1 if real != ret:
def test_classify_loaded(self):
with open('lenses.txt') as fr:
lenses = [line.strip().split('\t') for line in fr.readlines()]
lenses_labels = ['age', 'prescript', 'astigmatic', 'tearRate']
lenses_tree = trees.create_tree(lenses, lenses_labels)
tree_plot.create_plot(lenses_tree)