机器学习算法之四：5分钟上手Decision Tree

1.案例：这个数据用身高和体重来界定胖瘦。如下文字档(4.tree.txt)，三个栏位各代表身高(m)、体重(kg)与胖瘦(thin/fat)。

2.问题：现在有一身高1.5m与体重99kg的数据，请问是胖是瘦呢？

3.数据文档：4.tree.txt，内容如下。

1.5 50 thin
1.5 60 fat
1.6 40 thin
1.6 60 fat
1.7 60 thin
1.7 80 fat
1.8 60 thin
1.8 90 fat
1.9 70 thin
1.9 80 fat

4.Sampe code：

# -*- coding: utf-8 -*-
import numpy as np
import scipy as sp
from sklearn import tree
from sklearn.metrics import precision_recall_curve
from sklearn.metrics import classification_report
from sklearn.cross_validation import train_test_split


#''' 数据读入 '''
data = []
labels = []
with open("4.tree.txt") as ifile:
	for line in ifile:
		tokens = line.strip().split(' ')
		data.append([float(tk) for tk in tokens[:-1]])
		labels.append(tokens[-1])
x = np.array(data)
labels = np.array(labels)
y = np.zeros(labels.shape)


#''' 标签转换为0/1 '''
y[labels=='fat']=1

#''' 拆分训练数据与测试数据 '''
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2)

#''' 使用信息熵作为划分标准，对决策树进行训练 '''
clf = tree.DecisionTreeClassifier(criterion='entropy')
print(clf)
clf.fit(x_train, y_train)

#''' 把决策树结构写入文件 '''
with open("1.tree.dot", 'w') as f:
	f = tree.export_graphviz(clf, out_file=f)

#''' 系数反映每个特征的影响力。越大表示该特征在分类中起到的作用越大 '''
print(clf.feature_importances_)

#'''测试结果的打印'''
answer = clf.predict(x_train)
print(x_train)
print(answer)
print(y_train)
print(np.mean( answer == y_train))

#'''准确率与召回率'''
precision, recall, thresholds = precision_recall_curve(y_train, clf.predict(x_train))
answer = clf.predict_proba(x)[:,1]
print(classification_report(y, answer, target_names = ['thin', 'fat']))

#进行预测
print clf.predict([[1.5, 99]])

5.结果：

DecisionTreeClassifier(compute_importances=None, criterion=entropy,
            max_depth=None, max_features=None, min_density=None,
            min_samples_leaf=1, min_samples_split=2, random_state=None,
            splitter=best)
[ 0.34436094  0.65563906]
[[  1.8  90. ]
 [  1.7  80. ]
 [  1.9  70. ]
 [  1.6  60. ]
 [  1.6  40. ]
 [  1.5  50. ]
 [  1.8  60. ]
 [  1.9  80. ]]
[ 1.  1.  0.  1.  0.  0.  0.  1.]
[ 1.  1.  0.  1.  0.  0.  0.  1.]
1.0
                precision    recall  f1-score   support
thin                 1.00      1.00      1.00         5
fat                   1.00      1.00      1.00         5
avg / total       1.00      1.00      1.00        10

[ 1.]