数据读入
()
| 10 | |
| 11 | |
| 12 | def createDataSet(): |
| 13 | ''' 数据读入 ''' |
| 14 | data = [] |
| 15 | labels = [] |
| 16 | with open("input/3.DecisionTree/data.txt") as ifile: |
| 17 | for line in ifile: |
| 18 | # 特征： 身高 体重 label： 胖瘦 |
| 19 | tokens = line.strip().split(' ') |
| 20 | data.append([float(tk) for tk in tokens[:-1]]) |
| 21 | labels.append(tokens[-1]) |
| 22 | # 特征数据 |
| 23 | x = np.array(data) |
| 24 | # label分类的标签数据 |
| 25 | labels = np.array(labels) |
| 26 | # 预估结果的标签数据 |
| 27 | y = np.zeros(labels.shape) |
| 28 | |
| 29 | ''' 标签转换为0/1 ''' |
| 30 | y[labels == 'fat'] = 1 |
| 31 | print data, '-------', x, '-------', labels, '-------', y |
| 32 | return x, y |
| 33 | |
| 34 | |
| 35 | def predict_train(x_train, y_train): |