ML之回归预测：利用十类机器学习算法(线性回归、kNN、SVM、决策树、随机森林、极端随机树、SGD、提升树、LightGBM、XGBoost)对波士顿数据集回归预测(模型评估、推理并导到csv)

2022-07-23 959

版权

本文内容由阿里云实名注册用户自发贡献，版权归原作者所有，阿里云开发者社区不拥有其著作权，亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容，填写侵权投诉表单进行举报，一经查实，本社区将立刻删除涉嫌侵权内容。

简介： ML之回归预测：利用十类机器学习算法(线性回归、kNN、SVM、决策树、随机森林、极端随机树、SGD、提升树、LightGBM、XGBoost)对波士顿数据集回归预测(模型评估、推理并导到csv)

利用十类机器学习算法(线性回归、kNN、SVM、决策树、随机森林、极端随机树、SGD、提升树、LightGBM、XGBoost)对波士顿数据集【13+1,506】回归预测(模型评估、推理并导到csv)

利用十类机器学习算法(线性回归、kNN、SVM、决策树、随机森林、极端随机树、SGD、提升树、LightGBM、XGBoost)对波士顿数据集【13+1,506】回归预测(模型评估、推理并导到csv)

输出数据集

1. 数据集的描述:  
2.  .. _boston_dataset:
3. 
4. Boston house prices dataset
5. ---------------------------
6. 
7. **Data Set Characteristics:**  
8. 
9.     :Number of Instances: 506
10. 
11.     :Number of Attributes: 13 numeric/categorical predictive. Median Value (attribute 14) is usually the target.
12. 
13.     :Attribute Information (in order):
14.         - CRIM     per capita crime rate by town
15.         - ZN       proportion of residential land zoned for lots over 25,000 sq.ft.
16.         - INDUS    proportion of non-retail business acres per town
17.         - CHAS     Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)
18.         - NOX      nitric oxides concentration (parts per 10 million)
19.         - RM       average number of rooms per dwelling
20.         - AGE      proportion of owner-occupied units built prior to 1940
21.         - DIS      weighted distances to five Boston employment centres
22.         - RAD      index of accessibility to radial highways
23.         - TAX      full-value property-tax rate per $10,000
24.         - PTRATIO  pupil-teacher ratio by town
25.         - B        1000(Bk - 0.63)^2 where Bk is the proportion of blacks by town
26.         - LSTAT    % lower status of the population
27.         - MEDV     Median value of owner-occupied homes in $1000's
28. 
29.     :Missing Attribute Values: None
30. 
31.     :Creator: Harrison, D. and Rubinfeld, D.L.
32. 
33. This is a copy of UCI ML housing dataset.
34. https://archive.ics.uci.edu/ml/machine-learning-databases/housing/
35. 
36. 
37. This dataset was taken from the StatLib library which is maintained at Carnegie Mellon University.
38. 
39. The Boston house-price data of Harrison, D. and Rubinfeld, D.L. 'Hedonic
40. prices and the demand for clean air', J. Environ. Economics & Management,
41. vol.5, 81-102, 1978.   Used in Belsley, Kuh & Welsch, 'Regression diagnostics
42. ...', Wiley, 1980.   N.B. Various transformations are used in the table on
43. pages 244-261 of the latter.
44. 
45. The Boston house-price data has been used in many machine learning papers that address regression
46. problems.   
47.      
48. .. topic:: References
49. 
50.    - Belsley, Kuh & Welsch, 'Regression diagnostics: Identifying Influential Data and Sources of Collinearity', Wiley, 1980. 244-261.
51.    - Quinlan,R. (1993). Combining Instance-Based and Model-Based Learning. In Proceedings on the Tenth International Conference of Machine Learning, 236-243, University of Massachusetts, Amherst. Morgan Kaufmann.
52. 
53. 数据的初步查验：输出回归目标值target的差异
54. target_max 50.0
55. target_min 5.0
56. target_avg 22.532806324110677

1、LiR 线性回归算法

1. LiR Score value: 0.6757955014529482
2. LiR R2    value: 0.6757955014529482
3. LiR MAE   value: 3.5325325437053974
4. LiR MSE   value: 25.13923652035344