[pysterior] Python Machine Learning Library

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

pysterior

pysterior is a machine learning library for Python which aims to make Bayesian parametric regression and classification models accessible and easy to use. The library allows users to construct supervised learning models using an intuitive interface similar to that used by scikit-learn.

More documentation is to come - this is still a very new project.

Under the hood, pysterior uses the implementation of the No-U-Turn Sampler (Hoffman and Gelman, 2011) provided by the thoroughly wonderful pymc3. Pymc3 is a requirement to run pysterior; see the pymc3 page to find out how to get the latest version.

Download pysterior on PyPI: https://pypi.python.org/pypi/pysterior

You can install the latest version of this package from PyPI, where it is currently in alpha. The following models are currently supported:

• regression module:
  • (Bayesian) Linear Regression
  • Ridge Regression
  • Lasso Regression
  • Robust Linear regression (Cauchy-distributed noise)
  • Polynomial regression
    
• classification module:
  • Binary Logistic regression
    
  
  

Coming soon:

• k-class Logistic regression
• More non-linear models
  

本帖隐藏的内容

https://github.com/lmc2179/pysterior

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏1 回帖

关键词：Learning earning Library machine python

1. import numpy as np
   
2. from pysterior import regression
   
3. %matplotlib inline
   
4. from matplotlib import pyplot as plt
   
5. import warnings
   
6. warnings.filterwarnings("ignore")
   
7. In [7]:
   
8. TRUE_ALPHA, TRUE_SIGMA = 1, 1
   
9. TRUE_BETA = 2.5
   
10. size = 100
    
11. X = np.linspace(0, 1, size)
    
12. noise = (np.random.randn(size)*TRUE_SIGMA)
    
13. y = (TRUE_ALPHA + TRUE_BETA*X + noise)
    
14. 
    
15. lr = regression.LinearRegression()
    
16. lr.fit(X, y, 5000)
    
17. plt.plot(X, y, linewidth=0.0, marker='x', color='g')
    
18. pred_post_points = [lr.get_predictive_posterior_samples(x) for x in X]
    
19. transpose = list(zip(*pred_post_points))
    
20. for y_values in transpose:
    
21.     plt.plot(X, y_values, color='r')
    
22. predicted_line = lr.predict(X)
    
23. plt.plot(X, predicted_line)
    
24. plt.show()

复制代码

谢谢楼主分享！

Highest Posterior Density Estimation

1. import numpy as np
   
2. from pysterior import regression
   
3. %matplotlib inline
   
4. from matplotlib import pyplot as plt
   
5. import warnings
   
6. warnings.filterwarnings("ignore")
   
7. In [3]:
   
8. TRUE_ALPHA, TRUE_SIGMA = 1, 1.0
   
9. TRUE_BETA1 = 2.5
   
10. TRUE_BETA2 = 6.5
    
11. TRUE_BETA3 = 2.5
    
12. TRUE_BETA4 = -10.5
    
13. size = 10
    
14. X = np.linspace(-1.0, 1.0, size)
    
15. noise = (np.random.randn(size)*TRUE_SIGMA)
    
16. y = (TRUE_ALPHA + TRUE_BETA1*X + TRUE_BETA2*X**2 + TRUE_BETA3*X**3  + TRUE_BETA4*X**4 + noise)
    
17. 
    
18. holdout_X = np.array([0.23, 0.78])
    
19. noise = (np.random.randn(len(holdout_X))*TRUE_SIGMA)
    
20. holdout_y = (TRUE_ALPHA + TRUE_BETA1*holdout_X + TRUE_BETA2*holdout_X**2 + TRUE_BETA3*holdout_X**3  + TRUE_BETA4*holdout_X**4 + noise)
    
21. 
    
22. lr = regression.PolynomialRegression(degree=4)
    
23. lr.fit(X, y, 7000)
    
24. 
    
25. for alpha, color in [(0.01, 'y'), (0.05, 'r'), (0.1, 'g'), (0.2, 'b')]:
    
26.     intervals = lr.predict_hpd_interval(X, alpha)
    
27.     lower_bound, upper_bound = zip(*intervals)
    
28.     plt.plot(X, lower_bound, color=color)
    
29.     plt.plot(X, upper_bound, color=color)
    
30. 
    
31. predicted_line = lr.predict(X)
    
32. plt.plot(X, predicted_line)
    
33. plt.plot(X, y, linewidth=0.0, marker='x', color='g')
    
34. plt.plot(holdout_X, holdout_y, linewidth=0.0, marker='x', color='r')
    
35. plt.show()

复制代码

Polynomial Regression

1. import numpy as np
   
2. from pysterior import regression
   
3. %matplotlib inline
   
4. from matplotlib import pyplot as plt
   
5. import warnings
   
6. warnings.filterwarnings("ignore")
   
7. In [5]:
   
8. TRUE_ALPHA, TRUE_SIGMA = 1, 1.0
   
9. TRUE_BETA1 = 2.5
   
10. TRUE_BETA2 = 6.5
    
11. TRUE_BETA3 = 2.5
    
12. TRUE_BETA4 = -10.5
    
13. size = 10
    
14. X = np.linspace(-1.0, 1.0, size)
    
15. noise = (np.random.randn(size)*TRUE_SIGMA)
    
16. y = (TRUE_ALPHA + TRUE_BETA1*X + TRUE_BETA2*X**2 + TRUE_BETA3*X**3  + TRUE_BETA4*X**4 + noise)
    
17. 
    
18. lr = regression.PolynomialRegression(4)
    
19. lr.fit(X, y, 1000)
    
20. pred_post_points = [lr.get_predictive_posterior_samples(x) for x in X]
    
21. transpose = list(zip(*pred_post_points))
    
22. for y_values in transpose:
    
23.     plt.plot(X, y_values, color='r')
    
24. predicted_line = lr.predict(X)
    
25. plt.plot(X, predicted_line)
    
26. plt.plot(X, y, linewidth=0.0, marker='x', color='g')
    
27. plt.show()

复制代码

谢谢分享

hahhhhhh

谢谢你的书！

赞楼主，楼主是好人