logistic_regression

logistic_regression 说白了就是个binary classifier.遵从伯努利分布

代码如下:

点击(此处)折叠或打开

1. # coding: utf-8
   
2. 
   
3. import seaborn as sns
   
4. import matplotlib.pyplot as plt
   
5. import pandas as pd
   
6. import numpy as np
   
7. 
   
8. raw_data=pd.read_csv('data-analysis/python-jupyter/2.01. Admittance.csv')
   
9. 
   
10. type(raw_data)
    
11. print(raw_data.columns)
    
12. 
    
13. 
    
14. data=raw_data.copy()
    
15. data['Admitted']=raw_data['Admitted'].map({'Yes':1, 'No':0})
    
16. 
    
17. X1=data['SAT']
    
18. y=data['Admitted']
    
19. print('X shape: {},y shape: {}'.format(X1.shape, y.shape))
    
20. 
    
21. #plot
    
22. plt.scatter(X1, y, color='c0')
    
23. plt.xlabel('SAT', fontsize=20)
    
24. plt.ylabel('Admitted', fontsize=20)
    
25. plt.show()
    
26. 
    
27. 
    
28. import statsmodels.api as sm
    
29. import statsmodels.formula.api as smf
    
30. 
    
31. x=sm.add_constant(X1)
    
32. reg_log=sm.Logit(y, x)
    
33. results_log = reg_log.fit()
    
34. from scipy import stats
    
35. 
    
36. print(results_log.summary())
    
37. print()
    
38. 
    
39. from sklearn.linear_model import LogisticRegression
    
40. #Scikit-Learn LogisticRegression
    
41. reg=LogisticRegression(solver='lbfgs')
    
42. #reshape X
    
43. x_matrix = X1.values.reshape(168, 1)
    
44. reg.fit(x_matrix, y)
    
45. 
    
46. #cm_df: confustion matrix
    
47. cm_df=pd.DataFrame(results_log.pred_table())
    
48. cm_df.columns=['Predicted 0', 'Predicted 1']
    
49. cm_df = cm_df.rename(index={0:'Acutal 0', 1:'Actual 1'})
    
50. 
    
51. #print the confusion-matrix
    
52. print(cm_df)
    
53. 
    
54. #calculate the accuracy
    
55. cm = np.array(cm_df)
    
56. accuracy_train = (cm[0,0] + cm[1,1]) / cm.sum()
    
57. print('accuracy: {}'.format(accuracy_train))