Professional Documents
Culture Documents
Classification Problem: Breast Cancer Wisconsin Attribute Information
Classification Problem: Breast Cancer Wisconsin Attribute Information
Attribute Information:
1. Sample code number: id number
2. Clump Thickness: 1 - 10
3. Uniformity of Cell Size: 1 - 10
4. Uniformity of Cell Shape: 1 - 10
5. Marginal Adhesion: 1 - 10
6. Single Epithelial Cell Size: 1 - 10
7. Bare Nuclei: 1 - 10
8. Bland Chromatin: 1 - 10
9. Normal Nucleoli: 1 - 10
10. Mitoses: 1 - 10
11. Class: (2 for benign, 4 for malignant)
1. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Mitoses
Use 500 examples for training
Code
Number of iterations 3000
Parameters
Omega
b
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
2. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Normal Nucleoli
Use 500 examples for training
Code
Number of iterations 3000
Parameters
Omega
b
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
3. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Clump Thickness
Use 500 examples for training
Code
Number of iterations 3000
Parameters
Omega
b
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
4. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Uniformity of cell shape
Use 500 examples for training
Code
Number of iterations 3000
Parameters
Omega
b
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
5. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Marginal Adhesion
Use 500 examples for training
Code
Number of iterations 3000
Parameters
Omega
b
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
6. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Single Epithelial Cell Size
Use 500 examples for training
Code
Number of iterations 3000
Parameters
Omega
b
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
7. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Bare Nuclei
Use 500 examples for training
Code
Number of iterations 3000
Parameters
Omega
b
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
8. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Bland Chromatin
Use 500 examples for training
Code
Number of iterations 3000
Parameters
Omega
B
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
9. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Single Epithelial Cell Size
Use 500 examples for training and 200 for testing
Code
Number of iterations 3000
Parameters
Omega
B
Testing
Percentage of correct results
10. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Bland Chromatin
Use 500 examples for training and 200 for testing
Code
Number of iterations 3000
Parameters
Omega
B
Testing
Percentage of wrong results
11. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Bare Nuclei
Use 500 examples for training and 200 for testing
Code
Number of iterations 3000
Parameters
Omega
B
Testing
Percentage of not defined results (if
0.4 ≤ ^y ≤0.6 then answer is “not defined”
12. Apply logistic regression for classification, use inputs Uniformity of Cell Size and
Uniformity of cell shape
Use 500 examples for training and 200 for testing
Code
Number of iterations 3000
Parameters
Omega
B
Testing
Percentage of not defined results (if
0.35 ≤ ^y ≤ 0.65 then answer is “not defined”
13. Apply linear regression to find dependence of attribute area by FFMC, DMC and DC
Code
Number of iterations 3000
Parameters
Theta
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
14. Apply linear regression to find dependence of attribute area by DC and ISI
Code
Number of iterations 3000
Parameters
Theta
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
15. Apply linear regression to find dependence of attribute area by temp and RH
Code
Number of iterations 3000
Parameters
Theta
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
16. Apply linear regression to find dependence of attribute area by wind and rain
Code
Number of iterations 3000
Parameters
Theta
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
17. Apply linear regression to find dependence of attribute area by RH and wind
Code
Number of iterations 3000
Parameters
Theta
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
18. Apply linear regression to find dependence of attribute area by FFMC, wind and rain
Code
Number of iterations 3000
Parameters
Theta
Value of cost function in the 1st iteration
Value of cost function in the 101st iteration
Value of cost function in the last iteration
19. Apply linear regression to find dependence of attribute area by FFMC, DMC and DC
Use 300 examples for training and 100 for testing
Code
Number of iterations 3000
Parameters
Theta
100
For test examples find ∑ | y−^y|
i=1
20. Apply linear regression to find dependence of attribute area by DC and ISI
Code
Number of iterations 3000
Parameters
Theta
100
For test examples find ∑ | y−^y|
i=1
21. Apply linear regression to find dependence of attribute area by temp and RH
Code
Number of iterations 3000
Parameters
Theta
100
For test examples find ∑ | y−^y|
i=1
22. Apply linear regression to find dependence of attribute area by wind and rain
Code
Number of iterations 3000
Parameters
Theta
100
For test examples find ∑ | y−^y|
i=1
23. Apply linear regression to find dependence of attribute area by RH and wind
Code
Number of iterations 3000
Parameters
Theta
100
For test examples find ∑ | y−^y|
i=1
24. Apply linear regression to find dependence of attribute area by FFMC, wind and rain
Code
Number of iterations 3000
Parameters
Theta
100
For test examples find ∑ | y−^y|
i=1