43 lines
1.2 KiB
Markdown
43 lines
1.2 KiB
Markdown
## Modeling/predicting techniques per class:
|
|
2. Decision Trees
|
|
3.
|
|
4. Linear Regression + Logistical Regression (numerical data)
|
|
5.
|
|
6. Support Vector Machine (categorical data)
|
|
7. K-means clustering and K-medoids clustering (numerical data)
|
|
|
|
|
|
|
|
|
|
|
|
| testsize | 0.8 | 0.7 | 0.6 | 0.5 | 0.4 | 0.3 | 0.2 | 0.1 | 0.05 | 0.025| 0.01|
|
|
| -------- | ----- | ----- | ----- | ----- | ----- | ----- | --- | ----- | --| --|
|
|
| score | 0.255 | 0.308 | 0.357 | 0.410 | 0.459 | 0.515 | 0.556 | 0.621| 0.658 | 0.677 | 0.692
|
|
| | | | | | | | | |
|
|
|
|
Exemple:
|
|
|
|
| | acc | prec | rec | f1 |
|
|
| ---- | ---- | ---- | ---- | ---- |
|
|
| non | 0.65 | 0.7 | 0.72 | 0.71 |
|
|
| grid | 0.69 | 0.73 | 0.77 | 0.75 |
|
|
| rand | 0.64 | 0.69 | 0.71 | 0.70 |
|
|
| | | | | |
|
|
|
|
|
|
Classifier (test size= 0.6):
|
|
| | acc | prec | rec | f1 |
|
|
| ---- | ---- | ---- | ---- | ---- |
|
|
| non | 0.3614 | 0.3614 | 0.3614 | 0.3614 |
|
|
| grid | 0.69 | 0.73 | 0.77 | 0.75 |
|
|
| rand | 0.64 | 0.69 | 0.71 | 0.70 |
|
|
| | | | | |
|
|
|
|
|
|
Regressor (test size= 0.6):
|
|
| | mse | mae |
|
|
| --- | ----- | ---- |
|
|
| non | 50.41 | 3.78 |
|
|
| | | |
|
|
| rand | 36.02 | 3.86 |
|
|
|