Request edit access
JavaScript isn't enabled in your browser, so this file can't be opened. Enable and reload.
mlcourse.ai
. Assignment #3 (demo)
Decision trees with a toy task and the UCI Adult dataset.
Sign in to Google
to save your progress.
Learn more
* Indicates required question
3.1. What is the entropy S0 of the initial system?
*
1 point
0.966
0.985
0.885
0.764
3.2. Let's split the data with a feature "Looks_handsome". What is the entropy S1 of the left group - the one with "Looks_handsome". What is the entropy S2 in the opposite group? What is information gain (IG) if we consider such a split?
*
2 points
S1 = 0.967
S2 = 0.918
IG = 0.128
S1 = 0.811
S2 = 0.826
IG = 0.178
Required
3.3. What is the entropy of a state given by a list balls_left?
*
2 points
0.961
0.852
0.975
0.991
3.4. What is the entropy of a fair dice? (where we look at a dice as a system with 6 equally probable states)
*
1 point
0
1
2.585
3.125
0.167
3.5. What is the information gain of splitting the initial dataset into balls_left and balls_right?
*
2 points
0.182
0.175
0.161
0.158
3.6. What is the test set accuracy of a decision tree with maximum tree depth of 3 and random_state = 17?
*
1 point
0.895
0.856
0.788
0.845
3.7. What is the test set accuracy of a decision tree with maximum tree depth of 9 and random_state = 17?
*
1 point
0.91
0.859
0.848
0.791
Do you have any remarks concerning the assignment? In case of apparent errors/typos please use GitHub Issues and/or Pull Requests (
https://github.com/Yorko/mlcourse.ai
).
Your answer
Submit
Clear form
Never submit passwords through Google Forms.
This content is neither created nor endorsed by Google. -
Terms of Service
-
Privacy Policy
Does this form look suspicious?
Report
Forms
Help and feedback
Contact form owner
Help Forms improve
Report