Requesting help for C2_W4_Decision_Tree_with_Markdown

Course Q&A Machine Learning Specialization Advanced Learning Algorithms
1

Hey guys!,
While working on my assignment, I am facing the following error while running the exercise 4 (get_best_split).

AssertionError Traceback (most recent call last)
in
3
4 # UNIT TESTS
----> 5 get_best_split_test(get_best_split)

~/work/public_tests.py in get_best_split_test(target)
133 y = X[:,0]
134 result = target(X, y, node_indexes)
→ 135 assert result == 0, f"If the target is fully correlated with other feature, that feature must be the best split. Expected 0, got {result}"
136 y = X[:,1]
137 result = target(X, y, node_indexes)

AssertionError: If the target is fully correlated with other feature, that feature must be the best split. Expected 0, got 1

Note: My compute_information_gain worked well, But i am facing an issue in this one. Please help!

2

You are suppose to get 0 but you have got result 1, it means that in the most recent grader cell.

If the target is fully correlated with other feature, that feature must be the best split!!!

# Iterate through all features
    for feature in range(num_features): 
        
        # Your code here to compute the information gain from splitting on this feature
        info_gain = (for this code line you have missed one code, you are adding features)

get_best_split(X, y, node_indices) to this you are adding features which you have not mentioned for the info_gain code
3

I have added features in the info gain code! Still it wont run. Info gain code was tested on multiple features in case 3 and was run successfully

4

node_indexes to node_indices? I know both are same but sometimes grader cells might be particular about these typo mistakes. If you still having the issue. Please share the codes for this cell via DM. Click my name and then msg

5

please let me know if the indentation issue was resolved as per discussion

regards

bye

6

Issue was solved. Thanks a lot !