Supervised Machine Learning: Regression and Classification / Module 3

Course Q&A Machine Learning Specialization Supervised ML: Regression and Classification
1

Good evening everyone, on coursera I am completing the course “Supervised Machine Learning: Regression and Classification”

In the programming task “C1_W3_Logistic_Regression” this error appears: “Cell #3. Can’t compile the student’s code. Error: OSError(‘data/ex2data1.txt not found.’)”, even though the file does exist.

has this happened to anyone? How could I solve it?

I leave the programming file attached for completeness of information.

Thanks in advance

Gianluca

{mentor edit: file removed}

2

Please do not share your notebook. That’s not allowed by the Code of Conduct.
I’ll edit your message to remove the file.

If a mentor needs to see your notebook, we’ll contact you privately with instructions.

= = = =

What programming environment are you using? The Coursera Labs environment, or something else?

3

It appears that you added a new cell to the notebook.

image
image819×630 29.3 KB

Do not add any cells, or insert any functions. It is not necessary.

The load_data() function is part of the “utils.py” package. It is imported in Cell 1 of the notebook.

image
image914×321 16.7 KB

So you did not need to insert that function separately.

Tips:

  • Every time you open a notebook, you must run all of the cells starting from the top. That’s where the assets are imported, and the workspace is configured.
  • Only add your code to the places that are marked “### START CODE HERE ###”. Do not make any other changes.
  • Do not add, delete, or move any cells within the notebook.
  • Do not rename the notebook. The grader only uses the notebook with the original file name.
4

Thanks for the advice! In fact now I have another problem, during the exercise of the def compute_gradient_test.

Practically this error always comes out in the test:

dj_db at test w and b: -0.5999999999991071
dj_dw at test w and b: [-44.831353617873795, -44.37384124953978]

AssertionError Traceback (most recent call last)
in
8
9 # UNIT TESTS
—> 10 compute_gradient_test(compute_gradient)

in compute_gradient_test(compute_gradient_function)
18
19 # Test assert
—> 20 assert np.isclose(dj_db, expected_dj_db, atol=1e-3), f"dj_db computed {dj_db}, expected {expected_dj_db}"
21 assert np.allclose(dj_dw, expected_dj_dw, atol=1e-3), f"dj_dw computed {dj_dw}, expected {expected_dj_dw}"
22

AssertionError: dj_db computed 0.47194683434663404, expected -0.6666666666666667

Why do you think?

I think it’s the sigmond function, but I don’t see any errors about it.

5

There isn’t much to go wrong in sigmoid(), it’s only one line of code, and you only need to be sure you’re using the function argument in the math, not a constant value.

The most common error in the compute_gradient() function regards how your code uses indentation. That’s how Python defines blocks of code.

6

You’re right! Luckily, the bug was solved!

Thanks a lot for the interesting insights. Sometimes the simplest info is the most powerful :slight_smile:

1 Like
7

Nice work!