Error in code running

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

Continuing the discussion from Compute_gradient_test(compute_gradient):

{Moderator Edit: Solution Code Removed}

Compute and display cost and gradient with non-zero w and b

test_w = np.array([ 0.2, -0.5])
test_b = -24
dj_db, dj_dw = compute_gradient(X_train, y_train, test_w, test_b)

print(‘dj_db at test w and b:’, dj_db)
print(‘dj_dw at test w and b:’, dj_dw.tolist())

UNIT TESTS

compute_gradient_test(compute_gradient)

and I am getting this error :
dj_db at test w and b: -0.5999999999991071
dj_dw at test w and b: [-44.831353617873795, -44.37384124953978]

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

~/work/public_tests.py in compute_gradient_test(target)
49 test_w = np.array([1, 0.5, -0.35])
50 test_b = 1.7
—> 51 dj_db, dj_dw = target(X, y, test_w, test_b)
52
53 assert np.isclose(dj_db, 0.28936094), f"Wrong value for dj_db. Expected: {0.28936094} got: {dj_db}"

in compute_gradient(X_train, y_train, test_w, test_b, *argv)
25 test_b = -24
26 for i in range(m):
—> 27 z = np.dot(X_train[i],test_w) + test_b
28 f_wb_i = sigmoid(z)
29 err_i = f_wb_i - y_train[i]

<array_function internals> in dot(*args, **kwargs)

ValueError: shapes (3,) and (2,) not aligned: 3 (dim 0) != 2 (dim 0)

2

You don’t need to initialize the test_w = np.array([ 0.2, -0.5]) and
test_b = -24 inside the compute_gradient function. They are the arguments of the function and use it as it is. Don’t assign any value to it.

PS: Sharing your code is not allowed. Next time, only share your error.

3

My gradient descent value is coming out 0.22 where as expected is 0.30 and resultant plot is also way different from the expected one

4

You are also missing one more thing. After defining the dj_db = ... inside the loop, you also need to dj_db += None. Replace the None with the correct term. Feel free to check the hint.

5

but current code without that + factor gives correct value of dj_db. now the problem is in the next section where I am running code for gradient descent.

6

what this error means:

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

~/work/public_tests.py in compute_gradient_test(target)
49 test_w = np.array([1, 0.5, -0.35])
50 test_b = 1.7
—> 51 dj_db, dj_dw = target(X, y, test_w, test_b)
52
53 assert np.isclose(dj_db, 0.28936094), f"Wrong value for dj_db. Expected: {0.28936094} got: {dj_db}"

in compute_gradient(X_train, y_train, test_w, test_b, *argv)
27 err_i = f_wb_i - y_train[i]
28 for j in range(n):
—> 29 dj_dw[j] = dj_dw[j] + err_i * X_train[i,j] #scalar
30 dj_db = dj_db + err_i
31 dj_dw = dj_dw/m #(n,)

IndexError: index 2 is out of bounds for axis 0 with size 2

8

You also need to dj_dw[j]+= None. Replace the None with the correct term.