suraggupta / coursera-machine-learning-solutions-python

A repository with solutions to the assignments on Andrew Ng's machine learning MOOC on Coursera

coursera-machine-learning-solutions-python

A repository with solutions to the assignments on Andrew Ng's machine learning MOOC on Coursera. The credits for template for the python submission goes to @dibgerge[https://github.com/dibgerge]

coursera-machine-learning-solutions-python's Issues

Getting ValueError: Contour levels must be increasing in the optional exercise

Getting ValueError: Contour levels must be increasing un the optional exercise

Can anyone please help

i am using the same code for the regularization code but getting only 66% accuracy instead of 83%,Please help

Which part i am doing wrong?

Typo in err_array

the function dataset3Params on Excercice6 declares an array calls 'my_array' but uses another undeclared one called 'err_array'

`def dataset3Params(X, y, Xval, yval):
C = 1
sigma = 0.3
# ====================== YOUR CODE HERE ======================

C_array = np.array([0.01, 0.03, 0.1, 0.3, 1, 3, 10, 30])
sigma_array = np.array([0.01, 0.03, 0.1, 0.3, 1, 3, 10, 30])

**my_array** = np.zeros([C_array.size, sigma_array.size])

for i in np.arange(C_array.size):
    for j in np.arange(sigma_array.size):
        model= utils.svmTrain(X, y, C_array[i], gaussianKernel, args=(sigma_array[j],))
        predictions = utils.svmPredict(model, Xval)
        pred_error = np.mean(predictions != yval)
        
        **err_array**[i, j] = pred_error
    
ind = np.unravel_index(np.argmin(err_array, axis = None), err_array.shape)
C = C_array[ind[0]]
sigma = sigma_array[ind[1]]

# ============================================================
return C, sigma`

section 2.5 in the notebook - run it don't result with the same result saved there.

The sigmoidGradient function isn't defined

I was writing the nnCostFunction function, but the sigmoidGradient function isn't defined?

NameError Traceback (most recent call last)
in
1 lambda_ = 0
2 J, _ = nnCostFunction(nn_params, input_layer_size, hidden_layer_size,
----> 3 num_labels, X, y, lambda_)
4 print('Cost at parameters (loaded from ex4weights): %.6f ' % J)
5 print('The cost should be about : 0.287629.')

in nnCostFunction(nn_params, input_layer_size, hidden_layer_size, num_labels, X, y, lambda_)
42
43 delta_3 = a3 - y_matrix
---> 44 delta_2 = delta_3.dot(Theta2)[:, 1:] * sigmoidGradient(a1.dot(Theta1.T))
45
46 Delta1 = delta_2.T.dot(a1)

NameError: name 'sigmoidGradient' is not defined