C1 W3 predict - UnboundLocalError: local variable ‘cost’ referenced before assignment

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

Hello, can someone help me to figure out what is wrong in below as i am trying to solve Excercise-4 Prediction but getting erros;

UNQ_C4

GRADED FUNCTION: predict

def predict(X, w, b):
“”"
Predict whether the label is 0 or 1 using learned logistic
regression parameters w

Args:
  X : (ndarray Shape (m,n)) data, m examples by n features
  w : (ndarray Shape (n,))  values of parameters of the model      
  b : (scalar)              value of bias parameter of the model

Returns:
  p : (ndarray (m,)) The predictions for X using a threshold at 0.5
"""
# number of training examples
m, n = X.shape   
p = np.zeros(m)


 # Loop over each example
    
        
for i in range(m):
    z_i = np.dot(X[i],w) + b
    f_wb_i = sigmoid(z_i)
    cost +=  -y[i]*np.log(f_wb_i) - (1-y[i])*np.log(1-f_wb_i)
         
cost = cost / m
return cost
p[i] = f_wb >= 0.5

return p

following is the error i am getting

UnboundLocalError Traceback (most recent call last)
in
5 tmp_X = np.random.randn(4, 2) - 0.5
6
----> 7 tmp_p = predict(tmp_X, tmp_w, tmp_b)
8 print(f’Output of predict: shape {tmp_p.shape}, value {tmp_p}')
9

in predict(X, w, b)
26 z_i = np.dot(X[i],w) + b
27 f_wb_i = sigmoid(z_i)
—> 28 cost += -y[i]*np.log(f_wb_i) - (1-y[i])*np.log(1-f_wb_i)
29
30 cost = cost / m

UnboundLocalError: local variable ‘cost’ referenced before assignment

2

Hello @Sultan_Mubashir you don’t need to calculate cost in this exercise, you just have to return p. So remove the lines (28, 30) in which you are calculating costs.

SideNote: The error is due to the line cost += …, because it is viewed as cost = cost + …, as no cost is declared earlier so you are getting error.

3

But now getting the below error.

Test your predict code

np.random.seed(1)
tmp_w = np.random.randn(2)
tmp_b = 0.3
tmp_X = np.random.randn(4, 2) - 0.5

tmp_p = predict(tmp_X, tmp_w, tmp_b)
print(f’Output of predict: shape {tmp_p.shape}, value {tmp_p}')

UNIT TESTS

predict_test(predict)

NameError Traceback (most recent call last)
in
** 1 # Test your predict code**
----> 2 np.random.seed(1)
** 3 tmp_w = np.random.randn(2)**
** 4 tmp_b = 0.3**
** 5 tmp_X = np.random.randn(4, 2) - 0.5**

NameError: name ‘np’ is not defined

4

You have to run all the above cells every time you open your notebook.
One more thing. Users are not allowed to share their code in a public thread. Make sure to delete it to honor to code of conduct of our community.

5

Thanks. I have removed the code. also rerun all the cell. Now getting following error. Not sure what to do to correct it. Plz help.

NameError Traceback (most recent call last)
in
5 tmp_X = np.random.randn(4, 2) - 0.5
6
----> 7 tmp_p = predict(tmp_X, tmp_w, tmp_b)
8 print(f’Output of predict: shape {tmp_p.shape}, value {tmp_p}')
9

in predict(X, w, b)
27
28
—> 29 p[i] = f_wb >= 0.5
30
31 return p

NameError: name ‘f_wb’ is not defined

6

It means that your code of predict function doesn’t know what is f_wb. I suggest checking the hints and more hints given to you just below after that cell.

7

This is the hint i got for f_wb. Should i copy and paste it in the code?

You can calculate f_wb as
for i in range(m):
# Calculate f_wb (exactly how you did it in the compute_cost function above)
z_wb = 0
# Loop over each feature
for j in range(n):
# Add the corresponding term to z_wb
z_wb_ij = X[i, j] * w[j]
z_wb += z_wb_ij

         # Add bias term 
         z_wb += b

         # Calculate the prediction from the model
         f_wb = sigmoid(z_wb)
8

I don’t know. You think about it, what you have to do with it.

9

Still trying to figure out but no success as very new to ML. Maybe you get me some tips to move forward?

11

What are still you trying to figure out? Please be specific. What error now you are getting?

12

@Sultan_Mubashir I would suggest you to brush up your python language (or any programming language) knowledge. You will figure out these types of mistakes easily then.