Error analysis patterns in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to calculate the mean absolute error between true and predicted values.

TensorFlow

from sklearn.metrics import [1]
true = [3, -0.5, 2, 7]
pred = [2.5, 0.0, 2, 8]
error = [1](true, pred)
print(error)

Drag options to blanks, or click blank then click option'

Aaccuracy_score

Bmean_squared_error

Cr2_score

Dmean_absolute_error

Attempts:

3 left

💡 Hint

Common Mistakes

Using mean_squared_error which squares errors instead of absolute values.

Using accuracy_score which is for classification, not regression.

The mean_absolute_error function calculates the average absolute difference between true and predicted values, which is useful for error analysis.

2fill in blank

medium

Complete the code to identify samples where the prediction error is greater than 1.0.

TensorFlow

errors = [abs(t - p) for t, p in zip(true, pred)]
high_error_indices = [i for i, e in enumerate(errors) if e [1] 1.0]
print(high_error_indices)

Drag options to blanks, or click blank then click option'

A>

B<=

C==

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using < which selects small errors instead of large ones.

Using == which only selects errors exactly equal to 1.0.

We want to find errors greater than 1.0, so the comparison operator should be >.

3fill in blank

hard

Fix the error in the code to compute residuals (difference between true and predicted values).

TensorFlow

residuals = [true[i] [1] pred[i] for i in range(len(true))]
print(residuals)

Drag options to blanks, or click blank then click option'

A+

B*

C-

D/

Attempts:

3 left

💡 Hint

Common Mistakes

Adding true and predicted values instead of subtracting.

Multiplying or dividing which do not represent residuals.

Residuals are calculated as true value minus predicted value, so the operator is -.

4fill in blank

hard

Fill both blanks to create a dictionary of samples with residuals greater than 0.5.

TensorFlow

large_residuals = {i: residuals[i] for i in range(len(residuals)) if abs(residuals[i]) [1] 0.5 and residuals[i] [2] 0}
print(large_residuals)

Drag options to blanks, or click blank then click option'

A>

B<

C!=

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using < which selects smaller residuals.

Using == which only selects exact values.

We want residuals with absolute value greater than 0.5 and positive residuals, so both comparisons use >.

5fill in blank

hard

Fill all three blanks to create a dictionary of samples where the residual is negative and its absolute value is greater than 0.7.

TensorFlow

negative_large_residuals = {i: residuals[i] for i in range(len(residuals)) if residuals[i] [1] 0 and abs(residuals[i]) [2] 0.7 and residuals[i] [3] -1}
print(negative_large_residuals)

Drag options to blanks, or click blank then click option'

A<

B>

C!=

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using > instead of < for negative check.

Using == which restricts to exact values.

Residuals less than 0 are negative (< 0), absolute value greater than 0.7 (> 0.7), and residuals not equal to -1 (!= -1) to exclude that specific value.