Confusion matrix visualization in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the function that computes the confusion matrix.

TensorFlow

from sklearn.metrics import [1]

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

Aclassification_report

Broc_auc_score

Caccuracy_score

Dconfusion_matrix

Attempts:

3 left

💡 Hint

Common Mistakes

Importing accuracy_score instead of confusion_matrix

Using classification_report which summarizes metrics but does not return the matrix

Trying to import from tensorflow instead of sklearn.metrics

The confusion_matrix function from sklearn.metrics is used to compute the confusion matrix.

2fill in blank

medium

Complete the code to compute the confusion matrix from true and predicted labels.

TensorFlow

cm = [1](y_true, y_pred)

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

Aconfusion_matrix

Bmean_squared_error

Caccuracy_score

Droc_curve

Attempts:

3 left

💡 Hint

Common Mistakes

Using accuracy_score which returns a scalar accuracy value

Using mean_squared_error which is for regression

Using roc_curve which returns false positive and true positive rates

The confusion_matrix function takes true labels and predicted labels to compute the confusion matrix.

3fill in blank

hard

Fix the error in the code to plot the confusion matrix using matplotlib.

TensorFlow

import matplotlib.pyplot as plt
plt.imshow(cm, cmap=[1])
plt.colorbar()
plt.show()

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

A'viridis'

B'blue'

C'red'

D'gray'

Attempts:

3 left

💡 Hint

Common Mistakes

Using a single color name like 'blue' which is invalid for cmap

Passing a list or tuple instead of a string

Omitting the cmap argument causing default colors

The cmap argument expects a colormap name like 'viridis' to color the matrix visually.

4fill in blank

hard

Fill both blanks to add axis labels to the confusion matrix plot.

TensorFlow

plt.xlabel([1])
plt.ylabel([2])

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

A'Predicted label'

B'True label'

C'Accuracy'

D'Loss'

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping true and predicted labels

Using metric names like 'Accuracy' instead of axis labels

Omitting axis labels

The x-axis shows predicted labels and the y-axis shows true labels in a confusion matrix plot.

5fill in blank

hard

Fill all three blanks to create a normalized confusion matrix and plot it with labels.

TensorFlow

cm_norm = cm / cm.sum(axis=[1], keepdims=[2])
plt.imshow(cm_norm, cmap=[3])
plt.xlabel('Predicted label')
plt.ylabel('True label')
plt.colorbar()
plt.show()

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

A1

BTrue

C'Blues'

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using axis=0 which normalizes columns instead of rows

Setting keepdims=False causing shape errors

Using an invalid colormap name

Normalizing by rows (axis=1) with keepdims=True keeps the matrix shape. 'Blues' is a good colormap for normalized matrices.