Go Back to Machine Learning

Course Content

ML Quiz 1

Type : Graded Quiz

Attempts : 1/1

Questions : 10

Time : 45m

Due Date : Jan 30, 11:59 PM

Your Score : 10/10

Instructions

Attempt History

Attempt #1
Jan 30, 7:19
PM
Marks: 10

Q No: 1 Correct
Answer Marks:
1/1

It is estimated that 50% of emails are spam emails. Some software has been
applied to filter these spam emails before they reach your inbox. A certain brand
of software claims that it can detect 95% of spam emails and the probability for a
false positive (a non-spam email detected as spam) is 8%.

Now if an email is detected as spam, then what is the probability that it is in fact a
non-spam email?

1/8
 0.077 You Selected

0.00004

0.892

0.034

P(Actual Spam) = 0.5 P(SD |Actual Spam) = 0.95 P(SD |Not Spam) = 0.08
(P(SD | Not Spam) * P(Not Spam)) / (P(SD |Not Spam) *P(Not Spam) + P(SD |Spam)
*P(Spam))

= (0.08 *0.5) /( (0.08*0.5) + (0.95*0.5) ) = 0.077

Correct Answer
Q No: 2
Marks:
1/1

A doctor knows that cold causes fever 55% of the time. The prior probability of
any patient having a cold is 1/51,000. The prior probability of any patient having a
fever is 1/25

If a patient has a fever, what’s the probability he/she has a cold?

0.000269 You Selected

0.222231

0.000002

0.022019
 Given,

P(F) = 1/25 ; P(F |C) = 0.55 ; P (C) = 1/51000

P (C | F) = (P ( F | C) * P(C) ) / P(F) = 0.0002696

Q No: 3 Correct Answer

Marks:
1/1
On increasing k in kNN, the decision
boundary :

Gets Smoother You Selected

Decision boundary vanishes

Gets more complex

k does not affect the decision boundary

The only parameter that can adjust the complexity of KNN is the number of neighbors k. The larger k is, the sm

Correct Answer
Q No: 4
Marks:
1/1
Which of the following is true wrt. to kNN when the value of k=1 and infinity,
respectively:

High variance, high variance

high variance, low variance You Selected

Low variance, low variance

Low variance, high variance

Ans: Very high k has low variance unlike a very low k but is not useful for prediction.
Q No: 5 Correct Answer
Marks:
1/1
Which distance is a generalization of euclidean and manhattan
distances:
Minkowski distance You Selected

None of the mentioned

Mahalanobis distance

Cosine similarity

Correct Answer
Q No: 6
Marks:
1/1
Choose the most appropriate answer wrt the KD Tree nearest
Neighbour:

It is generally used when there are a very large number of data points in a lesser no of dimensions.

It is also a neighborhood search algorithm.

All of the mentioned. You Selected

It is computationally less expensive.

Ans: All are correct with respect to the KDT NN

Q No: 7 Correct Answer

Marks:
1/1
Select the true statement regarding
KNN:
 Complex to implement and understand

It outputs a model and a new point is quickly calculated without actually calculating distances.

It can work on multi classes simultaneously. You Selected

It is not computationally intensive.

Ans: Whatever may be the classes in the neighborhood, KNn can work with them simultaneously and gives the

Q No: 8 Correct Answer

Marks:
1/1

To answer the below question, please follow the

instructions:

1. Load this dataset

2. Take the Target variable as 'default'
3. Do not scale the data
4. Split the data using test_size=0.30 and
random_state=1
5. Make a Naive Bayes model

What is the accuracy/Model Score of the model on the

Train set?

~0.6883

~0.7821

~0.9698 You Selected

 ~0.8377

x train x test y train y test = train test split(x y test size=0 30 random state=1)
 model = GaussianNB() model.fit(x_train, y_train) y_predict = model.predict(x_test)
model_score = model.score(x_train, y_train) print(model_score)
0.9698924731182795

Q No: 9 Correct Answer

Marks:
1/1

To answer the below question, please follow the

instructions:

1. Load this dataset

2. Take the Target variable as 'default'
3. Do not scale the data
4. Split the data using test_size=0.30 and
random_state=1
5. Make a Naive Bayes model

What is the accuracy/Model Score of the model on the

Test set?

~0.9113

~0.9749 You Selected

~0.8932

~0.8327
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.30, random_state=1) model = GaussianNB()
model.fit(x_train, y_train) y_predict = model.predict(x_test)
model_score = model.score(x_test, y_test) print(model_score)
Q No: 10 Correct Answer
Marks:
1/1

To answer the below question, please follow the

instructions:

1. Load this dataset

2. Take the Target variable as 'default'
3. Do not scale the data
4. Split the data using test_size=0.30 and
random_state=1
5. Make a Naive Bayes model
6. Print a classification_report on test data.

What is the recall for target classes-No and Yes for the
test data?

1.00 and 0.12 You Selected

1.00 and 0.53

0.70 and 0.42

1.00 and 0.37

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.30,

random_state=1)

model = GaussianNB()
model.fit(x_train, y_train)
test_predict =
model.predict(x_test)
print(metrics.classification_report(y_test, test_predict))
Comments:

+ Add comments