Databricks-Certified-Professional-Data-Scientist Exam Practice Test Instant Access

Question 1

You are working on a email spam filtering assignment, while working on this you find there is new word e.g. HadoopExam comes in email, and in your solutions you never come across this word before, hence probability of this words is coming in either email could be zero. So which of the following algorithm can help you to avoid zero probability?

ANaive Bayes

BLaplace Smoothing

CLogistic Regression

DAll of the above
Laplace smoothing is a technique for parameter estimation which accounts for unobserved events. It is more robust and will not fail completely when data that has never been observed in training shows up.

Answer : B

Question 2

A denote the event 'student is female' and let B denote the event 'student is French'. In a class of 100 students suppose 60 are French, and suppose that 10 of the French students are females. Find the probability that if I pick a French student, it will be a girl, that is, find P(A|B).

A1/3

B2/3

C1/6

D2/6
Since 10 out of 100 students are both French and female, then
P(AandB)=10100
Also. 60 out of the 100 students are French, so
P(B)=60100
So the required probability is:
P(A|B)=P(AandB)P(B)=10/10060/100=16

Answer : C

Question 3

What is the probability that the total of two dice will be greater than 8, given that the first die is a 6?

A1/3

B2/3

C1/6

D2/6

Answer : B

Question 4

If E1 and E2 are two events, how do you represent the conditional probability given that E2 occurs given that E1 has occurred?

AP(E1)/P(E2)

BP(E1+E2)/P(E1)

CP(E2)/P(E1)

DP(E2)/(P(E1+E2)

Answer : C

Question 5

Question-26. There are 5000 different color balls, out of which 1200 are pink color. What is the maximum likelihood estimate for the proportion of "pink" items in the test set of color balls?

A2.4

B24 0

C.24

D.48

E4.8

Answer : C

In general, for a fixed set of data and underlying statistical model the method of maximum likelihood selects the set of values of the model parameters that maximizes the likelihood function. Intuitively, this maximizes the 'agreement' of the selected model with the observed data, and for discrete random variables it indeed maximizes the probability of the observed data under the resulting distribution. Maximum-likelihood estimation gives a unified approach to estimation, which is well-defined in the case of the normal distribution and many other problems. However in some complicated problems, difficulties do occur: in such problems, maximum-likelihood estimators are unsuitable or do not exist.

Question 6

What is the best way to evaluate the quality of the model found by an unsupervised algorithm like k-means clustering, given metrics for the cost of the clustering (how well it fits the data) and its stability (how similar the clusters are across multiple runs over the same data)?

AThe lowest cost clustering subject to a stability constraint

BThe lowest cost clustering

CThe most stable clustering subject to a minimal cost constraint

DThe most stable clustering
There is a tradeoff between cost and stability in unsupervised learning. The more tightly you fit the data, the less stable the model will be, and vice versa. The idea is to find a good balance with more weight given to the cost. Typically a good approach is to set a stability threshold and select the model that achieves the lowest cost above the stability threshold.

Answer : A

Question 7

Which of the following metrics are useful in measuring the accuracy and quality of a recommender system?

ACluster Density

BSupport Vector Count

CMean Absolute Error

DSum of Absolute Errors
The MAE measures the average magnitude of the errors in a set of forecasts, without considering their direction. It measures accuracy for continuous variables. The equation is given in the library references. Expressed in words, the MAE is the average over the verification sample of the absolute values of the differences between forecast and the corresponding observation. The MAE is a linear score which means that all the individual differences are weighted equally in the average.
The sum of absolute errors is a valid metric, but doesn't give any useful sense of how the recommender system is performing.
Support vector count and cluster density do not apply to recommender systems.
MAE and AUC are both valid and useful metrics for measuring recommender systems.

Answer : C

Databricks Certified Professional Data Scientist Exam Practice Test