D-DS-FN-23 無料問題集「EMC Dell Data Science Foundations」

（A）Numeric

（B）Ordinal

（C）Text

（D）Nominal

（A）that a newly created model provides a prediction of a null sample mean

（B）that a newly created model provides a prediction of a null population mean

（C）that a newly created model does not provide better predictions than the currently existing model

（D）that a newly created model provides a prediction that will be well fit to the null distribution

（A）Tree A

（B）Tree B

（C）Tree D

（D）Tree C

（A）A few large files split into blocks processed serially on one machine

（B）Many small files processed in parallel across multiple machines

（C）A few large files split into blocks processed in parallel across multiple machines

（D）Many small files processed serially on one machine

（A）All population means are equal to each other

（B）At most k-1 population means are equal

（C）At least two population means are not equal

（D）At least two population means are equal

（A）Model building

（B）Discovery

（C）Model planning

（D）Data preparation

（A）Operationalize

（B）Model building

（C）Discovery

（D）Data preparation

（A）Estimate the size of the dataset and plan for 5-10 times the size

（B）Discuss with business experts the best ways to join different datasets

（C）Establish the database tables for extract, translate, and load

（D）Define the hardware and Hadoop network requirements

（A）Model building

（B）Discovery

（C）Model planning

（D）Data preparation

（A）They don't require ordering of data within a window.

（B）They group rows into a single output row.

（C）They can be used between the keywords FROM and WHERE in a SELECT command.

（D）They can be used to calculate moving averages over various intervals.

（A）Density Plot

（B）Box and Whisker Plot

（C）Bar Chart

（D）Pie Chart

（A）Accounts of sizes greater than 2,500 are rare and are most likely outliers. Eliminate them from future analysis.

（B）Data is extremely skewed but looks bimodal. Replot the data in the range 2,500 - 10,000 to be certain.

（C）Data is extremely skewed. Replot the data on a logarithmic scale to get a better understanding of it.

（D）Data is extremely skewed. Split the analysis into two cohorts; accounts less than 2,500 and accounts greater than 2,500.

（A）Centroid positioning and entropy of each record in each cluster

（B）Two dimensional representation of the data and the clusters

（C）Intercept and coefficients for each input variable in the dataset

（D）Center of each discovered cluster and mapping of each record to a cluster

（A）Pig

（B）Hive

（C）HBase

（D）Mahout

（A）The tree did not split on all the input variables. You need a larger data set to get a more accurate model.

（B）The AUC is high, so the overall model is accurate. It is not well-calibrated, because the small nodes will give poor estimates of probability.

（C）The tree is probably overfit. Try fitting shallower trees and using an ensemble method.

（D）The AUC is high, and the small nodes are all very pure. This is an accurate model.

（A）RANK

（B）OVER

（C）PARTITION BY

（D）RANK BY