每日一练 | Data Scientist & Business Analyst & Leetcode 面试题 357

点击上方 蓝字 会变美

“

”

DS Interview Question

What's difference between pca and kernel pca?

BA Interview Question

R Programing: imagine you have two columns in a dataframe, ‘Gender’ and ‘Loan_Status’, both are categorical variables. ‘Gender’ has ‘Male’,’Female’ and NA values, ‘Loan_Status’ with ‘Yes’ and ‘No’. Now, how do you use ‘dplyr’ package to calculate the percentage for male and female when Loan Status equals to ‘No’, remember to ignore NA values.

Sample Output:

LeetCode Question

Remove Duplicates from Sorted Array II

Description:

Follow up for "Romove Duplicates"

What if duplicates are allowed at most twice?

Input: [1,1,2,2,2,3,3,3]

Output: [1,1,2,2,3,3]

DS Interview Question & Answer

What are the advantages of random projection comparing to PCA?

Answer:

* With very high dimensions, if speed is an issue, then consider that on a matrix of size n×k, PCA takes O(k^2×n+k^3) time, whereas a random projection takes O(nkd), where you're projecting on a subspace of size d.

* With a sparse matrix its even faster.

* The data may well be low-dimensional, but not in a linear subspace. PCA assumes this.

* Random projection are also quite fast for reducing the dimension of a mixture of Gaussians.

* If the data is very large, you don't need to hold it in memory for a random projections, whereas for PCA you do.

* In general PCA works well on relatively low dimensional data. Of course, PCA maintains the best possible projection.

BA Interview Question & Answer

R Programming: How to check the frequency distribution of a categorical variable?

Imagine we have a table names gender:

Gender = factor(c(‘M’,’F’,’M’,’F’,’F’,’F’）

table(Gender)

Sample Table:

Gender

F  M

4  2