Session 4 LAB: Working with Data Frames

Part 1:

# one input, and several output in simple data structure:
factors=function(number){
    # empty vector that will collect output
    vectorOfAnswers=c(1 )

    
    # for every value in the sequence...
    for (i in 2:number){
        
        #if the remainder of 'number'/'i' equals zero...
        if ((number %% i ) == 0){ 
            
            # ...add 'i' to the vector of factors!
            vectorOfAnswers=c(vectorOfAnswers,i)
    }
  }
  return (vectorOfAnswers) # returning  the vector
}

factors(30)

## [1]  1  2  3  5  6 10 15 30

This function accepted an integer number and returned its factors. Please answer these questions:

1. For any number N, how many times does the for section is executed to compute the factos of N?

The function will execute n number of times depending on n input.

2. Make a change in the code to reduce the times the for section is executed

By including 1 in vector of answers and changing the value to sequence to 2:number, the for section will now execute n-1 times depending on n input value used.

Part 2:

setwd("C:/Users/leoto/OneDrive/Documents/598/Week 4/session4")

library(rio)


fileName='demo_hdi.csv'
hdi.dat=import(fileName)

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(pander)

tapply(hdi.dat$hdi, hdi.dat$demType, max)

##    Authoritarian Flawed democracy   Full democracy    Hybrid regime 
##            0.863            0.933            0.953            0.814

hdi.dat  %>% group_by( demType )  %>% summarize(max(hdi))

## # A tibble: 4 x 2
##   demType          `max(hdi)`
##   <chr>                 <dbl>
## 1 Authoritarian         0.863
## 2 Flawed democracy      0.933
## 3 Full democracy        0.953
## 4 Hybrid regime         0.814

hdi.dat %>% filter(hdi==0.933 | hdi==0.814 | hdi==0.953 | hdi==0.863)

##                country          demType demScore   hdi
## 1            Hong Kong Flawed democracy     6.15 0.933
## 2           Montenegro    Hybrid regime     5.74 0.814
## 3               Norway   Full democracy     9.87 0.953
## 4               Sweden   Full democracy     9.39 0.933
## 5 United Arab Emirates    Authoritarian     2.76 0.863

tophdi <- c(.863,.933,.953,.814)
hdi.dat[hdi.dat$hdi %in% tophdi,]

##                  country          demType demScore   hdi
## 63             Hong Kong Flawed democracy     6.15 0.933
## 99            Montenegro    Hybrid regime     5.74 0.814
## 110               Norway   Full democracy     9.87 0.953
## 139               Sweden   Full democracy     9.39 0.933
## 152 United Arab Emirates    Authoritarian     2.76 0.863

dat2 <- hdi.dat %>% select(-demScore, -country)
tapply(X=dat2$hdi, INDEX = list(dat2$demType), FUN = max)

##    Authoritarian Flawed democracy   Full democracy    Hybrid regime 
##            0.863            0.933            0.953            0.814

dat2 %>% group_by(demType) %>% summarize(max(hdi))

## # A tibble: 4 x 2
##   demType          `max(hdi)`
##   <chr>                 <dbl>
## 1 Authoritarian         0.863
## 2 Flawed democracy      0.933
## 3 Full democracy        0.953
## 4 Hybrid regime         0.814

library(reshape2, warn.conflicts = FALSE)

hdi_L1 = melt(hdi.dat)

## Using country, demType as id variables

head(hdi_L1)

##       country          demType variable value
## 1 Afghanistan    Authoritarian demScore  2.97
## 2     Albania    Hybrid regime demScore  5.98
## 3     Algeria    Authoritarian demScore  3.50
## 4      Angola    Authoritarian demScore  3.62
## 5   Argentina Flawed democracy demScore  7.02
## 6     Armenia    Hybrid regime demScore  4.79