# Load required packages
library(readxl)
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
# Step 1: Load the dataset
countries_data <- read.csv("C:/Users/manja/Downloads/countries.csv")
# Step 2: Filter countries with 'High income'
# Filter high-income countries based on GDP per capita
high_income_countries <- subset(countries_data, `GDP....per.capita.` > 50000)
# View the resulting high-income countries
print(high_income_countries)
## Country Region Population Area..sq..mi..
## 122 Luxembourg WESTERN EUROPE 474413 2586
## Pop..Density..per.sq..mi.. Coastline..coast.area.ratio. Net.migration
## 122 183,5 0,00 8,97
## Infant.mortality..per.1000.births. GDP....per.capita. Literacy....
## 122 4,81 55100 100,0
## Phones..per.1000. Arable.... Crops.... Other.... Climate Birthrate
## 122 515,4 23,28 0,4 76,32 11,94
## Deathrate Agriculture Industry Service
## 122 8,41 0,01 0,13 0,86
# Step 3: Filter countries in 'Europe' or 'Americas' with life expectancy > 80
# Filter countries in 'Europe' or 'Americas' with life expectancy greater than 80
filtered_countries <- subset(countries_data, (Region == "Europe" | Region == "Americas") & `Infant.mortality..per.1000.births.` < 80)
# View the resulting filtered countries
print(filtered_countries)
## [1] Country Region
## [3] Population Area..sq..mi..
## [5] Pop..Density..per.sq..mi.. Coastline..coast.area.ratio.
## [7] Net.migration Infant.mortality..per.1000.births.
## [9] GDP....per.capita. Literacy....
## [11] Phones..per.1000. Arable....
## [13] Crops.... Other....
## [15] Climate Birthrate
## [17] Deathrate Agriculture
## [19] Industry Service
## <0 rows> (or 0-length row.names)
# Step 4: Filter top 5 countries based on GDP growth
# Filter the top 5 countries based on GDP growth
top_5_countries <- countries_data %>% top_n(5, `GDP....per.capita.`)
# View the resulting top 5 countries
print(top_5_countries)
## Country Region Population Area..sq..mi..
## 1 Bermuda NORTHERN AMERICA 65773 53
## 2 Cayman Islands LATIN AMER. & CARIB 45436 262
## 3 Luxembourg WESTERN EUROPE 474413 2586
## 4 Norway WESTERN EUROPE 4610820 323802
## 5 United States NORTHERN AMERICA 298444215 9631420
## Pop..Density..per.sq..mi.. Coastline..coast.area.ratio. Net.migration
## 1 1241,0 194,34 2,49
## 2 173,4 61,07 18,75
## 3 183,5 0,00 8,97
## 4 14,2 7,77 1,74
## 5 31,0 0,21 3,41
## Infant.mortality..per.1000.births. GDP....per.capita. Literacy....
## 1 8,53 36000 98,0
## 2 8,19 35000 98,0
## 3 4,81 55100 100,0
## 4 3,7 37800 100,0
## 5 6,5 37800 97,0
## Phones..per.1000. Arable.... Crops.... Other.... Climate Birthrate Deathrate
## 1 851,4 20 0 80 2 11,4 7,74
## 2 836,3 3,85 0 96,15 2 12,74 4,89
## 3 515,4 23,28 0,4 76,32 11,94 8,41
## 4 461,7 2,87 0 97,13 3 11,46 9,4
## 5 898,0 19,13 0,22 80,65 3 14,14 8,26
## Agriculture Industry Service
## 1 0,01 0,1 0,89
## 2 0,014 0,032 0,954
## 3 0,01 0,13 0,86
## 4 0,021 0,415 0,564
## 5 0,01 0,204 0,787
# Step 5: Create the 'NED' variable
countries_data$NED <- ifelse(countries_data$Country == "Netherlands", 1, 0)
# Step 6: Select and arrange the columns
selected_columns <- select(countries_data, Country, NED)
arranged_data <- arrange(selected_columns, desc(NED))
# View the column names of the dataset
colnames(countries_data)
## [1] "Country" "Region"
## [3] "Population" "Area..sq..mi.."
## [5] "Pop..Density..per.sq..mi.." "Coastline..coast.area.ratio."
## [7] "Net.migration" "Infant.mortality..per.1000.births."
## [9] "GDP....per.capita." "Literacy...."
## [11] "Phones..per.1000." "Arable...."
## [13] "Crops...." "Other...."
## [15] "Climate" "Birthrate"
## [17] "Deathrate" "Agriculture"
## [19] "Industry" "Service"
## [21] "NED"
# Load necessary libraries
library(readxl)
library(dplyr)
library(tidyr)
# Read the dataset
countries_data <- read.csv("C:/Users/manja/Downloads/countries.csv")
# Filter for income level equal to "Lower middle income"
filtered_data <- countries_data %>%
filter(GDP....per.capita. == "Lower middle income") %>%
group_by(Region) %>%
summarise(Unemployment_Median = median(Service, na.rm = TRUE),
Number_of_Countries = n())
# Sort the results from the highest median unemployment downward
sorted_data <- filtered_data %>%
arrange(desc(Unemployment_Median))
# View the sorted data
print(sorted_data)
## # A tibble: 0 × 3
## # ℹ 3 variables: Region <chr>, Unemployment_Median <chr>,
## # Number_of_Countries <int>
hprice <- read.csv("C:/Users/manja/Downloads/hprice.csv")
library(dplyr)
filtered_hprice <- hprice %>% filter(Price > 9999)
library(tidyr)
pivot_hprice <- filtered_hprice %>%
group_by(Brick, Neighborhood) %>%
summarise(
Price.avg = mean(Price),
SqFt.avg = mean(SqFt),
Price.per.SqFt = mean(Price/SqFt)
)
## `summarise()` has grouped output by 'Brick'. You can override using the
## `.groups` argument.
library(knitr)
library(kableExtra)
##
## Attaching package: 'kableExtra'
##
## The following object is masked from 'package:dplyr':
##
## group_rows
kable(pivot_hprice, "html") %>%
kable_styling("striped", full_width = F)
|
Brick
|
Neighborhood
|
Price.avg
|
SqFt.avg
|
Price.per.SqFt
|
|
No
|
East
|
117750.0
|
2001.538
|
59.01310
|
|
No
|
North
|
108583.8
|
1928.108
|
56.42026
|
|
No
|
West
|
148230.4
|
2073.478
|
71.88587
|
|
Yes
|
East
|
135468.4
|
2031.053
|
66.80893
|
|
Yes
|
North
|
118457.1
|
1857.143
|
64.27986
|
|
Yes
|
West
|
175200.0
|
2091.250
|
83.85290
|