DATA1001 Project #1
Chandler Elissa, Nikolovski Mihael, Villar Miguel, Ando Koki
4/08/2018
1 Introduction
The pursuit of happiness had been a part of humanity longer than some may think; some even argue that it’s the reason we continue to do more than just exist. Evidence of this stems back to Ancient Greece, when Philosophers such as Aristotle wrote about it in many of his texts. In fact, the “pursuit of happiness” was a vital part of the United States Declaration of Independence, written in 1776. With Thomas Jefferson stating how he believed that happiness is attainable by gaining knowledge and living a self-sufficient life surrounded by friends. If we look at the multitude of global religions, we see a similar importance placed on the idea of happiness.
- For the 1st project of Data1001, our group decided to focus on the analysis and presentation of data surrounding the Global Happiness Report.
2 Literature
The information was gathered from a single direct primary source: the Global Happiness Report created by the United Nations Sustainable Development Solutions Network (UNSDSN.)
3 Research Questions
- What are the different factors that lead to happiness of a country?
- What similarities and differences do the countries experiencing the highest/lowest WHS have?
- Does being in a certain region [continent] have any correlation to the average score of countries?
- What role does the economy play in determining the happiness of a country?
- Which factor, on average, contributes most/least to happiness?
4 Analysis of Sources
UNSDSN
SDSN (Sustainable development solutions network) is a UN group run by scholars from around the world. They largely receive funding from government sources, mostly from European countries in departments relating to foreign affairs (naturally). Several firms, including BT (British Telecom), eni, Digicel, Glaxo Smith Kline, Novartis, Verizon, and Ericsson also fund projects by SDSN. While the possibility of a bias is always possible, these companies likely stand to profit more from accurate international information pertaining to people’s desires, so it seems very unlikely that an agenda is being pushed meaning the data is very likely accurate.
Gallup
American analytics/data firm. The SDSN would have hired them for the specific task of conducting happiness surveys around the world.. Being as large and reputable as they are, it’s in their best interest to make sure the information is collected properly. The happiness score was received from Gallup’s data, which was done by performing randomised phone surveys (that were still representative of the overall demographics of the country above 15years old) in countries where that was a proven method. In countries where it wasn’t or where phone lines weren’t readily available country-wide, face to face surveys were conducted. Phone surveys were 15-30 minutes, face to face ones 30-60 minutes usually. Self reports are always sketchy, but no real other way to measure happiness so needs to be taken at face value. Information unclear on how many people were interviewed.
5 Discussion of Stakeholders
The people surveyed were asked the following: “Please imagine a ladder, with steps numbered from 0 at the bottom to 10 at the top. The top of the ladder represents the best possible life for you and the bottom of the ladder represents the worst possible life for you. On which step of the ladder would you say you personally feel you stand at this time?”
If we asked you now, today, what your life goals are, what do you want out of life? You would all have different ideas/thoughts. Of course! We all have different desires, priorities, aspirations. However, there would be an underlying theme of wanting to be happy. Ultimately, all the decisions we make in life either stem from or lead to our desire to be happy.
In 2012, the UN declared March 20th to be International Day of Happiness and produced its first Happiness Report. A survey of the state of global happiness and an acknowledgement that “the pursuit of happiness is a fundamental human goal and right”.1. A Happiness Report has been produced annually since 2012 and each year continues to gain momentum and popularity as more and more governments, organisations and civil societies seek to use happiness indicators to inform policy decisions. “Increasingly, happiness is considered to be the proper measure of social progress and the goal of public policy.”
The report is carried out by experts of different fields from psychology, health, economics and more, and looks at six key conditions of each country: 1. economic prosperity, including decent work for all who want it; 2. the physical and mental health of the citizens; 3. freedom of individuals to make key life decisions; 4. strong and vibrant social support networks (social capital); 5. shared public values of generosity; and 6. social trust, including confidence in the honesty of business and government.
The sum of the conditions determines the overall score for each country. The Happiness Reports are compiled by Sustainable Development Solutions Network- A Global
6 Code
6.1 Preparation
6.1.1 Packages
library(data.table)
library(tidyverse)## ── Attaching packages ────────────────────────────────── tidyverse 1.2.1 ──## ✔ ggplot2 2.2.1.9000 ✔ purrr 0.2.4
## ✔ tibble 1.4.2 ✔ dplyr 0.7.4
## ✔ tidyr 0.8.0 ✔ stringr 1.3.0
## ✔ readr 1.1.1 ✔ forcats 0.3.0## ── Conflicts ───────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::between() masks data.table::between()
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::first() masks data.table::first()
## ✖ dplyr::lag() masks stats::lag()
## ✖ dplyr::last() masks data.table::last()
## ✖ purrr::transpose() masks data.table::transpose()
## ✖ dplyr::vars() masks ggplot2::vars()library(corrplot)## corrplot 0.84 loadedlibrary(plotly)##
## Attaching package: 'plotly'## The following object is masked from 'package:ggplot2':
##
## last_plot## The following object is masked from 'package:stats':
##
## filter## The following object is masked from 'package:graphics':
##
## layoutlibrary(wildcard)
library(shiny)
library(PerformanceAnalytics)## Loading required package: xts## Loading required package: zoo##
## Attaching package: 'zoo'## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric##
## Attaching package: 'xts'## The following objects are masked from 'package:dplyr':
##
## first, last## The following objects are masked from 'package:data.table':
##
## first, last##
## Attaching package: 'PerformanceAnalytics'## The following object is masked from 'package:graphics':
##
## legendlibrary(DT)##
## Attaching package: 'DT'## The following objects are masked from 'package:shiny':
##
## dataTableOutput, renderDataTable6.1.2 Data Importing & Cleaning
setwd("/Users/KokiAndo/Desktop/R/R report/World Happiness")
#(https://www.kaggle.com/unsdsn/world-happiness)
wh15 <- fread("2015.csv", data.table = FALSE)
wh16 <- fread("2016.csv", data.table = FALSE)
wh17 <- fread("2017.csv", data.table = FALSE)
wh15$year <- 2015
wh16$year <- 2016
wh17$year <- 2017
names(wh17)[2] <- "Happiness Rank"
names(wh17)[3] <- "Happiness Score"
names(wh17)[6] <- "Economy (GDP per Capita)"
names(wh17)[8] <- "Health (Life Expectancy)"
names(wh17)[11] <- "Trust (Government Corruption)"
names(wh17)[12] <- "Dystopia Residual"
wh15_17 <- bind_rows(wh15,wh16,wh17)
names(wh15_17)[5] <- "SD_error"
wh15_17 <- wh15_17 %>% select(Country:year,-Region, -SD_error)
names(wh15_17) <- c("Country","Happiness_Rank","Happiness_Score","Economy_GDP",
"Family","Health","Freedom","Trust",
"Generosity","Dystopia_Residual","year")6.1.3 Data Components
names(wh15_17)## [1] "Country" "Happiness_Rank" "Happiness_Score"
## [4] "Economy_GDP" "Family" "Health"
## [7] "Freedom" "Trust" "Generosity"
## [10] "Dystopia_Residual" "year"head(wh15_17)## Country Happiness_Rank Happiness_Score Economy_GDP Family Health
## 1 Switzerland 1 7.587 1.39651 1.34951 0.94143
## 2 Iceland 2 7.561 1.30232 1.40223 0.94784
## 3 Denmark 3 7.527 1.32548 1.36058 0.87464
## 4 Norway 4 7.522 1.45900 1.33095 0.88521
## 5 Canada 5 7.427 1.32629 1.32261 0.90563
## 6 Finland 6 7.406 1.29025 1.31826 0.88911
## Freedom Trust Generosity Dystopia_Residual year
## 1 0.66557 0.41978 0.29678 2.51738 2015
## 2 0.62877 0.14145 0.43630 2.70201 2015
## 3 0.64938 0.48357 0.34139 2.49204 2015
## 4 0.66973 0.36503 0.34699 2.46531 2015
## 5 0.63297 0.32957 0.45811 2.45176 2015
## 6 0.64169 0.41372 0.23351 2.61955 2015str(wh15_17)## 'data.frame': 470 obs. of 11 variables:
## $ Country : chr "Switzerland" "Iceland" "Denmark" "Norway" ...
## $ Happiness_Rank : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Happiness_Score : num 7.59 7.56 7.53 7.52 7.43 ...
## $ Economy_GDP : num 1.4 1.3 1.33 1.46 1.33 ...
## $ Family : num 1.35 1.4 1.36 1.33 1.32 ...
## $ Health : num 0.941 0.948 0.875 0.885 0.906 ...
## $ Freedom : num 0.666 0.629 0.649 0.67 0.633 ...
## $ Trust : num 0.42 0.141 0.484 0.365 0.33 ...
## $ Generosity : num 0.297 0.436 0.341 0.347 0.458 ...
## $ Dystopia_Residual: num 2.52 2.7 2.49 2.47 2.45 ...
## $ year : num 2015 2015 2015 2015 2015 ...summary(wh15_17)## Country Happiness_Rank Happiness_Score Economy_GDP
## Length:470 Min. : 1.00 Min. :2.693 Min. :0.0000
## Class :character 1st Qu.: 40.00 1st Qu.:4.509 1st Qu.:0.6053
## Mode :character Median : 79.00 Median :5.282 Median :0.9954
## Mean : 78.83 Mean :5.371 Mean :0.9278
## 3rd Qu.:118.00 3rd Qu.:6.234 3rd Qu.:1.2524
## Max. :158.00 Max. :7.587 Max. :1.8708
## Family Health Freedom Trust
## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.00000
## 1st Qu.:0.7930 1st Qu.:0.4023 1st Qu.:0.2976 1st Qu.:0.05978
## Median :1.0257 Median :0.6301 Median :0.4183 Median :0.09950
## Mean :0.9903 Mean :0.5800 Mean :0.4028 Mean :0.13479
## 3rd Qu.:1.2287 3rd Qu.:0.7683 3rd Qu.:0.5169 3rd Qu.:0.17316
## Max. :1.6106 Max. :1.0252 Max. :0.6697 Max. :0.55191
## Generosity Dystopia_Residual year
## Min. :0.0000 Min. :0.3286 Min. :2015
## 1st Qu.:0.1528 1st Qu.:1.7380 1st Qu.:2015
## Median :0.2231 Median :2.0946 Median :2016
## Mean :0.2422 Mean :2.0927 Mean :2016
## 3rd Qu.:0.3158 3rd Qu.:2.4556 3rd Qu.:2017
## Max. :0.8381 Max. :3.8377 Max. :20176.2 Countries that did not appear in 3 years in a row
countries.didnt.appear.3years <- wh15_17 %>% group_by(Country) %>% mutate(count = sum(year))
countries.didnt.appear.3years %>% filter(count != 6048) %>% select(Country, Happiness_Rank, year) %>% arrange(Country)## # A tibble: 32 x 3
## # Groups: Country [20]
## Country Happiness_Rank year
## <chr> <int> <dbl>
## 1 Belize 52 2016.
## 2 Belize 50 2017.
## 3 Central African Republic 148 2015.
## 4 Central African Republic 155 2017.
## 5 Comoros 140 2015.
## 6 Comoros 138 2016.
## 7 Djibouti 126 2015.
## 8 Hong Kong 72 2015.
## 9 Hong Kong 75 2016.
## 10 Hong Kong S.A.R., China 71 2017.
## # ... with 22 more rowsSome countries underwent a name change such as Hong Kong S.A.R., China to Hong Kong in 2017 for political reasons. While other countries—as admitted by the UNSDSN—did not fulfill the survey or gave the survey to its citizens. In order to minimize issues, the committee used the 2014 data of these countries. This of course affects the accuracy of the data, which was stated under the source validity.
6.3 Analysis
6.3.1 Correlation
6.3.1.1 Correlation check No.1
corrplot(cor(wh15_17 %>%
select(Happiness_Score:Dystopia_Residual)),
method="color",
sig.level = 0.01, insig = "blank",
addCoef.col = "black",
tl.srt=45,
type="upper"
)
This correlation plot shows that the Economic GDP score tends to have the biggest impact to happiness score and the Health score has the second biggest impact.
6.3.1.2 Histogram all the year
hist(wh15_17$Happiness_Score , xlab = "World Happiness Score from 2015 to 2017", main = "World Happiness Score from 2015 to 2017")
6.3.2 Ranking
p <- ggplot(wh15_17 %>% filter(year==2017), aes(x= Happiness_Score,y=
reorder(Country,Happiness_Score))) +
geom_point(colour = "red", alpha = .5) +
geom_segment(aes(yend=reorder(Country, Happiness_Score)), xend = 0, colour="pink", alpha = .5) +
theme(axis.text.y = element_text(angle = 0, hjust = 1)) +
labs(title = "World Happiness Rank in 2017", y = "Country Name", x = "Happiness Score")
ggplotly(p)6.3.2.1 2017 Happiness Score World Map
world <- map_data('world')##
## Attaching package: 'maps'## The following object is masked from 'package:purrr':
##
## mapworld <- world %>% filter(region != "Antarctica")
world <- fortify(world)
happiness.score17 <- wh15_17 %>% select(Country, Happiness_Score, year) %>% filter(year == 2017)
happiness.score17 <- wildcard(df = happiness.score17, wildcard = "United States", values = "USA",
expand = TRUE, rules = NULL)
happiness.score17 <- wildcard(df = happiness.score17, wildcard = "United Kingdom", values = "UK",
expand = TRUE, rules = NULL)
happiness.score17 <- wildcard(df = happiness.score17, wildcard = "Democratic Republic of the Congo", values = "Congo (Kinshasa)",
expand = TRUE, rules = NULL)
ggplot() +
geom_map(data=world, map=world,
aes(x=long, y=lat, group=group, map_id=region),
fill="white", colour="black") +
geom_map(data=happiness.score17, map=world,
aes(fill=Happiness_Score, map_id=Country),
colour="black") +
scale_fill_continuous(low="red", high="yellow",
guide="colorbar") +
labs(title = "World Happiness Score in 2017")## Warning: Ignoring unknown aesthetics: x, y
World map - showing World at a glance and the state of global happiness
6.3.3 Scatter Plot
6.3.3.1 Scatter Plot No.1
plot_ly(data = wh15_17,
x=~Economy_GDP, y=~Happiness_Score, color=~Health, type = "scatter",
text = ~paste("Country:", Country)) %>%
layout(title = "Happiness, GDP and Health relationship",
xaxis = list(title = "GDP per Capita"),
yaxis = list(title = "Happiness Score"))## No scatter mode specifed:
## Setting the mode to markers
## Read more about this attribute -> https://plot.ly/r/reference/#scatter-modeThis interactive scatterplot shows that there is a strong positive correlation between GDP and Happiness Also points are coloured by the Health score, which also suggeests that Health tends to have big impact to happiness.
6.3.4 Boxplot
6.3.4.1 Happiness score by region(boxplot)
names(wh16)[4] <- "Happiness_Score"
ggplot(wh16, aes(x=Region, y= Happiness_Score, colour = Region)) +
geom_boxplot() +
theme(axis.text.x = element_text(angle = 60, hjust = 1)) +
labs(title = "Happiness Score Boxplot",
x = "Region",
y = "Happiness Score")
6.3.5 Extract & Compare Top5, Middle5 and Worst5 Countries
world.happiness17 <- wh15_17 %>% filter(year == 2017)
top5 <- world.happiness17 %>% head(5) %>% mutate(Level = "TOP5")
middle5 <- world.happiness17[76:80, ] %>% mutate(Level = "MIDDLE5")
worst5 <- world.happiness17 %>% tail(5) %>% mutate(Level = "WORST5")
comparison <- bind_rows(top5, middle5, worst5)
comparison$Level <- as.factor(comparison$Level)
comparison <- transform(comparison, Level = factor(Level, levels = c("TOP5", "MIDDLE5", "WORST5" )))datatable(comparison,
options = list(
lengthMenu = c(5, 10, 15)
),
caption =
htmltools::tags$caption(
style = 'caption-side: bottom; text-align: center;',
htmltools::em('Data table that only includes top5, middle5 and worst5 countries'))
)comparison.score <- comparison %>% gather(key = "columns", value = "score", Happiness_Score:Dystopia_Residual)
comparison.score %>%
ggplot(aes(x = Level, y = score, colour = Level, fill = Level)) +
geom_boxplot(position=position_dodge(width=1)) + facet_wrap(~columns, scales = "free")
Analysis of the six different key conditions used to determine overall state of happiness of a country. Looking at the top five, middle five and bottom five countries of the dataset.
7 Conclusion
After analysing data of Global Happiness Levels in the world, created by the United Nations Sustainable Development Solutions Network, we were able to discover the impact of each different factor in determining “happiness.” We had also found that among the different factors, Economic GDP tends to have the greatest on happiness with Health following close by. We then decided to focus on these two by establishing graphs of their relationships to discover that there is a direct relation between these factors.
In addition to these facts, we decided to explore the topic deeper by classifying certain countries in the data to the top, median and bottom five countries according to ranked scores, in order to get a better sense of similarities and differences. The group determined that the “happiest” countries were located in Europe, particularly Scandinavia and Switzerland. Meanwhile the “least happy” countries were located in Africa and the Middle East. This suggests that countries in close proximity or those in the same region often have similar living conditions and are thus affected by factors similarly.
One bigger concern is how Trust has the lowest scores of all conditions looked at. Countries that have little to no trust and confidence in the governments, make it so that the citizens feel disenfranchised and are not able to take the life choices they wish, which is illustrated in the correlation between low trust and low Freedom scores.
By looking at and analysing these reports, we are able to decipher what makes countries and their citizens happier, thus allowing us to focus on prioritizing and improving these aspects of each nation. It is through this that we are able to achieve the true pursuit of happiness, which we as human beings strive for.