#PROJECT 1 

##SETTING UP CODE FOR THE PROJECT

setwd("/Users/dpatel78/Desktop")
female <- read.csv("female.csv")
male <- read.csv("male.csv")

is.data.frame(female)
## [1] TRUE
head(female)
##                                                                                                               Series.Name
## 1 Account ownership at a financial institution or with a mobile-money-service provider, female (% of population ages 15+)
## 2 Account ownership at a financial institution or with a mobile-money-service provider, female (% of population ages 15+)
## 3 Account ownership at a financial institution or with a mobile-money-service provider, female (% of population ages 15+)
## 4 Account ownership at a financial institution or with a mobile-money-service provider, female (% of population ages 15+)
## 5 Account ownership at a financial institution or with a mobile-money-service provider, female (% of population ages 15+)
## 6 Account ownership at a financial institution or with a mobile-money-service provider, female (% of population ages 15+)
##         Series.Code   Country.Name Country.Code X1990..YR1990. X2000..YR2000.
## 1 FX.OWN.TOTL.FE.ZS    Afghanistan          AFG             ..             ..
## 2 FX.OWN.TOTL.FE.ZS        Albania          ALB             ..             ..
## 3 FX.OWN.TOTL.FE.ZS        Algeria          DZA             ..             ..
## 4 FX.OWN.TOTL.FE.ZS American Samoa          ASM             ..             ..
## 5 FX.OWN.TOTL.FE.ZS        Andorra          AND             ..             ..
## 6 FX.OWN.TOTL.FE.ZS         Angola          AGO             ..             ..
##   X2013..YR2013. X2014..YR2014. X2015..YR2015. X2016..YR2016. X2017..YR2017.
## 1             ..           3.81             ..             ..           7.16
## 2             ..          33.59             ..             ..           38.1
## 3             ..          40.07             ..             ..          29.27
## 4             ..             ..             ..             ..             ..
## 5             ..             ..             ..             ..             ..
## 6             ..          22.33             ..             ..             ..
##   X2018..YR2018. X2019..YR2019. X2020..YR2020. X2021..YR2021. X2022..YR2022.
## 1             ..             ..             ..            4.7             ..
## 2             ..             ..             ..          45.69             ..
## 3             ..             ..             ..          31.19             ..
## 4             ..             ..             ..             ..             ..
## 5             ..             ..             ..             ..             ..
## 6             ..             ..             ..             ..             ..
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.0     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
female <- female %>%
  filter(Country.Name == "Brazil" | Country.Name == "India" | 
  Country.Name == "United States")
  
head(female)
##                                                                                                               Series.Name
## 1 Account ownership at a financial institution or with a mobile-money-service provider, female (% of population ages 15+)
## 2 Account ownership at a financial institution or with a mobile-money-service provider, female (% of population ages 15+)
## 3 Account ownership at a financial institution or with a mobile-money-service provider, female (% of population ages 15+)
##         Series.Code  Country.Name Country.Code X1990..YR1990. X2000..YR2000.
## 1 FX.OWN.TOTL.FE.ZS        Brazil          BRA             ..             ..
## 2 FX.OWN.TOTL.FE.ZS         India          IND             ..             ..
## 3 FX.OWN.TOTL.FE.ZS United States          USA             ..             ..
##   X2013..YR2013. X2014..YR2014. X2015..YR2015. X2016..YR2016. X2017..YR2017.
## 1             ..          64.77             ..             ..          67.51
## 2             ..          43.13             ..             ..          76.64
## 3             ..           94.8             ..             ..          92.69
##   X2018..YR2018. X2019..YR2019. X2020..YR2020. X2021..YR2021. X2022..YR2022.
## 1             ..             ..             ..          80.87             ..
## 2             ..             ..             ..          77.55             ..
## 3             ..             ..             ..          96.79             ..
colnames(female)
##  [1] "Series.Name"    "Series.Code"    "Country.Name"   "Country.Code"  
##  [5] "X1990..YR1990." "X2000..YR2000." "X2013..YR2013." "X2014..YR2014."
##  [9] "X2015..YR2015." "X2016..YR2016." "X2017..YR2017." "X2018..YR2018."
## [13] "X2019..YR2019." "X2020..YR2020." "X2021..YR2021." "X2022..YR2022."
rel_col <- which(colnames(female)=="Country.Name" | colnames(female)== "X2014..YR2014." | colnames(female)== "X2017..YR2017." | colnames(female) == "X2021..YR2021." )
rel_col
## [1]  3  8 11 15
female <- female[rel_col] %>% rename("2014" = 2, "2017" = 3, "2021" = 4)
head(female)
##    Country.Name  2014  2017  2021
## 1        Brazil 64.77 67.51 80.87
## 2         India 43.13 76.64 77.55
## 3 United States  94.8 92.69 96.79
transpose_f <- data.frame(t(female[-1]))
colnames(transpose_f) <- female[, 1]
head(transpose_f)
##      Brazil India United States
## 2014  64.77 43.13          94.8
## 2017  67.51 76.64         92.69
## 2021  80.87 77.55         96.79
print(sapply(transpose_f, class))
##        Brazil         India United States 
##   "character"   "character"   "character"
transpose_f$Brazil = as.numeric(transpose_f$Brazil) 
transpose_f$India = as.numeric(transpose_f$India)
transpose_f$"United States" = as.numeric(transpose_f$"United States")
head(transpose_f)
##      Brazil India United States
## 2014  64.77 43.13         94.80
## 2017  67.51 76.64         92.69
## 2021  80.87 77.55         96.79
transpose_f <- transpose_f %>% mutate_if(is.numeric, as.character)
head(transpose_f)
##      Brazil India United States
## 2014  64.77 43.13          94.8
## 2017  67.51 76.64         92.69
## 2021  80.87 77.55         96.79
transpose_f <- transpose_f %>% mutate_if(is.character, as.numeric)
head(transpose_f)
##      Brazil India United States
## 2014  64.77 43.13         94.80
## 2017  67.51 76.64         92.69
## 2021  80.87 77.55         96.79
summarise_each(transpose_f, list(mean))
## Warning: `summarise_each()` was deprecated in dplyr 0.7.0.
## ℹ Please use `across()` instead.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
##   Brazil    India United States
## 1  71.05 65.77333         94.76
transpose_f %>%
  summarise(across(c(Brazil, India, "United States"), list(mean=mean, sd=sd)))
##   Brazil_mean Brazil_sd India_mean India_sd United States_mean United States_sd
## 1       71.05  8.614012   65.77333 19.61498              94.76         2.050293
year <- c(2014, 2017,2021)
ggplot(data=transpose_f, aes(x=year, y=India, group=1)) +
  geom_line()+
  geom_point()

male <- read.csv(file = "male.csv")
male <- male %>%
  filter(Country.Name == "Brazil" | Country.Name == "India" | Country.Name == "United States") 

male <- male[rel_col] %>% 
  rename("2014" = 2, "2017" = 3, "2021" = 4)

transpose_m <- data.frame(t(male[-1]))
colnames(transpose_m) <- male[, 1]

transpose_m$Brazil = as.numeric(as.character(transpose_m$Brazil)) 
transpose_m$India = as.numeric(as.character(transpose_m$India))
transpose_m$"United States" = as.numeric(as.character((transpose_m$"United States")))

head(transpose_m)
##      Brazil India United States
## 2014  71.69 62.76         92.36
## 2017  72.85 83.01         93.57
## 2021  87.05 77.51         93.09
transpose_m <- rename(transpose_m, "Brazil_m" = 1, "India_m" = 2, "United_States_m" = 3)

head(transpose_m)
##      Brazil_m India_m United_States_m
## 2014    71.69   62.76           92.36
## 2017    72.85   83.01           93.57
## 2021    87.05   77.51           93.09
transpose_m <- rownames_to_column(transpose_m, var="Year") 
transpose_f <- rownames_to_column(transpose_f, var="Year")

acct_owner_by_gender <- merge(x = transpose_m, y = transpose_f, by = "Year", all.x = TRUE)
acct_owner_by_gender <- rename(acct_owner_by_gender, "United_States" = 7)
head(acct_owner_by_gender)
##   Year Brazil_m India_m United_States_m Brazil India United_States
## 1 2014    71.69   62.76           92.36  64.77 43.13         94.80
## 2 2017    72.85   83.01           93.57  67.51 76.64         92.69
## 3 2021    87.05   77.51           93.09  80.87 77.55         96.79
gfg_plot <- ggplot(acct_owner_by_gender, aes(x=year)) +  
    geom_line(aes(y = India), color = "black") +
    geom_line(aes(y = India_m), color = "red") +
    geom_line(aes(y = Brazil), color = "green") +
    geom_line(aes(y = Brazil_m), color = "blue") +
    geom_line(aes(y = United_States), color = "purple") +
    geom_line(aes(y = United_States_m), color = "violet") 
gfg_plot

#PART 1 - CLEANING UP THE FINAL PLOT

gfg_plot <- ggplot(acct_owner_by_gender, aes(x = year)) +  
  geom_line(aes(y = India), color = "black") +
  geom_line(aes(y = India_m), color = "red") +
  geom_line(aes(y = Brazil), color = "green") +
  geom_line(aes(y = Brazil_m), color = "blue") +
  geom_line(aes(y = United_States), color = "purple") +
  geom_line(aes(y = United_States_m), color = "violet") +
  labs(y = "Percentage Ownership")

gfg_plot

#PART 2 - DRAWING CONCLUSIONS

###GENERAL OBSERVATION

####Based on the graph provided , it can be observed that the percentage 
####ownership in the United States is much more than both of India and Brazil.
####In the graph it can be seen that India starts of at the lowest , however
####it sees immense growth whilst still remaning below that of Brazil

###UNITED STATES

####Based on the graph provided , it can be observed that in the United States,
####both female and male ownership have remained relatively equal over time, and
####and above the 90% mark over the period of 2014-2020.

###INDIA

####Based on the graph provided , it can be observed that in India , the male
####population had a relatively higher percentage ownership than that of female
####population during the priod of 2014-2017 . However , in the period of 2017-
####2021 , both the female and male population had almost the same percentage 
####ownership , leveling at about 85%.

###BRAZIL

####Based on the graph provided , it can be observed that in Brazil , 
####both female and male population have seen an increase in the percentage 
####ownership how the female ownership is still below that of male percentage
####ownership.
 ###PART 3 - CHERRY PICKING

####In the context of India, it can be observed that there's a trend of 
####increasing percentage ownerships when the previous year is excluded from 
####consideration. In the case of Brazil, there's a consistent rise in
####percentage ownerships over time, unaffected by disregarding any specific 
####year.Conversely, in the US, the percentage ownerships exhibit minimal 
####fluctuation, maintaining a relatively constant pattern. Additionally,
####regardless of gender, the trends in ownership percentages remain consistent.
###PART 4 - SUMMARIZING THE DATA YOURSELF

setwd("/Users/dpatel78/Desktop")

primary_ed <- read.csv(file = "first_file.csv")
primary_ed <- primary_ed %>%
  filter(Country.Name == "Algeria" | Country.Name == "Argentina" | Country.Name == "Belgium" | Country.Name == "France" | Country.Name == "Germany") 

primary_ed <- primary_ed[rel_col] %>% 
  rename("2014" = 2, "2017" = 3, "2021" = 4)

transpose_p <- data.frame(t(primary_ed[-1]))
colnames(transpose_p) <- primary_ed[, 1]

transpose_p$Algeria = as.numeric(as.character(transpose_p$Algeria)) 
transpose_p$Argentina = as.numeric(as.character(transpose_p$Argentina))
transpose_p$Belgium = as.numeric(as.character(transpose_p$Belgium))
transpose_p$France = as.numeric(as.character(transpose_p$France))
transpose_p$Germany  = as.numeric(as.character(transpose_p$Germany))

head(transpose_p)
##      Algeria Argentina Belgium France Germany
## 2014   55.32     48.90   97.85  97.26   98.80
## 2017   48.96     52.28   98.84  97.23   99.30
## 2021   46.23     79.69   99.28  99.76   99.97
transpose_p <- rename(transpose_p, "Algeria" = 1, "Argentina" = 2, "Belgium" = 3  , "France"=4 , "Germany"=5)

head(transpose_p)
##      Algeria Argentina Belgium France Germany
## 2014   55.32     48.90   97.85  97.26   98.80
## 2017   48.96     52.28   98.84  97.23   99.30
## 2021   46.23     79.69   99.28  99.76   99.97
secondary_ed <- read.csv(file = "spya.csv")
secondary_ed <- secondary_ed %>%
  filter(Country.Name == "Algeria" | Country.Name == "Argentina" | Country.Name == "Belgium" | Country.Name == "France" | Country.Name == "Germany") 

secondary_ed <- secondary_ed[rel_col] %>% 
  rename("2014" = 2, "2017" = 3, "2021" = 4)

transpose_s <- data.frame(t(secondary_ed[-1]))
colnames(transpose_s) <- secondary_ed[, 1]

transpose_s$Algeria = as.numeric(as.character(transpose_s$Algeria)) 
transpose_s$Argentina = as.numeric(as.character(transpose_s$Argentina))
transpose_s$Belgium = as.numeric(as.character(transpose_s$Belgium))
transpose_s$France = as.numeric(as.character(transpose_s$France))
transpose_s$Germany  = as.numeric(as.character(transpose_s$Germany))

head(transpose_s)
##      Algeria Argentina Belgium France Germany
## 2014   48.35     52.27  100.00  83.36   97.64
## 2017   38.95     43.05  100.00  79.82  100.00
## 2021   38.99     57.10   93.81  95.87  100.00
transpose_s <- rename(transpose_s, "Algeria_m" = 1, "Argentina_m" = 2, "Belgium_m" = 3  , "France_m"=4 , "Germany_m"=5)

head(transpose_s)
##      Algeria_m Argentina_m Belgium_m France_m Germany_m
## 2014     48.35       52.27    100.00    83.36     97.64
## 2017     38.95       43.05    100.00    79.82    100.00
## 2021     38.99       57.10     93.81    95.87    100.00
transpose_p <- rownames_to_column(transpose_p, var="Year") 
transpose_s <- rownames_to_column(transpose_s, var="Year")

acct_owner_by_ed_level <- merge(x = transpose_p, y = transpose_s, by = "Year", all.x = TRUE)
acct_owner_by_ed_level <- rename(acct_owner_by_ed_level, "Algeria_m" = 7)
head(acct_owner_by_ed_level)
##   Year Algeria Argentina Belgium France Germany Algeria_m Argentina_m Belgium_m
## 1 2014   55.32     48.90   97.85  97.26   98.80     48.35       52.27    100.00
## 2 2017   48.96     52.28   98.84  97.23   99.30     38.95       43.05    100.00
## 3 2021   46.23     79.69   99.28  99.76   99.97     38.99       57.10     93.81
##   France_m Germany_m
## 1    83.36     97.64
## 2    79.82    100.00
## 3    95.87    100.00
gfg_plot <- ggplot(acct_owner_by_ed_level, aes(x = Year)) +  
    geom_line(aes(y = Algeria), color = "darkorange3", group = 1) +
    geom_line(aes(y = Algeria_m), color = "darkorange2", group = 1) +
    geom_line(aes(y = Argentina), color = "darkorchid4", group = 1) +
    geom_line(aes(y = Argentina_m), color = "darkorchid3", group = 1) +
    geom_line(aes(y = Belgium), color = "deeppink4", group = 1) +
    geom_line(aes(y = Belgium_m), color = "deeppink3", group = 1) +
    geom_line(aes(y = France), color = "olivedrab4", group = 1) +
    geom_line(aes(y = France_m), color = "olivedrab3", group = 1) +
    geom_line(aes(y = Germany), color = "purple4", group = 1) +
    geom_line(aes(y = Germany_m), color = "purple3", group = 1) +
    labs(y = "Percentage Ownership")
gfg_plot

####GENERAL ANALYSIS
####The analysis reveals diverse trends in account ownership across countries 
####and education levels. Algeria experiences a concerning decline in ownership, 
####particularly pronounced in primary education, highlighting the need for 
####intervention. Argentina shows a significant increase in ownership, notably
####in secondary education, suggesting successful accessibility efforts. Belgium
####presents an unusual pattern where secondary education starts lower than
####primary education in ownership, with primary education showing a slight 
####decline over time while secondary education steadily rises. France and 
####Germany both exhibit consistent growth in ownership across primary and 
####secondary education, indicating stable financial inclusion efforts. These
####insights underscore the importance of tailored strategies to address varying
####levels of financial inclusion globally.
####ANALYSIS BY COUNTRY 

#####ALGERIA
######For Algeria , we can see that the account ownership is rather less since
######it is less than 55% for both secondary and primary education . A rather
#####observation is than instead of increasing the account ownership decreases
#####overtime rather an increase , and the decrease is rather steep decreasing 
#####from about 47% to about 39% for primary education .

gfg_plot <- ggplot(acct_owner_by_ed_level, aes(x = Year)) +  
    geom_line(aes(y = Algeria), color = "darkorange3", group = 1) +
    geom_line(aes(y = Algeria_m), color = "darkorange2", group = 1) +
    labs(y = "Percentage Ownership")
gfg_plot

#####ARGENTINA
######For Argentina , we can see that the account ownership starts at 50% , 
######however from 2017 , we can see a drastic increase in the ownership for 
######both secondary and primary education , with secondary education reaching
######80% , and primary education reaching just about 58% percent.

gfg_plot <- ggplot(acct_owner_by_ed_level, aes(x = Year)) +  
    geom_line(aes(y = Argentina), color = "darkorchid4", group = 1) +
    geom_line(aes(y = Argentina_m), color = "darkorchid3", group = 1) +
    labs(y = "Percentage Ownership")
gfg_plot

#####BELGIUM
######For Belgium , we can see a strang occurence where the secondary education
######starts of less than the primary education , and the account ownership for 
######primary education starting at 100% and then lowering down to about 94%, 
######whereas the secondary education increases at a steady rate from about 98%
######to nearly 99%.

gfg_plot <- ggplot(acct_owner_by_ed_level, aes(x = Year)) +  
    geom_line(aes(y = Belgium), color = "deeppink4", group = 1) +
    geom_line(aes(y = Belgium_m), color = "deeppink3", group = 1) +
    labs(y = "Percentage Ownership")
gfg_plot

#####FRANCE
#####For France ,we can see a that the account ownership for both secondary start
#####off from around 96% and steadily grow to about 100% , whereas primary 
#####education start off from  around 84% and drastically grow to about 96%.


gfg_plot <- ggplot(acct_owner_by_ed_level, aes(x = Year)) +  
     geom_line(aes(y = France), color = "olivedrab4", group = 1) +
    geom_line(aes(y = France_m), color = "olivedrab3", group = 1) +
    labs(y = "Percentage Ownership")
gfg_plot

####GERMANY
#####For Germany , we can see that account ownership for both primary and 
#####secondary education start off higher than other countries , where secondary
#####starts off from about 99% and reaches 100% steadily , whereas for primary
#####we see a drastic increase from about 97.5% to about 100%.

gfg_plot <- ggplot(acct_owner_by_ed_level, aes(x = Year)) +  
   geom_line(aes(y = Germany), color = "purple4", group = 1) +
    geom_line(aes(y = Germany_m), color = "purple3", group = 1) +
    labs(y = "Percentage Ownership")
gfg_plot