DATA607 Project 2

Dataset 1: Annual estimates of mean surface temperature change measured with respect to a baseline climatology

Analysis: i cleaned the data, transformed and calculated the mean statistic.

Conclusion: Based on this analysis, Luxemberg ,Estonia, Serbia,Belgium and latvia countries may be experiencing a more pronounced impact in terms of temperature change.

library(dplyr,warn.conflicts = FALSE)
library(tidyr,warn.conflicts = FALSE)
library(readr,warn.conflicts = FALSE)


#read the csv file on Climate_Indicators_Annual_Mean_Global_Surface_Temperature
load <- read.csv('https://raw.githubusercontent.com/datanerddhanya/DATA607/main/Indicator_3_1_Climate_Indicators_Annual_Mean_Global_Surface_Temperature_577579683071085080.csv',sep = ",", stringsAsFactors=FALSE, quote = "\"")

#parse the data into a dataframe
#load<- data.frame(load)

# the data is wide as teh years are in the columns. i would like to tidy the data by moving it into #rows.
load_pivot <- load  %>%
  pivot_longer(
     cols = !(ObjectId:CTS.Full.Descriptor) ,
     names_to = "Year", 
     values_to = "Mean.Surface.Temp.change" ,
    values_drop_na = TRUE
   ) 

#need to split the Year column to remove the X value in it 
load_clean <- load_pivot |> 
   separate_wider_delim(Year, delim = "X", names = c("Blank", "Year"))
  
# cleaning up Country column to remove text after comma
  extract_value <- function(x) {
  if (grepl(",", x)) {
    split_values <- strsplit(x, ",")[[1]]
    return(trimws(split_values[1]))
  } else {
    return(trimws(x))
  }
  }

# Apply the function to the entire column
load_clean$Country <- sapply(load_clean$Country, extract_value)


 
#Create an new data frame with the required columns
load_final <- load_clean[,c('ObjectId','Country','ISO3','Unit','Year','Mean.Surface.Temp.change')]
# transform(load_final, Mean.Surface.Temp.change = as.numeric(Mean.Surface.Temp.change))
# load_final$Mean.Surface.Temp.change = as.numeric(load_final$Mean.Surface.Temp.change)


#Calculate average climate change over all the years for a country
load_climate_change <- load_final %>%
 group_by(Country) %>%
#summarise(across(everything(), list(mean))) %>%
  summarise( Mean.Surface.Temp.change = mean(Mean.Surface.Temp.change)) %>%
#  summarise(.funs = mean,na.rm=T)          
arrange(desc(Mean.Surface.Temp.change))

head(load_climate_change)

## # A tibble: 6 × 2
##   Country    Mean.Surface.Temp.change
##   <chr>                         <dbl>
## 1 Luxembourg                     1.58
## 2 Estonia                        1.56
## 3 Serbia                         1.54
## 4 Belgium                        1.53
## 5 Latvia                         1.51
## 6 Belarus                        1.51

# calculate overall center and spread
mean = mean(load_climate_change$Mean.Surface.Temp.change)
sd= sd(load_climate_change$Mean.Surface.Temp.change)

#mean
head(mean)

## [1] 0.5820715

#standard deviation
head(sd)

## [1] 0.3223647