Resident session code
Wenlu Xu
2023-09-22
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── 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 errorsdata() ?msleep glimpse(msleep)
fruit <- tibble( name= c(“apple”,“banana”,“orange”), price = c(2.5,2.0,3.5), vitamin_c = c(20,45,250) ) fruit
Energy.df <- read_csv("global-data-on-sustainable-energy.csv", col_names = TRUE)## Rows: 3649 Columns: 21
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): Entity
## dbl (19): Year, Access to electricity (% of population), Access to clean fue...
## num (1): Density\n(P/Km2)
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.glimpse(Energy.df)## Rows: 3,649
## Columns: 21
## $ Entity <chr> "Af…
## $ Year <dbl> 200…
## $ `Access to electricity (% of population)` <dbl> 1.6…
## $ `Access to clean fuels for cooking` <dbl> 6.2…
## $ `Renewable-electricity-generating-capacity-per-capita` <dbl> 9.2…
## $ `Financial flows to developing countries (US $)` <dbl> 200…
## $ `Renewable energy share in the total final energy consumption (%)` <dbl> 44.…
## $ `Electricity from fossil fuels (TWh)` <dbl> 0.1…
## $ `Electricity from nuclear (TWh)` <dbl> 0, …
## $ `Electricity from renewables (TWh)` <dbl> 0.3…
## $ `Low-carbon electricity (% electricity)` <dbl> 65.…
## $ `Primary energy consumption per capita (kWh/person)` <dbl> 302…
## $ `Energy intensity level of primary energy (MJ/$2017 PPP GDP)` <dbl> 1.6…
## $ Value_co2_emissions_kt_by_country <dbl> 760…
## $ `Renewables (% equivalent primary energy)` <dbl> NA,…
## $ gdp_growth <dbl> NA,…
## $ gdp_per_capita <dbl> NA,…
## $ `Density\\n(P/Km2)` <dbl> 60,…
## $ `Land Area(Km2)` <dbl> 652…
## $ Latitude <dbl> 33.…
## $ Longitude <dbl> 67.…unique(Energy.df$Entity)## [1] "Afghanistan" "Albania"
## [3] "Algeria" "Angola"
## [5] "Antigua and Barbuda" "Argentina"
## [7] "Armenia" "Aruba"
## [9] "Australia" "Austria"
## [11] "Azerbaijan" "Bahamas"
## [13] "Bahrain" "Bangladesh"
## [15] "Barbados" "Belarus"
## [17] "Belgium" "Belize"
## [19] "Benin" "Bermuda"
## [21] "Bhutan" "Bosnia and Herzegovina"
## [23] "Botswana" "Brazil"
## [25] "Bulgaria" "Burkina Faso"
## [27] "Burundi" "Cambodia"
## [29] "Cameroon" "Canada"
## [31] "Cayman Islands" "Central African Republic"
## [33] "Chad" "Chile"
## [35] "China" "Colombia"
## [37] "Comoros" "Congo"
## [39] "Costa Rica" "Croatia"
## [41] "Cuba" "Cyprus"
## [43] "Czechia" "Denmark"
## [45] "Djibouti" "Dominica"
## [47] "Dominican Republic" "Ecuador"
## [49] "Egypt" "El Salvador"
## [51] "Equatorial Guinea" "Eritrea"
## [53] "Estonia" "Eswatini"
## [55] "Ethiopia" "Fiji"
## [57] "Finland" "France"
## [59] "French Guiana" "Gabon"
## [61] "Gambia" "Georgia"
## [63] "Germany" "Ghana"
## [65] "Greece" "Grenada"
## [67] "Guatemala" "Guinea"
## [69] "Guinea-Bissau" "Guyana"
## [71] "Haiti" "Honduras"
## [73] "Hungary" "Iceland"
## [75] "India" "Indonesia"
## [77] "Iraq" "Ireland"
## [79] "Israel" "Italy"
## [81] "Jamaica" "Japan"
## [83] "Jordan" "Kazakhstan"
## [85] "Kenya" "Kiribati"
## [87] "Kuwait" "Kyrgyzstan"
## [89] "Latvia" "Lebanon"
## [91] "Lesotho" "Liberia"
## [93] "Libya" "Lithuania"
## [95] "Luxembourg" "Madagascar"
## [97] "Malawi" "Malaysia"
## [99] "Maldives" "Mali"
## [101] "Malta" "Mauritania"
## [103] "Mauritius" "Mexico"
## [105] "Mongolia" "Montenegro"
## [107] "Morocco" "Mozambique"
## [109] "Myanmar" "Namibia"
## [111] "Nauru" "Nepal"
## [113] "Netherlands" "New Caledonia"
## [115] "New Zealand" "Nicaragua"
## [117] "Niger" "Nigeria"
## [119] "North Macedonia" "Norway"
## [121] "Oman" "Pakistan"
## [123] "Panama" "Papua New Guinea"
## [125] "Paraguay" "Peru"
## [127] "Philippines" "Poland"
## [129] "Portugal" "Puerto Rico"
## [131] "Qatar" "Romania"
## [133] "Rwanda" "Saint Kitts and Nevis"
## [135] "Saint Lucia" "Saint Vincent and the Grenadines"
## [137] "Samoa" "Sao Tome and Principe"
## [139] "Saudi Arabia" "Senegal"
## [141] "Serbia" "Seychelles"
## [143] "Sierra Leone" "Singapore"
## [145] "Slovakia" "Slovenia"
## [147] "Solomon Islands" "Somalia"
## [149] "South Africa" "South Sudan"
## [151] "Spain" "Sri Lanka"
## [153] "Sudan" "Suriname"
## [155] "Sweden" "Switzerland"
## [157] "Tajikistan" "Thailand"
## [159] "Togo" "Tonga"
## [161] "Trinidad and Tobago" "Tunisia"
## [163] "Turkey" "Turkmenistan"
## [165] "Tuvalu" "Uganda"
## [167] "Ukraine" "United Arab Emirates"
## [169] "United Kingdom" "United States"
## [171] "Uruguay" "Uzbekistan"
## [173] "Vanuatu" "Yemen"
## [175] "Zambia" "Zimbabwe"colSums(is.na(Energy.df))## Entity
## 0
## Year
## 0
## Access to electricity (% of population)
## 10
## Access to clean fuels for cooking
## 169
## Renewable-electricity-generating-capacity-per-capita
## 931
## Financial flows to developing countries (US $)
## 2089
## Renewable energy share in the total final energy consumption (%)
## 194
## Electricity from fossil fuels (TWh)
## 21
## Electricity from nuclear (TWh)
## 126
## Electricity from renewables (TWh)
## 21
## Low-carbon electricity (% electricity)
## 42
## Primary energy consumption per capita (kWh/person)
## 0
## Energy intensity level of primary energy (MJ/$2017 PPP GDP)
## 207
## Value_co2_emissions_kt_by_country
## 428
## Renewables (% equivalent primary energy)
## 2137
## gdp_growth
## 317
## gdp_per_capita
## 282
## Density\\n(P/Km2)
## 1
## Land Area(Km2)
## 1
## Latitude
## 1
## Longitude
## 1cnames <-colnames(Energy.df) %>%
str_replace_all( " ","_") %>%
str_replace_all( "\\\\","_") %>%
str_replace_all("\\%", "perc")
cnames## [1] "Entity"
## [2] "Year"
## [3] "Access_to_electricity_(perc_of_population)"
## [4] "Access_to_clean_fuels_for_cooking"
## [5] "Renewable-electricity-generating-capacity-per-capita"
## [6] "Financial_flows_to_developing_countries_(US_$)"
## [7] "Renewable_energy_share_in_the_total_final_energy_consumption_(perc)"
## [8] "Electricity_from_fossil_fuels_(TWh)"
## [9] "Electricity_from_nuclear_(TWh)"
## [10] "Electricity_from_renewables_(TWh)"
## [11] "Low-carbon_electricity_(perc_electricity)"
## [12] "Primary_energy_consumption_per_capita_(kWh/person)"
## [13] "Energy_intensity_level_of_primary_energy_(MJ/$2017_PPP_GDP)"
## [14] "Value_co2_emissions_kt_by_country"
## [15] "Renewables_(perc_equivalent_primary_energy)"
## [16] "gdp_growth"
## [17] "gdp_per_capita"
## [18] "Density_n(P/Km2)"
## [19] "Land_Area(Km2)"
## [20] "Latitude"
## [21] "Longitude"colnames(Energy.df) <-cnamesEnergy.df %>%
filter(Entity=="Saudi Arabia")## # A tibble: 21 × 21
## Entity Year Access_to_electricity_(perc_of_po…¹ Access_to_clean_fuel…²
## <chr> <dbl> <dbl> <dbl>
## 1 Saudi Arabia 2000 100 100
## 2 Saudi Arabia 2001 100 100
## 3 Saudi Arabia 2002 100 100
## 4 Saudi Arabia 2003 100 100
## 5 Saudi Arabia 2004 100 100
## 6 Saudi Arabia 2005 100 100
## 7 Saudi Arabia 2006 100 100
## 8 Saudi Arabia 2007 100 100
## 9 Saudi Arabia 2008 100 100
## 10 Saudi Arabia 2009 100 100
## # ℹ 11 more rows
## # ℹ abbreviated names: ¹`Access_to_electricity_(perc_of_population)`,
## # ²Access_to_clean_fuels_for_cooking
## # ℹ 17 more variables:
## # `Renewable-electricity-generating-capacity-per-capita` <dbl>,
## # `Financial_flows_to_developing_countries_(US_$)` <dbl>,
## # `Renewable_energy_share_in_the_total_final_energy_consumption_(perc)` <dbl>, …Energy.df %>%
filter(!is.na(`Low-carbon_electricity_(perc_electricity)`)) %>%
group_by(Entity) %>%
summarise(avg_perc_electricity = mean(`Low-carbon_electricity_(perc_electricity)`)) %>%
arrange(desc(avg_perc_electricity)) %>%
top_n(20) %>%
ggplot(aes(Entity, avg_perc_electricity))+
geom_bar(stat = "identity")+
coord_flip()## Selecting by avg_perc_electricity
Value_co2_emissions (metric tons per capita): Carbon dioxide emissions per person in metric tons.
co2 <- Energy.df %>%
filter(!is.na(`Value_co2_emissions_kt_by_country`)) %>%
group_by(Entity) %>%
summarise(avg_co2_emissions = mean(`Value_co2_emissions_kt_by_country`)) %>%
arrange(desc(avg_co2_emissions)) %>%
top_n(10)## Selecting by avg_co2_emissions ggplot(co2, aes(Entity, avg_co2_emissions))+
geom_bar(stat = "identity")+
coord_flip()
co22 <- Energy.df %>%
filter(!is.na(`Value_co2_emissions_kt_by_country`)) %>%
group_by(Entity) %>%
summarise(avg_co2_emissions = mean(`Value_co2_emissions_kt_by_country`)) %>%
arrange(desc(avg_co2_emissions))
ccname <- unique(co22$Entity)
Energy.df %>%
filter(!is.na(`Value_co2_emissions_kt_by_country`)) %>%
filter(Entity %in% ccname[1:2]) %>%
ggplot(aes(x=Year,y=Value_co2_emissions_kt_by_country,color=Entity))+
geom_line()
Energy.df %>%
filter(!is.na(`Value_co2_emissions_kt_by_country`)) %>%
filter(Entity %in% ccname[3:10]) %>%
ggplot(aes(x=Year,y=Value_co2_emissions_kt_by_country,color=Entity))+
geom_line()
Energy.df %>%
filter(!is.na(`Low-carbon_electricity_(perc_electricity)`)) %>%
filter(Entity %in% ccname[1:9]) %>%
ggplot(aes(x=Year,y=`Low-carbon_electricity_(perc_electricity)`,color=Entity))+
geom_line()
Energy.df %>%
filter(!is.na(`Low-carbon_electricity_(perc_electricity)`)) %>%
filter(Entity %in% ccname[10]) %>%
ggplot(aes(x=Year,y=`Low-carbon_electricity_(perc_electricity)`,color=Entity))+
geom_line()
library(gplots)##
## Attaching package: 'gplots'## The following object is masked from 'package:stats':
##
## lowessEnergy.df %>%
filter(!is.na(`Low-carbon_electricity_(perc_electricity)`)) %>%
filter(Entity=="France") %>%
ggplot(aes(x=Year,y=`Low-carbon_electricity_(perc_electricity)`))+
geom_line()
cor_df <-Energy.df %>%
select(-Entity,-`Financial_flows_to_developing_countries_(US_$)`,-`Renewables_(perc_equivalent_primary_energy)`) %>%
na.omit()
heatmap.2(cor(cor_df), Rowv = FALSE, Colv = FALSE, dendrogram = "none",
cellnote = round(cor(cor_df),2),
notecol = "black", key = FALSE, trace = 'none', margins = c(15,10))
library(ggplot2)
library(reshape) # to generate input for the plot##
## Attaching package: 'reshape'## The following object is masked from 'package:lubridate':
##
## stamp## The following object is masked from 'package:dplyr':
##
## rename## The following objects are masked from 'package:tidyr':
##
## expand, smithscor.mat <- round(cor(cor_df),2) # rounded correlation matrix
melted.cor.mat <- melt(cor.mat)## Warning in type.convert.default(X[[i]], ...): 'as.is' should be specified by
## the caller; using TRUE
## Warning in type.convert.default(X[[i]], ...): 'as.is' should be specified by
## the caller; using TRUEggplot(melted.cor.mat, aes(x = X1, y = X2, fill = value)) +
geom_tile()+
geom_text(aes(x = X1, y = X2, label = value))+
theme(axis.text.x = element_text(angle=90, vjust = 0.5, hjust=1))
melted.cor.mat %>%
filter(X1=="Value_co2_emissions_kt_by_country") %>%
arrange(desc(value)) # %>%## X1
## 1 Value_co2_emissions_kt_by_country
## 2 Value_co2_emissions_kt_by_country
## 3 Value_co2_emissions_kt_by_country
## 4 Value_co2_emissions_kt_by_country
## 5 Value_co2_emissions_kt_by_country
## 6 Value_co2_emissions_kt_by_country
## 7 Value_co2_emissions_kt_by_country
## 8 Value_co2_emissions_kt_by_country
## 9 Value_co2_emissions_kt_by_country
## 10 Value_co2_emissions_kt_by_country
## 11 Value_co2_emissions_kt_by_country
## 12 Value_co2_emissions_kt_by_country
## 13 Value_co2_emissions_kt_by_country
## 14 Value_co2_emissions_kt_by_country
## 15 Value_co2_emissions_kt_by_country
## 16 Value_co2_emissions_kt_by_country
## 17 Value_co2_emissions_kt_by_country
## 18 Value_co2_emissions_kt_by_country
## X2 value
## 1 Value_co2_emissions_kt_by_country 1.00
## 2 Electricity_from_fossil_fuels_(TWh) 0.99
## 3 Electricity_from_renewables_(TWh) 0.90
## 4 Electricity_from_nuclear_(TWh) 0.89
## 5 Land_Area(Km2) 0.70
## 6 Latitude 0.15
## 7 Longitude 0.13
## 8 Access_to_electricity_(perc_of_population) 0.12
## 9 gdp_growth 0.08
## 10 Energy_intensity_level_of_primary_energy_(MJ/$2017_PPP_GDP) 0.06
## 11 Access_to_clean_fuels_for_cooking 0.05
## 12 Renewable-electricity-generating-capacity-per-capita 0.05
## 13 Year 0.04
## 14 Primary_energy_consumption_per_capita_(kWh/person) 0.02
## 15 gdp_per_capita 0.01
## 16 Density_n(P/Km2) -0.01
## 17 Low-carbon_electricity_(perc_electricity) -0.06
## 18 Renewable_energy_share_in_the_total_final_energy_consumption_(perc) -0.11 # top_n(5)unique(Energy.df$Year)## [1] 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014
## [16] 2015 2016 2017 2018 2019 2020