data_explore
YiranZHA
2022-11-09
glimpse(energy_co2_updated)## Rows: 26,136
## Columns: 45
## $ country <chr> …
## $ year <dbl> …
## $ iso3_country <chr> …
## $ sector_detail <chr> …
## $ energy_price_flow_detail <chr> …
## $ high_sulphur_fuel_oil_tonne <dbl> …
## $ low_sulphur_fuel_oil_tonne <dbl> …
## $ light_fuel_oil_1000_litres <dbl> …
## $ automotive_diesel_litre <dbl> …
## $ premium_unleaded_98_ron_litre <dbl> …
## $ premium_unleaded_95_ron_litre <dbl> …
## $ regular_unleaded_gasoline_litre <dbl> …
## $ premium_leaded_gasoline_litre <dbl> …
## $ regular_leaded_gasoline_litre <dbl> …
## $ liquefied_petroleum_gas_litre <dbl> …
## $ natural_gas_m_wh <dbl> …
## $ steam_coal_tonne <dbl> …
## $ coking_coal_tonne <dbl> …
## $ electricity_m_wh <dbl> …
## $ consumer_price_index <dbl> …
## $ cpi_energy <dbl> …
## $ producer_price_index <dbl> …
## $ purchasing_power_parities <dbl> …
## $ u_s_dollar_exchange_rate <dbl> …
## $ group_type <chr> …
## $ advanced_economies <dbl> …
## $ advanced_g20 <dbl> …
## $ emerging_g20 <dbl> …
## $ emerging_market_and_middle_income_africa <dbl> …
## $ emerging_market_and_middle_income_asia <dbl> …
## $ emerging_market_and_middle_income_europe <dbl> …
## $ emerging_market_and_middle_income_latin_america <dbl> …
## $ emerging_market_and_middle_income_middle_east_north_africa_and_pakistan <dbl> …
## $ emerging_market_economies <dbl> …
## $ euro_area <dbl> …
## $ g20 <dbl> …
## $ g7 <dbl> …
## $ low_income_developing_asia <dbl> …
## $ low_income_developing_countries <dbl> …
## $ low_income_developing_latin_america <dbl> …
## $ low_income_developing_others <dbl> …
## $ low_income_developing_sub_saharan_africa <dbl> …
## $ low_income_oil_producers <dbl> …
## $ oil_producers <dbl> …
## $ co2_per_capital <dbl> …glimpse(energy_co2_2)## Rows: 365,904
## Columns: 33
## $ country <chr> …
## $ year <dbl> …
## $ iso3_country <chr> …
## $ product_detail <chr> …
## $ sector_detail <chr> …
## $ energy_price_flow_detail <chr> …
## $ energy_price_value <dbl> …
## $ consumer_price_index <dbl> …
## $ cpi_energy <dbl> …
## $ producer_price_index <dbl> …
## $ purchasing_power_parities <dbl> …
## $ u_s_dollar_exchange_rate <dbl> …
## $ group_type <chr> …
## $ advanced_economies <dbl> …
## $ advanced_g20 <dbl> …
## $ emerging_g20 <dbl> …
## $ emerging_market_and_middle_income_africa <dbl> …
## $ emerging_market_and_middle_income_asia <dbl> …
## $ emerging_market_and_middle_income_europe <dbl> …
## $ emerging_market_and_middle_income_latin_america <dbl> …
## $ emerging_market_and_middle_income_middle_east_north_africa_and_pakistan <dbl> …
## $ emerging_market_economies <dbl> …
## $ euro_area <dbl> …
## $ g20 <dbl> …
## $ g7 <dbl> …
## $ low_income_developing_asia <dbl> …
## $ low_income_developing_countries <dbl> …
## $ low_income_developing_latin_america <dbl> …
## $ low_income_developing_others <dbl> …
## $ low_income_developing_sub_saharan_africa <dbl> …
## $ low_income_oil_producers <dbl> …
## $ oil_producers <dbl> …
## $ co2_per_capital <dbl> …energy_co2_2 %>%
count(year, sort = TRUE) %>%
arrange(desc(year))## # A tibble: 44 × 2
## year n
## <dbl> <int>
## 1 2021 8316
## 2 2020 8316
## 3 2019 8316
## 4 2018 8316
## 5 2017 8316
## 6 2016 8316
## 7 2015 8316
## 8 2014 8316
## 9 2013 8316
## 10 2012 8316
## # … with 34 more rowsenergy_co2_updated %>%
count(year, sort = TRUE) %>%
arrange(desc(year))## # A tibble: 44 × 2
## year n
## <dbl> <int>
## 1 2021 594
## 2 2020 594
## 3 2019 594
## 4 2018 594
## 5 2017 594
## 6 2016 594
## 7 2015 594
## 8 2014 594
## 9 2013 594
## 10 2012 594
## # … with 34 more rowsunique(energy_co2_2$product_detail)## [1] "Liquefied petroleum gas (litre)" "Coking coal (tonne)"
## [3] "Regular unleaded gasoline (litre)" "Premium leaded gasoline (litre)"
## [5] "Steam coal (tonne)" "Light fuel oil (1000 litres)"
## [7] "Natural gas (MWh)" "Regular leaded gasoline (litre)"
## [9] "High sulphur fuel oil (tonne)" "Automotive diesel (litre)"
## [11] "Premium unleaded 95 RON (litre)" "Electricity (MWh)"
## [13] "Premium unleaded 98 RON (litre)" "Low sulphur fuel oil (tonne)"unique(energy_co2_2$sector_detail)## [1] "Households" "Electricity generation" "Industry"unique(energy_co2_2$energy_price_flow_detail)## [1] "Total tax (USD/unit)" "Total price (USD/unit)"
## [3] "Total price (USD/unit using PPP)" "Total tax (USD/unit using PPP)"
## [5] "Total tax (USD/toe NCV)" "Total price (USD/toe NCV)"#Descriptive ##Energy Price ###Adcanced Economies repeat this for all
energy_co2_advanced_2000 <- energy_co2_2 %>%
filter(year >= 2000) %>%
filter(advanced_g20 == 1) %>%
#filter(sector_detail == "Industry") %>%
filter(energy_price_flow_detail == "Total price (USD/unit)") %>%
filter(product_detail == "Liquefied petroleum gas (litre)") %>%
group_by(country)
ggplot(energy_co2_advanced_2000,
aes(x = year, y = energy_price_value)
) + #why the color is not working here
geom_point(aes(color = country)) +
geom_smooth(method = lm, level = 0.99) +
#https://www.r-bloggers.com/2021/09/draw-a-trend-line-using-ggplot-quick-guide/
facet_grid(sector_detail ~.)## `geom_smooth()` using formula 'y ~ x'
energy_co2_advanced_economy_2000 <- energy_co2_2 %>%
filter(year >= 2000) %>%
filter(advanced_g20 == 1) %>%
#filter(sector_detail == "Industry") %>%
pivot_wider(names_from = energy_price_flow_detail,
values_from = energy_price_value) %>%
#filter(energy_price_flow_detail == "Total price (USD/unit)") %>%
filter(product_detail == "Liquefied petroleum gas (litre)") %>%
janitor::clean_names() %>%
group_by(country)
ggplot(energy_co2_advanced_economy_2000,
aes(x = year)) +
geom_point(aes(y = total_price_usd_unit, color = country)) +
geom_line(aes(y = total_tax_usd_unit, color = country)) +
scale_y_continuous(limits = c(0,1.25),name = "Total price (USD/unit)",
sec.axis = sec_axis(~.*0.1,
name = "Total tax (USD/unit)")) +
facet_grid(sector_detail ~.)
#https://r-graph-gallery.com/line-chart-dual-Y-axis-ggplot2.html##CO2 emission
ggplot(energy_co2_advanced_2000,
aes(x = year, y = co2_per_capital)
) + #why the color is not working here
geom_point(aes(color = country)) +
geom_smooth(method = lm, level = 0.99) ## `geom_smooth()` using formula 'y ~ x'
#https://www.r-bloggers.com/2021/09/draw-a-trend-line-using-ggplot-quick-guide/#Interaction
energy_co2_g20_2000 <- energy_co2_2 %>%
drop_na(energy_price_value) %>%
drop_na(co2_per_capital)%>%
filter(year == 2019) %>%
filter(g20 == 1 ) %>%
#filter(sector_detail == "Industry") %>%
filter(energy_price_flow_detail == c("Total price (USD/unit)", "Total tax (USD/unit)")) %>%
#filter(product_detail == "Liquefied petroleum gas (litre)") %>%
pivot_wider(names_from = energy_price_flow_detail,
values_from = energy_price_value) %>%
janitor::clean_names() %>%
group_by(country)
#view(energy_co2_g20_2000)
energy_co2_g20_2000 %>%
ggplot(aes(axis1 = product_detail,
axis2 = total_tax_usd_unit,
axis3 = total_price_usd_unit,
y = co2_per_capital))+
geom_alluvium(aes(fill = country)) +
geom_stratum() 
#regression to be added
#test other variables#Prediction time series - to be added