```{r} rm(list = ls()) library(rio)
#Data_energy
```{r}
data1= import("Refined petroleum products - production.csv")
data2= import("Energy consumption per capita.csv")
data3= import("Electricity - installed generating capacity.csv")
data4= import("Carbon dioxide emissions.csv"){r} selected_data1 <- data1[, c(1, 3)] selected_data2 <- data2[, c(1, 3)] selected_data3 <- data3[, c(1, 3)] selected_data4 <- data4[, c(1, 3)]
{r} names(selected_data1) names (selected_data2) names (selected_data3) names(selected_data4)
```{r} names(selected_data1)[names(selected_data1) == “bbl/day”] <-
“day” names(selected_data2)[names(selected_data2) == “Btu/person”] <-
“byperson” names(selected_data4)[names(selected_data4) == “metric tonnes
of CO2”] <- “carbono”
#Data_communications
```{r}
data5= import("Telephones - mobile cellular.csv")
data6= import("Telephones - fixed lines.csv")
data7= import("Broadband - fixed subscriptions.csv")```{r} selected_data5 <- data5[, c(1, 3)] selected_data6 <- data6[, c(1, 3)] selected_data7 <- data7[, c(1, 3)]
```{r}
names(selected_data5)
names (selected_data6)
names (selected_data7){r} names(selected_data5)[names(selected_data5) == "value"] <- "value_2022" names(selected_data6)[names(selected_data6) == "value"] <- "value_202x" names(selected_data7)[names(selected_data7) == "value"] <- "value_2020"
{r} names(selected_data5) names (selected_data6) names (selected_data7)
#Data_economy
{r} data8= import("Inflation rate (consumer prices).csv") data9= import("Youth unemployment rate (ages 15-24).csv") data10= import("Public debt.csv") data11= import("Debt - external.csv")
{r} selected_data8 <- data8[, c(1, 3)] selected_data9 <- data9[, c(1, 3)] selected_data10 <- data10[, c(1, 3)] selected_data11 <- data11[, c(1, 3)]
{r} names(selected_data8) names (selected_data9) names (selected_data10) names (selected_data11)
{r} names(selected_data8)[names(selected_data8) == "%"] <- "porcentaje1" names(selected_data9)[names(selected_data9) == "%"] <- "porcentaje2" names(selected_data10)[names(selected_data10) == "% of GDP"] <- "GDP" names(selected_data11)[names(selected_data11) == "value"] <- "monto"
{r} str(selected_data11)
{r} selected_data1=selected_data1[complete.cases(selected_data1),] selected_data2=selected_data2[complete.cases(selected_data2),] selected_data3=selected_data3[complete.cases(selected_data3),] selected_data4=selected_data4[complete.cases(selected_data4),] selected_data5=selected_data5[complete.cases(selected_data5),] selected_data6=selected_data6[complete.cases(selected_data6),] selected_data7=selected_data7[complete.cases(selected_data7),] selected_data8=selected_data8[complete.cases(selected_data8),] selected_data9=selected_data9[complete.cases(selected_data9),] selected_data10=selected_data10[complete.cases(selected_data10),] selected_data11=selected_data11[complete.cases(selected_data11),]
{r} library(dplyr)
{r} energy_data <- selected_data1 %>% full_join(selected_data2, by = "name") %>% full_join(selected_data3, by = "name") %>% full_join(selected_data4, by = "name")
{r} communications_data <- selected_data5 %>% full_join(selected_data6, by = "name") %>% full_join(selected_data7, by = "name")
{r} economy_data <- selected_data8 %>% full_join(selected_data9, by = "name") %>% full_join(selected_data10, by = "name") %>% full_join(selected_data11, by = "name")
{r} data_real <- energy_data %>% full_join(communications_data, by = "name") %>% full_join(economy_data, by = "name")
{r} names(data_real)
{r} str(data_real)
{r} data_real$day <- as.numeric(gsub("\\$|,", "", data_real$day), na.rm = TRUE)
```{r} data_real\(byperson <- as.numeric(gsub("\\\)|,“,”“, data_real\(byperson), na.rm = TRUE) data_real\)kW <- as.numeric(gsub(”\\(|,", "", data_real\)kW), na.rm = TRUE) data_real\(carbono <- as.numeric(gsub("\\\)|,“,”“, data_real\(carbono), na.rm = TRUE) data_real\)value_2022 <- as.numeric(gsub(”\\(|,", "", data_real\)value_2022), na.rm = TRUE)
data_real\(value_202x <- as.numeric(gsub("\\\)|,“,”“, data_real\(value_202x), na.rm = TRUE) data_real\)value_2020 <- as.numeric(gsub(”\\(|,", "", data_real\)value_2020), na.rm = TRUE) data_real\(porcentaje1 <- as.numeric(gsub("\\\)|,“,”“, data_real$porcentaje1), na.rm = TRUE)
data_real\(monto <- as.numeric(gsub("\\\)|,“,”“, data_real$monto), na.rm = TRUE)
```{r}
data_real$byperson <- format(data_real$byperson, decimal.mark = ".", big.mark = ",", scientific = FALSE)
data_real$kW <- format(data_real$kW, decimal.mark = ".", big.mark = ",", scientific = FALSE)
data_real$carbono <- format(data_real$carbono, decimal.mark = ".", big.mark = ",", scientific = FALSE)
data_real$value_2022 <- format(data_real$value_2022, decimal.mark = ".", big.mark = ",", scientific = FALSE)
data_real$value_202x <- format(data_real$value_202x, decimal.mark = ".", big.mark = ",", scientific = FALSE)
data_real$value_2020 <- format(data_real$value_2020, decimal.mark = ".", big.mark = ",", scientific = FALSE)
data_real$porcentaje1 <- format(data_real$porcentaje1, decimal.mark = ".", big.mark = ",", scientific = FALSE)
data_real$monto <- format(data_real$monto, decimal.mark = ".", big.mark = ",", scientific = FALSE)