# Instalar plotly si aún no está instalado
if (!requireNamespace("plotly", quietly = TRUE)) {
install.packages("plotly")
}
# Instalación de librerías
#install.packages("ggplot2")
#install.packages("reshape2")
##install.packages("dplyr")
#install.packages("data.table")
# Carga de librerías
library(ggplot2)
library(reshape2)
library(dplyr)
##
## Adjuntando el paquete: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(data.table)
##
## Adjuntando el paquete: 'data.table'
## The following objects are masked from 'package:dplyr':
##
## between, first, last
## The following objects are masked from 'package:reshape2':
##
## dcast, melt
# Lectura del archivo CSV
energia_sus <- fread("global_data_sustainable_energy.csv")
# Visualización de los primeros y últimos 5 datos
head(energia_sus)
## Entity Year Access to electricity (% of population)
## <char> <int> <num>
## 1: Afghanistan 2000 1.613591
## 2: Afghanistan 2001 4.074574
## 3: Afghanistan 2002 9.409158
## 4: Afghanistan 2003 14.738506
## 5: Afghanistan 2004 20.064968
## 6: Afghanistan 2005 25.390894
## Access to clean fuels for cooking
## <num>
## 1: 6.2
## 2: 7.2
## 3: 8.2
## 4: 9.5
## 5: 10.9
## 6: 12.2
## Renewable-electricity-generating-capacity-per-capita
## <num>
## 1: 9.22
## 2: 8.86
## 3: 8.47
## 4: 8.09
## 5: 7.75
## 6: 7.51
## Financial flows to developing countries (US $)
## <i64>
## 1: 20000
## 2: 130000
## 3: 3950000
## 4: 25970000
## 5: <NA>
## 6: 9830000
## Renewable energy share in the total final energy consumption (%)
## <num>
## 1: 44.99
## 2: 45.60
## 3: 37.83
## 4: 36.66
## 5: 44.24
## 6: 33.88
## Electricity from fossil fuels (TWh) Electricity from nuclear (TWh)
## <num> <num>
## 1: 0.16 0
## 2: 0.09 0
## 3: 0.13 0
## 4: 0.31 0
## 5: 0.33 0
## 6: 0.34 0
## Electricity from renewables (TWh) Low-carbon electricity (% electricity)
## <num> <num>
## 1: 0.31 65.95744
## 2: 0.50 84.74577
## 3: 0.56 81.15942
## 4: 0.63 67.02128
## 5: 0.56 62.92135
## 6: 0.59 63.44086
## Primary energy consumption per capita (kWh/person)
## <num>
## 1: 302.5948
## 2: 236.8919
## 3: 210.8622
## 4: 229.9682
## 5: 204.2312
## 6: 252.0691
## Energy intensity level of primary energy (MJ/$2017 PPP GDP)
## <num>
## 1: 1.64
## 2: 1.74
## 3: 1.40
## 4: 1.40
## 5: 1.20
## 6: 1.41
## Value_co2_emissions_kt_by_country Renewables (% equivalent primary energy)
## <num> <num>
## 1: 760 NA
## 2: 730 NA
## 3: 1030 NA
## 4: 1220 NA
## 5: 1030 NA
## 6: 1550 NA
## gdp_growth gdp_per_capita Density\\n(P/Km2) Land Area(Km2) Latitude
## <num> <num> <char> <int> <num>
## 1: NA NA 60 652230 33.93911
## 2: NA NA 60 652230 33.93911
## 3: NA 179.4266 60 652230 33.93911
## 4: 8.832278 190.6838 60 652230 33.93911
## 5: 1.414118 211.3821 60 652230 33.93911
## 6: 11.229715 242.0313 60 652230 33.93911
## Longitude
## <num>
## 1: 67.70995
## 2: 67.70995
## 3: 67.70995
## 4: 67.70995
## 5: 67.70995
## 6: 67.70995
tail(energia_sus)
## Entity Year Access to electricity (% of population)
## <char> <int> <num>
## 1: Zimbabwe 2015 33.70000
## 2: Zimbabwe 2016 42.56173
## 3: Zimbabwe 2017 44.17863
## 4: Zimbabwe 2018 45.57265
## 5: Zimbabwe 2019 46.78148
## 6: Zimbabwe 2020 52.74767
## Access to clean fuels for cooking
## <num>
## 1: 29.5
## 2: 29.8
## 3: 29.8
## 4: 29.9
## 5: 30.1
## 6: 30.4
## Renewable-electricity-generating-capacity-per-capita
## <num>
## 1: 63.54
## 2: 62.88
## 3: 62.33
## 4: 82.53
## 5: 81.40
## 6: 80.61
## Financial flows to developing countries (US $)
## <i64>
## 1: <NA>
## 2: 30000
## 3: 5570000
## 4: 10000
## 5: 250000
## 6: 30000
## Renewable energy share in the total final energy consumption (%)
## <num>
## 1: 80.82
## 2: 81.90
## 3: 82.46
## 4: 80.23
## 5: 81.50
## 6: 81.90
## Electricity from fossil fuels (TWh) Electricity from nuclear (TWh)
## <num> <num>
## 1: 4.02 0
## 2: 3.50 0
## 3: 3.05 0
## 4: 3.73 0
## 5: 3.66 0
## 6: 3.40 0
## Electricity from renewables (TWh) Low-carbon electricity (% electricity)
## <num> <num>
## 1: 5.37 57.18850
## 2: 3.32 48.68035
## 3: 4.30 58.50341
## 4: 5.46 59.41241
## 5: 4.58 55.58253
## 6: 4.19 55.20422
## Primary energy consumption per capita (kWh/person)
## <num>
## 1: 3860.920
## 2: 3227.680
## 3: 3068.012
## 4: 3441.986
## 5: 3003.655
## 6: 2680.132
## Energy intensity level of primary energy (MJ/$2017 PPP GDP)
## <num>
## 1: 10.36
## 2: 10.00
## 3: 9.51
## 4: 9.83
## 5: 10.47
## 6: 10.00
## Value_co2_emissions_kt_by_country Renewables (% equivalent primary energy)
## <num> <num>
## 1: 12430 NA
## 2: 11020 NA
## 3: 10340 NA
## 4: 12380 NA
## 5: 11760 NA
## 6: NA NA
## gdp_growth gdp_per_capita Density\\n(P/Km2) Land Area(Km2) Latitude
## <num> <num> <char> <int> <num>
## 1: 1.7798727 1445.070 38 390757 -19.01544
## 2: 0.7558693 1464.589 38 390757 -19.01544
## 3: 4.7094922 1235.189 38 390757 -19.01544
## 4: 4.8242105 1254.642 38 390757 -19.01544
## 5: -6.1442363 1316.741 38 390757 -19.01544
## 6: -6.2487482 1214.510 38 390757 -19.01544
## Longitude
## <num>
## 1: 29.15486
## 2: 29.15486
## 3: 29.15486
## 4: 29.15486
## 5: 29.15486
## 6: 29.15486
# Información de la base de datos
str(energia_sus)
## Classes 'data.table' and 'data.frame': 3649 obs. of 21 variables:
## $ Entity : chr "Afghanistan" "Afghanistan" "Afghanistan" "Afghanistan" ...
## $ Year : int 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 ...
## $ Access to electricity (% of population) : num 1.61 4.07 9.41 14.74 20.06 ...
## $ Access to clean fuels for cooking : num 6.2 7.2 8.2 9.5 10.9 ...
## $ Renewable-electricity-generating-capacity-per-capita : num 9.22 8.86 8.47 8.09 7.75 7.51 7.4 7.25 7.49 7.5 ...
## $ Financial flows to developing countries (US $) :integer64 20000 130000 3950000 25970000 NA 9830000 10620000 15750000 ...
## $ Renewable energy share in the total final energy consumption (%): num 45 45.6 37.8 36.7 44.2 ...
## $ Electricity from fossil fuels (TWh) : num 0.16 0.09 0.13 0.31 0.33 0.34 0.2 0.2 0.19 0.16 ...
## $ Electricity from nuclear (TWh) : num 0 0 0 0 0 0 0 0 0 0 ...
## $ Electricity from renewables (TWh) : num 0.31 0.5 0.56 0.63 0.56 0.59 0.64 0.75 0.54 0.78 ...
## $ Low-carbon electricity (% electricity) : num 66 84.7 81.2 67 62.9 ...
## $ Primary energy consumption per capita (kWh/person) : num 303 237 211 230 204 ...
## $ Energy intensity level of primary energy (MJ/$2017 PPP GDP) : num 1.64 1.74 1.4 1.4 1.2 1.41 1.5 1.53 1.94 2.25 ...
## $ Value_co2_emissions_kt_by_country : num 760 730 1030 1220 1030 ...
## $ Renewables (% equivalent primary energy) : num NA NA NA NA NA NA NA NA NA NA ...
## $ gdp_growth : num NA NA NA 8.83 1.41 ...
## $ gdp_per_capita : num NA NA 179 191 211 ...
## $ Density\n(P/Km2) : chr "60" "60" "60" "60" ...
## $ Land Area(Km2) : int 652230 652230 652230 652230 652230 652230 652230 652230 652230 652230 ...
## $ Latitude : num 33.9 33.9 33.9 33.9 33.9 ...
## $ Longitude : num 67.7 67.7 67.7 67.7 67.7 ...
## - attr(*, ".internal.selfref")=<externalptr>
# Dimensión de la base de datos
dimensiones <- dim(energia_sus)
print(dimensiones)
## [1] 3649 21
# Estadísticas básicas: media, desviación estándar, min, max, percentiles (25, 50, 75)
summary(energia_sus)
## Entity Year Access to electricity (% of population)
## Length:3649 Min. :2000 Min. : 1.252
## Class :character 1st Qu.:2005 1st Qu.: 59.801
## Mode :character Median :2010 Median : 98.362
## Mean :2010 Mean : 78.934
## 3rd Qu.:2015 3rd Qu.:100.000
## Max. :2020 Max. :100.000
## NA's :10
## Access to clean fuels for cooking
## Min. : 0.00
## 1st Qu.: 23.18
## Median : 83.15
## Mean : 63.26
## 3rd Qu.:100.00
## Max. :100.00
## NA's :169
## Renewable-electricity-generating-capacity-per-capita
## Min. : 0.00
## 1st Qu.: 3.54
## Median : 32.91
## Mean : 113.14
## 3rd Qu.: 112.21
## Max. :3060.19
## NA's :931
## Financial flows to developing countries (US $)
## Min. : 0
## 1st Qu.: 260000
## Median : 5660000
## Mean : 94224000
## 3rd Qu.: 55290000
## Max. :5202310000
## NA's : 2089
## Renewable energy share in the total final energy consumption (%)
## Min. : 0.000
## 1st Qu.: 6.515
## Median :23.300
## Mean :32.638
## 3rd Qu.:55.245
## Max. :96.040
## NA's :194
## Electricity from fossil fuels (TWh) Electricity from nuclear (TWh)
## Min. : 0.00 Min. : 0.00
## 1st Qu.: 0.29 1st Qu.: 0.00
## Median : 2.97 Median : 0.00
## Mean : 70.36 Mean : 13.45
## 3rd Qu.: 26.84 3rd Qu.: 0.00
## Max. :5184.13 Max. :809.41
## NA's :21 NA's :126
## Electricity from renewables (TWh) Low-carbon electricity (% electricity)
## Min. : 0.00 Min. : 0.000
## 1st Qu.: 0.04 1st Qu.: 2.878
## Median : 1.47 Median : 27.865
## Mean : 23.97 Mean : 36.801
## 3rd Qu.: 9.60 3rd Qu.: 64.404
## Max. :2184.94 Max. :100.000
## NA's :21 NA's :42
## Primary energy consumption per capita (kWh/person)
## Min. : 0
## 1st Qu.: 3117
## Median : 13121
## Mean : 25744
## 3rd Qu.: 33893
## Max. :262586
##
## Energy intensity level of primary energy (MJ/$2017 PPP GDP)
## Min. : 0.110
## 1st Qu.: 3.170
## Median : 4.300
## Mean : 5.307
## 3rd Qu.: 6.027
## Max. :32.570
## NA's :207
## Value_co2_emissions_kt_by_country Renewables (% equivalent primary energy)
## Min. : 10 Min. : 0.000
## 1st Qu.: 2020 1st Qu.: 2.137
## Median : 10500 Median : 6.291
## Mean : 159866 Mean :11.987
## 3rd Qu.: 60580 3rd Qu.:16.842
## Max. :10707220 Max. :86.837
## NA's :428 NA's :2137
## gdp_growth gdp_per_capita Density\\n(P/Km2) Land Area(Km2)
## Min. :-62.076 Min. : 111.9 Length:3649 Min. : 21
## 1st Qu.: 1.383 1st Qu.: 1337.8 Class :character 1st Qu.: 25713
## Median : 3.560 Median : 4578.6 Mode :character Median : 117600
## Mean : 3.442 Mean : 13283.8 Mean : 633213
## 3rd Qu.: 5.830 3rd Qu.: 15768.6 3rd Qu.: 513120
## Max. :123.140 Max. :123514.2 Max. :9984670
## NA's :317 NA's :282 NA's :1
## Latitude Longitude
## Min. :-40.901 Min. :-175.20
## 1st Qu.: 3.203 1st Qu.: -11.78
## Median : 17.190 Median : 19.15
## Mean : 18.246 Mean : 14.82
## 3rd Qu.: 38.970 3rd Qu.: 46.20
## Max. : 64.963 Max. : 178.07
## NA's :1 NA's :1
# Conteo de valores NaN (NA en R) en todo el DataFrame
nan_counts <- sapply(energia_sus, function(x) sum(is.na(x)))
cat("Número de valores NaN por columna:\n")
## Número de valores NaN por columna:
print(nan_counts)
## 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)
## 0
## Land Area(Km2)
## 1
## Latitude
## 1
## Longitude
## 1
# Total de valores NaN en el DataFrame
total_nan <- sum(nan_counts)
cat("\nTotal de valores NaN en el DataFrame:", total_nan, "\n")
##
## Total de valores NaN en el DataFrame: 6977
# Nombres de las columnas
print(names(energia_sus))
## [1] "Entity"
## [2] "Year"
## [3] "Access to electricity (% 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 (%)"
## [8] "Electricity from fossil fuels (TWh)"
## [9] "Electricity from nuclear (TWh)"
## [10] "Electricity from renewables (TWh)"
## [11] "Low-carbon electricity (% 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 (% equivalent primary energy)"
## [16] "gdp_growth"
## [17] "gdp_per_capita"
## [18] "Density\\n(P/Km2)"
## [19] "Land Area(Km2)"
## [20] "Latitude"
## [21] "Longitude"
# Renombrar columnas
energia_sus <- energia_sus %>%
rename(CO2 = Value_co2_emissions_kt_by_country, Country = Entity)
# Seleccionar columnas de interés para el boxplot
variables <- c(
'Access to electricity (% of population)',
'Access to clean fuels for cooking',
'Renewable-electricity-generating-capacity-per-capita',
'Financial flows to developing countries (US $)',
'Renewable energy share in the total final energy consumption (%)',
'Electricity from fossil fuels (TWh)',
'Electricity from nuclear (TWh)',
'Electricity from renewables (TWh)',
'Low-carbon electricity (% electricity)',
'Primary energy consumption per capita (kWh/person)',
'Energy intensity level of primary energy (MJ/$2017 PPP GDP)',
'CO2',
'Renewables (% equivalent primary energy)',
'gdp_growth',
'gdp_per_capita',
'Land Area(Km2)'
)
# Filtrar las columnas seleccionadas
df_selected <- energia_sus %>% select(all_of(variables))
# Derretir el DataFrame para el gráfico de caja
df_melted <- melt(df_selected, variable.name = 'Variable', value.name = 'Value')
## Warning in melt.data.table(df_selected, variable.name = "Variable", value.name
## = "Value"): id.vars and measure.vars are internally guessed when both are
## 'NULL'. All non-numeric/integer/logical type columns are considered id.vars,
## which in this case are columns []. Consider providing at least one of 'id' or
## 'measure' vars in future.
## Warning in melt.data.table(df_selected, variable.name = "Variable", value.name
## = "Value"): 'measure.vars' [Access to electricity (% of population), Access to
## clean fuels for cooking, Renewable-electricity-generating-capacity-per-capita,
## Financial flows to developing countries (US $), ...] are not all of the same
## type. By order of hierarchy, the molten data value column will be of type
## 'double'. All measure variables not of type 'double' will be coerced too. Check
## DETAILS in ?melt.data.table for more on coercion.
library(ggplot2)
library(reshape2) # Para melt()
# Supongamos que tienes un data frame df_melted ya creado que contiene las columnas "Value" y "Variable"
# Crear el gráfico de caja
ggplot(df_melted, aes(x = Value, y = Variable)) +
geom_boxplot(outlier.colour = "red", outlier.size = 1, fill = "lightblue") +
geom_jitter(color = "black", size = 0.5, alpha = 0.5) +
labs(title = "Distribución de Variables de Energía y Desarrollo",
x = "Valores",
y = "Variables") +
theme_minimal()
## Warning: Removed 4886 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
## Warning: Removed 4886 rows containing missing values or values outside the scale range
## (`geom_point()`).
## **Boxplot Individual para la variable 'Financial flows to developing countries (US $)'**
# Filtrar la columna específica
df_financial_flows <- energia_sus[, "Financial flows to developing countries (US $)"]
# Cargar la librería
library(plotly)
##
## Adjuntando el paquete: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
# Crear el gráfico de caja
fig <- plot_ly(
data = df_financial_flows,
x = ~`Financial flows to developing countries (US $)`,
type = "box",
title = 'Distribución de los Flujos Financieros hacia los Países en Desarrollo (US $)',
xaxis = list(title = 'Flujos Financieros (US $)')
)
# Mostrar el gráfico
fig
## Warning: 'box' objects don't have these attributes: 'title'
## Valid attributes include:
## 'alignmentgroup', 'boxmean', 'boxpoints', 'customdata', 'customdatasrc', 'dx', 'dy', 'fillcolor', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'jitter', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'lowerfence', 'lowerfencesrc', 'marker', 'mean', 'meansrc', 'median', 'mediansrc', 'meta', 'metasrc', 'name', 'notched', 'notchspan', 'notchspansrc', 'notchwidth', 'offsetgroup', 'opacity', 'orientation', 'pointpos', 'q1', 'q1src', 'q3', 'q3src', 'quartilemethod', 'sd', 'sdsrc', 'selected', 'selectedpoints', 'showlegend', 'stream', 'text', 'textsrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'upperfence', 'upperfencesrc', 'visible', 'whiskerwidth', 'width', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## **Histograma de los flujos financieros para los países en desarrollo**
# Crear el histograma
fig_hist <- plot_ly(
data = df_financial_flows,
x = ~`Financial flows to developing countries (US $)`,
type = "histogram",
nbinsx = 100,
title = 'Histograma de los Flujos Financieros hacia los Países en Desarrollo (US $)',
xaxis = list(title = 'Flujos Financieros (US $)')
)
fig_hist
## Warning: 'histogram' objects don't have these attributes: 'title'
## Valid attributes include:
## '_deprecated', 'alignmentgroup', 'autobinx', 'autobiny', 'bingroup', 'cliponaxis', 'constraintext', 'cumulative', 'customdata', 'customdatasrc', 'error_x', 'error_y', 'histfunc', 'histnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'insidetextanchor', 'insidetextfont', 'legendgroup', 'legendgrouptitle', 'legendrank', 'marker', 'meta', 'metasrc', 'name', 'nbinsx', 'nbinsy', 'offsetgroup', 'opacity', 'orientation', 'outsidetextfont', 'selected', 'selectedpoints', 'showlegend', 'stream', 'text', 'textangle', 'textfont', 'textposition', 'textsrc', 'texttemplate', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'xaxis', 'xbins', 'xcalendar', 'xhoverformat', 'xsrc', 'y', 'yaxis', 'ybins', 'ycalendar', 'yhoverformat', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## **Boxplot para el valor de las emisiones de CO2 en Kt por país**
# Filtrar la columna específica
df_box_co2 <- energia_sus %>% select(CO2)
# Crear el gráfico de caja para la variable seleccionada
fig_co2 <- plot_ly(
data = df_box_co2,
x = ~CO2,
type = "box",
title = 'Valor de las emisiones de CO2 en kt por país',
xaxis = list(title = 'Valor de las emisiones de CO2 en kt por país')
)
fig_co2
## Warning: Ignoring 428 observations
## Warning: 'box' objects don't have these attributes: 'title'
## Valid attributes include:
## 'alignmentgroup', 'boxmean', 'boxpoints', 'customdata', 'customdatasrc', 'dx', 'dy', 'fillcolor', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'jitter', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'lowerfence', 'lowerfencesrc', 'marker', 'mean', 'meansrc', 'median', 'mediansrc', 'meta', 'metasrc', 'name', 'notched', 'notchspan', 'notchspansrc', 'notchwidth', 'offsetgroup', 'opacity', 'orientation', 'pointpos', 'q1', 'q1src', 'q3', 'q3src', 'quartilemethod', 'sd', 'sdsrc', 'selected', 'selectedpoints', 'showlegend', 'stream', 'text', 'textsrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'upperfence', 'upperfencesrc', 'visible', 'whiskerwidth', 'width', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## **Histograma del valor de las emisiones de CO2 en Kt por país**
# Crear el histograma
fig_hist_co2 <- plot_ly(
data = df_box_co2,
x = ~CO2,
type = "histogram",
nbinsx = 100,
title = 'Valor de las emisiones de CO2 en kt por país',
xaxis = list(title = 'Valor de las emisiones de CO2 en kt por país')
)
fig_hist_co2
## Warning: Ignoring 428 observations
## Warning: 'histogram' objects don't have these attributes: 'title'
## Valid attributes include:
## '_deprecated', 'alignmentgroup', 'autobinx', 'autobiny', 'bingroup', 'cliponaxis', 'constraintext', 'cumulative', 'customdata', 'customdatasrc', 'error_x', 'error_y', 'histfunc', 'histnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'insidetextanchor', 'insidetextfont', 'legendgroup', 'legendgrouptitle', 'legendrank', 'marker', 'meta', 'metasrc', 'name', 'nbinsx', 'nbinsy', 'offsetgroup', 'opacity', 'orientation', 'outsidetextfont', 'selected', 'selectedpoints', 'showlegend', 'stream', 'text', 'textangle', 'textfont', 'textposition', 'textsrc', 'texttemplate', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'xaxis', 'xbins', 'xcalendar', 'xhoverformat', 'xsrc', 'y', 'yaxis', 'ybins', 'ycalendar', 'yhoverformat', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## **Coeficiente de variación**
# Excluir las columnas específicas que no quieres analizar
columnas_excluir <- c('Year', 'Land Area(Km2)', 'Latitude', 'Longitude')
# Seleccionar solo las columnas numéricas excluyendo las que no queremos
columnas_incluidas <- setdiff(names(energia_sus)[sapply(energia_sus, is.numeric)], columnas_excluir)
# Calcular la media, desviación estándar y coeficiente de variación para las columnas seleccionadas
for (column in columnas_incluidas) {
media <- mean(energia_sus[[column]], na.rm = TRUE)
desviacion <- sd(energia_sus[[column]], na.rm = TRUE)
# Evitar la división por cero
if (media != 0) {
coef_variacion <- (desviacion / media) * 100
cat("El coeficiente de variación para", column, "es:", round(coef_variacion, 2), "%\n")
} else {
cat("La media de la columna", column, "es cero, no se puede calcular el coeficiente de variación.\n")
}
}
## El coeficiente de variación para Access to electricity (% of population) es: 38.36 %
## El coeficiente de variación para Access to clean fuels for cooking es: 61.72 %
## El coeficiente de variación para Renewable-electricity-generating-capacity-per-capita es: 215.81 %
## El coeficiente de variación para Financial flows to developing countries (US $) es: 316.43 %
## El coeficiente de variación para Renewable energy share in the total final energy consumption (%) es: 91.59 %
## El coeficiente de variación para Electricity from fossil fuels (TWh) es: 494.64 %
## El coeficiente de variación para Electricity from nuclear (TWh) es: 542.79 %
## El coeficiente de variación para Electricity from renewables (TWh) es: 435.71 %
## El coeficiente de variación para Low-carbon electricity (% electricity) es: 93.24 %
## El coeficiente de variación para Primary energy consumption per capita (kWh/person) es: 135.07 %
## El coeficiente de variación para Energy intensity level of primary energy (MJ/$2017 PPP GDP) es: 66.55 %
## El coeficiente de variación para CO2 es: 483.94 %
## El coeficiente de variación para Renewables (% equivalent primary energy) es: 125.09 %
## El coeficiente de variación para gdp_growth es: 165.23 %
## El coeficiente de variación para gdp_per_capita es: 148.38 %
## **Coeficiente de asimetría de Pearson**
asimetria_pearson <- list()
# Calcular la media, mediana, desviación estándar y coeficiente de asimetría de Pearson para cada columna numérica
for (column in columnas_incluidas) {
media <- mean(energia_sus[[column]], na.rm = TRUE)
mediana <- median(energia_sus[[column]], na.rm = TRUE)
desviacion <- sd(energia_sus[[column]], na.rm = TRUE)
# Evitar la división por cero
if (desviacion != 0) {
coef_asimetria <- (3 * (media - mediana)) / desviacion
asimetria_pearson[[column]] <- coef_asimetria
cat("El coeficiente de asimetría de Pearson para", column, "es:", round(coef_asimetria, 2), "\n")
} else {
cat("La desviación estándar de la columna", column, "es cero, no se puede calcular el coeficiente de asimetría.\n")
}
}
## El coeficiente de asimetría de Pearson para Access to electricity (% of population) es: -1.93
## El coeficiente de asimetría de Pearson para Access to clean fuels for cooking es: -1.53
## El coeficiente de asimetría de Pearson para Renewable-electricity-generating-capacity-per-capita es: 0.99
## El coeficiente de asimetría de Pearson para Financial flows to developing countries (US $) es: 0.89
## El coeficiente de asimetría de Pearson para Renewable energy share in the total final energy consumption (%) es: 0.94
## El coeficiente de asimetría de Pearson para Electricity from fossil fuels (TWh) es: 0.58
## El coeficiente de asimetría de Pearson para Electricity from nuclear (TWh) es: 0.55
## El coeficiente de asimetría de Pearson para Electricity from renewables (TWh) es: 0.65
## El coeficiente de asimetría de Pearson para Low-carbon electricity (% electricity) es: 0.78
## El coeficiente de asimetría de Pearson para Primary energy consumption per capita (kWh/person) es: 1.09
## El coeficiente de asimetría de Pearson para Energy intensity level of primary energy (MJ/$2017 PPP GDP) es: 0.86
## El coeficiente de asimetría de Pearson para CO2 es: 0.58
## El coeficiente de asimetría de Pearson para Renewables (% equivalent primary energy) es: 1.14
## El coeficiente de asimetría de Pearson para gdp_growth es: -0.06
## El coeficiente de asimetría de Pearson para gdp_per_capita es: 1.32
# Mostrar los resultados como DataFrame
df_asimetria <- data.frame(
Variable = names(asimetria_pearson),
Coeficiente_Asimetria_de_Pearson = unlist(asimetria_pearson)
)
print(df_asimetria)
## Variable
## Access to electricity (% of population) Access to electricity (% of population)
## Access to clean fuels for cooking Access to clean fuels for cooking
## Renewable-electricity-generating-capacity-per-capita Renewable-electricity-generating-capacity-per-capita
## Financial flows to developing countries (US $) Financial flows to developing countries (US $)
## Renewable energy share in the total final energy consumption (%) Renewable energy share in the total final energy consumption (%)
## Electricity from fossil fuels (TWh) Electricity from fossil fuels (TWh)
## Electricity from nuclear (TWh) Electricity from nuclear (TWh)
## Electricity from renewables (TWh) Electricity from renewables (TWh)
## Low-carbon electricity (% electricity) Low-carbon electricity (% electricity)
## Primary energy consumption per capita (kWh/person) Primary energy consumption per capita (kWh/person)
## Energy intensity level of primary energy (MJ/$2017 PPP GDP) Energy intensity level of primary energy (MJ/$2017 PPP GDP)
## CO2 CO2
## Renewables (% equivalent primary energy) Renewables (% equivalent primary energy)
## gdp_growth gdp_growth
## gdp_per_capita gdp_per_capita
## Coeficiente_Asimetria_de_Pearson
## Access to electricity (% of population) -1.92510524
## Access to clean fuels for cooking -1.52865130
## Renewable-electricity-generating-capacity-per-capita 0.98572797
## Financial flows to developing countries (US $) 0.89112216
## Renewable energy share in the total final energy consumption (%) 0.93709943
## Electricity from fossil fuels (TWh) 0.58090482
## Electricity from nuclear (TWh) 0.55269740
## Electricity from renewables (TWh) 0.64630210
## Low-carbon electricity (% electricity) 0.78124529
## Primary energy consumption per capita (kWh/person) 1.08906319
## Energy intensity level of primary energy (MJ/$2017 PPP GDP) 0.85561098
## CO2 0.57919341
## Renewables (% equivalent primary energy) 1.13959506
## gdp_growth -0.06237959
## gdp_per_capita 1.32499239
#if (!require("tidyr")) install.packages("tidyr")
library(tidyr)
##
## Adjuntando el paquete: 'tidyr'
## The following object is masked from 'package:reshape2':
##
## smiths
## **Valores Faltantes**
# Contar valores faltantes por variable
missing_data <- energia_sus %>%
summarise(across(everything(), ~ sum(is.na(.)))) %>%
pivot_longer(cols = everything(), names_to = "variable", values_to = "missing_count")
# Crear el gráfico de valores faltantes
ggplot(missing_data, aes(x = reorder(variable, -missing_count), y = missing_count)) +
geom_bar(stat = "identity", fill = "steelblue") +
coord_flip() +
labs(title = "Cantidad de valores faltantes por variable", x = "Variables", y = "Cantidad de valores faltantes") +
theme_minimal()
# Calcular el porcentaje de valores faltantes
missing_percentage <- energia_sus %>%
summarise(across(everything(), ~ sum(is.na(.)) / nrow(energia_sus) * 100)) %>%
pivot_longer(cols = everything(), names_to = "variable", values_to = "missing_percentage")
# Crear el gráfico de porcentaje de valores faltantes
ggplot(missing_percentage, aes(x = reorder(variable, -missing_percentage), y = missing_percentage)) +
geom_bar(stat = "identity", fill = "steelblue") +
coord_flip() +
labs(title = "Porcentaje de valores faltantes por variable", x = "Variables", y = "Porcentaje de valores faltantes") +
theme_minimal()
# Gráfico de barras para visualizar el porcentaje de valores faltantes
ggplot(missing_percentage, aes(x = reorder(variable, -missing_percentage), y = missing_percentage)) +
geom_bar(stat = "identity", fill = "steelblue") +
coord_flip() +
labs(title = "Porcentaje de valores faltantes por variable en el DataFrame energia_sus",
x = "Variables",
y = "Porcentaje de valores faltantes") +
theme_minimal()
# Mapa de calor del patrón de datos faltantes
library(ggplot2)
library(reshape2)
# Mapa de calor para ver patrones de valores faltantes
missing_matrix <- is.na(energia_sus)
missing_heatmap <- melt(missing_matrix)
## Warning: The melt generic in data.table has been passed a matrix and will
## attempt to redirect to the relevant reshape2 method; please note that reshape2
## is superseded and is no longer actively developed, and this redirection is now
## deprecated. To continue using melt methods from reshape2 while both libraries
## are attached, e.g. melt.list, you can prepend the namespace, i.e.
## reshape2::melt(missing_matrix). In the next version, this warning will become
## an error.
ggplot(missing_heatmap, aes(Var2, Var1, fill = value)) +
geom_tile() +
scale_fill_manual(values = c("white", "blue"), labels = c("Presente", "Faltante")) +
labs(title = "Mapa de calor del patrón de datos faltantes en 'energia_sus'",
x = "Variables",
y = "Observaciones") +
theme_minimal()
## **Mapa geo-referenciado del porcentaje de población por país que tiene acceso a la electricidad en 2014**
df_2014 <- filter(energia_sus, Year == 2014)
# Filtrar los datos para el año 2014
df_2014 <- energia_sus %>% filter(Year == 2014)
# Crear el mapa coroplético para el acceso a electricidad
fig <- plot_geo(df_2014) %>%
add_trace(
z = ~`Access to electricity (% of population)`,
locations = ~Country,
color = ~`Access to electricity (% of population)`,
colors = "Blues", # Cambiar 'Plasma' a 'Viridis'
colorbar = list(title = "Acceso a electricidad (%)")
) %>%
layout(title = "Porcentaje de población por país que tiene acceso a electricidad en 2014")
# Mostrar el gráfico
fig
## **Mapa geo-referenciado del porcentaje de población por país que tiene acceso a combustibles limpios 2014**
fig <- plot_geo(df_2014) %>%
add_trace(
z = ~`Access to clean fuels for cooking`,
locations = ~Country,
color = ~`Access to clean fuels for cooking`,
colors = "Blues"
) %>%
layout(title = "Porcentaje de población por país que tiene acceso a combustibles limpios para cocinar en 2014")
fig
## Warning: Ignoring 8 observations
## **Principales fuentes de electricidad en Colombia**
# Agrupar y transformar datos para Colombia
energia_agrupado <- energia_sus %>%
group_by(Country) %>%
summarise(
`Electricity from fossil fuels (TWh)` = sum(`Electricity from fossil fuels (TWh)`, na.rm = TRUE),
`Electricity from nuclear (TWh)` = sum(`Electricity from nuclear (TWh)`, na.rm = TRUE),
`Electricity from renewables (TWh)` = sum(`Electricity from renewables (TWh)`, na.rm = TRUE)
)
df_colombia <- filter(energia_agrupado, Country == "Colombia") %>%
pivot_longer(-Country, names_to = "Source", values_to = "Electricity (TWh)")
# Gráfico de pastel
fig <- plot_ly(df_colombia, labels = ~Source, values = ~`Electricity (TWh)`, type = 'pie') %>%
layout(title = 'Principales fuentes de electricidad en Colombia')
fig
## **Países que usan energías renovables**
fig <- plot_geo(energia_sus) %>%
add_trace(
z = ~`Electricity from renewables (TWh)`,
locations = ~Country,
color = ~`Electricity from renewables (TWh)`,
colors = "Blues"
) %>%
layout(title = "Países que usan energías renovables")
fig
## Warning: Ignoring 21 observations
## **Países que usan energía nuclear**
fig <- plot_geo(energia_sus) %>%
add_trace(
z = ~`Electricity from nuclear (TWh)`,
locations = ~Country,
color = ~`Electricity from nuclear (TWh)`,
colors = "Blues"
) %>%
layout(title = "Países que usan energía nuclear")
fig
## Warning: Ignoring 126 observations
## **Países que usan energía de combustibles fósiles**
fig <- plot_geo(energia_sus) %>%
add_trace(
z = ~`Electricity from fossil fuels (TWh)`,
locations = ~Country,
color = ~`Electricity from fossil fuels (TWh)`,
colors = "Blues"
) %>%
layout(title = "Países que usan energía de combustibles fósiles")
fig
## Warning: Ignoring 21 observations
## **Acceso a la electricidad en Colombia a través del (2000-2020)**
# Acceso a la electricidad en promedio global
electricidad_global <- energia_sus %>%
group_by(Year) %>%
summarise(`Access to electricity (% of population)` = mean(`Access to electricity (% of population)`, na.rm = TRUE))
fig <- plot_ly(electricidad_global, x = ~Year, y = ~`Access to electricity (% of population)`, type = 'scatter', mode = 'lines') %>%
layout(title = 'Acceso a la electricidad (2000-2020)', xaxis = list(title = 'Año'), yaxis = list(title = 'Acceso a la electricidad (%)'))
fig
# Acceso a la electricidad en Colombia
energia_colombia <- filter(energia_sus, Country == "Colombia")
electricidad_colombia <- energia_colombia %>%
group_by(Year) %>%
summarise(`Access to electricity (% of population)` = mean(`Access to electricity (% of population)`, na.rm = TRUE))
fig <- plot_ly(electricidad_colombia, x = ~Year, y = ~`Access to electricity (% of population)`, type = 'scatter', mode = 'lines') %>%
layout(title = 'Acceso a la electricidad en Colombia (2000-2020)', xaxis = list(title = 'Año'), yaxis = list(title = 'Acceso a la electricidad (%)'))
fig
## **Países con mayores emisiones de CO2**
# Agrupar y obtener los máximos de emisiones de CO2
maxco2 <- energia_sus %>%
group_by(Country) %>%
summarise(CO2 = max(CO2, na.rm = TRUE)) %>%
arrange(desc(CO2))
## Warning: There were 13 warnings in `summarise()`.
## The first warning was:
## ℹ In argument: `CO2 = max(CO2, na.rm = TRUE)`.
## ℹ In group 12: `Country = "Bahamas"`.
## Caused by warning in `max()`:
## ! ningun argumento finito para max; retornando -Inf
## ℹ Run `dplyr::last_dplyr_warnings()` to see the 12 remaining warnings.
top10co2 <- head(maxco2, 10)
# Crear el gráfico de barras
fig1 <- plot_ly(
top10co2,
x = ~Country,
y = ~CO2,
type = 'bar',
color = ~CO2,
title = 'Países con mayores emisiones de CO2',
labels = list(x = 'Países', y = 'Emisiones CO2 (kt)')
)
fig1 <- fig1 %>% layout(height = 800)
## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()
fig1
## Warning: textfont.color doesn't (yet) support data arrays
## Warning: textfont.color doesn't (yet) support data arrays
## Warning: 'bar' objects don't have these attributes: 'title', 'labels'
## Valid attributes include:
## '_deprecated', 'alignmentgroup', 'base', 'basesrc', 'cliponaxis', 'constraintext', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'insidetextanchor', 'insidetextfont', 'legendgroup', 'legendgrouptitle', 'legendrank', 'marker', 'meta', 'metasrc', 'name', 'offset', 'offsetgroup', 'offsetsrc', 'opacity', 'orientation', 'outsidetextfont', 'selected', 'selectedpoints', 'showlegend', 'stream', 'text', 'textangle', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'width', 'widthsrc', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## **Mapa geo-referenciado del porcentaje de población por países con mayores emisiones de CO2**
df_co2 <- energia_sus %>%
group_by(Country) %>%
summarise(CO2 = sum(CO2, na.rm = TRUE)) %>%
arrange(desc(CO2)) %>%
head(13)
fig2 <- plot_ly(
df_co2,
locations = ~Country,
locationmode = 'country names',
z = ~CO2,
type = 'choropleth',
color = ~CO2,
colorbar = list(title = 'Emisiones CO2 (kt)'),
title = 'Países con mayores emisiones de CO2 (2000-2020)'
)
fig2
## Warning: 'choropleth' objects don't have these attributes: 'title'
## Valid attributes include:
## 'autocolorscale', 'coloraxis', 'colorbar', 'colorscale', 'customdata', 'customdatasrc', 'featureidkey', 'geo', 'geojson', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'locationmode', 'locations', 'locationssrc', 'marker', 'meta', 'metasrc', 'name', 'reversescale', 'selected', 'selectedpoints', 'showlegend', 'showscale', 'stream', 'text', 'textsrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'z', 'zauto', 'zmax', 'zmid', 'zmin', 'zsrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## **Los principales países por consumo de electricidad a partir de combustibles fósiles (2000-2020)**
consumo_fossil_fuel <- energia_sus %>%
group_by(Country) %>%
summarise(Electricity_from_fossil_fuels = sum(`Electricity from fossil fuels (TWh)`, na.rm = TRUE)) %>%
arrange(desc(Electricity_from_fossil_fuels)) %>%
head(10)
fig3 <- plot_ly(
consumo_fossil_fuel,
x = ~Country,
y = ~Electricity_from_fossil_fuels,
type = 'bar',
title = 'Los principales países por consumo de electricidad a partir de combustibles fósiles (2000-2020)'
)
fig3
## Warning: 'bar' objects don't have these attributes: 'title'
## Valid attributes include:
## '_deprecated', 'alignmentgroup', 'base', 'basesrc', 'cliponaxis', 'constraintext', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'insidetextanchor', 'insidetextfont', 'legendgroup', 'legendgrouptitle', 'legendrank', 'marker', 'meta', 'metasrc', 'name', 'offset', 'offsetgroup', 'offsetsrc', 'opacity', 'orientation', 'outsidetextfont', 'selected', 'selectedpoints', 'showlegend', 'stream', 'text', 'textangle', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'width', 'widthsrc', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## **Histograma del consumo de electricidad a partir de los combustibles fósiles (2000-2020)**
# Filtrar datos para Colombia
energia_colombia <- energia_sus %>% filter(Country == 'Colombia')
# Agrupar por año y calcular el consumo total de electricidad a partir de combustibles fósiles
fosil_colombia <- energia_colombia %>%
group_by(Year) %>%
summarise(Electricity_from_fossil_fuels = sum(`Electricity from fossil fuels (TWh)`, na.rm = TRUE))
fig4 <- plot_ly(
fosil_colombia,
x = ~Year,
y = ~Electricity_from_fossil_fuels,
type = 'bar',
title = 'Consumo de electricidad a partir de combustibles fósiles en Colombia (2000-2020)',
labels = list(x = 'Año', y = 'Electricidad de combustibles fósiles (TWh)')
)
fig4
## Warning: 'bar' objects don't have these attributes: 'title', 'labels'
## Valid attributes include:
## '_deprecated', 'alignmentgroup', 'base', 'basesrc', 'cliponaxis', 'constraintext', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'insidetextanchor', 'insidetextfont', 'legendgroup', 'legendgrouptitle', 'legendrank', 'marker', 'meta', 'metasrc', 'name', 'offset', 'offsetgroup', 'offsetsrc', 'opacity', 'orientation', 'outsidetextfont', 'selected', 'selectedpoints', 'showlegend', 'stream', 'text', 'textangle', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'width', 'widthsrc', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## **Tasa de consumo de combustibles fósiles a lo largo de los años para los 10 principales países**
top_fossil_fuel_countries <- energia_sus %>%
group_by(Country) %>%
summarise(mean_fossil_fuels = mean(`Electricity from fossil fuels (TWh)`, na.rm = TRUE)) %>%
arrange(desc(mean_fossil_fuels))
top_fossil_fuel_countries <- head(top_fossil_fuel_countries, 10)
# Filtrar datos para los países seleccionados
filtered_data <- energia_sus %>%
filter(Country %in% top_fossil_fuel_countries$Country)
fig5 <- plot_ly(
filtered_data,
x = ~Year,
y = ~`Electricity from fossil fuels (TWh)`,
color = ~Country,
type = 'scatter',
mode = 'lines',
title = 'Tendencias en la Generación de Electricidad de Combustibles Fósiles entre los Principales 10 Países'
)
fig5
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors
## Warning: 'scatter' objects don't have these attributes: 'title'
## Valid attributes include:
## 'cliponaxis', 'connectgaps', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'fill', 'fillcolor', 'fillpattern', 'groupnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'marker', 'meta', 'metasrc', 'mode', 'name', 'opacity', 'orientation', 'selected', 'selectedpoints', 'showlegend', 'stackgaps', 'stackgroup', 'stream', 'text', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## Warning: 'scatter' objects don't have these attributes: 'title'
## Valid attributes include:
## 'cliponaxis', 'connectgaps', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'fill', 'fillcolor', 'fillpattern', 'groupnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'marker', 'meta', 'metasrc', 'mode', 'name', 'opacity', 'orientation', 'selected', 'selectedpoints', 'showlegend', 'stackgaps', 'stackgroup', 'stream', 'text', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## Warning: 'scatter' objects don't have these attributes: 'title'
## Valid attributes include:
## 'cliponaxis', 'connectgaps', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'fill', 'fillcolor', 'fillpattern', 'groupnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'marker', 'meta', 'metasrc', 'mode', 'name', 'opacity', 'orientation', 'selected', 'selectedpoints', 'showlegend', 'stackgaps', 'stackgroup', 'stream', 'text', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## Warning: 'scatter' objects don't have these attributes: 'title'
## Valid attributes include:
## 'cliponaxis', 'connectgaps', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'fill', 'fillcolor', 'fillpattern', 'groupnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'marker', 'meta', 'metasrc', 'mode', 'name', 'opacity', 'orientation', 'selected', 'selectedpoints', 'showlegend', 'stackgaps', 'stackgroup', 'stream', 'text', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## Warning: 'scatter' objects don't have these attributes: 'title'
## Valid attributes include:
## 'cliponaxis', 'connectgaps', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'fill', 'fillcolor', 'fillpattern', 'groupnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'marker', 'meta', 'metasrc', 'mode', 'name', 'opacity', 'orientation', 'selected', 'selectedpoints', 'showlegend', 'stackgaps', 'stackgroup', 'stream', 'text', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## Warning: 'scatter' objects don't have these attributes: 'title'
## Valid attributes include:
## 'cliponaxis', 'connectgaps', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'fill', 'fillcolor', 'fillpattern', 'groupnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'marker', 'meta', 'metasrc', 'mode', 'name', 'opacity', 'orientation', 'selected', 'selectedpoints', 'showlegend', 'stackgaps', 'stackgroup', 'stream', 'text', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## Warning: 'scatter' objects don't have these attributes: 'title'
## Valid attributes include:
## 'cliponaxis', 'connectgaps', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'fill', 'fillcolor', 'fillpattern', 'groupnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'marker', 'meta', 'metasrc', 'mode', 'name', 'opacity', 'orientation', 'selected', 'selectedpoints', 'showlegend', 'stackgaps', 'stackgroup', 'stream', 'text', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## Warning: 'scatter' objects don't have these attributes: 'title'
## Valid attributes include:
## 'cliponaxis', 'connectgaps', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'fill', 'fillcolor', 'fillpattern', 'groupnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'marker', 'meta', 'metasrc', 'mode', 'name', 'opacity', 'orientation', 'selected', 'selectedpoints', 'showlegend', 'stackgaps', 'stackgroup', 'stream', 'text', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## Warning: 'scatter' objects don't have these attributes: 'title'
## Valid attributes include:
## 'cliponaxis', 'connectgaps', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'fill', 'fillcolor', 'fillpattern', 'groupnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'marker', 'meta', 'metasrc', 'mode', 'name', 'opacity', 'orientation', 'selected', 'selectedpoints', 'showlegend', 'stackgaps', 'stackgroup', 'stream', 'text', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## Warning: 'scatter' objects don't have these attributes: 'title'
## Valid attributes include:
## 'cliponaxis', 'connectgaps', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'fill', 'fillcolor', 'fillpattern', 'groupnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'marker', 'meta', 'metasrc', 'mode', 'name', 'opacity', 'orientation', 'selected', 'selectedpoints', 'showlegend', 'stackgaps', 'stackgroup', 'stream', 'text', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
## **Tendencias en la generación de electricidad de combustibles fósiles entre los 10 principales países**
# Asegurar que Colombia esté en la lista de países seleccionados
# Asegurar que Colombia esté en la lista de países seleccionados
top_fossil_fuel_countries <- energia_sus %>%
group_by(Country) %>%
summarise(mean_fossil_fuels = mean(`Electricity from fossil fuels (TWh)`, na.rm = TRUE)) %>%
arrange(desc(mean_fossil_fuels)) %>%
slice(1:3) # Selecciona los 3 principales países
# Filtrar los datos para los países seleccionados (top 3 + Colombia)
filtered_data <- energia_sus %>%
filter(Country %in% top_fossil_fuel_countries$Country)
# Crear el gráfico de líneas para mostrar la tendencia en el uso de electricidad de combustibles fósiles
fig <- plot_ly(
data = filtered_data,
x = ~Year,
y = ~`Electricity from fossil fuels (TWh)`,
color = ~Country,
type = 'scatter',
mode = 'lines+markers'
) %>%
layout(
title = 'Tendencias en la Generación de Electricidad de Combustibles Fósiles entre los Principales 10 Países y Colombia',
xaxis = list(title = 'Año'),
yaxis = list(title = 'Electricidad de Combustibles Fósiles (TWh)')
)
fig
# Definir los países que se quieren visualizar
paises <- c('United States', 'Colombia', 'China', 'Brazil')
# Filtrar los datos para los países seleccionados
tenden_co2 <- energia_sus %>%
filter(Country %in% paises)
# Crear el gráfico de líneas para mostrar la tendencia de emisiones de CO2
ggplot(tenden_co2, aes(x = Year, y = CO2, color = Country)) +
geom_line() +
ggtitle('Tendencia de Emisiones de CO2 para Estados Unidos, Colombia, China y Brasil') +
theme_minimal()
## Warning: Removed 4 rows containing missing values or values outside the scale range
## (`geom_line()`).
# **Tendencia de emisiones de CO2 para Colombia y Brasil**
# Definir los países que se quieren visualizar
paises <- c('Colombia', 'Brazil', 'Argentina', 'Chile', 'Ecuador', 'Uruguay')
# Filtrar los datos para los países seleccionados
tenden_co2 <- energia_sus %>%
filter(Country %in% paises)
# Crear el gráfico de líneas para mostrar la tendencia de emisiones de CO2
ggplot(tenden_co2, aes(x = Year, y = CO2, color = Country)) +
geom_line() +
ggtitle('Tendencia de Emisiones de CO2 para Colombia y Brasil') +
theme_minimal()
## Warning: Removed 6 rows containing missing values or values outside the scale range
## (`geom_line()`).
# **Eliminación de los NAN*
# Especificar las columnas a eliminar
columns_to_drop <- c("Financial.flows.to.developing.countries..US....",
"Renewables....equivalent.primary.energy.",
"CO2",
"gdp_growth",
"Renewable.electricity.generating.capacity.per.capita")
# Eliminar las columnas
data_clean <- energia_sus[, !(names(energia_sus) %in% columns_to_drop)]
data_clean <- as.data.frame(data_clean)
# **Imputación**
# Visualización del mapa de valores faltantes
library(ggplot2)
library(mice)
##
## Adjuntando el paquete: 'mice'
## The following object is masked from 'package:stats':
##
## filter
## The following objects are masked from 'package:base':
##
## cbind, rbind
# Mapa de valores faltantes
missing_data <- data_clean %>%
summarise(across(everything(), ~ sum(is.na(.)))) %>%
pivot_longer(cols = everything(), names_to = "variable", values_to = "missing_count")
ggplot(missing_data, aes(x = variable, y = missing_count)) +
geom_bar(stat = 'identity') +
coord_flip() +
ggtitle('Mapa de valores faltantes en el DataFrame data_clean') +
theme_minimal()
# **Gráfico de la distribución para cada una de las variables**
library(ggplot2)
# Lista de variables a graficar
variables <- c(
'Access to electricity (% of population)',
'Access to clean fuels for cooking',
'Renewable energy share in the total final energy consumption (%)',
'Electricity from fossil fuels (TWh)',
'Electricity from nuclear (TWh)',
'Electricity from renewables (TWh)',
'Low-carbon electricity (% electricity)',
'Primary energy consumption per capita (kWh/person)',
'Energy intensity level of primary energy (MJ/$2017 PPP GDP)',
'gdp_per_capita'
)
# Crear un histograma para cada variable en la lista
# Crear un histograma para cada variable en la lista
library(rlang) # Cargar rlang para usar `ensym`
##
## Adjuntando el paquete: 'rlang'
## The following object is masked from 'package:data.table':
##
## :=
for (column in variables) {
column_sym <- ensym(column) # Convertir el nombre de la columna en símbolo
ggplot(data_clean, aes(x = !!column_sym)) + # Usar !! para desreferenciar el símbolo
geom_histogram(binwidth = 30, fill = 'blue', alpha = 0.7, color = 'black') +
labs(title = paste('Distribución de', column), x = column, y = 'Frecuencia') +
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5)) +
geom_density(color = "red", size = 1) +
ggtitle(paste("Distribución de", column))
}
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
# Cargar las bibliotecas necesarias
library(dplyr)
library(tidyr)
library(VIM)
## Cargando paquete requerido: colorspace
## Cargando paquete requerido: grid
## VIM is ready to use.
## Suggestions and bug-reports can be submitted at: https://github.com/statistikat/VIM/issues
##
## Adjuntando el paquete: 'VIM'
## The following object is masked from 'package:datasets':
##
## sleep
library(ggplot2)
library(Amelia)
## Cargando paquete requerido: Rcpp
## ##
## ## Amelia II: Multiple Imputation
## ## (Version 1.8.2, built: 2024-04-10)
## ## Copyright (C) 2005-2024 James Honaker, Gary King and Matthew Blackwell
## ## Refer to http://gking.harvard.edu/amelia/ for more information
## ##
# Suponiendo que 'energia_sus' es tu data frame original con valores faltantes
# Separar columnas numéricas y categóricas
numeric_cols <- select_if(energia_sus, is.numeric)
categorical_cols <- select_if(energia_sus, Negate(is.numeric))
# Imputar valores faltantes en datos numéricos con la media
numeric_imputed <- numeric_cols %>%
mutate(across(everything(), ~ ifelse(is.na(.), mean(., na.rm = TRUE), .)))
# Imputar valores faltantes en datos categóricos con el valor más frecuente
categorical_imputed <- categorical_cols %>%
mutate(across(everything(), ~ ifelse(is.na(.), names(sort(table(.), decreasing = TRUE)[1]), .)))
# Combinar datos numéricos y categóricos imputados
data_imputed <- bind_cols(numeric_imputed, categorical_imputed)
# Imputar todo el data frame con la estrategia de 'valor más frecuente'
imputer_most_frequent <- function(column) {
if (is.numeric(column)) {
column[is.na(column)] <- mean(column, na.rm = TRUE)
} else {
column[is.na(column)] <- names(sort(table(column), decreasing = TRUE)[1])
}
return(column)
}
data_imputed <- energia_sus %>%
mutate(across(everything(), imputer_most_frequent))
# Crear un gráfico del mapa de valores faltantes
missmap(data_imputed, main = "Mapa de valores faltantes en el DataFrame data_imputed", col = c("red", "blue"), legend = FALSE)
# Establecer el estilo de los gráficos y mostrar un gráfico personalizado con ggplot2
theme_set(theme_minimal())
# Utilizar pivot_longer() en lugar de melt()
na_data <- as.data.frame(is.na(data_imputed)) %>%
mutate(row_id = row_number()) %>%
pivot_longer(cols = -row_id, names_to = "Var2", values_to = "value")
# Crear el gráfico del mapa de valores faltantes
ggplot(na_data, aes(x = Var2, y = row_id, fill = value)) +
geom_tile(color = "white") +
scale_fill_manual(values = c("TRUE" = "red", "FALSE" = "blue"), name = "Faltante") +
labs(title = "Mapa de valores faltantes en el DataFrame data_imputed",
x = "Variables",
y = "Observaciones") +
theme(axis.text.x = element_text(angle = 45, hjust = 1),
plot.title = element_text(hjust = 0.5))
# **Modelo ARIMA**
# **Gráfico de electricidad renovable**
# Filtrar los datos para que solo incluyan Brasil, Colombia y Alemania
data_filtered <- data_imputed[data_imputed$Country %in% c("Brazil", "Colombia", "Germany"), ]
# Cargar el paquete plotly
library(plotly)
# Crear el gráfico interactivo con los nombres de los países seleccionados
fig <- plot_ly(data_filtered,
x = ~Year,
y = ~`Electricity from renewables (TWh)`,
color = ~Country, # Agrupar por país
type = 'scatter',
mode = 'lines') %>%
layout(title = 'Electricity from Renewables (TWh) en Brasil, Colombia y Alemania',
xaxis = list(title = 'Año'),
yaxis = list(title = 'Electricidad de Renovables (TWh)'))
# Mostrar el gráfico interactivo
fig
# **Autocorrelación de Electricidad renovable**
# Calcular la autocorrelación sobre la variable 'Electricity from renewables (TWh)'
autocorr_values <- acf(data_filtered$`Electricity from renewables (TWh)`, plot = FALSE)$acf
# Crear el gráfico interactivo de autocorrelación
fig_acf <- plot_ly(x = ~seq_along(autocorr_values), y = ~autocorr_values,
type = 'scatter', mode = 'markers',
marker = list(size = 8, color = 'blue'),
name = 'Autocorrelación - Puntos') %>%
add_lines(x = ~seq_along(autocorr_values),
y = ~autocorr_values,
line = list(color = 'blue')) %>%
layout(title = 'Autocorrelación - Electricity from Renewables (TWh)',
xaxis = list(title = 'Lag'),
yaxis = list(title = 'Autocorrelación'))
fig_acf
## A marker object has been specified, but markers is not in the mode
## Adding markers to the mode...
# **Autocorrelación Parcial**
# Calcular la autocorrelación parcial sobre la variable 'Electricity from renewables (TWh)'
partial_autocorr_values <- pacf(data_filtered$`Electricity from renewables (TWh)`, plot = FALSE)$acf
# Crear el gráfico interactivo de autocorrelación parcial
fig_pacf <- plot_ly(x = ~seq_along(partial_autocorr_values), y = ~partial_autocorr_values,
type = 'scatter', mode = 'markers',
marker = list(size = 8, color = 'blue'),
name = 'Autocorrelación Parcial - Puntos') %>%
add_lines(x = ~seq_along(partial_autocorr_values),
y = ~partial_autocorr_values,
line = list(color = 'blue')) %>%
layout(title = 'Autocorrelación Parcial - Electricity from Renewables (TWh)',
xaxis = list(title = 'Lag'),
yaxis = list(title = 'Autocorrelación Parcial'))
fig_pacf
## A marker object has been specified, but markers is not in the mode
## Adding markers to the mode...
#install.packages("tseries")
# **Test de Dickey-Fuller**
# Realizar la prueba de Dickey-Fuller Aumentada (ADF)
# Cargar el paquete tseries
library(tseries)
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
# Realizar la prueba de Dickey-Fuller Aumentada (ADF) sobre la variable 'Electricity from renewables (TWh)'
adf_result <- adf.test(data_filtered$`Electricity from renewables (TWh)`)
# Imprimir los resultados del test ADF
print(adf_result)
##
## Augmented Dickey-Fuller Test
##
## data: data_filtered$`Electricity from renewables (TWh)`
## Dickey-Fuller = -1.3794, Lag order = 3, p-value = 0.8262
## alternative hypothesis: stationary
# **Descomposición de la serie**
# Descomposición de la serie
decompose_model <- stl(ts(data_filtered$`Electricity from renewables (TWh)`, frequency = 20), s.window = "periodic")
# Crear un gráfico para la serie de tiempo original
fig1 <- plot_ly(data = data_filtered, x = ~Year, y = ~`Electricity from renewables (TWh)`,
type = 'scatter', mode = 'lines',
line = list(color = 'blue', width = 2),
name = 'Electricidad de Renovables (TWh)') %>%
layout(title = 'Serie de tiempo - Electricity from Renewables (TWh)',
xaxis = list(title = 'Año'),
yaxis = list(title = 'Electricidad de Renovables (TWh)'))
fig1
# Crear un gráfico para el componente tendencial
fig2 <- plot_ly(x = ~data_filtered$Year,
y = ~decompose_model$time.series[, "trend"],
type = 'scatter', mode = 'lines',
line = list(color = 'red', width = 2),
name = 'Componente tendencial') %>%
layout(title = 'Componente tendencial',
xaxis = list(title = 'Año'),
yaxis = list(title = 'Valores'))
fig2
# Crear un gráfico para el componente estacional
fig3 <- plot_ly(x = ~data_filtered$Year,
y = ~decompose_model$time.series[, "seasonal"],
type = 'scatter', mode = 'lines',
line = list(color = 'green', width = 2),
name = 'Componente estacional') %>%
layout(title = 'Componente estacional',
xaxis = list(title = 'Año'),
yaxis = list(title = 'Valores'))
fig3
# Crear un gráfico para las variaciones irregulares (ruido)
fig4 <- plot_ly(x = ~data_filtered$Year,
y = ~decompose_model$time.series[, "remainder"],
type = 'scatter', mode = 'lines',
line = list(color = 'black', width = 2),
name = 'Variaciones irregulares (Ruido)') %>%
layout(title = 'Variaciones irregulares (Ruido)',
xaxis = list(title = 'Año'),
yaxis = list(title = 'Valores'))
fig4
## **P-Value**
# Aplicar el test ADF solo a los valores finitos (no NA) de los residuos
resid_non_nan <- decompose_model$resid[is.finite(decompose_model$resid)]
# Imprimir el p-valor
cat('p-valor:', adf_result$p.value, "\n")
## p-valor: 0.8262307
## **Prueba de normalidad.**
# Evaluar la normalidad del conjunto de datos residuales
library(stats) # Para la prueba Shapiro-Wilk
resid_clean <- decompose_model$resid
resid_clean[is.infinite(resid_clean)] <- NA # Reemplazar infinitos por NA
resid_clean <- na.omit(resid_clean) # Eliminar los NA
## **Residuos**
# Crear el gráfico Q-Q interactivo con Plotly
# Asegúrate de que residuals es un vector numérico
residuals <- as.numeric(decompose_model$resid) # Cambia esto si aún no lo has hecho
# Eliminar NA e infinitos
residuals <- residuals[is.finite(residuals)] # Eliminar NAs y valores infinitos
# Verificar la longitud después de la limpieza
cat("Número de residuos después de la limpieza:", length(residuals), "\n")
## Número de residuos después de la limpieza: 0
## **Modelo ARIMA**
## **Diferenciación**
nlag <- 30 # Definir el número de lags
# Crear el gráfico para la serie original
fig1 <- plot_ly(data_filtered, x = ~Year, y = ~`Electricity from renewables (TWh)`,
type = 'scatter', mode = 'lines',
line = list(width = 1, color = 'blue')) %>%
layout(title = 'Serie Original',
xaxis = list(title = 'Fecha'),
yaxis = list(title = 'Precio Ajustado'))
# Mostrar el gráfico interactivo de la serie original
fig1
# Gráfico de ACF para la serie original
acf_values <- acf(data_filtered$`Electricity from renewables (TWh)`, plot = FALSE, lag.max = nlag)
fig2 <- plot_ly()
# Añadir los puntos de ACF conectados al eje X
for (i in seq_along(acf_values$acf)) {
fig2 <- fig2 %>%
add_trace(x = c(i-1, i-1), y = c(0, acf_values$acf[i]), mode = 'lines', line = list(color = 'blue', width = 0.5)) %>%
add_trace(x = i-1, y = acf_values$acf[i], mode = 'markers', marker = list(color = 'blue', size = 8))
}
fig2 <- fig2 %>%
layout(title = 'Autocorrelación (ACF)',
xaxis = list(title = 'Lags'),
yaxis = list(title = 'ACF'))
# Mostrar el gráfico interactivo de ACF
fig2
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
# Gráfico de PACF para la serie original
pacf_values <- pacf(data_filtered$`Electricity from renewables (TWh)`, plot = FALSE, lag.max = nlag)
fig3 <- plot_ly()
# Añadir los puntos de PACF conectados al eje X
for (i in seq_along(pacf_values$acf)) {
fig3 <- fig3 %>%
add_trace(x = c(i-1, i-1), y = c(0, pacf_values$acf[i]), mode = 'lines', line = list(color = 'blue', width = 0.5)) %>%
add_trace(x = i-1, y = pacf_values$acf[i], mode = 'markers', marker = list(color = 'blue', size = 8))
}
fig3 <- fig3 %>%
layout(title = 'Autocorrelación Parcial (PACF)',
xaxis = list(title = 'Lags'),
yaxis = list(title = 'PACF'))
# Mostrar el gráfico interactivo de PACF
fig3
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
# Crear el gráfico para el diferenciador de primer orden
differenced_data <- diff(data_filtered$`Electricity from renewables (TWh)`)
differenced_years <- data_filtered$Year[-1] # Ajustar el año para el gráfico
fig4 <- plot_ly(x = differenced_years, y = differenced_data,
type = 'scatter', mode = 'lines',
line = list(width = 1, color = 'green')) %>%
layout(title = 'Diferenciador de Primer Orden',
xaxis = list(title = 'Fecha'),
yaxis = list(title = 'Diferencia'))
# Mostrar el gráfico interactivo del diferenciador de primer orden
fig4
# Gráfico de ACF para el diferenciador de primer orden
# Calcular el diferenciador de primer orden
differenced_values <- data_filtered$`Electricity from renewables (TWh)` %>%
diff() %>%
na.omit() # Eliminar el NA resultante
# Asegúrate de que el eje x tenga la misma longitud
years <- data_filtered$Year[-1] # Eliminar el primer año correspondiente al NA en el diferenciador
# Crear el gráfico para el diferenciador de primer orden
fig4 <- plot_ly() %>%
add_trace(x = years,
y = differenced_values,
type = 'scatter',
mode = 'lines',
line = list(width = 1, color = 'green')) %>%
layout(title = 'Diferenciador de Primer Orden',
xaxis = list(title = 'Fecha'),
yaxis = list(title = 'Diferencia'),
height = 400)
## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()
# Mostrar el gráfico interactivo del diferenciador de primer orden
fig4
# Gráfico de PACF para el diferenciador de primer orden
pacf_diff_values <- pacf(data_filtered$`Electricity from renewables (TWh)` %>% diff() %>% na.omit(), plot = FALSE, lag.max = nlag)
fig6 <- plot_ly()
# Añadir los puntos de PACF del diferenciador conectados al eje X
for (i in seq_along(pacf_diff_values$acf)) {
fig6 <- fig6 %>%
add_trace(x = c(i-1, i-1), y = c(0, pacf_diff_values$acf[i]), mode = 'lines', line = list(color = 'green', width = 0.5)) %>%
add_trace(x = i-1, y = pacf_diff_values$acf[i], mode = 'markers', marker = list(color = 'green', size = 8))
}
fig6 <- fig6 %>%
layout(title = 'Autocorrelación Parcial (PACF) del Diferenciador',
xaxis = list(title = 'Lags'),
yaxis = list(title = 'PACF'))
# Mostrar el gráfico interactivo de PACF del diferenciador
fig6
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plotly.com/r/reference/#scatter
# Realizar la prueba ADF para el diferenciador
adjclose_diff <- data_filtered$`Electricity from renewables (TWh)` %>% diff() %>% na.omit()
adf_result2 <- adf.test(adjclose_diff, alternative = "stationary", k = 0) # Ajusta el parámetro k si es necesario
## Warning in adf.test(adjclose_diff, alternative = "stationary", k = 0): p-value
## smaller than printed p-value
# Imprimir resultados de la prueba ADF
cat('ADF Statistic:', adf_result2$statistic, "\n")
## ADF Statistic: -7.621159
cat('p-value:', adf_result2$p.value, "\n")
## p-value: 0.01
# Cargar librerías necesarias
library(forecast) # Para el modelo ARIMA
library(dplyr) # Para manipulación de datos
library(tidyr) # Para manipulación de datos
library(ggplot2) # Para visualización
## **Criterios AIC, BIC y HQIC**
# Número total de observaciones en el conjunto de datos filtrado
n_data <- nrow(data_filtered)
# Definir el tamaño del conjunto de prueba (por ejemplo, 30 observaciones)
n_test <- 30
# Calcular el tamaño del conjunto de entrenamiento
train_size <- n_data - n_test
# Dividir los datos en conjuntos de entrenamiento y prueba
train <- data_filtered$`Electricity from renewables (TWh)`[1:train_size]
dates_train <- data_filtered$Year[1:train_size]
test <- data_filtered$`Electricity from renewables (TWh)`[(train_size + 1):(train_size + n_test)]
dates_test <- data_filtered$Year[(train_size + 1):(train_size + n_test)]
# Mostrar las formas de los conjuntos de entrenamiento y prueba
cat("Train:", length(train), "\n")
## Train: 33
cat("Test:", length(test), "\n")
## Test: 30
# Obtener los conjuntos de prueba de diferentes tamaños
test7 <- data_filtered$`Electricity from renewables (TWh)`[(train_size + 1):(train_size + 7)]
dates_test7 <- data_filtered$Year[(train_size + 1):(train_size + 7)]
test14 <- data_filtered$`Electricity from renewables (TWh)`[(train_size + 1):(train_size + 14)]
dates_test14 <- data_filtered$Year[(train_size + 1):(train_size + 14)]
test21 <- data_filtered$`Electricity from renewables (TWh)`[(train_size + 1):(train_size + 21)]
dates_test21 <- data_filtered$Year[(train_size + 1):(train_size + 21)]
test28 <- data_filtered$`Electricity from renewables (TWh)`[(train_size + 1):(train_size + 28)]
dates_test28 <- data_filtered$Year[(train_size + 1):(train_size + 28)]
# Crear DataFrames para los conjuntos de entrenamiento y prueba
train_df <- data_filtered[1:train_size, c("Electricity from renewables (TWh)")]
test_df <- data_filtered[(train_size + 1):(train_size + n_test), c("Electricity from renewables (TWh)")]
# Función para encontrar el mejor modelo ARIMA basado en AIC, BIC y HQIC
best_model <- function(train) {
best_aic <- Inf
best_bic <- Inf
best_hqic <- Inf
best_order_aic <- NULL
best_order_bic <- NULL
best_order_hqic <- NULL
best_mdl_aic <- NULL
best_mdl_bic <- NULL
best_mdl_hqic <- NULL
pq_rng <- 0:4
d_rng <- 0:2
# Iterar sobre todos los posibles valores de p, d y q
for (p in pq_rng) {
for (d in d_rng) {
for (q in pq_rng) {
# Ajustar el modelo ARIMA
tmp_mdl <- tryCatch(
Arima(train, order = c(p, d, q)),
error = function(e) NULL
)
if (!is.null(tmp_mdl)) {
# Obtener los valores de AIC, BIC y HQIC
tmp_aic <- AIC(tmp_mdl)
tmp_bic <- BIC(tmp_mdl)
# Calcular HQIC manualmente
n <- length(train) # Número de observaciones
tmp_hqic <- tmp_aic + 2 * (log(log(n))) # HQIC: AIC + 2 * log(log(n))
# Comparar el AIC
if (tmp_aic < best_aic) {
best_aic <- tmp_aic
best_order_aic <- c(p, d, q)
best_mdl_aic <- tmp_mdl
}
# Comparar el BIC
if (tmp_bic < best_bic) {
best_bic <- tmp_bic
best_order_bic <- c(p, d, q)
best_mdl_bic <- tmp_mdl
}
# Comparar el HQIC
if (tmp_hqic < best_hqic) {
best_hqic <- tmp_hqic
best_order_hqic <- c(p, d, q)
best_mdl_hqic <- tmp_mdl
}
}
}
}
}
return(list(
AIC = list(best_aic = best_aic, best_order = best_order_aic, best_model = best_mdl_aic),
BIC = list(best_bic = best_bic, best_order = best_order_bic, best_model = best_mdl_bic),
HQIC = list(best_hqic = best_hqic, best_order = best_order_hqic, best_model = best_mdl_hqic)
))
}
# Usar la función con tus datos de entrenamiento
results <- best_model(train_df$`Electricity from renewables (TWh)`)
# Mostrar resultados del AIC
cat("Mejor modelo basado en AIC:", results$AIC$best_aic, "\n")
## Mejor modelo basado en AIC: 373.612
cat("Mejor orden para AIC:", sprintf("(p=%d, d=%d, q=%d)",
results$AIC$best_order[1],
results$AIC$best_order[2],
results$AIC$best_order[3]), "\n")
## Mejor orden para AIC: (p=0, d=2, q=1)
# Mostrar resultados del BIC
cat("Mejor modelo basado en BIC:", results$BIC$best_bic, "\n")
## Mejor modelo basado en BIC: 376.4799
cat("Mejor orden para BIC:", sprintf("(p=%d, d=%d, q=%d)",
results$BIC$best_order[1],
results$BIC$best_order[2],
results$BIC$best_order[3]), "\n")
## Mejor orden para BIC: (p=0, d=2, q=1)
# Mostrar resultados del HQIC
cat("Mejor modelo basado en HQIC:", results$HQIC$best_hqic, "\n")
## Mejor modelo basado en HQIC: 376.1155
cat("Mejor orden para HQIC:", sprintf("(p=%d, d=%d, q=%d)",
results$HQIC$best_order[1],
results$HQIC$best_order[2],
results$HQIC$best_order[3]), "\n")
## Mejor orden para HQIC: (p=0, d=2, q=1)
library(forecast)
library(plotly)
# Función para el modelo ARIMA con pronóstico rodante
arima_rolling <- function(train_list, test, best_order_aic) {
# Inicializar un historial con los datos de entrenamiento
history <- unlist(train_list)
predictions <- numeric() # Inicializar un vector para las predicciones
# Asegúrate de que 'test' sea un vector
if (is.data.frame(test)) {
test <- as.numeric(test[,1]) # Convertir a vector numérico si es un data frame
}
# Iterar sobre cada punto de tiempo en el conjunto de prueba
for (t in seq_along(test)) {
# Ajustar modelo ARIMA
tryCatch({
model <- Arima(history, order = best_order_aic)
model_fit <- fit(model) # Ajustar el modelo
}, error = function(e) {
cat(sprintf("Error al ajustar el modelo en el paso %d: %s\n", t, e$message))
break
})
# Realizar la predicción
yhat <- forecast(model_fit, h = 1)$mean
predictions <- c(predictions, yhat) # Almacenar la predicción
# Obtener el valor real observado en el conjunto de prueba
obs <- test[t]
# Añadir la observación actual al conjunto de datos históricos
if (is.numeric(obs)) {
history <- c(history, obs)
} else {
cat(sprintf("Valor inesperado en test en el paso %d: %s\n", t, obs))
}
}
return(predictions)
}
# Cargar las librerías necesarias
library(forecast)
library(ggplot2)
library(dplyr)
library(lmtest)
## Cargando paquete requerido: zoo
##
## Adjuntando el paquete: 'zoo'
## The following objects are masked from 'package:data.table':
##
## yearmon, yearqtr
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
# Suponiendo que 'train', 'test7', 'test14', 'test21', 'test28' son tus conjuntos de datos
# Asegúrate de que estos datos estén correctamente definidos antes de ajustar el modelo
# Ajuste del modelo ARIMA automáticamente
model_fit_aic <- auto.arima(train)
# Función para el modelo ARIMA sin rolling forecast
arima_sin_rolling <- function(test, modelo) {
# Calcular el número de pasos de predicción basados en el tamaño del conjunto de prueba
forecast_steps <- length(test)
# Realizar las predicciones para el número de pasos determinado
forecast_tipo <- forecast(modelo, h = forecast_steps)
# Obtener los valores predichos
forecast_values <- as.numeric(forecast_tipo$mean)
# Imprimir los valores observados y predichos
for (i in seq_along(test)) {
observado <- test[i] # Valores observados
predicho <- forecast_values[i] # Acceder a los valores predichos por índice
cat(sprintf("Predicho: %.2f, Observado: %.2f\n", predicho, observado))
}
# Devolver las predicciones
return(forecast_values)
}
# Llamadas a la función para diferentes horizontes de predicción
cat('ARIMA sin Rolling AIC - Horizonte de 7 días.\n')
## ARIMA sin Rolling AIC - Horizonte de 7 días.
yhat7_sin_aic <- arima_sin_rolling(test7, model_fit_aic)
## Predicho: 48.81, Observado: 47.58
## Predicho: 48.81, Observado: 50.48
## Predicho: 48.81, Observado: 48.06
## Predicho: 48.81, Observado: 49.00
## Predicho: 48.81, Observado: 49.54
## Predicho: 48.81, Observado: 61.39
## Predicho: 48.81, Observado: 60.08
cat('\nARIMA sin Rolling AIC - Horizonte de 14 días.\n')
##
## ARIMA sin Rolling AIC - Horizonte de 14 días.
yhat14_sin_aic <- arima_sin_rolling(test14, model_fit_aic)
## Predicho: 48.81, Observado: 47.58
## Predicho: 48.81, Observado: 50.48
## Predicho: 48.81, Observado: 48.06
## Predicho: 48.81, Observado: 49.00
## Predicho: 48.81, Observado: 49.54
## Predicho: 48.81, Observado: 61.39
## Predicho: 48.81, Observado: 60.08
## Predicho: 48.81, Observado: 54.31
## Predicho: 48.81, Observado: 49.97
## Predicho: 48.81, Observado: 35.47
## Predicho: 48.81, Observado: 37.90
## Predicho: 48.81, Observado: 44.48
## Predicho: 48.81, Observado: 46.67
## Predicho: 48.81, Observado: 57.97
cat('\nARIMA sin Rolling AIC - Horizonte de 21 días.\n')
##
## ARIMA sin Rolling AIC - Horizonte de 21 días.
yhat21_sin_aic <- arima_sin_rolling(test21, model_fit_aic)
## Predicho: 48.81, Observado: 47.58
## Predicho: 48.81, Observado: 50.48
## Predicho: 48.81, Observado: 48.06
## Predicho: 48.81, Observado: 49.00
## Predicho: 48.81, Observado: 49.54
## Predicho: 48.81, Observado: 61.39
## Predicho: 48.81, Observado: 60.08
## Predicho: 48.81, Observado: 54.31
## Predicho: 48.81, Observado: 49.97
## Predicho: 48.81, Observado: 35.47
## Predicho: 48.81, Observado: 37.90
## Predicho: 48.81, Observado: 44.48
## Predicho: 48.81, Observado: 46.67
## Predicho: 48.81, Observado: 57.97
## Predicho: 48.81, Observado: 63.40
## Predicho: 48.81, Observado: 72.51
## Predicho: 48.81, Observado: 89.38
## Predicho: 48.81, Observado: 94.28
## Predicho: 48.81, Observado: 95.94
## Predicho: 48.81, Observado: 105.18
## Predicho: 48.81, Observado: 124.04
cat('\nARIMA sin Rolling AIC - Horizonte de 28 días.\n')
##
## ARIMA sin Rolling AIC - Horizonte de 28 días.
yhat28_sin_aic <- arima_sin_rolling(test28, model_fit_aic)
## Predicho: 48.81, Observado: 47.58
## Predicho: 48.81, Observado: 50.48
## Predicho: 48.81, Observado: 48.06
## Predicho: 48.81, Observado: 49.00
## Predicho: 48.81, Observado: 49.54
## Predicho: 48.81, Observado: 61.39
## Predicho: 48.81, Observado: 60.08
## Predicho: 48.81, Observado: 54.31
## Predicho: 48.81, Observado: 49.97
## Predicho: 48.81, Observado: 35.47
## Predicho: 48.81, Observado: 37.90
## Predicho: 48.81, Observado: 44.48
## Predicho: 48.81, Observado: 46.67
## Predicho: 48.81, Observado: 57.97
## Predicho: 48.81, Observado: 63.40
## Predicho: 48.81, Observado: 72.51
## Predicho: 48.81, Observado: 89.38
## Predicho: 48.81, Observado: 94.28
## Predicho: 48.81, Observado: 95.94
## Predicho: 48.81, Observado: 105.18
## Predicho: 48.81, Observado: 124.04
## Predicho: 48.81, Observado: 143.04
## Predicho: 48.81, Observado: 152.34
## Predicho: 48.81, Observado: 162.54
## Predicho: 48.81, Observado: 188.79
## Predicho: 48.81, Observado: 189.67
## Predicho: 48.81, Observado: 216.32
## Predicho: 48.81, Observado: 222.07
# Crear gráficos para cada horizonte de predicción
par(mfrow = c(2, 2), mar = c(4, 4, 2, 1)) # Ajustar la ventana de gráficos
# Gráfico para Horizonte de 7 días
plot(dates_train, train, type = "l", col = '#00008B', xlab = "Date", ylab = "Electricity", main = "7-Day Horizon")
lines(dates_test7, test7, col = '#9A32CD')
lines(dates_test7, yhat7_sin_aic, col = '#EE7600')
legend("topright", legend = c("Train", "Test", "Forecast"), col = c('#00008B', '#9A32CD', '#EE7600'), lty = 1)
# Gráfico para Horizonte de 14 días
plot(dates_train, train, type = "l", col = '#00008B', xlab = "Date", ylab = "Electricity", main = "14-Day Horizon")
lines(dates_test14, test14, col = '#9A32CD')
lines(dates_test14, yhat14_sin_aic, col = '#EE7600')
legend("topright", legend = c("Train", "Test", "Forecast"), col = c('#00008B', '#9A32CD', '#EE7600'), lty = 1)
# Gráfico para Horizonte de 21 días
plot(dates_train, train, type = "l", col = '#00008B', xlab = "Date", ylab = "Electricity", main = "21-Day Horizon")
lines(dates_test21, test21, col = '#9A32CD')
lines(dates_test21, yhat21_sin_aic, col = '#EE7600')
legend("topright", legend = c("Train", "Test", "Forecast"), col = c('#00008B', '#9A32CD', '#EE7600'), lty = 1)
# Gráfico para Horizonte de 28 días
plot(dates_train, train, type = "l", col = '#00008B', xlab = "Date", ylab = "Electricity", main = "28-Day Horizon")
lines(dates_test28, test28, col = '#9A32CD')
lines(dates_test28, yhat28_sin_aic, col = '#EE7600')
legend("topright", legend = c("Train", "Test", "Forecast"), col = c('#00008B', '#9A32CD', '#EE7600'), lty = 1)
# Análisis de residuos del modelo ARIMA basado en el criterio AIC
checkresiduals(model_fit_aic) # Esta función de forecast package muestra varios diagnósticos
##
## Ljung-Box test
##
## data: Residuals from ARIMA(0,1,0)
## Q* = 0.48703, df = 7, p-value = 0.9995
##
## Model df: 0. Total lags used: 7
# Realizar la prueba de Shapiro-Wilk para la normalidad de los residuos
shapiro_test <- shapiro.test(residuals(model_fit_aic))
cat(sprintf("Statistic = %.3f\n", shapiro_test$statistic))
## Statistic = 0.304
cat(sprintf("P-Value = %.3f\n", shapiro_test$p.value))
## P-Value = 0.000
# Interpretar el resultado de la prueba
if (shapiro_test$p.value < 0.05) {
cat("Se rechaza la hipótesis nula, por lo tanto los residuales no siguen una distribución normal.\n")
} else {
cat("No se rechaza la hipótesis nula, por lo tanto los residuales siguen una distribución normal.\n")
}
## Se rechaza la hipótesis nula, por lo tanto los residuales no siguen una distribución normal.
# Independencia de los residuos
# Extraer residuos del modelo ARIMA ajustado
residuos <- residuals(model_fit_aic)
# Aplicar la prueba Durbin-Watson a los residuos
dw <- dwtest(residuos ~ 1) # El "~ 1" indica que no estamos usando ninguna variable predictora
cat(sprintf("Statistic d = %.3f\n", dw$statistic))
## Statistic d = 2.022
if (dw$statistic < 1.5 || dw$statistic > 2.5) {
cat("La estadística Durbin-Watson indica posible autocorrelación en los residuos.\n")
} else {
cat("No hay evidencia significativa de autocorrelación en los residuos.\n")
}
## No hay evidencia significativa de autocorrelación en los residuos.