How to remove space between axis and plot area in ggplot2

Problem

We want to remove the space between the axis and the plotting area. The space between the axis and the tick marks.

# data
set.seed(0)
the.df <- data.frame( x = rnorm(800, 50, 10), group = rep(letters[1:8], each = 100))

# Original plot
p <- ggplot(the.df) + 
  stat_density(aes(x = x, linetype = group), geom = "line", position = "identity") +
  xlim(10, 90) + ylim(0, 0.06) +
  scale_linetype_manual(values = c("11", "12", "13", "14", "21", "22", "23", "24")) +
  geom_segment(aes(x = 10, y = 0, xend = 90, yend = 0)) +
  geom_segment(aes(x = 10, y = 0, xend = 10, yend = 0.06))

Solution

Two alternatives

Scale continuous an expand

Instead of xlim(10, 90) + ylim(0, 0.06) we use a continous scale for both axis scale_x_continuous y scale_x_continuous, specifying expand = c(0, 0).

p <- ggplot(the.df) + 
  stat_density(aes(x = x, linetype = group), geom = "line", position = "identity") +
  scale_linetype_manual(values = c("11", "12", "13", "14", "21", "22", "23", "24")) +
  scale_x_continuous(limits=c(10, 90), expand = c(0, 0)) +
  scale_y_continuous(limits=c(0, 0.06), expand = c(0, 0)) +
  geom_segment(aes(x = 10, y = 0, xend = 90, yend = 0)) +
  geom_segment(aes(x = 10, y = 0, xend = 10, yend = 0.06))

coord_cartesian

We can user coord_cartesian instead of scale_x_continuous y scale_x_continuous.

p <- ggplot(the.df) + 
  stat_density(aes(x = x, linetype = group), geom = "line", position = "identity") +
  scale_linetype_manual(values = c("11", "12", "13", "14", "21", "22", "23", "24")) +
  geom_segment(aes(x = 10, y = 0, xend = 90, yend = 0)) +
  geom_segment(aes(x = 10, y = 0, xend = 10, yend = 0.06))+
  coord_cartesian(xlim = c(10, 90), ylim = c(0, .06))

Another example

uniq <- structure(list(year = c(1986L, 1987L, 1991L, 1992L, 1993L, 1994L, 1995L, 1996L, 1997L, 1998L, 1999L, 2000L, 2001L, 2002L, 2003L, 2004L, 2005L, 2006L, 2007L, 2008L, 2009L, 2010L, 2011L, 2012L, 2013L, 2014L, 1986L, 1987L, 1991L, 1992L, 1993L, 1994L, 1995L, 1996L, 1997L, 1998L, 1999L, 2000L, 2001L, 2002L, 2003L, 2004L, 2005L, 2006L, 2007L, 2008L, 2009L, 2010L, 2011L, 2012L, 2013L, 2014L, 1986L, 1987L, 1991L, 1992L, 1993L, 1994L, 1995L, 1996L, 1997L, 1998L, 1999L, 2000L, 2001L, 2002L, 2003L, 2004L, 2005L, 2006L, 2007L, 2008L, 2009L, 2010L, 2011L, 2012L, 2013L, 2014L), uniq.loc = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("u.1", "u.2", "u.3"), class = "factor"), uniq.n = c(1, 1, 1, 2, 5, 4, 2, 16, 16, 10, 15, 14, 8, 12, 20, 11, 17, 30, 17, 21, 22, 19, 34, 44, 56, 11, 0, 0, 3, 3, 7, 17, 12, 21, 18, 10, 12, 9, 7, 11, 25, 14, 11, 17, 12, 24, 59, 17, 36, 50, 59, 12, 0, 0, 0, 1, 4, 6, 3, 3, 9, 3, 4, 2, 5, 2, 12, 6, 8, 8, 3, 2, 9, 5, 20, 7, 10, 8), uniq.p = c(100, 100, 25, 33.3, 31.2, 14.8, 11.8, 40, 37.2, 43.5, 48.4, 56, 40, 48, 35.1, 35.5, 47.2, 54.5, 53.1, 44.7, 24.4, 46.3, 37.8, 43.6, 44.8, 35.5, 0, 0, 75, 50, 43.8, 63, 70.6, 52.5, 41.9, 43.5, 38.7, 36, 35, 44, 43.9, 45.2, 30.6, 30.9, 37.5, 51.1, 65.6, 41.5, 40, 49.5, 47.2, 38.7, 0, 0, 0, 16.7, 25, 22.2, 17.6, 7.5, 20.9, 13, 12.9, 8, 25, 8, 21.1, 19.4, 22.2, 14.5, 9.4, 4.3, 10, 12.2, 22.2, 6.9, 8, 25.8)), .Names = c("year", "uniq.loc", "uniq.n", "uniq.p"), class = "data.frame", row.names = c(NA, -78L))

Original plot

ggplot(data = uniq) + 
  geom_area(aes(x = year, y = uniq.p, fill = uniq.loc), stat = "identity", position = "stack") +
  scale_x_continuous(limits=c(1986,2014)) +
  scale_y_continuous(limits=c(0,101)) +
  theme_bw()

Plot without spaces

# Scale_x_continuous y expand = c(0, 0)
ggplot(data = uniq) + 
  geom_area(aes(x = year, y = uniq.p, fill = uniq.loc), stat = "identity", position = "stack") +
  scale_x_continuous(limits=c(1986,2014), expand = c(0, 0)) +
  scale_y_continuous(limits=c(0,101), expand = c(0, 0)) +
  theme_bw() + theme(panel.grid=element_blank(), panel.border=element_blank())

 # coord_cartesian
ggplot(data = uniq) +  
  geom_area(aes(x = year, y = uniq.p, fill = uniq.loc), stat = "identity", position = "stack") +  
  coord_cartesian(xlim = c(1986,2014), ylim = c(0,101))+
  theme_bw() + theme(panel.grid=element_blank(), panel.border=element_blank())

References

• How to remove extra space beyond xlim and ylim in ggplot?
• How to remove space between axis & area-plot in ggplot2?

Calcular y representar la duración del día con R

Problema

Queremos calcular y representar la duración del día con R en función de unas coordinadas geográficas.

Solución

1. Calculamos la salida y puesta de sol

Primero calculamos la salida y la puesta de sol con la función getSunlightTimes del paquete suncalc. Indicamos el intervalo deseado, las coordinadas (latitud y longitud), y el huso horario (tz, time zone) correspondiente.

library(suncalc) 
library(tidyverse)
library(scales)
df <-
  getSunlightTimes(
    date = seq.Date(as.Date("2017-12-01"), as.Date("2018-12-31"), by = 1),
    keep = c("sunrise", "sunriseEnd", "sunset", "sunsetStart"),
    lat = 39.8628,
    lon = 4.0273,
    tz = "CET"
  )

2. Gráfico de la salida y puesta de sol

Necesitamos manipular los datos originales para calcular la diferencia entre el inicio del día, y la salida y puesta de sol. Después representamos las dos nuevas variables usando geom_ribbon de ggplot2. Luego personalizamos los ejes y el título.

# Amanecer/ocaso
df %>%
  mutate(
    date = as.POSIXct(date) - 12 * 60 * 60 ,
    sunrise = sunrise - date,
    sunset =  sunset - date,
  ) %>%
  ggplot() +
  geom_ribbon(aes(x = date, ymin = sunrise, ymax = sunset),
              fill = "#FDE725FF",
              alpha = .8) + # "#ffeda0"
  scale_x_datetime(
    breaks = seq(as.POSIXct(min(df$date)), as.POSIXct(max(df$date)), "month"),
    expand = c(0, 0),
    labels = date_format("%b %y"),
    minor_breaks = NULL
  ) +
  scale_y_continuous(
    limits = c(0, 24),
    breaks = seq(0, 24, 2),
    expand = c(0, 0),
    minor_breaks = NULL
  ) +
  labs(
    x = "Date",
    y = "Hours",
    title = sprintf(
      "Sunrise and Sunset for %s\n%s ",
      "Toledo (Spain)",
      paste0(as.Date(range(df$date)), sep = " ", collapse = "to ")
    )
  ) +
  theme(
    panel.background = element_rect(fill = "#180F3EFF"),
    panel.grid = element_line(colour = "grey", linetype = "dashed")
  )

3. Duración del día

Muy similar al gráfico anterior. Ahora solamente necesitamos calcular la duración del día day_length y representar los resultados con geom_area and geom_line.

df %>%
  mutate(
    date = as.POSIXct(date),
    day_length = as.numeric(sunset - sunrise)
  ) %>%
  ggplot(aes(x = date, y = day_length)) +
  geom_area(fill = "#FDE725FF", alpha = .4) +
  geom_line(color = "#525252") +
  scale_x_datetime(
    expand = c(0, 0),
    labels = date_format("%b '%y"),
    breaks =  seq(as.POSIXct(min(df$date)), as.POSIXct(max(df$date)), "month"),
    minor_breaks = NULL
  ) +
  scale_y_continuous(
    limits = c(0, 24),
    breaks = seq(0, 24, 2),
    expand = c(0, 0),
    minor_breaks = NULL
  ) +
  labs(x = "Date", y = "Hours", title = "Toledo (Spain) - Daytime duration") +
  theme_bw()

Entradas relacionadas

• Versión en inglés: Calculate and plot sunrise and sunset times with R
• English posts

Referencias

• suncalc
• ggplot2 formats

Calculate and plot sunrise and sunset times with R

Problem

We would like to calculate and plot the sunrise and sunset times based on any location's latitude and longitude coordinates with R.

Solution

1. Compute sunrise and sunset times

First we calculate the sunrise and sunset times using the function getSunlightTimes from the package suncalc. We pass the desired date interval, the appropiate latitude and longitude coordinates, and time zone (tz).

library(suncalc) 
library(tidyverse)
library(scales)
df <-
  getSunlightTimes(
    date = seq.Date(as.Date("2017-12-01"), as.Date("2018-12-31"), by = 1),
    keep = c("sunrise", "sunriseEnd", "sunset", "sunsetStart"),
    lat = 39.8628,
    lon = 4.0273,
    tz = "CET"
  )

2. Sunrise and sunset times plot

We need to manipulate the original data frame to calculate the difference between midnight start of day, and the sunrise and sunset times. Then we plot those two new variables using geom_ribbon from ggplot2. We further customize the axes, and title.

# Sunrise/set
df %>%
  mutate(
    date = as.POSIXct(date) - 12 * 60 * 60 ,
    sunrise = sunrise - date,
    sunset =  sunset - date,
  ) %>%
  ggplot() +
  geom_ribbon(aes(x = date, ymin = sunrise, ymax = sunset),
              fill = "#FDE725FF",
              alpha = .8) + # "#ffeda0"
  scale_x_datetime(
    breaks = seq(as.POSIXct(min(df$date)), as.POSIXct(max(df$date)), "month"),
    expand = c(0, 0),
    labels = date_format("%b %y"),
    minor_breaks = NULL
  ) +
  scale_y_continuous(
    limits = c(0, 24),
    breaks = seq(0, 24, 2),
    expand = c(0, 0),
    minor_breaks = NULL
  ) +
  labs(
    x = "Date",
    y = "Hours",
    title = sprintf(
      "Sunrise and Sunset for %s\n%s ",
      "Toledo (Spain)",
      paste0(as.Date(range(df$date)), sep = " ", collapse = "to ")
    )
  ) +
  theme(
    panel.background = element_rect(fill = "#180F3EFF"),
    panel.grid = element_line(colour = "grey", linetype = "dashed")
  )

3. Daytime duration

Very similar to the preceding plot. This time we only need to calculate the day_length and plot the results using geom_area and geom_line.

df %>%
  mutate(
    date = as.POSIXct(date),
    day_length = as.numeric(sunset - sunrise)
  ) %>%
  ggplot(aes(x = date, y = day_length)) +
  geom_area(fill = "#FDE725FF", alpha = .4) +
  geom_line(color = "#525252") +
  scale_x_datetime(
    expand = c(0, 0),
    labels = date_format("%b '%y"),
    breaks =  seq(as.POSIXct(min(df$date)), as.POSIXct(max(df$date)), "month"),
    minor_breaks = NULL
  ) +
  scale_y_continuous(
    limits = c(0, 24),
    breaks = seq(0, 24, 2),
    expand = c(0, 0),
    minor_breaks = NULL
  ) +
  labs(x = "Date", y = "Hours", title = "Toledo (Spain) - Daytime duration") +
  theme_bw()

Related posts

• Spanish version: Cómo controlar la dispersión de puntos dentro de un diagrama de violín con ggplot2
• English posts

References

• suncalc
• ggplot2 formats

Cambiar el color y añadir leyenda en un diagrama de barras por subgrupos en ggplot2

Problema

Cuando creamos un diagrama de barras por subgrupos (facet_grid), aunque especifiquemos color para el eje x, ggplot2 crea un gráfico monocromático, sin cambiar el color de cada columna.

library("ggplot2")    
ggplot(data = diamonds) + 
      geom_bar(mapping = aes(x = color, y = ..prop.., group = 2)) + 
      scale_y_continuous(labels=scales::percent) +
      facet_grid(~cut)

Solución

Al calcular la proporción por grupo, necesitamos especificar en una aesthetics (aes) diferente el color para alterar el comportamiento por defecto de ggplot2. Una dentro de la función ggplot y otra dentro de geom_bar con fill.

ggplot(data = diamonds, aes(x = color, y = ..prop.., group = cut)) + 
  geom_bar(aes(fill = factor(..x.., labels = LETTERS[seq(from = 4, to = 10 )]))) + 
  labs(fill = "color") + 
  scale_y_continuous(labels = scales::percent) + 
  facet_grid(~ cut)

Referencias

• stackoverflow

Cómo eliminar el espacio entre los ejes y el área del gráfico en ggplot2

Problema

Deseamos eliminar el espacio que existe entre los ejes y el área del gráfico (plotting area). Como se aprecia en el gráfico de más abajo, hay un espacio entre los ejes y el área gris que no comienza en las coordenadas (0, 0).

# Datos
set.seed(0)
the.df <- data.frame( x = rnorm(800, 50, 10), group = rep(letters[1:8], each = 100))

# Gráfico original
p <- ggplot(the.df) + 
  stat_density(aes(x = x, linetype = group), geom = "line", position = "identity") +
  xlim(10, 90) + ylim(0, 0.06) +
  scale_linetype_manual(values = c("11", "12", "13", "14", "21", "22", "23", "24")) +
  geom_segment(aes(x = 10, y = 0, xend = 90, yend = 0)) +
  geom_segment(aes(x = 10, y = 0, xend = 10, yend = 0.06))

Solución

Dos opciones:

Scale continuous y expand

En lugar de xlim(10, 90) + ylim(0, 0.06) empleamos escalas continuas, scale_x_continuous y scale_x_continuous y dentro incluimos expand = c(0, 0).

p <- ggplot(the.df) + 
  stat_density(aes(x = x, linetype = group), geom = "line", position = "identity") +
  scale_linetype_manual(values = c("11", "12", "13", "14", "21", "22", "23", "24")) +
  scale_x_continuous(limits=c(10, 90), expand = c(0, 0)) +
  scale_y_continuous(limits=c(0, 0.06), expand = c(0, 0)) +
  geom_segment(aes(x = 10, y = 0, xend = 90, yend = 0)) +
  geom_segment(aes(x = 10, y = 0, xend = 10, yend = 0.06))

coord_cartesian

Usar coord_cartesian en lugar de scale_x_continuous y scale_x_continuous.

p <- ggplot(the.df) + 
  stat_density(aes(x = x, linetype = group), geom = "line", position = "identity") +
  scale_linetype_manual(values = c("11", "12", "13", "14", "21", "22", "23", "24")) +
  geom_segment(aes(x = 10, y = 0, xend = 90, yend = 0)) +
  geom_segment(aes(x = 10, y = 0, xend = 10, yend = 0.06))+
  coord_cartesian(xlim = c(10, 90), ylim = c(0, .06))

Otro ejemplo

uniq <- structure(list(year = c(1986L, 1987L, 1991L, 1992L, 1993L, 1994L, 1995L, 1996L, 1997L, 1998L, 1999L, 2000L, 2001L, 2002L, 2003L, 2004L, 2005L, 2006L, 2007L, 2008L, 2009L, 2010L, 2011L, 2012L, 2013L, 2014L, 1986L, 1987L, 1991L, 1992L, 1993L, 1994L, 1995L, 1996L, 1997L, 1998L, 1999L, 2000L, 2001L, 2002L, 2003L, 2004L, 2005L, 2006L, 2007L, 2008L, 2009L, 2010L, 2011L, 2012L, 2013L, 2014L, 1986L, 1987L, 1991L, 1992L, 1993L, 1994L, 1995L, 1996L, 1997L, 1998L, 1999L, 2000L, 2001L, 2002L, 2003L, 2004L, 2005L, 2006L, 2007L, 2008L, 2009L, 2010L, 2011L, 2012L, 2013L, 2014L), uniq.loc = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("u.1", "u.2", "u.3"), class = "factor"), uniq.n = c(1, 1, 1, 2, 5, 4, 2, 16, 16, 10, 15, 14, 8, 12, 20, 11, 17, 30, 17, 21, 22, 19, 34, 44, 56, 11, 0, 0, 3, 3, 7, 17, 12, 21, 18, 10, 12, 9, 7, 11, 25, 14, 11, 17, 12, 24, 59, 17, 36, 50, 59, 12, 0, 0, 0, 1, 4, 6, 3, 3, 9, 3, 4, 2, 5, 2, 12, 6, 8, 8, 3, 2, 9, 5, 20, 7, 10, 8), uniq.p = c(100, 100, 25, 33.3, 31.2, 14.8, 11.8, 40, 37.2, 43.5, 48.4, 56, 40, 48, 35.1, 35.5, 47.2, 54.5, 53.1, 44.7, 24.4, 46.3, 37.8, 43.6, 44.8, 35.5, 0, 0, 75, 50, 43.8, 63, 70.6, 52.5, 41.9, 43.5, 38.7, 36, 35, 44, 43.9, 45.2, 30.6, 30.9, 37.5, 51.1, 65.6, 41.5, 40, 49.5, 47.2, 38.7, 0, 0, 0, 16.7, 25, 22.2, 17.6, 7.5, 20.9, 13, 12.9, 8, 25, 8, 21.1, 19.4, 22.2, 14.5, 9.4, 4.3, 10, 12.2, 22.2, 6.9, 8, 25.8)), .Names = c("year", "uniq.loc", "uniq.n", "uniq.p"), class = "data.frame", row.names = c(NA, -78L))

Gráfico original

ggplot(data = uniq) + 
  geom_area(aes(x = year, y = uniq.p, fill = uniq.loc), stat = "identity", position = "stack") +
  scale_x_continuous(limits=c(1986,2014)) +
  scale_y_continuous(limits=c(0,101)) +
  theme_bw()

Gráfico sin espacios

# Scale_x_continuous y expand = c(0, 0)
ggplot(data = uniq) + 
  geom_area(aes(x = year, y = uniq.p, fill = uniq.loc), stat = "identity", position = "stack") +
  scale_x_continuous(limits=c(1986,2014), expand = c(0, 0)) +
  scale_y_continuous(limits=c(0,101), expand = c(0, 0)) +
  theme_bw() + theme(panel.grid=element_blank(), panel.border=element_blank())

 # coord_cartesian
ggplot(data = uniq) +  
  geom_area(aes(x = year, y = uniq.p, fill = uniq.loc), stat = "identity", position = "stack") +  
  coord_cartesian(xlim = c(1986,2014), ylim = c(0,101))+
  theme_bw() + theme(panel.grid=element_blank(), panel.border=element_blank())

Referencias

• How to remove extra space beyond xlim and ylim in ggplot?
• How to remove space between axis & area-plot in ggplot2?