Calendar heatmap by hour and weekday in ggplot2

Problem

We want to create a calendar heatmap using ggplot2.

Solution

In our example we generate random dates, and then group the results by hour of the day and day of the week.

library(tidyverse)
library(lubridate)
# Data
set.seed(2020)
df <-
  data.frame(dates = sample(seq(
    as.POSIXct('2019/01/01', tz = "CET"),
    as.POSIXct('2019/12/31', tz = "CET"),
    by = "sec"
  ), 1000))

# Data manipulation
df %>%
  mutate(days = factor(weekdays(dates, abbreviate = TRUE),
                       levels = rev(
                         c('Sun', 'Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat')
                       ))) %>%
  group_by(hours= hour(dates), days) %>%
  summarise(sessions = n()) %>%

# Plot
ggplot(aes(hours, days)) +
  geom_tile(aes(fill = sessions), colour = "white") +
  scale_fill_distiller(palette = "YlGnBu", direction = 1) +
  scale_x_continuous(breaks = 0:23) +
  theme_minimal() +
  theme(
    legend.position = "bottom",
    legend.key.width = unit(2, "cm"),
    panel.grid = element_blank()
  ) +
  coord_equal()

Results

Related posts

• How to create a calendar heatmap in R

References

• stackoverflow

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?

Generar un mapa de calor por días y horas con ggplot2

Problema

Queremos crear un mapa de calor, con teselas coloreadas en función de la frecuencia en ggplot2.

Solución

library(dplyr)
library(lubridate)
library(ggplot2)

# Generamos fechas aleatorias
set.seed(2015)
df <-
  data.frame(fechas = sample(seq(
    as.POSIXct('2018/01/01', tz = "CET"),
    as.POSIXct('2018/12/31', tz = "CET"),
    by = "sec"
  ), 1000))

# Manipulamos el data frame 
# 1. Cambiamos el nombre de los días de la semana
# 2. Agrupamos por horas y días
df %>%
  mutate(Días = factor(
    weekdays(fechas),
    levels = rev(
      c(
        "Monday",
        "Tuesday",
        "Wednesday",
        "Thursday",
        "Friday",
        "Saturday",
        "Sunday"
      )
    ),
    labels = c(
      "Domingo",
      "Sábado",
      "Viernes",
      "Jueves",
      "Miércoles",
      "Martes",
      "Lunes"
    )
  )) %>%
  group_by(Horas = hour(fechas), Días) %>%
  summarise(Sesiones = n()) %>%
# Creamos el gráfico
  ggplot(aes(Horas, Días)) +
  geom_tile(aes(fill = Sesiones), colour = "white") +
  scale_fill_distiller(palette = "YlGnBu", direction = 1) +
  scale_x_continuous(breaks = 0:23) +
  theme_minimal() +
  theme(
    legend.position = "bottom",
    legend.key.width = unit(2, "cm"),
    panel.grid = element_blank()
  ) +
  coord_equal()

Resultado

Referencias

• stackoverflow
• Entradas de geom_tile

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?