Smoothing in ggplot2

How to use Smoothing in ggplot2 online to add a line with specified slope and intercept to the plot.


Plotly Studio: Transform any dataset into an interactive data application in minutes with AI. Sign up for early access now.

Gaussian

library(plotly)

p <- qplot(speed, dist, data=cars)
p <- p + geom_smooth(method = "glm", formula = y~x, family = gaussian(link = 'log'))

ggplotly(p)

Inspired by Stack Overflow

Horizontal Line & Fit

library(plotly)

the.data <- read.table( header=TRUE, sep=",",
                        text="source,year,value
    S1,1976,56.98
    S1,1977,55.26
    S1,1978,68.83
    S1,1979,59.70
    S1,1980,57.58
    S1,1981,61.54
    S1,1982,48.65
    S1,1983,53.45
    S1,1984,45.95
    S1,1985,51.95
    S1,1986,51.85
    S1,1987,54.55
    S1,1988,51.61
    S1,1989,52.24
    S1,1990,49.28
    S1,1991,57.33
    S1,1992,51.28
    S1,1993,55.07
    S1,1994,50.88
    S2,1993,54.90
    S2,1994,51.20
    S2,1995,52.10
    S2,1996,51.40
    S3,2002,57.95
    S3,2003,47.95
    S3,2004,48.15
    S3,2005,37.80
    S3,2006,56.96
    S3,2007,48.91
    S3,2008,44.00
    S3,2009,45.35
    S3,2010,49.40
    S3,2011,51.19")

cutoff <- data.frame( x = c(-Inf, Inf), y = 50, cutoff = factor(50) )

p <- ggplot(the.data, aes( year, value ) ) +
    geom_point(aes( colour = source )) +
    geom_smooth(aes( group = 1 )) +
    geom_hline(yintercept = 50)

ggplotly(p)

Inspired by Stack Overflow

Facets

library(plyr)
library(plotly)
library(Lahman)

hr_stats_df <- ddply(Batting, .(playerID), function(df) c(mean(df$HR, na.rm = T),
                                                          max(df$HR, na.rm = T), sum(df$HR, na.rm = T), nrow(df)))
names(hr_stats_df)[c(2, 3, 4, 5)] <- c("HR.mean", "HR.max", "HR.total", "career.length")
hr_stats_long_df <- subset(hr_stats_df, career.length >= 10)
Batting_hr <- merge(Batting, hr_stats_long_df)
Batting_hr_cy <- ddply(Batting_hr, .(playerID), function(df) transform(df, career.year = yearID -
                                                                           min(yearID) + 1))
start_year_df <- ddply(Batting_hr_cy, .(playerID), function(df) min(df$yearID))
names(start_year_df)[2] <- "start.year"

# Merge this with other data.
Batting_hr_cy2 <- merge(Batting_hr_cy, start_year_df)
Batting_early <- subset(Batting_hr_cy2, start.year < 1940)
Batting_late <- subset(Batting_hr_cy2, start.year > 1950)
tot_HR_early <- subset(Batting_early, select = c(playerID, HR.total))

# Remove the duplicate rows:
tot_HR_early <- unique(tot_HR_early)
tot_HR_early_srt <- arrange(tot_HR_early, desc(HR.total))
top10_HR_hitters_early <- tot_HR_early_srt[1:10, "playerID"]
tot_HR_late <- subset(Batting_late, select = c(playerID, HR.total))

# Remove the duplicate rows:
tot_HR_late <- unique(tot_HR_late)
tot_HR_late_srt <- arrange(tot_HR_late, desc(HR.total))
top10_HR_hitters_late <- tot_HR_late_srt[1:10, "playerID"]
Batting_early_top10 <- subset(Batting_early, playerID %in% top10_HR_hitters_early)

p <- ggplot(data = Batting_early_top10, aes(x = career.year, y = HR/AB)) +
  geom_point() +
  facet_wrap(~playerID, ncol = 3) + 
  geom_smooth()

ggplotly(p)

Inspired by Steven Buechler.

What About Dash?

Dash for R is an open-source framework for building analytical applications, with no Javascript required, and it is tightly integrated with the Plotly graphing library.

Learn about how to install Dash for R at https://dashr.plot.ly/installation.

Everywhere in this page that you see fig, you can display the same figure in a Dash for R application by passing it to the figure argument of the Graph component from the built-in dashCoreComponents package like this:

library(plotly)

fig <- plot_ly() 
# fig <- fig %>% add_trace( ... )
# fig <- fig %>% layout( ... ) 

library(dash)
library(dashCoreComponents)
library(dashHtmlComponents)

app <- Dash$new()
app$layout(
    htmlDiv(
        list(
            dccGraph(figure=fig) 
        )
     )
)

app$run_server(debug=TRUE, dev_tools_hot_reload=FALSE)