AmberGuzman_FinalProject_

###GGplot ###Barplots Now lets take a look at some ggplot2 barplots

we’ll start with making a dataframe based on the tooth data

df <- data.frame(dose = c("D0.5", "D1", "D2"),
                 len = c(4.2, 10, 29.5))

df

##   dose  len
## 1 D0.5  4.2
## 2   D1 10.0
## 3   D2 29.5

And now lets make a second dataframe

df2 <- data.frame(supp=rep(c("vc", "oj"), each = 3), 
                  dose = rep(c("D0.5", "D1", "D2"), 2),
                  len = c(6.8, 15, 33, 4.2, 10, 29.5))

df2

##   supp dose  len
## 1   vc D0.5  6.8
## 2   vc   D1 15.0
## 3   vc   D2 33.0
## 4   oj D0.5  4.2
## 5   oj   D1 10.0
## 6   oj   D2 29.5

lets load up ggplot2

library(ggplot2)

Lets set our parameters for ggplot

theme_set(
  theme_classic() + 
    theme(legend.position = "top")
)

Lets start with some basic barplots using tooth data

f <- ggplot(df, aes(x = dose, y = len))

f + geom_col()

Now lets chnage the fill, and add labels to the top

f + geom_col(fill = "purple") +
  geom_text(aes(label = len), vjust = -0.3)

Now lets add the label inside the bars

f + geom_col(fill = "purple") + 
  geom_text(aes(label = len), vjust = 1.6, color = "white")

Now lets change the barplot colors by group

f + geom_col(aes(color = dose), fill = "white") + scale_color_manual(values = c("pink", "yellow", "purple"))

this is kinda hard to see, so lets change the fill

f + geom_col(aes(fill = dose)) + scale_fill_manual(values = c("pink", "yellow", "purple"))

ok how do we do this multiple groups

ggplot(df2, aes(x = dose, y = len)) + 
  geom_col(aes(color = supp, fill =supp), position =  position_stack()) + 
  scale_color_manual(values = c("pink", "yellow")) + 
  scale_fill_manual(values = c("pink", "yellow"))

p <- ggplot(df2, aes(x = dose, y = len)) + 
  geom_col(aes(color =supp, fill = supp), position = position_dodge(0.8), width = 0.7) + 
  scale_color_manual(values = c("pink", "yellow")) + 
  scale_fill_manual(values= c("pink", "yellow"))

p

Now lets add those labels to the dodged barplot

p + geom_text(
  aes(label = len, group = supp), 
  position = position_dodge(0.8), 
  vjust = -0.3, size = 3.5
)

Now what if we want to add labels to our stacked barplots? For this we need dplyr

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

df2 <- df2 %>%
  group_by(dose) %>%
  arrange(dose, desc(supp)) %>%
  mutate(lab_ypos = cumsum(len) - 0.5 * len)

df2

## # A tibble: 6 × 4
## # Groups:   dose [3]
##   supp  dose    len lab_ypos
##   <chr> <chr> <dbl>    <dbl>
## 1 vc    D0.5    6.8      3.4
## 2 oj    D0.5    4.2      8.9
## 3 vc    D1     15        7.5
## 4 oj    D1     10       20  
## 5 vc    D2     33       16.5
## 6 oj    D2     29.5     47.8

Now lets recreate our stacked graphs

ggplot(df2, aes(x= dose, y = len)) + 
  geom_col(aes(fill = supp), width = 0.7) + 
  geom_text(aes(y= lab_ypos, label = len, group = supp), color = "black") + 
  scale_color_manual(values = c("pink", "yellow")) + 
  scale_fill_manual(values = c("pink", "yellow"))

###Boxplots Lets look ar some boxplots

data("ToothGrowth")

Lets change the dose to a factor, and look at the top of the dataframe

ToothGrowth$dose <- as.factor(ToothGrowth$dose)

head(ToothGrowth, 4)

##    len supp dose
## 1  4.2   VC  0.5
## 2 11.5   VC  0.5
## 3  7.3   VC  0.5
## 4  5.8   VC  0.5

Lets load ggplot

library(ggplot2)

Lets set the theme for our plots to classic

theme_set(
  theme_bw() + 
    theme(legend.position = "top")
)

Lets start with a very basic boxplot with dose vs length

tg <- ggplot(ToothGrowth, aes(x = dose, y = len))
tg + geom_boxplot()

Now lets look at a boxplot with points for the mean

tg + geom_boxplot(notch = TRUE, fill = "Lightblue") + 
  stat_summary(fun.y = mean, geom = "point", shape = 18, size = 2.5, color = "indianred")

## Warning: The `fun.y` argument of `stat_summary()` is deprecated as of ggplot2 3.3.0.
## ℹ Please use the `fun` argument instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

We can also change the scale number of variables included, and their order

tg + geom_boxplot() + 
  scale_x_discrete(limits = c("0.5", "2"))

## Warning: Removed 20 rows containing missing values (`stat_boxplot()`).

Lets put our x axis in descending order

tg + geom_boxplot() + 
  scale_x_discrete(limits = c("2", "1", "0.5"))

we can also change boxplot colors by groups

tg + geom_boxplot(aes(color = dose)) + 
  scale_color_manual(values = c("indianred", "blue1", "green2"))

what if er want to display our data subset by oj vs vitamin c?

tg2 <- tg + geom_boxplot(aes(fill = supp), position = position_dodge(0.9)) + 
  scale_fill_manual(values = c("orange", "yellow"))

tg2

we can also arrange this as two plots with facet_wrap

tg2 + facet_wrap(~supp)

###Histograms

set.seed(1234)

wdata = data.frame(
  sex = factor(rep(c("F", "M"), each = 200)), 
  weight = c(rnorm(200, 50), rnorm(200, 58))
)

head(wdata, 4)

##   sex   weight
## 1   F 48.79293
## 2   F 50.27743
## 3   F 51.08444
## 4   F 47.65430

Now lets load dplyr

library(dplyr)

mu <- wdata %>%
  group_by(sex) %>%
  summarise(grp.mean = mean(weight))

Now lets load a plotting package

library(ggplot2)

theme_set(
  theme_classic() + 
    theme(legend.position = "bottom")
)

Now lets create a ggplot object

a <- ggplot(wdata, aes(x= weight))

a + geom_histogram(bins = 30, color = "black", fill = "grey") + 
  geom_vline(aes(xintercept = mean(weight)),
             linetype = "dashed", size = 0.6)

## 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.

Now lets change the color by group

a + geom_histogram(aes(color = sex), fill = "white", position = "identity") + 
  scale_color_manual(values = c("pink", "blue"))

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

a + geom_histogram(aes(color = sex, fill = sex), position = "identity") + 
  scale_color_manual(values = c("pink", "blue")) + 
  scale_fill_manual(values = c("pink", "blue"))

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

what if we want to combine density plots and histograms?

a + geom_histogram(aes(y = stat(density)), 
                   color = "black", fill = "white") + 
  geom_density(alpha = 0.2, fill = "#FF6666")

## Warning: `stat(density)` was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(density)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

a + geom_histogram(aes(y = stat(density), color = sex), 
                   fill = "white", position = "identity") + 
  geom_density(aes(color = sex), size = 1) + 
  scale_color_manual(values = c("indianred", "lightblue"))

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

###DotPlots First lets load the required packages

library(ggplot2)

Lets set our theme

theme_set(
  theme_dark() + 
    theme(legend.position = "top")
)

First lets initiate a ggplot object called TG

data("ToothGrowth")
ToothGrowth$dose <- as.factor(ToothGrowth$dose)

tg <- ggplot(ToothGrowth, aes(x = dose, y = len))

lets create a dotplot with a summary statistic

tg + geom_dotplot(binaxis = "y", stackdir = "center", fill = "white") + 
  stat_summary(fun = mean, fun.args = list(mult = 1))

## Bin width defaults to 1/30 of the range of the data. Pick better value with
## `binwidth`.

## Warning: Removed 3 rows containing missing values (`geom_segment()`).

Lets add a boxplot and dotplot together

tg + geom_boxplot(width = 0.5) + 
  geom_dotplot(binaxis = "y", stackdir = "center", fill = "white")

## Bin width defaults to 1/30 of the range of the data. Pick better value with
## `binwidth`.

tg + geom_violin(trim = FALSE) + 
  geom_dotplot(binaxis = "y", stackdir = "center", fill = "#999999") + 
  stat_summary(fun = mean, fun.args = list(mult = 1))

## Bin width defaults to 1/30 of the range of the data. Pick better value with
## `binwidth`.

## Warning: Removed 3 rows containing missing values (`geom_segment()`).

Lets create a dotplot with multiple groups

tg + geom_boxplot(width = 0.5) + 
  geom_dotplot(aes(fill = supp), binaxis = "y", stackdir = "center") + 
  scale_fill_manual(values = c("indianred", "lightblue"))

## Bin width defaults to 1/30 of the range of the data. Pick better value with
## `binwidth`.

tg + geom_boxplot(aes(color = supp), width = 0.5, position = position_dodge(0.8)) + 
  geom_dotplot(aes(fill = supp, color = supp), binaxis = "y", stackdir = "center", 
               dotsize = 0.8, position = position_dodge(0.8)) + 
  scale_fill_manual(values = c("#00AFBB", "#E7B800")) +
  scale_color_manual(values = c("#00AFBB", "#E7B800"))

## Bin width defaults to 1/30 of the range of the data. Pick better value with
## `binwidth`.

###Lineplots Now lets change it up and look at some line plots

we’ll start by making a cusotm dataframe kinda like the tooth dataset. This way we can see the lines and stuff that we’re modifying

df <- data.frame(dose = c("D0.5", "D1", "D2"), 
                 len = c(4.2, 10, 29.5))

Now lets create a second dataframe for plotting by groups

df2 <- data.frame(supp = rep(c("vc", "oj"), each = 3), 
                  dose = rep(c("D0.5", "D1", "D2"), 2), 
                  len = c(6.8, 15, 33, 4.2, 10, 29.5))

df2

##   supp dose  len
## 1   vc D0.5  6.8
## 2   vc   D1 15.0
## 3   vc   D2 33.0
## 4   oj D0.5  4.2
## 5   oj   D1 10.0
## 6   oj   D2 29.5

Now lets again load ggplot2 and set a theme

library(ggplot2)

theme_set(
  theme_gray() + 
    theme(legend.position = "right")
  
)

Now lets do some basic line plots. First we will build a function to display all the different line types

generateRLineTypes <- function(){
  oldpar <- par()
  par(font = 2, mar = c(0,0,0,0))
  plot(1, pch = "", ylim = c(0,6), xlim = c(0, 0.7), axes = FALSE, xlab = "", ylab = "")
  for(i in 0.6) lines(c(0.3, 0.7), c(i, i), lty = i, lwd = 3)
  text(rep(0.1, 6), 0:6, labels = c("0. 'Blank'", "1. 'solid'", "2. 'dashed'", "3. 'dotted'",
                                 "4. 'dotdash'", "5. 'longdash'", "6. 'twodash'"))
  par(mar = oldpar$mar, font = oldpar$font)
}

generateRLineTypes()

Now lets build a basic line plot

p <- ggplot(data = df, aes(x = dose, y = len, group = 1))

p + geom_line() + geom_point()

Now lets modify the line type and color

p + geom_line(linetype = "dashed", color = "steelblue") + 
  geom_point(color = "steelblue")

Now lets try a step graph, which indicates a threshold type progression

p + geom_step() + geom_point()

Now lets move on to making multiple groups. First we’ll create our ggplot object

p <- ggplot(df2, aes(x = dose, y = len, group = supp))

Now lets change line types and point shapes by group

p + geom_line(aes(linetype = supp, color = supp)) + 
  geom_point(aes(shape = supp, color = supp)) + 
  scale_color_manual(values = c("red", "blue"))

Now lets look at line plots with a numeric x axis

df3 <- data.frame(supp = rep(c("vc", "oj"), each = 3), 
                  dose = rep(c("0.5", "1","2"), 2), 
                  len = c(6.8, 15, 33, 4.2, 10, 29.5))

df3

##   supp dose  len
## 1   vc  0.5  6.8
## 2   vc    1 15.0
## 3   vc    2 33.0
## 4   oj  0.5  4.2
## 5   oj    1 10.0
## 6   oj    2 29.5

Now lets plot where both axises are treated as continous labels

df3$dose <- as.numeric(as.vector(df3$dose))
ggplot(data = df3, aes(x = dose, y = len, goup = supp, color = supp)) + 
  geom_line() + geom_point()

Now lets look at a line graph with having the x axis as dates. We’ll use teh build in economics time series for this example.

head(economics)

## # A tibble: 6 × 6
##   date         pce    pop psavert uempmed unemploy
##   <date>     <dbl>  <dbl>   <dbl>   <dbl>    <dbl>
## 1 1967-07-01  507. 198712    12.6     4.5     2944
## 2 1967-08-01  510. 198911    12.6     4.7     2945
## 3 1967-09-01  516. 199113    11.9     4.6     2958
## 4 1967-10-01  512. 199311    12.9     4.9     3143
## 5 1967-11-01  517. 199498    12.8     4.7     3066
## 6 1967-12-01  525. 199657    11.8     4.8     3018

ggplot(data = economics, aes(x = date, y = pop)) + 
  geom_line()

Now lets subset the data

ss <- subset(economics, date > as.Date("2006-1-1"))
ggplot(data = ss, aes(x = date, y = pop)) + geom_line()

We can also change the line size, for instance by another vairable like unemployment

ggplot(data = economics, aes(x = date, y = pop)) + 
  geom_line(aes(size = unemploy/pop))

we can also plot multiple time-series data

ggplot(economics, aes(x = date)) + 
  geom_line(aes(y = psavert), color = "darkred") + 
  geom_line(aes(y = uempmed), color = "steelblue", linetype = "twodash")

Lastly, lets make this into an area plot

ggplot(economics, aes(x = date)) + 
  geom_area(aes(y = psavert), fill = "#999999", 
            color = "#999999", alpha = 0.5) + 
  geom_area(aes(y = uempmed), fill = "#E69F00", 
            color = "#E69F00", alpha = 0.5)

###Ridge Plots First lets load the required packages

library(ggplot2)
library(ggridges)

#BiocManager::install("ggridges")

Now lets load some sample data

?airquality

air <- ggplot(airquality) + aes(Temp, Month, group = Month) + geom_density_ridges()

air

## Picking joint bandwidth of 2.65

Now lets add some pazzaz to our graph

library(viridis)

## Loading required package: viridisLite

ggplot(airquality) + aes(Temp, Month, group = Month, fill = ..x..) + 
  geom_density_ridges_gradient() + 
  scale_fill_viridis(option = "c", name = "temp")

## Warning in viridisLite::viridis(256, alpha, begin, end, direction, option):
## Option 'c' does not exist. Defaulting to 'viridis'.

## Warning: The dot-dot notation (`..x..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(x)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

## Picking joint bandwidth of 2.65

Last thing we will do is creat a facet plot for all our data.

library(tidyr)

airquality %>%
gather(key = "Measurement", value = "value", Ozone, Solar.R, Wind, Temp) %>%
  ggplot() + aes(value, Month, group = Month) + 
  geom_density_ridges() + 
  facet_wrap(~ Measurement, scales = "free")

## Picking joint bandwidth of 11

## Picking joint bandwidth of 40.1

## Picking joint bandwidth of 2.65

## Picking joint bandwidth of 1.44

## Warning: Removed 44 rows containing non-finite values
## (`stat_density_ridges()`).

###Density Plots A density plot is a nice alternative to a histogram

set.seed(1234)

wdata = data.frame(
  sex = factor(rep(c("F", "M"), each = 200)), 
  weight = c(rnorm(200, 55), rnorm(200, 58))
)

library(dplyr)
mu <- wdata %>%
  group_by(sex) %>%
summarise(grp.mean = mean(weight))

Now lets load the graphing packages

library(ggplot2)
theme_set(
  theme_classic() + 
    theme(legend.position = "right")
)

Now lets do the basic plot function. First we will create a ggplot object

d <- ggplot(wdata, aes(x = weight))

Now lets do a basic density plot

d + geom_density() + 
  geom_vline(aes(xintercept = mean(weight)), linetype = "dashed")

Noe lwts change the y axis to count instead of density

d + geom_density(aes(y = stat(count)), fill = "lightgray") + 
  geom_vline(aes(xintercept = mean(weight)), linetype = "dashed")

d + geom_density(aes(color = sex)) + 
  scale_color_manual(values = c("darkgray", "gold"))

Lastly, lets fill the density plots

d + geom_density(aes(fill =sex), alpha = 0.4) + 
  geom_vline(aes(xintercept = grp.mean, color = sex), data = mu, linetype = "dashed") + 
  scale_color_manual(values = c("gray", "gold")) + 
  scale_fill_manual(values = c("gray", "gold"))

###Plotly ###Line Plots First lets load our required package

library(plotly)

## 
## Attaching package: '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

Lets start with a scatter plot of the orange dataset

Orange <- as.data.frame(Orange)

plot_ly(data = Orange, x = ~age, y = ~circumference)

## 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 scatter mode specifed:
##   Setting the mode to markers
##   Read more about this attribute -> https://plotly.com/r/reference/#scatter-mode

Now lets add some more info

plot_ly(data = Orange, x = ~age, y = ~circumference,
        color = ~Tree, size = ~age,
        text = ~paste("Tree ID:", Tree, "<br>Age:", age, "circ:", circumference)
)

## 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 scatter mode specifed:
##   Setting the mode to markers
##   Read more about this attribute -> https://plotly.com/r/reference/#scatter-mode

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

Now lets create a random distribution and add it to our dataframe

trace_1 <- rnorm(35, mean = 120, sd = 10)
new_data <- data.frame(Orange, trace_1)

we’ll use the random numbers as lines on the graph

plot_ly(data = new_data, x = ~age, y = ~circumference, color = ~Tree, size = ~age,
        text = ~paste("Tree ID:", Tree, "br>Age:", age, "<br>circ:", circumference)) %>%
  add_trace(y = ~trace_1, mode = 'line') %>%
  add_trace(y = ~circumference, mode = 'markers')

## 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

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

Now lets create a graph to option of showing as a scatter or line, and add labels.

plot_ly(data = Orange, x= ~age, y = ~circumference,
        color = ~Tree, size = ~circumference,
        text = ~paste("Tree ID:", Tree, "<br>Age:",age, "circ:", circumference)) %>%
  add_trace(y = ~circumference, mode = 'markers') %>%
  layout(
    title = "plot or Orange data with switchable trace",
    updatemenus = list(
      type = 'downdrop', 
      y = 0.8,
      buttons = list(
        list(method = 'resyle',
             args = list('mode', 'markers'),
             labels = "markers"
      ),
      list(method = "restyle",
           args = list('mode', 'lines'),
           labels = "Lines"
           )
     )
   )
  )

## 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

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

## Warning: `line.width` does not currently support multiple values.

###Plotly 3D First lets load our required packages

library(plotly)

Now lets create a random 3d matrix

d <- data.frame(
  x <- seq(1, 10, by = 0.5),
  y <- seq(1, 10, by = 0.5)
)

z <- matrix(rnorm(length(d$x) * length(d$y)), nrow = length(d$x), ncol = length(d$y))

Now lets plot our 3D data

plot_ly(d, x = ~x, y = ~y, z = ~z) %>%
  add_surface()

Lets add some more aspects to it, such as at topography

plot_ly(d, x = ~x, y = ~y, z = ~z) %>%
  add_surface(
    contours = list(
      z = list(
        show = TRUE,
        usecolormap = TRUE, 
        highlightcolor = "FF0000", 
        project = list(z = TRUE)
      )
    )
  )

Now lets look at a 3d scatter plot

plot_ly(longley, x = ~GNP, y = ~Population, z = ~Employed, marker = list(color = ~GNP)) %>%
  add_markers()

###Other Graphing Techniques ###Error Bars First lets load our required librbaries

library(ggplot2)
library(dplyr)
library(plotrix)

theme_set(
  theme_classic() + 
    theme(legend.position = 'top')
)

Lets again use the tooth data for this exercise

df <- ToothGrowth
df$dose <- as.factor(df$dose)

NOw lets use dplyr for manipulation purpose

df.summary <- df %>%
  group_by(dose) %>%
  summarise(
    sd = sd(len, na.rm = TRUE),
    stderr = std.error(len, na.rm = TRUE),
    len = mean(len),
  )

df.summary

## # A tibble: 3 × 4
##   dose     sd stderr   len
##   <fct> <dbl>  <dbl> <dbl>
## 1 0.5    4.50  1.01   10.6
## 2 1      4.42  0.987  19.7
## 3 2      3.77  0.844  26.1

Lets now look at some key functions

geom_crossbar() for hollow bars with middle indicated by a horizontal line geom_errorbar() for error bars geom_errorbarh() for horizontal error bars geom_linrange() for drawing an internal represted by a vertical line *geom_pointrange() for creating an internal represnted by a vertical line; with a point in the middle

lets start by creating a ggplot object

tg <- ggplot(
  df.summary,
  aes(x = dose, y = len, ymin = len - sd, ymax = len +sd)
)

Now lets look at the most basic error bars

tg + geom_pointrange()

tg + geom_errorbar(width = 0.2) + 
  geom_point(size = 1.5)

Now lets create horizontal error bars by maninpuating our graph

ggplot(df.summary, aes(x = len, y = dose, xmin = len - sd, xmax = len + sd)) + 
  geom_point() + 
  geom_errorbarh(height = 0.2)

This just give you an idea of error bars on the horizontal axis

Now lets look at adding jitter points (actual measurements) to our data.

ggplot(df, aes(dose, len)) + 
  geom_jitter(position = position_jitter(0.2), color = "darkgray") + 
  geom_pointrange(aes(ymin = len - sd, ymax = len + sd), data = df.summary)

Now lets try error bars on a violin plot

ggplot(df, aes(dose, len)) + 
  geom_violin(color = "darkgray", trim = FALSE) + 
  geom_pointrange(aes(ymin = len - sd, ymax = len + sd), data = df.summary)

Now how about with a line graph?

ggplot(df.summary, aes(dose, len)) + 
  geom_line(aes(group = 1)) + # always specify this when you have 1 line
  geom_errorbar(aes(ymin = len - stderr, ymax = len + stderr), width = 0.2) + 
  geom_point(size = 2)

Now lets make a bar graph with halve error bars

ggplot(df.summary, aes(dose, len)) + 
  geom_col(fill = "lightgray", color = "black") + 
  geom_errorbar(aes(ymin = len, ymax = len + stderr), width = 0.2)

You can see that by not specifying wmin = len - stderr, we have in essence cut our error bar in half.

How about we add jitter points to line plots? We need to use the original dataframe for the jitter plot, and the summary df for the geom layers.

ggplot(df, aes(dose, len)) + 
  geom_jitter(position = position_jitter(0.2), color = "darkgray") + 
  geom_line(aes(group = 1), data = df.summary) + 
  geom_errorbar(
    aes(ymin = len - stderr, ymax = len + stderr), 
    data = df.summary, width = 0.2) + 
  geom_point(data = df.summary, size = 0.2)

what about adding jitterpoints to a barplot?

ggplot(df, aes(dose, len)) + 
  geom_col(data = df.summary, fill = NA, color ="black") + 
  geom_jitter(position = position_jitter(0.2), color= "pink") + 
  geom_errorbar(aes(ymin = len - stderr, ymax = len + stderr),
                data = df.summary, width = 0.2)

what if we wanted to have our error bars per group? (oj vs vc)

df.summary2 <- df %>%
  group_by(dose, supp) %>%
  summarise(
    sd = sd(len),
    stderr = std.error(len),
    len = mean(len)
  )

## `summarise()` has grouped output by 'dose'. You can override using the
## `.groups` argument.

df.summary2

## # A tibble: 6 × 5
## # Groups:   dose [3]
##   dose  supp     sd stderr   len
##   <fct> <fct> <dbl>  <dbl> <dbl>
## 1 0.5   OJ     4.46  1.41  13.2 
## 2 0.5   VC     2.75  0.869  7.98
## 3 1     OJ     3.91  1.24  22.7 
## 4 1     VC     2.52  0.795 16.8 
## 5 2     OJ     2.66  0.840 26.1 
## 6 2     VC     4.80  1.52  26.1

Now you can see we have mean and error for each dose and supp

ggplot(df.summary2, aes(dose, len)) + 
  geom_pointrange(
    aes(ymin = len - stderr, ymax = len + stderr, color = supp),
    position = position_dodge(0.3)) + 
  scale_color_manual(values = c("indianred", "lightblue"))

how about line plots with multiple error bars?

ggplot(df.summary2, aes(dose, len)) + 
  geom_line(aes(linetype = supp, group = supp)) + 
  geom_point() +
  geom_errorbar(aes(ymin = len - stderr, ymax = len + stderr, group = supp), width = 0.2)

And the same with a bar plot

ggplot(df.summary2, aes(dose, len)) + 
  geom_col(aes(fill =supp), position = position_dodge(0.8), width = 0.7) + 
  geom_errorbar(
    aes(ymin = len - stderr, ymax = len + stderr, group = supp),
    width = 0.2, position = position_dodge(0.8)) +
  scale_fill_manual(values = c("indianred", "lightblue"))

Now lets add some jitterpoints

ggplot(df, aes(dose, len, color = supp)) + 
  geom_jitter(position = position_jitterdodge(0.2)) + 
  geom_line(aes(group = supp), data = df.summary2) + 
  geom_point() +
  geom_errorbar(aes(ymin = len - stderr, ymax = len + stderr, group = supp), data = df.summary2, width = 0.2)

ggplot(df, aes(dose, len, color = supp)) + 
  geom_col(data = df.summary2, position = position_dodge(0.8), width = 0.7, fill = "white") +
  geom_jitter(
    position = position_jitterdodge(jitter.width = 0.2, dodge.width = 0.8)) +
  geom_errorbar(
    aes(ymin = len - stderr, ymax = len + stderr), data = df.summary2,
    width = 0.2, position = position_dodge(0.8)) +
  scale_color_manual(values = c("indianred", "lightblue")) + 
  theme(legend.position = "top")

###ECDF Plots Now lets do an empirical cumulative distribution function. This reports any given number percentile of individuals that are above or below that treshold.

set.seed(1234)

wdata = data.frame(
  sex = factor(rep(c("F", "M"), each = 200)),
  weight = c(rnorm(200, 50), rnorm(200, 58)))

Now lets look at our dataframe

head(wdata, 5)

##   sex   weight
## 1   F 48.79293
## 2   F 50.27743
## 3   F 51.08444
## 4   F 47.65430
## 5   F 50.42912

Now lets load our plotting package

library(ggplot2)

theme_set(
  theme_classic() + 
    theme(legend.position = "bottom")
)

Now lets create our ECDF plot

ggplot(wdata, aes(x = weight)) +
  stat_ecdf(aes(color = sex, linetype = sex),
            geom = "step", size = 1.5) +
  scale_color_manual(values = c("#00AFBB", "#E7B900")) +
  labs(y = "weight")

###qq Plots Now lets take a look at qq plots. These are used to determine if the given data follows a normal distribution.

#install.packages("ggpubr")

set.seed(1234)

Now lets randomly generate some data

wdata = data.frame(
  sex = factor(rep(c("F", "M"), each = 200)),
  weight = c(rnorm(200, 55), rnorm(200, 58))
)

Lets set our theme for the graphing with ggplot

library(ggplot2)

theme_set(
  theme_classic() + 
    theme(legend.position = "top")
)

create a qq plot of the weight

ggplot(wdata, aes(sample = weight)) + 
  stat_qq(aes(color = sex)) + 
  scale_color_manual(values = c("#0073C2FF", "#FC4E07")) +
  labs(y = "weight")

#install.packages(ggpubr)
library(ggpubr)

ggqqplot(wdata, x = "weight",
         color = "sex",
         palettes = c("#0073C2FF", "#FC4E07"),
         ggtheme = theme_pubclean())

Now what would a non-normal distribution look like?

#install.packages(mnonr)

library(mnonr)

data2 <- mnonr::mnonr(n = 1000, p = 2, ms = 3, mk = 61, Sigma = matrix(c(1, 0.5, 0.5, 1), 2, 2), initial = NULL)

data2 <- as.data.frame(data2)

Now lets plot the non normal data

ggplot(data2, aes(sample = V1)) +
  stat_qq()

ggqqplot(data2, x = "V1",
         palette = "#0073C2FF",
         ggtheme = theme_pubclean())

###Facet Plots Lets look at how to put multiple plots together into a single figure

library(ggpubr)
library(ggplot2)

theme_set(
  theme_bw() +
    theme(legend.position = "top")
)

First lets crete a nice boxplot

Lets load the data

df <- ToothGrowth
df$dose <- as.factor(df$dose)

and create the plot object

p <- ggplot(df,aes(x = dose, y = len)) + 
  geom_boxplot(aes(fill = supp), position = position_dodge(0.9)) +
  scale_fill_manual(values = c("#00AFBB", "#E7B800"))

p

Now lets look at the ggplot facet function

p + facet_grid(rows = vars(supp))

Now lets do a facet with multiple variables

p + facet_grid(rows = vars(dose), cols = vars(supp))

p

Now lets look at the facet_wrap functions. This allows facets to be placed side-by-side

p + facet_wrap(vars(dose), ncol = 2)

Now how do we combine multiple plots using ggarrange()

Lets start by making some basic plots.First we will define a color palette and data

my3cols <- c("#e7B800", "#2E9FDF", "#FC4E07")
ToothGrowth$dose <- as.factor(ToothGrowth$dose)

Now lets make some basic plots

p <- ggplot(ToothGrowth, aes(x = dose, y = len))
bxp <- p + geom_boxplot(aes(color = dose)) + 
  scale_color_manual(values = my3cols)

ok now lets do a dotplot

dp <- p + geom_dotplot(aes(color = dose, fill = dose),
                       binaxis = 'y', stackdir = 'center') +
  scale_color_manual(values = my3cols) +
  scale_fill_manual(values = my3cols)

Now lastly lets creat a lineplot

lp <- ggplot(economics, aes(x = date, y = psavert)) +
  geom_line(color = "indianred")

Now we can make the figure

figure <- ggarrange(bxp, dp, lp, labels = c("A","B", "C"), ncol = 2, nrow = 2)

## Bin width defaults to 1/30 of the range of the data. Pick better value with
## `binwidth`.

This looks great, but we can make it look even better

figure2 <- ggarrange(
  lp,
  ggarrange(bxp, dp, ncol = 2, nlabs = c("B", "C")),
  nrow = 2,
  labels = "A")

## Bin width defaults to 1/30 of the range of the data. Pick better value with
## `binwidth`.

## Warning in as_grob.default(plot): Cannot convert object of class character into
## a grob.

## Warning in as_grob.default(plot): Cannot convert object of class listggarrange
## into a grob.

figure2

Ok this looks really good, but you’ll notice that there are two legends that are the same.

ggarrange(
  bxp, dp, labels = c("A", "B"),
  common.legned = TRUE, legend = "bottom")

## Bin width defaults to 1/30 of the range of the data. Pick better value with
## `binwidth`.

lastly, we should export the plot

ggexport(figure2, filename = "facetfigure.pdf")

## file saved to facetfigure.pdf

we can also export multiple plots to a pdf

ggexport(bxp, dp, lp, filename = "multi.pdf")

## Bin width defaults to 1/30 of the range of the data. Pick better value with
## `binwidth`.
## file saved to multi.pdf

lastly, we can export to pdf with multiple pages and multiple columns

ggexport(bxp, dp, lp, bxp, filename = "test2.pdf", nrow = 2, ncol = 1)

## Bin width defaults to 1/30 of the range of the data. Pick better value with
## `binwidth`.
## file saved to test2.pdf

###Heatmaps Lets get started with heatmaps

#install.package(heatmap3)

library(heatmap3)

Now lets get our data.

data <- ldeaths

data2 <- do.call(cbind, split(data, cycle(data)))
dimnames(data2) <- dimnames(.preformat.ts(data))

Now lets generate a heat map

heatmap(data2)

heatmap(data2, Rowv = NA, Colv = NA)

Now lets play with the colors

rc <- rainbow(nrow(data2), start = 0, end = 0.3)
cc<- rainbow(ncol(data2), start = 0 , end = 0.3)

Now lets apply our color selection

heatmap(data2, ColSideColors = cc)

library(RColorBrewer)
heatmap(data2, ColSideColors = cc,
        col = colorRampPalette(brewer.pal(8, "PiYG"))(25))

Theres more that we can customize

library(gplots)

## 
## Attaching package: 'gplots'

## The following object is masked from 'package:plotrix':
## 
##     plotCI

## The following object is masked from 'package:stats':
## 
##     lowess

heatmap.2(data2, ColSideColors = cc,
          col = colorRampPalette(brewer.pal(8, "PiYG"))(25))

###Outlier Detection ###Missing Values Missing Values

If you encouter a unusual values in your dataset, and simply want to move on to the rest of your analysis, you have two options:

Drop the entire row with the strange values:

library(dplyr)
library(ggplot2)

diamonds <- diamonds

diamonds2 <- diamonds %>%
  filter(between(y, 3, 20))

In this instance, y is the width of the diamon, so anything under 3 mm or above 20 is excluded

I don’t recommand this option, just because there is one bad measurement doesn’t mean they are all bad

Instead, I recommand replacing the unusual values with missing values

diamonds3 <- diamonds %>%
  mutate(y = ifelse(y < 3 | y > 20, NA, y))

Like R, ggplot2 subscribes to the idea that missing values shouldn’t pass silently into the night.

ggplot(data = diamonds2, mapping = aes(x = x, y = y)) +
  geom_point()

If you want to supress that warning you can use na.rm = TRUE

ggplot(data = diamonds3, mapping = aes(x = x, y = y)) +
  geom_point(na.rm = TRUE)

Other times you want to understand what makes observations with missing values different to the other observation with record values. For example, in the NYCflights13 dataset, missing values in the dept_time variable indicate that the flight was cancelled. So you might want to compare the scheduled departure time for cancelled and non-cancelled times.

library(nycflights13)

nycflights13::flights %>%
  mutate(
    cancelled = is.na(dep_time),
    sched_hour = sched_dep_time %% 100, 
    sched_min = sched_dep_time %% 100, 
    sched_dep_time = sched_hour + sched_min / 60 
  ) %>%
  ggplot(mapping = aes(sched_dep_time)) + 
  geom_freqpoly(mapping = aes(color = cancelled), bindwith = 1/4)

## Warning in geom_freqpoly(mapping = aes(color = cancelled), bindwith = 1/4):
## Ignoring unknown parameters: `bindwith`

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

###Outliers What if we ant to know what our outliers are?

First we need to load the required libraries

library(outliers)
library(ggplot2)
library(readxl)

And reload the dataset because we removed outliers

Air_data <- read_xlsx("AirQualityUCI.xlsx")

Lets creat a function using the grubb test to identify all outliers. The grubbs test identifies outliers in a univeriate dataset that is presumed to come from a normal distribution.

grubbs.flag <- function(x) {
  #lets creat a variable called outliers and save nothing in it, we'll add to the variables
  # as we identify them 
  outliers <- NULL
  # we'll create a varibale called test to identify which univariate we are testing
  test <- x
  # now using the outliers package, use grubbs.test to find outliers in our variable 
  grubbs.result <- grubbs.test(test)
  # lets get the p-values of all tested variables
  pv <- grubbs.result$p.value
  # now lets search through our p-values for ones that are outside of 0.5
  while(pv < 0.5) {
    # anything with pvalues greater than p = 0.5, we add to our emtpy outliers vecotr
    outliers <- c(outliers, as.numeric(strsplit(grubbs.result$alternative," ")[[1]] [3]))
    # now we want to remove thouse outliers from our test variable
    test <- x[!x %in% outliers]
    # and run the grubbs test again without the outliers
    grubbs.result <- grubbs.test(test)
    # and save the new p values
    pv <- grubbs.result$p.value
  }
  return(data.frame(x = x, outliers = (x %in% outliers)))
}

idenitified_outliers <- grubbs.flag(Air_data$AH)

Now we can create a histogram showing where the outliers were

ggplot(grubbs.flag(Air_data$AH), aes(x = Air_data$AH, color = outliers, fill = outliers)) + 
  geom_histogram(bindwidth = diff(range(Air_data$AH))/30) +
  theme_bw()

## Warning in geom_histogram(bindwidth = diff(range(Air_data$AH))/30): Ignoring
## unknown parameters: `bindwidth`

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

###Covariation CATEGORICAL VARIABLES

library(ggplot2)

ggplot(data = diamonds, mapping = aes(x = price)) +
  geom_freqpoly(mapping = aes(color = cut), bindwidth = 500)

## Warning in geom_freqpoly(mapping = aes(color = cut), bindwidth = 500): Ignoring
## unknown parameters: `bindwidth`

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Its hard to see the difference in distribution because the counts differ so much

ggplot(diamonds) +
  geom_bar(mapping = aes(x = cut))

to make the comparison easier, we need to swap the display on the y-axis. Instead of diplaying count, we’ll display density, which is the count standardized so that the area under tech curve is one.

ggplot(data = diamonds, mapping = aes(x = price, y = ..density..)) +
  geom_freqpoly(mapping = aes(color = cut), bindwidth = 500)

## Warning in geom_freqpoly(mapping = aes(color = cut), bindwidth = 500): Ignoring
## unknown parameters: `bindwidth`

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

It appears that fair diamonds (the lowest cut quality) have the highest average price. But maybe that because frequency polygons are little hard to interpret.

Another alternative is the boxplot. A boxplot is a type of visual shorthand for a distribution of values.

ggplot(data = diamonds, mapping = aes(x = cut, y = price)) +
  geom_boxplot()

We see much less information about the distribution, but the boxplots are much more compact, so we can more easily compare them. It supports the conterintuitive finding that better quality diamonds are cheaper on average!

lets look at some car data

ggplot(data = mpg, mapping = aes(x = class, y = hwy)) + 
  geom_boxplot()

ggplot(data = mpg) +
  geom_boxplot(mapping = aes(x = reorder(class, hwy, FUN = median), y = hwy))

If you have long variable names, you can switch the axis and flip it 90 degrees.

ggplot(data = mpg) +
  geom_boxplot(mapping = aes(x = reorder(class, hwy, FUN = median), y = hwy)) +
  coord_flip()

To visualize the correlation between to continous variables, we can use a scatter plot.

ggplot(data = diamonds) +
  geom_point(mapping = aes(x = carat, y = price))

scatterplots become less useful as the size of your dataset grows, because we get overplot. We can fix this using the alpha aesthetic

ggplot(data = diamonds) +
  geom_point(mapping = aes(x = carat, y = price), alpha = 1/100)

###Exploratory Data Analysis 1-5 First lets load required library

library(RCurl)

## 
## Attaching package: 'RCurl'

## The following object is masked from 'package:tidyr':
## 
##     complete

library(dplyr)

Now lets get our data

site <- "https://raw.githubusercontent.com/nytimes/covid-19-data/master/colleges/colleges.csv"

college_Data <- read.csv(site)

First lets use the str function, this shows the structure of the object

str(college_Data)

## 'data.frame':    1948 obs. of  9 variables:
##  $ date      : chr  "2021-05-26" "2021-05-26" "2021-05-26" "2021-05-26" ...
##  $ state     : chr  "Alabama" "Alabama" "Alabama" "Alabama" ...
##  $ county    : chr  "Madison" "Montgomery" "Limestone" "Lee" ...
##  $ city      : chr  "Huntsville" "Montgomery" "Athens" "Auburn" ...
##  $ ipeds_id  : chr  "100654" "100724" "100812" "100858" ...
##  $ college   : chr  "Alabama A&M University" "Alabama State University" "Athens State University" "Auburn University" ...
##  $ cases     : int  41 2 45 2742 220 4 263 137 49 76 ...
##  $ cases_2021: int  NA NA 10 567 80 NA 49 53 10 35 ...
##  $ notes     : chr  "" "" "" "" ...

what if we want to arrange our dataset alphabetically by college?

alphabetical <- college_Data %>%
  arrange(college_Data$college)

The glimpse package is another way to preview data

glimpse(college_Data)

## Rows: 1,948
## Columns: 9
## $ date       <chr> "2021-05-26", "2021-05-26", "2021-05-26", "2021-05-26", "20…
## $ state      <chr> "Alabama", "Alabama", "Alabama", "Alabama", "Alabama", "Ala…
## $ county     <chr> "Madison", "Montgomery", "Limestone", "Lee", "Montgomery", …
## $ city       <chr> "Huntsville", "Montgomery", "Athens", "Auburn", "Montgomery…
## $ ipeds_id   <chr> "100654", "100724", "100812", "100858", "100830", "102429",…
## $ college    <chr> "Alabama A&M University", "Alabama State University", "Athe…
## $ cases      <int> 41, 2, 45, 2742, 220, 4, 263, 137, 49, 76, 67, 0, 229, 19, …
## $ cases_2021 <int> NA, NA, 10, 567, 80, NA, 49, 53, 10, 35, 5, NA, 10, NA, 19,…
## $ notes      <chr> "", "", "", "", "", "", "", "", "", "", "", "", "", "", "",…

we can also sybset with select()

college_cases <- select(college_Data, college, cases)

we can also filter or subset with the filter function

Louisiana_cases <- filter(college_Data, state == "Louisiana")

Lets filter out a smaller amount of states

south_cases <- filter(college_Data, state == "Louisiana" | state == "Texas" | state == "Arkansas" | state == "Mississippi")

Lets look at some time series data

First we’ll load the required libraries

library(lubridate)

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

library(dplyr)
library(ggplot2)
library(gridExtra)

## 
## Attaching package: 'gridExtra'

## The following object is masked from 'package:dplyr':
## 
##     combine

library(scales)

## 
## Attaching package: 'scales'

## The following object is masked from 'package:plotrix':
## 
##     rescale

## The following object is masked from 'package:viridis':
## 
##     viridis_pal

Now lets load some data

state_site <- "https://raw.githubusercontent.com/nytimes/covid-19-data/master/us-states.csv"

state_Data <- read.csv(state_site)

Lets create group_by object using the state column

state_cases <- group_by(state_Data, state)

class(state_cases)

## [1] "grouped_df" "tbl_df"     "tbl"        "data.frame"

How many meausurements were made by state? This gives us an idea of when states started reporting

Days_since_first_reported <- tally(state_cases)

Lets visualize some data

First lets start off with some definitions

Data - obvious - the stuff we want to visualize

Layer - made of gemetric elements and requisite statistical information. Include geomtric objects with represents the plot

scales = used to map values in the data space that is used for creation of values (color, size, shape, etc)

coordinate system - describes how the data coordinates are mapped together in relation to the plan on the graphing

Faceting - how to break up data in to subsets to display multiple types or groups of data

theme - controls finer points of the display, such as font size and background color

options(repr.plot.width = 6, repr.plot.height = 6)

class(college_Data)

## [1] "data.frame"

head(college_Data)

##         date   state     county       city ipeds_id
## 1 2021-05-26 Alabama    Madison Huntsville   100654
## 2 2021-05-26 Alabama Montgomery Montgomery   100724
## 3 2021-05-26 Alabama  Limestone     Athens   100812
## 4 2021-05-26 Alabama        Lee     Auburn   100858
## 5 2021-05-26 Alabama Montgomery Montgomery   100830
## 6 2021-05-26 Alabama     Walker     Jasper   102429
##                           college cases cases_2021 notes
## 1          Alabama A&M University    41         NA      
## 2        Alabama State University     2         NA      
## 3         Athens State University    45         10      
## 4               Auburn University  2742        567      
## 5 Auburn University at Montgomery   220         80      
## 6  Bevill State Community College     4         NA

summary(college_Data)

##      date              state              county              city          
##  Length:1948        Length:1948        Length:1948        Length:1948       
##  Class :character   Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character  
##                                                                             
##                                                                             
##                                                                             
##                                                                             
##    ipeds_id           college              cases          cases_2021    
##  Length:1948        Length:1948        Min.   :   0.0   Min.   :   0.0  
##  Class :character   Class :character   1st Qu.:  32.0   1st Qu.:  23.0  
##  Mode  :character   Mode  :character   Median : 114.5   Median :  65.0  
##                                        Mean   : 363.5   Mean   : 168.1  
##                                        3rd Qu.: 303.0   3rd Qu.: 159.0  
##                                        Max.   :9914.0   Max.   :3158.0  
##                                                         NA's   :337     
##     notes          
##  Length:1948       
##  Class :character  
##  Mode  :character  
##                    
##                    
##                    
## 

Now lets take a look at a different dataset

iris <- as.data.frame(iris)

class(iris)

## [1] "data.frame"

head(iris)

##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 5          5.0         3.6          1.4         0.2  setosa
## 6          5.4         3.9          1.7         0.4  setosa

summary(iris)

##   Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
##  Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100  
##  1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300  
##  Median :5.800   Median :3.000   Median :4.350   Median :1.300  
##  Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199  
##  3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800  
##  Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500  
##        Species  
##  setosa    :50  
##  versicolor:50  
##  virginica :50  
##                 
##                 
## 

Lets start by creating a scatter plot of the college Data

ggplot(data = college_Data, aes(x = cases, y = cases_2021)) +
  geom_point() + 
  theme_minimal()

## Warning: Removed 337 rows containing missing values (`geom_point()`).

Now lets do the iris data

ggplot(data = iris, aes(x = Sepal.Width, y = Sepal.Length)) + 
  geom_point() +
  theme_minimal()

Lets color coordinate our college Data

ggplot(data = college_Data, aes(x = cases, y = cases_2021, color = state)) + 
  geom_point() +
  theme_minimal()

## Warning: Removed 337 rows containing missing values (`geom_point()`).

Lets color coordinate the iris data

ggplot(data = iris, aes(x = Sepal.Width, y = Sepal.Length, color = Species)) +
  geom_point() +
  theme_minimal()

Lets run a simple histogram of our Louisiana Case Data

hist(Louisiana_cases$cases, freq = NULL, density = NULL, breaks = 10, xlab = "Total cases", ylab
     = "Frequency", main = "Total College covid-19 Infections (Louisiana)")

Lets run a simple histogram for the Iris data

hist(iris$Sepal.Width, freq = NULL, density = NULL, breaks = 10, xlab = "Sepal Width", ylab = 
       "Frequency", main = "Iris Sepal Width")

histogram_college <- ggplot(data = Louisiana_cases, aes(x = cases))

histogram_college + geom_histogram(bindwidth = 100, color = "black", aes(fill = county)) + 
  xlab("cases") + ylab("Frequency") + ggtitle("Histogram of covid-19 cases in Louisiana")

## Warning in geom_histogram(bindwidth = 100, color = "black", aes(fill =
## county)): Ignoring unknown parameters: `bindwidth`

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Lets create a ggplot of the IRIS data

histogram_iris <- ggplot(data = iris, aes(x = Sepal.Width))

histogram_iris + geom_histogram(bindwith = 0.2, color = "black",aes(fill = Species)) + 
  xlab("sepal width") + ylab("Frequency") + ggtitle("Histogram of Iris Sepal Width by Species")

## Warning in geom_histogram(bindwith = 0.2, color = "black", aes(fill =
## Species)): Ignoring unknown parameters: `bindwith`

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Maybe a density plot makes more sense for our college data

ggplot(south_cases) +
  geom_density(aes(x = cases, fill = state), alpha = 0.25)

Lets do it with the iris data

ggplot(iris) + 
  geom_density(aes(x = Sepal.Width, fill = Species), aplha = 0.25)

## Warning in geom_density(aes(x = Sepal.Width, fill = Species), aplha = 0.25):
## Ignoring unknown parameters: `aplha`

Lets look at violin plots for iris

ggplot(data = iris, aes(x = Species, y = Sepal.Length, color = Species)) + 
  geom_violin() + 
  theme_classic() +
  theme(legend.position = "none")

Now lets try the south data

ggplot(data = south_cases, aes(x = state, y = cases, color = state)) + 
  geom_violin() + 
  theme_gray() +
  theme(legend.position = "none")

Now lets take a look at residual plots. This is a graph that displays the residuals on the vertical axis, and the independent variable on the horizontal. In the event that the points in a residual plot are dispersed in a random manner around the horizontal axis, it is appropriate to use a linear regression. If they are not randomly dispersed, a non linear model is more appropriate.

Lets start with the iris data

ggplot(lm(Sepal.Length ~ Sepal.Width, data = iris)) + 
  geom_point(aes(x = .fitted, y = .resid))

Now look at the souther cases

ggplot(lm(cases ~ cases_2021, data = south_cases)) +
  geom_point(aes(x = .fitted, y = .resid))

A linear model is not a good call for the state cases

Now lets do some correlations

obesity <- read.csv("Obesity_insurance.csv")

library(tidyr)
library(dplyr)
library(plyr)

## ------------------------------------------------------------------------------

## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)

## ------------------------------------------------------------------------------

## 
## Attaching package: 'plyr'

## The following object is masked from 'package:ggpubr':
## 
##     mutate

## The following objects are masked from 'package:plotly':
## 
##     arrange, mutate, rename, summarise

## The following objects are masked from 'package:dplyr':
## 
##     arrange, count, desc, failwith, id, mutate, rename, summarise,
##     summarize

Lets look at the structure of the dataset

str(obesity)

## 'data.frame':    1338 obs. of  7 variables:
##  $ age     : int  19 18 28 33 32 31 46 37 37 60 ...
##  $ sex     : chr  "female" "male" "male" "male" ...
##  $ bmi     : num  27.9 33.8 33 22.7 28.9 ...
##  $ children: int  0 1 3 0 0 0 1 3 2 0 ...
##  $ smoker  : chr  "yes" "no" "no" "no" ...
##  $ region  : chr  "southwest" "southeast" "southeast" "northwest" ...
##  $ charges : num  16885 1726 4449 21984 3867 ...

Lets look at the column classes

class(obesity)

## [1] "data.frame"

[1] “data.frame”

And get a summary of distribution of the variables

summary(obesity)

##       age            sex                 bmi           children    
##  Min.   :18.00   Length:1338        Min.   :15.96   Min.   :0.000  
##  1st Qu.:27.00   Class :character   1st Qu.:26.30   1st Qu.:0.000  
##  Median :39.00   Mode  :character   Median :30.40   Median :1.000  
##  Mean   :39.21                      Mean   :30.66   Mean   :1.095  
##  3rd Qu.:51.00                      3rd Qu.:34.69   3rd Qu.:2.000  
##  Max.   :64.00                      Max.   :53.13   Max.   :5.000  
##     smoker             region             charges     
##  Length:1338        Length:1338        Min.   : 1122  
##  Class :character   Class :character   1st Qu.: 4740  
##  Mode  :character   Mode  :character   Median : 9382  
##                                        Mean   :13270  
##                                        3rd Qu.:16640  
##                                        Max.   :63770

Now lets look at the distribution for insurance charges

hist(obesity$charges)

we can also get an idea of the distribution using a boxplot

boxplot(obesity$charges)

boxplot(obesity$bmi)

Now lets look at some correlations. The cor() command is used to determine correlations between two vectors, all of the columns of a data frame, or two data frames. The cov() command, on the otherhand examines the covariance. The cor.test() command carries out a test as to the significance of the corraltion

cor(obesity$charges, obesity$bmi)

## [1] 0.198341

This test uses a spearman Rho correlation, or you use Kendall’s tau by specifying it

cor(obesity$charges, obesity$bmi, method = 'kendall')

## [1] 0.08252397

This correlation measures strength of a correlation between -1 and 1.

Now lets look at the Tietjen=Moore test. This is used for univeriate datasets. The algorithm depicts the direction of the outliers in a univariate dataset.

TietjenMoore <- function(dataseries, k)
{
  n = length(dataseries)
  #comput the absolute residuals
  r = abs(dataseries - mean(dataseries))
  # sort data according to size of residual
  df = data.frame(dataseries, r)
  dfs = df[order(df$r),]
  # create a subset of the data without the largest values.
  klarge = c((n-k+1):n)
  subdataseries = df$dataseries[-klarge]
  # compute the sums of squares.
  ksub = (subdataseries = mean(subdataseries)) **2
  all = (df$dataseries - mean(df$dataseries)) **2
  # compute the test statistic. 
  sum(ksub)/sum(all)
  
}

This function helps to compute the absolute resudials and sort data according to the size of teh residuals. Later, we will focus on the computation of sum of squares.

FindOutliersTietjenMooreTest <- function(dataseries, k, alpha = 0.5){
  ek <- TietjenMoore(dataseries, k)
  #compute critical values based on simulation.
  test = c(1:10000)
  for (i in 1:10000){
    dataseriesdataseries = rnorm(length(dataseries))
    test[i] = TietjenMoore(dataseriesdataseries, k)}
  Talpha = quantile(test, alpha)
  list(T = ek, Talpha = Talpha)
  }

This function helps us to compute the critical values based on stimulation data. Now lets demostrate these functions with sample data and the obesity dataset for evaluating this argorithm.

the critical region for the TietjenMoore test is determine by simulation. The simulation is performed by generating a standard normal random sample of size n and computing the TietjenMoore test statistic. Typically, 10,000 random samples are use. the values of the TietjenMoore statistic obtained from the data is compared to this reference distribution. The values of the test statistic is between zero and one. If there are no outliers in the data, the test statistic is close to 1. If there are outliers the test statistic will be closer to zero. Thus, the test is always a lower, one-tailed test regardless of which test statistic issued, Lk or Ek.

First we will look at charges

boxplot(obesity$charges)

FindOutliersTietjenMooreTest(obesity$charges, 50)

## $T
## [1] 0.00089138
## 
## $Talpha
##          50% 
## 2.642507e-07

Lets check out bmi

boxplot(obesity$bmi)

FindOutliersTietjenMooreTest(obesity$bmi, 7)

## $T
## [1] 0.01889396
## 
## $Talpha
##          50% 
## 2.561196e-07

Probability plots

library(ggplot2)
library(tigerstats)

## Loading required package: abd

## Loading required package: nlme

## 
## Attaching package: 'nlme'

## The following object is masked from 'package:dplyr':
## 
##     collapse

## Loading required package: lattice

## Loading required package: grid

## Loading required package: mosaic

## Registered S3 method overwritten by 'mosaic':
##   method                           from   
##   fortify.SpatialPolygonsDataFrame ggplot2

## 
## The 'mosaic' package masks several functions from core packages in order to add 
## additional features.  The original behavior of these functions should not be affected by this.

## 
## Attaching package: 'mosaic'

## The following object is masked from 'package:Matrix':
## 
##     mean

## The following object is masked from 'package:plyr':
## 
##     count

## The following object is masked from 'package:scales':
## 
##     rescale

## The following object is masked from 'package:plotrix':
## 
##     rescale

## The following object is masked from 'package:plotly':
## 
##     do

## The following objects are masked from 'package:dplyr':
## 
##     count, do, tally

## The following object is masked from 'package:ggplot2':
## 
##     stat

## The following objects are masked from 'package:stats':
## 
##     binom.test, cor, cor.test, cov, fivenum, IQR, median, prop.test,
##     quantile, sd, t.test, var

## The following objects are masked from 'package:base':
## 
##     max, mean, min, prod, range, sample, sum

## Welcome to tigerstats!
## To learn more about this package, consult its website:
##  http://homerhanumat.github.io/tigerstats

We will use the probability plot function and their output dnorm: density function of the normal distribution. Using the density, it is possible to determine the probability of events. Or for example, you may wonder “what is the likelyhood that a person has an BMI of exactly _? In this case, you would need to retrieve the density of the BMI distribution at values 140. The BMI distribution can be modeled with a mean of 100 and a standard deviation of 15. The corresponding density is:

bmi.mean <- mean(obesity$bmi)
bmi.sd <- sd(obesity$bmi)

Lets create a plot of our normal distribution

bmi.dist <- dnorm(obesity$bmi, mean = bmi.mean, sd = bmi.sd)
bmi.df <- data.frame("bmi" = obesity$bmi, "Density" = bmi.dist)

ggplot(bmi.df, aes(x = bmi, y = Density)) +
  geom_point()

This gives us the probability of every single point occurring

Now lets use the pnorm function for more info

bmi.dist <- pnorm(obesity$bmi, mean = bmi.mean, sd = bmi.sd)
bmi.df <- data.frame("bmi" = obesity$bmi, "Density" = bmi.dist)

ggplot(bmi.df, aes(x = bmi, y = Density)) +
  geom_point()

What if we want to find the probility of the bmi being greater than 40 in out dirstribution?

pp_greater <- function(x) {
  paste(round(100 * pnorm(x,, mean = 30.66339, sd = 6.09818, lower.tail = FALSE), 2), "%")
}

pp_greater(40)

## [1] "6.29 %"

What about the probaility that a bmi is less than 40 in our population?

pp_less <- function(x) {
  paste(round(100 *(1-pnorm(x, mean = 30.66339, sd = 6.09818, lower.tail = FALSE)), 2), "%")
}

pp_less(40)

## [1] "93.71 %"

What if we want to find the area in between?

pnormGC(c(20, 40 ), region = "between", mean = 30.66339, sd = 6.09818, graph = TRUE)

## [1] 0.8969428

What if we want to know the quantiles? Lets use the gnorm function. We need to assume a normal distribution for this.

What bmi represesnts the lowest 1% of the population?

qnorm(0.01, mean = 30.66339, sd = 6.09818, lower.tail = TRUE)

## [1] 16.4769

What if you want a random sampling of values within your distribution?

subset <- rnorm(50, mean = 30.66339, sd = 6.09818)

hist(subset)

subset2 <- rnorm(5000, mean = 30.66339, sd = 6.09818)

hist(subset2)

Shapiro-Wilk Test

So now we know how to generate a normal distribution, how do we tell if out samples came from a normal distribution?

shapiro.test(obesity$charges[1:5])

## 
##  Shapiro-Wilk normality test
## 
## data:  obesity$charges[1:5]
## W = 0.84164, p-value = 0.1695

You can see here, with a small sample size, we would reject the null hypothesis that the samples came from a normal distribution. We can increase the power of the test by increasing the sample size

shapiro.test(obesity$charges[1:1000])

## 
##  Shapiro-Wilk normality test
## 
## data:  obesity$charges[1:1000]
## W = 0.8119, p-value < 2.2e-16

And lastlt bmi

shapiro.test(obesity$bmi[1:1000])

## 
##  Shapiro-Wilk normality test
## 
## data:  obesity$bmi[1:1000]
## W = 0.99471, p-value = 0.001426

Time series data

First lets load our packages

library(readr)

## 
## Attaching package: 'readr'

## The following object is masked from 'package:scales':
## 
##     col_factor

library(readxl)

Air_data <- read_xlsx("AirQualityUCI.xlsx")

Date - date of measurement time - time of measurement co(GT) - average hourly co2 PTO8,s1(co) - tin oxide hourly average sensor response NMHC - average hourly non-metallic hydrocarbon concentration C6HC - average benzene concentration PTO8.S3(NMHC) - Titania average hourly sensir respose NOx- average hourly NOx concentration NO2 - average hourly NO2 concentration T - temper RH - relative humidity AH - absolute humidity

str(Air_data)

## tibble [9,357 × 15] (S3: tbl_df/tbl/data.frame)
##  $ Date         : POSIXct[1:9357], format: "2004-03-10" "2004-03-10" ...
##  $ Time         : POSIXct[1:9357], format: "1899-12-31 18:00:00" "1899-12-31 19:00:00" ...
##  $ CO(GT)       : num [1:9357] 2.6 2 2.2 2.2 1.6 1.2 1.2 1 0.9 0.6 ...
##  $ PT08.S1(CO)  : num [1:9357] 1360 1292 1402 1376 1272 ...
##  $ NMHC(GT)     : num [1:9357] 150 112 88 80 51 38 31 31 24 19 ...
##  $ C6H6(GT)     : num [1:9357] 11.88 9.4 9 9.23 6.52 ...
##  $ PT08.S2(NMHC): num [1:9357] 1046 955 939 948 836 ...
##  $ NOx(GT)      : num [1:9357] 166 103 131 172 131 89 62 62 45 -200 ...
##  $ PT08.S3(NOx) : num [1:9357] 1056 1174 1140 1092 1205 ...
##  $ NO2(GT)      : num [1:9357] 113 92 114 122 116 96 77 76 60 -200 ...
##  $ PT08.S4(NO2) : num [1:9357] 1692 1559 1554 1584 1490 ...
##  $ PT08.S5(O3)  : num [1:9357] 1268 972 1074 1203 1110 ...
##  $ T            : num [1:9357] 13.6 13.3 11.9 11 11.2 ...
##  $ RH           : num [1:9357] 48.9 47.7 54 60 59.6 ...
##  $ AH           : num [1:9357] 0.758 0.725 0.75 0.787 0.789 ...

library(tidyr)
library(dplyr)
library(lubridate)
library(hms)

## 
## Attaching package: 'hms'

## The following object is masked from 'package:lubridate':
## 
##     hms

library(ggplot2)

Lets get rid of the data in the time column

Air_data$Time <- as_hms(Air_data$Time)

glimpse(Air_data)

## Rows: 9,357
## Columns: 15
## $ Date            <dttm> 2004-03-10, 2004-03-10, 2004-03-10, 2004-03-10, 2004-…
## $ Time            <time> 18:00:00, 19:00:00, 20:00:00, 21:00:00, 22:00:00, 23:…
## $ `CO(GT)`        <dbl> 2.6, 2.0, 2.2, 2.2, 1.6, 1.2, 1.2, 1.0, 0.9, 0.6, -200…
## $ `PT08.S1(CO)`   <dbl> 1360.00, 1292.25, 1402.00, 1375.50, 1272.25, 1197.00, …
## $ `NMHC(GT)`      <dbl> 150, 112, 88, 80, 51, 38, 31, 31, 24, 19, 14, 8, 16, 2…
## $ `C6H6(GT)`      <dbl> 11.881723, 9.397165, 8.997817, 9.228796, 6.518224, 4.7…
## $ `PT08.S2(NMHC)` <dbl> 1045.50, 954.75, 939.25, 948.25, 835.50, 750.25, 689.5…
## $ `NOx(GT)`       <dbl> 166, 103, 131, 172, 131, 89, 62, 62, 45, -200, 21, 16,…
## $ `PT08.S3(NOx)`  <dbl> 1056.25, 1173.75, 1140.00, 1092.00, 1205.00, 1336.50, …
## $ `NO2(GT)`       <dbl> 113, 92, 114, 122, 116, 96, 77, 76, 60, -200, 34, 28, …
## $ `PT08.S4(NO2)`  <dbl> 1692.00, 1558.75, 1554.50, 1583.75, 1490.00, 1393.00, …
## $ `PT08.S5(O3)`   <dbl> 1267.50, 972.25, 1074.00, 1203.25, 1110.00, 949.25, 73…
## $ T               <dbl> 13.600, 13.300, 11.900, 11.000, 11.150, 11.175, 11.325…
## $ RH              <dbl> 48.875, 47.700, 53.975, 60.000, 59.575, 59.175, 56.775…
## $ AH              <dbl> 0.7577538, 0.7254874, 0.7502391, 0.7867125, 0.7887942,…

plot(Air_data$AH, Air_data$RH, main = "Humidity Analysis", xlab = "Absolute Humidity", ylab = 
       "Relative Humidity")

Notice we have an outlier in our data

t.test(Air_data$RH, Air_data$AH)

## 
##  Welch Two Sample t-test
## 
## data:  Air_data$RH and Air_data$AH
## t = 69.62, df = 17471, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  45.01707 47.62536
## sample estimates:
## mean of x mean of y 
## 39.483611 -6.837604

###Text Mining 1-2 First we’ll look at the unnest_token function

Lets start by looking at an Emily Dickenson passage

text <- c("Because I could not stop from Death = ", 
          "He kindly stopped for me - ", 
          "The carriage held but just ourselves - ",
          "and Immortality")

text

## [1] "Because I could not stop from Death = " 
## [2] "He kindly stopped for me - "            
## [3] "The carriage held but just ourselves - "
## [4] "and Immortality"

This is a typical character vector that we might want to analyze. In order to turn it into a tidytext dataset, we first need to put it into a dataframe.

library(dplyr)

text_df <- tibble(line = 1:4, text = text)

text_df

## # A tibble: 4 × 2
##    line text                                     
##   <int> <chr>                                    
## 1     1 "Because I could not stop from Death = " 
## 2     2 "He kindly stopped for me - "            
## 3     3 "The carriage held but just ourselves - "
## 4     4 "and Immortality"

Reminder: A tibble is a modern class sof data frame with R. ITs available in the dyplr and tibble package, that has a convenient print method, will not convert strongs to factors, and does not use row names. Tibbles are great for use with tidy tools.

Next we will use the ‘unset_tokens’ function.

First we have the output column name that will be created as the text is unnested into it

library(tidytext)

text_df %>%
  unnest_tokens(word, text)

## # A tibble: 20 × 2
##     line word       
##    <int> <chr>      
##  1     1 because    
##  2     1 i          
##  3     1 could      
##  4     1 not        
##  5     1 stop       
##  6     1 from       
##  7     1 death      
##  8     2 he         
##  9     2 kindly     
## 10     2 stopped    
## 11     2 for        
## 12     2 me         
## 13     3 the        
## 14     3 carriage   
## 15     3 held       
## 16     3 but        
## 17     3 just       
## 18     3 ourselves  
## 19     4 and        
## 20     4 immortality

Lets use the janeaustenr package to anaylze some Jane Austen texts. There are 6 books in this package.

library(janeaustenr)
library(dplyr)
library(stringr)

original_books <- austen_books() %>%
  group_by(book) %>%
  dplyr::mutate(linenumber = row_number(),
         chapter = cumsum(str_detect(text, regex("^chater [\\divxlc]",
                                                 ignore_case = TRUE)))) %>%
  ungroup()

original_books

## # A tibble: 73,422 × 4
##    text                    book                linenumber chapter
##    <chr>                   <fct>                    <int>   <int>
##  1 "SENSE AND SENSIBILITY" Sense & Sensibility          1       0
##  2 ""                      Sense & Sensibility          2       0
##  3 "by Jane Austen"        Sense & Sensibility          3       0
##  4 ""                      Sense & Sensibility          4       0
##  5 "(1811)"                Sense & Sensibility          5       0
##  6 ""                      Sense & Sensibility          6       0
##  7 ""                      Sense & Sensibility          7       0
##  8 ""                      Sense & Sensibility          8       0
##  9 ""                      Sense & Sensibility          9       0
## 10 "CHAPTER 1"             Sense & Sensibility         10       0
## # ℹ 73,412 more rows

To work with this as a tidy dataset, we need to restructure it in the one-token-per-row format, which as we saw earlier is done with the unnest_tokens() function

library(tidytext)
tidy_books <- original_books %>%
  unnest_tokens(word, text)

tidy_books

## # A tibble: 725,055 × 4
##    book                linenumber chapter word       
##    <fct>                    <int>   <int> <chr>      
##  1 Sense & Sensibility          1       0 sense      
##  2 Sense & Sensibility          1       0 and        
##  3 Sense & Sensibility          1       0 sensibility
##  4 Sense & Sensibility          3       0 by         
##  5 Sense & Sensibility          3       0 jane       
##  6 Sense & Sensibility          3       0 austen     
##  7 Sense & Sensibility          5       0 1811       
##  8 Sense & Sensibility         10       0 chapter    
##  9 Sense & Sensibility         10       0 1          
## 10 Sense & Sensibility         13       0 the        
## # ℹ 725,045 more rows

This function usees the tokenizers package to separate each line of text in the original dataframe into tokens.

The default tokenizing is for words, but other options including characters, n-grams, sentences, lines, or paragraphs can be used.

Now that the data is in a one-word-per-row format, we can manipulate it with tools like dplyr.

Often in text analysis, we will want to remove stop words. Stop words are words that are NOT USEFUl for an analysis. These include words like the, of, to , and, and so forth.

We can remove stop words (kept in the tidytext dataset ‘stop_words’) with an anti_join()

data(stop_words)

tidy_books <- tidy_books %>%
  anti_join(stop_words)

## Joining with `by = join_by(word)`

The stop words dataset in the tidytext package contains stop words from three lexicons. We can use them all together, as we have here, or filter() to only use one set of stop words if thats more appropiate for yout analysis.

tidy_books %>%
  count(word, sort = TRUE)

## # A tibble: 13,914 × 2
##    word       n
##    <chr>  <int>
##  1 miss    1855
##  2 time    1337
##  3 fanny    862
##  4 dear     822
##  5 lady     817
##  6 sir      806
##  7 day      797
##  8 emma     787
##  9 sister   727
## 10 house    699
## # ℹ 13,904 more rows

Beause we’ve been using tidy tools, our word counts are stored in a tidy data frame. This allows us to pipe this directly into ggplot2. For example, we can create a visualization of the common words.

library(ggplot2)

tidy_books %>%
  count(word, sort = TRUE) %>%
  filter(n > 600) %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(n, word)) +
  geom_col() +
  labs(y = NULL, x = "word count")

The gutenbergr package

This package provides access to the public domain works from the gutenberg project (www.gutenberg.org). This package inlcude tools for both downloading books and a complete dataset of project gutenberg metadata that can be used to find works of interest. We will mostly use the function gutenberg_download().

word frequencies

Lets look at some biology tetxs, starting with Darwin

The voyage of the Beagle - 944 On the origin of species by the means of natural selection - 1228 The expression of emotions in man and animals - 1227 The descent of man, and selection in relation to sex - 2300

We can access these works using the gutenberg_download() and the Project Gutenberg IDnumbers

library(gutenbergr)

darwin <- gutenberg_download(c(944, 1227, 1228, 2300), mirror =  "https://gutenberg.nabasny.com/")

## Warning: ! Could not download a book at
##   https://gutenberg.nabasny.com//1/2/2/1228/1228.zip.
## ℹ The book may have been archived.
## ℹ Alternatively, You may need to select a different mirror.
## → See https://www.gutenberg.org/MIRRORS.ALL for options.

Lets break these into tokens

tidy_darwin <- darwin %>%
  unnest_tokens(word, text) %>%
  anti_join(stop_words)

## Joining with `by = join_by(word)`

Lets check out what the most common darwin words are.

tidy_darwin %>%
  count(word, sort = TRUE)

## # A tibble: 22,315 × 2
##    word        n
##    <chr>   <int>
##  1 male     1620
##  2 species  1452
##  3 males    1286
##  4 female   1173
##  5 birds    1124
##  6 sexes    1062
##  7 animals  1013
##  8 females  1003
##  9 sexual    749
## 10 vol       712
## # ℹ 22,305 more rows

Now lets get some work from Thomas Hunt Morgan, who is credited with discovering chromosomes.

Regeneration - 57198 The genetic and operative evidence relating to secondary sexual characteristics - 57460 Evolution and Adaptation - 63540

morgan <- gutenberg_download(c(57198, 57460, 63540), mirror = "https://gutenberg.nabasny.com/" )

Lets tokenize THM

tidy_morgan <- morgan %>%
  unnest_tokens(word, text) %>%
  anti_join(stop_words)

## Joining with `by = join_by(word)`

What are THM’s most common words?

tidy_morgan %>%
  count(word, sort = TRUE)

## # A tibble: 13,855 × 2
##    word             n
##    <chr>        <int>
##  1 species        869
##  2 regeneration   814
##  3 piece          702
##  4 cut            669
##  5 male           668
##  6 forms          631
##  7 selection      604
##  8 cells          576
##  9 found          552
## 10 development    546
## # ℹ 13,845 more rows

Lastly lets look at Thomas Henry Huxley

Evidence as to mans place in nature - 2931 on the reception of the origin of species - 2089 Evolution and Ethnics, anf other essays - 2940 Science and culture, and other essays - 52344

huxley <- gutenberg_download(c(2931, 2089, 2940, 52344), mirror = "https://gutenberg.nabasny.com/")

## Warning: ! Could not download a book at
##   https://gutenberg.nabasny.com//2/9/4/2940/2940.zip.
## ℹ The book may have been archived.
## ℹ Alternatively, You may need to select a different mirror.
## → See https://www.gutenberg.org/MIRRORS.ALL for options.

tidy_huxley <- huxley %>%
  unnest_tokens(word, text) %>%
  anti_join(stop_words)

## Joining with `by = join_by(word)`

tidy_huxley %>%
  count(word, sort = TRUE)

## # A tibble: 11,749 × 2
##    word          n
##    <chr>     <int>
##  1 knowledge   194
##  2 de          174
##  3 science     169
##  4 animals     162
##  5 life        160
##  6 time        157
##  7 animal      154
##  8 species     132
##  9 body        127
## 10 nature      126
## # ℹ 11,739 more rows

Now, lets calculate the frequency for each word for the workd of darwin, Morgan and Huxley by binding the frames together.

library(tidyr)

frequency <- bind_rows(mutate(tidy_morgan, author = "Thomas Hunt Morgan"),
                      mutate(tidy_darwin, author = "Charles Darwin"),
                      mutate(tidy_huxley, author = "Thomas Henry Huxley")) %>%
  mutate(word = str_extract(word, "[a-z]+")) %>%
  count(author, word) %>%
  group_by(author) %>%
  mutate(proportion = n/ sum(n)) %>%
  select(-n) %>%
  pivot_wider(names_from = author, values_from = proportion) %>%
  pivot_longer('Thomas Hunt Morgan' : 'Charles Darwin' , names_to = "author", values_to = "proportion")

frequency

## # A tibble: 87,165 × 3
##    word    author               proportion
##    <chr>   <chr>                     <dbl>
##  1 a       Thomas Hunt Morgan   0.000633  
##  2 a       Thomas Henry Huxley  0.0000162 
##  3 a       Charles Darwin       0.0000485 
##  4 ab      Thomas Hunt Morgan   0.0000508 
##  5 ab      Thomas Henry Huxley  0.0000185 
##  6 ab      Charles Darwin       0.00000462
##  7 abaiss  Thomas Hunt Morgan  NA         
##  8 abaiss  Thomas Henry Huxley NA         
##  9 abaiss  Charles Darwin       0.00000462
## 10 abandon Thomas Hunt Morgan   0.00000231
## # ℹ 87,155 more rows

Now we need to change the table so that each author has its own row

frequency2 <- pivot_wider(frequency, names_from = author, values_from = proportion)

frequency2

## # A tibble: 29,055 × 4
##    word        `Thomas Hunt Morgan` `Thomas Henry Huxley` `Charles Darwin`
##    <chr>                      <dbl>                 <dbl>            <dbl>
##  1 a                     0.000633              0.0000162        0.0000485 
##  2 ab                    0.0000508             0.0000185        0.00000462
##  3 abaiss               NA                    NA                0.00000462
##  4 abandon               0.00000231            0.00000231       0.00000231
##  5 abandoned             0.00000462            0.00000231       0.00000231
##  6 abashed              NA                    NA                0.00000231
##  7 abatement            NA                     0.00000231       0.00000231
##  8 abbot                NA                     0.00000462       0.00000231
##  9 abbott               NA                    NA                0.00000462
## 10 abbreviated          NA                    NA                0.00000924
## # ℹ 29,045 more rows

Now lets plot

library(scales)

ggplot(frequency2, aes(x = `Charles Darwin`, y = `Thomas Hunt Morgan`), 
       color = abs(- 'Charles Darwin' - 'Thomas Hunt Morgan')) +
  geom_abline(color = "gray40", lty = 2) +
  geom_jitter(alpha = 0.1, size = 2.5, width = 0.3, height = 0.3) +
  geom_text(aes(label = word), check_overlap = TRUE, vjust = 1.5) +
  scale_x_log10(labels = percent_format()) +
  scale_y_log10(labels = percent_format()) +
  scale_color_gradient(limits = c(0, 0.001), 
                       low = "darkslategray4", high = "gray75") +
  theme(legend.position = "none") +
  labs(y = "Thomas Hunt Morgan", x = "Charles Darwin")

## Warning: Removed 21938 rows containing missing values (`geom_point()`).

## Warning: Removed 21939 rows containing missing values (`geom_text()`).

library(scales)

ggplot(frequency2, aes(x = `Charles Darwin`, y = `Thomas Henry Huxley`),
                       color = abs(- 'Charles Darwin' - 'Thomas Henry Huxley')) +
  geom_abline(color = "gray40", lty = 2) +
  geom_jitter(aplha = 0.1, size = 2.5, width = 0.3, height = 0.3) +
  geom_text(aes(label = word), check_overlap = TRUE, vjust = 1.5) +
  scale_x_log10(labels = percent_format()) +
  scale_y_log10(labels = percent_format()) +
  scale_color_gradient(limits = c(0, 0.001), 
                       low = "darkslategray4", high = "gray75") +
  theme(legend.position = "none") +
  labs(y = "Thomas Henry Huxley", x = "Charles Darwin")

## Warning in geom_jitter(aplha = 0.1, size = 2.5, width = 0.3, height = 0.3):
## Ignoring unknown parameters: `aplha`

## Warning: Removed 22441 rows containing missing values (`geom_point()`).

## Warning: Removed 22442 rows containing missing values (`geom_text()`).

library(scales)

ggplot(frequency2, aes(x = `Thomas Hunt Morgan`, y = `Thomas Henry Huxley`),
                       color = abs(- 'Thomas Hunt Morgan' - 'Thomas Henry Huxley')) +
  geom_abline(color = "gray40", lty = 2) +
  geom_jitter(alpha = 0.1, size = 2.5, width = 0.3, height = 0.3) +
  geom_text(aes(label = word), check_overlap = TRUE, vjust = 1.5) +
  scale_x_log10(labels = percent_format()) +
  scale_y_log10(labels = percent_format()) +
  scale_color_gradient(limits = c(0,0.001), 
                       low = "darkslategray4", high = "gray75") +
  theme(legend.position = "none") +
  labs(y = "Thomas Henry Huxley", x = "Thomas Hunt Morgan")

## Warning: Removed 24133 rows containing missing values (`geom_point()`).

## Warning: Removed 24134 rows containing missing values (`geom_text()`).

###Sentiment Analysis 1-3 The Sentiment datasets

There are a variety of methods and dictionaries that exist for evaluating the opinion or emtion of the text.

AFFIN bing nrc

bing categories words in a binary fashion into positive or negative nrc categories into positive, negative, anger, anticipation, discust, fear, joy, sadness, suprise, and trust. AFFIN assigns a score between -5 and 5, with negative indicating negative sentiment, and 5 positive.

The function get_sentiment() allows us to get the specific sentiments lexicon with the measures for each one.

library(tidytext)
library(textdata)

afinn <- get_sentiments("afinn")

afinn

## # A tibble: 2,477 × 2
##    word       value
##    <chr>      <dbl>
##  1 abandon       -2
##  2 abandoned     -2
##  3 abandons      -2
##  4 abducted      -2
##  5 abduction     -2
##  6 abductions    -2
##  7 abhor         -3
##  8 abhorred      -3
##  9 abhorrent     -3
## 10 abhors        -3
## # ℹ 2,467 more rows

Lets look at bing

bing <- get_sentiments("bing")

bing

## # A tibble: 6,786 × 2
##    word        sentiment
##    <chr>       <chr>    
##  1 2-faces     negative 
##  2 abnormal    negative 
##  3 abolish     negative 
##  4 abominable  negative 
##  5 abominably  negative 
##  6 abominate   negative 
##  7 abomination negative 
##  8 abort       negative 
##  9 aborted     negative 
## 10 aborts      negative 
## # ℹ 6,776 more rows

And lastly nrc

nrc <- get_sentiments("nrc")

nrc

## # A tibble: 13,872 × 2
##    word        sentiment
##    <chr>       <chr>    
##  1 abacus      trust    
##  2 abandon     fear     
##  3 abandon     negative 
##  4 abandon     sadness  
##  5 abandoned   anger    
##  6 abandoned   fear     
##  7 abandoned   negative 
##  8 abandoned   sadness  
##  9 abandonment anger    
## 10 abandonment fear     
## # ℹ 13,862 more rows

These libraries were created either using corwdourcing or cloud computing/ai like Amazon Mechanical Turk, or by labor of one of the authors, and then validated with crowdsourcing.

Lets look at the words with a joy score from NRC

library(gutenbergr)
library(dplyr)
library(stringr)

darwin <- gutenberg_download(c(944, 1227, 1228, 2300), mirror = "https://gutenberg.nabasny.com/")

## Warning: ! Could not download a book at
##   https://gutenberg.nabasny.com//1/2/2/1228/1228.zip.
## ℹ The book may have been archived.
## ℹ Alternatively, You may need to select a different mirror.
## → See https://www.gutenberg.org/MIRRORS.ALL for options.

tidy_books <- darwin %>%
  group_by(gutenberg_id) %>%
  dplyr::mutate(linenumber = row_number(), chapter = cumsum(str_detect(text, regex("^chapter [\\divxlc]", ignore_case = TRUE)))) %>%
  ungroup() %>%
  unnest_tokens(word, text)

tidy_books

## # A tibble: 629,573 × 4
##    gutenberg_id linenumber chapter word   
##           <int>      <int>   <int> <chr>  
##  1          944          1       0 the    
##  2          944          1       0 voyage 
##  3          944          1       0 of     
##  4          944          1       0 the    
##  5          944          1       0 beagle 
##  6          944          1       0 by     
##  7          944          2       0 charles
##  8          944          2       0 darwin 
##  9          944          8       0 about  
## 10          944          8       0 the    
## # ℹ 629,563 more rows

Lets add the book name instead of GID

colnames(tidy_books)[1] <- "book"

tidy_books$book[tidy_books$book == 944] <- "The voyage of the Beagle"
tidy_books$book[tidy_books$book == 1227] <- "The Expression of the Emotions in Men and Animals"
tidy_books$book[tidy_books$book == 1228] <- "On the Origin of species By Means of Natural Selection"
tidy_books$book[tidy_books$book == 2300] <- "The Descent of Man, and Selection in Relation to sex"

tidy_books

## # A tibble: 629,573 × 4
##    book                     linenumber chapter word   
##    <chr>                         <int>   <int> <chr>  
##  1 The voyage of the Beagle          1       0 the    
##  2 The voyage of the Beagle          1       0 voyage 
##  3 The voyage of the Beagle          1       0 of     
##  4 The voyage of the Beagle          1       0 the    
##  5 The voyage of the Beagle          1       0 beagle 
##  6 The voyage of the Beagle          1       0 by     
##  7 The voyage of the Beagle          2       0 charles
##  8 The voyage of the Beagle          2       0 darwin 
##  9 The voyage of the Beagle          8       0 about  
## 10 The voyage of the Beagle          8       0 the    
## # ℹ 629,563 more rows

Now that we have a tidy format with one word per row, we are ready for sentiment analysis, First lets use NRC.

nrc_joy <- get_sentiments("nrc") %>%
  filter(sentiment == "joy")

tidy_books %>%
  filter(book == "The Voyage of the Beagle") %>%
  inner_join(nrc_joy) %>%
  count(word, sort = TRUE)

## Joining with `by = join_by(word)`

## # A tibble: 0 × 2
## # ℹ 2 variables: word <chr>, n <int>

We can also examine how sentimetns changes throughout a work.

library(tidyr)

charles_Darwin_sentiment <- tidy_books %>%
  inner_join(get_sentiments("bing")) %>%
  count(book, index = linenumber %% 80, sentiment) %>%
  pivot_wider(names_from = sentiment, values_from = n, values_fill = 0) %>%
  dplyr::mutate(sentiment = positive - negative)

## Joining with `by = join_by(word)`

Now lets plot it

library(ggplot2)

ggplot(charles_Darwin_sentiment, aes(index, sentiment, fill = book)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~book, ncol = 2, scales = "free_x")

Lets compare the three sentiment dictions

There are several options for sentiment lexicons, you might want some more info on which is appropriate for you purpose. Here we will use all three of our dictionaries and examine how the sentiment changes across the arc of TVOTB.

library(tidyr)

voyage <- tidy_books %>%
  filter(book == "The voyage of the Beagle")

voyage

## # A tibble: 208,118 × 4
##    book                     linenumber chapter word   
##    <chr>                         <int>   <int> <chr>  
##  1 The voyage of the Beagle          1       0 the    
##  2 The voyage of the Beagle          1       0 voyage 
##  3 The voyage of the Beagle          1       0 of     
##  4 The voyage of the Beagle          1       0 the    
##  5 The voyage of the Beagle          1       0 beagle 
##  6 The voyage of the Beagle          1       0 by     
##  7 The voyage of the Beagle          2       0 charles
##  8 The voyage of the Beagle          2       0 darwin 
##  9 The voyage of the Beagle          8       0 about  
## 10 The voyage of the Beagle          8       0 the    
## # ℹ 208,108 more rows

let again use interger division (‘%/%’) to define larger selections of the text that span multiple lines, and we can use the same pattern with ‘count()’, ‘pivot_wider()’, to find the net sentiment in each of these sections of text.

affin <- voyage %>%
  inner_join(get_sentiments("afinn")) %>%
  group_by(index = linenumber %/% 80) %>%
  summarise(sentiment = sum(value)) %>%
  mutate(method = "AFINN")

## Joining with `by = join_by(word)`

bing_and_nrc <- bind_rows(
  voyage %>%
    mutate(method = "Bing et al."),
  voyage %>%
    inner_join(get_sentiments("nrc") %>%
                 filter(sentiment %in% c("positive", "negative"))
               ) %>%
    mutate(method = "NRC")) %>%
  count(method, index = linenumber %/% 80, sentiment) %>%
  pivot_wider(names_from = sentiment,
              values_from = n,
              values_fill = 0) %>%
  mutate(sentiment = positive - negative)

## Joining with `by = join_by(word)`

## Warning in inner_join(., get_sentiments("nrc") %>% filter(sentiment %in% : Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 1154 of `x` matches multiple rows in `y`.
## ℹ Row 4245 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
##   "many-to-many"` to silence this warning.

We can now estimate the net sentiment (positive - negative) in each chunk of thenovel text for each lexion (dictionary). Lets bind them all together and visualize with ggplot

bind_rows(affin, bing_and_nrc) %>%
  ggplot(aes(index, sentiment, fill = method)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~method, ncol = 1, scales = "free_y")

## Warning: Removed 1 rows containing missing values (`position_stack()`).

Lets look at the counts based on each dictionary

get_sentiments("nrc") %>%
  filter(sentiment %in% c("positive", "negative")) %>%
  count(sentiment)

## # A tibble: 2 × 2
##   sentiment     n
##   <chr>     <int>
## 1 negative   3316
## 2 positive   2308

get_sentiments("bing") %>%
  count(sentiment)

## # A tibble: 2 × 2
##   sentiment     n
##   <chr>     <int>
## 1 negative   4781
## 2 positive   2005

bing_word_counts <- tidy_books %>%
  inner_join(get_sentiments("bing")) %>%
  count(word, sentiment, sort = TRUE) %>%
  ungroup()

## Joining with `by = join_by(word)`

bing_word_counts

## # A tibble: 2,421 × 3
##    word       sentiment     n
##    <chr>      <chr>     <int>
##  1 great      positive    964
##  2 like       positive    705
##  3 well       positive    701
##  4 good       positive    384
##  5 doubt      negative    306
##  6 respect    positive    266
##  7 wild       negative    266
##  8 bright     positive    252
##  9 remarkable positive    247
## 10 savages    negative    217
## # ℹ 2,411 more rows

This can be shown visually, and we can pipe striaght into ggplot2

bing_word_counts %>%
  group_by(sentiment) %>%
  slice_max(n, n = 10) %>%
  ungroup() %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(n, word, fill = sentiment)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~sentiment, scale = "free_y") +
  labs(x = "contribution to sentiment", y = NULL)

Lets spot an anomoly in the dataset.

custom_stop_words <- bind_rows(tibble(word = c("wild", "dark", "great", "like"), lexicon = c("custom")), stop_words)

custom_stop_words

## # A tibble: 1,153 × 2
##    word      lexicon
##    <chr>     <chr>  
##  1 wild      custom 
##  2 dark      custom 
##  3 great     custom 
##  4 like      custom 
##  5 a         SMART  
##  6 a's       SMART  
##  7 able      SMART  
##  8 about     SMART  
##  9 above     SMART  
## 10 according SMART  
## # ℹ 1,143 more rows

Word Clouds!

We can see that tidy text mining and sentiment analysis works well with ggplot2, but having our data in tidy format leads to other nice graphing techniques

lets use the wordcloud package!!

library(wordcloud)

## 
## Attaching package: 'wordcloud'

## The following object is masked from 'package:gplots':
## 
##     textplot

tidy_books %>%
  anti_join(stop_words) %>%
  count(word) %>%
  with (wordcloud(word, n, max.words = 100))

## Joining with `by = join_by(word)`

## Warning in wordcloud(word, n, max.words = 100): female could not be fit on
## page. It will not be plotted.

## Warning in wordcloud(word, n, max.words = 100): birds could not be fit on page.
## It will not be plotted.

Lets also look at comparison.cloud(), which may require turing the dataframe into a matrix.

we can change to matrix using the acast() funciton.

library(reshape2)

## 
## Attaching package: 'reshape2'

## The following object is masked from 'package:tigerstats':
## 
##     tips

## The following object is masked from 'package:tidyr':
## 
##     smiths

tidy_books %>%
  inner_join(get_sentiments("bing")) %>%
  count(word, sentiment, sort = TRUE) %>%
  acast(word ~sentiment, value.var = "n", fill = 0) %>%
  comparison.cloud(colors = c("gray20", "gray80"), max.words = 100)

## Joining with `by = join_by(word)`

Looking at units beyond words

Lots of useful work can be done by tokenizing nat the word leve, but sometimes its nice to look at different units of text. For example, we can look beyond just unigrams.

Ex I am not having a good day.

bingnegative <- get_sentiments("bing") %>%
  filter(sentiment == "negative")

wordcounts <- tidy_books %>%
  group_by(book, chapter) %>%
  dplyr::summarize(words = n())

## `summarise()` has grouped output by 'book'. You can override using the
## `.groups` argument.

tidy_books %>%
  semi_join(bingnegative) %>%
  group_by(book, chapter) %>%
  dplyr::summarize(negativewords = n()) %>%
  left_join(wordcounts, by = c("book", "chapter")) %>%
  mutate(ratio = negativewords/words) %>%
  filter(chapter !=0) %>%
  slice_max(ratio, n = 1) %>%
  ungroup()

## Joining with `by = join_by(word)`
## `summarise()` has grouped output by 'book'. You can override using the
## `.groups` argument.

## # A tibble: 3 × 5
##   book                                        chapter negativewords words  ratio
##   <chr>                                         <int>         <int> <int>  <dbl>
## 1 The Descent of Man, and Selection in Relat…      20             4    87 0.0460
## 2 The Expression of the Emotions in Men and …      10           249  4220 0.0590
## 3 The voyage of the Beagle                         10           375 11202 0.0335

###N-grams 1-3 So far we’ve only looked at single words, but many interesting (more accurate) analyses are based on the relationship between words.

Lets look at some methods of tidytext for calculating and visualizing relationships.

library(dplyr)
library(tidytext)

darwin_books <- gutenberg_download(c(944, 1227, 1228, 2300), mirror = "https://gutenberg.nabasny.com/")

## Warning: ! Could not download a book at
##   https://gutenberg.nabasny.com//1/2/2/1228/1228.zip.
## ℹ The book may have been archived.
## ℹ Alternatively, You may need to select a different mirror.
## → See https://www.gutenberg.org/MIRRORS.ALL for options.

colnames(darwin_books)[1] <- "book"

darwin_books$book[darwin_books$book == 944] <- "The Voyage of the Beagle"
darwin_books$book[darwin_books$book == 1227] <- "The Expression of the Emotions in Man and Animals"
darwin_books$book[darwin_books$book == 1228] <- "On the origin of species By Means of Natural Selection"
darwin_books$book[darwin_books$book == 2300] <- "The Descent of Man, and Selection in Relation to Sex"

darwin_bigrams <- darwin_books %>%
  unnest_tokens(bigram, text, token = "ngrams", n = 2)

darwin_bigrams

## # A tibble: 580,636 × 2
##    book                     bigram        
##    <chr>                    <chr>         
##  1 The Voyage of the Beagle the voyage    
##  2 The Voyage of the Beagle voyage of     
##  3 The Voyage of the Beagle of the        
##  4 The Voyage of the Beagle the beagle    
##  5 The Voyage of the Beagle beagle by     
##  6 The Voyage of the Beagle charles darwin
##  7 The Voyage of the Beagle <NA>          
##  8 The Voyage of the Beagle <NA>          
##  9 The Voyage of the Beagle <NA>          
## 10 The Voyage of the Beagle <NA>          
## # ℹ 580,626 more rows

This data is still in tidytext format, and ist structured as one-token-per-row. Each token is a bigram.

Counting and filtering n-gram

darwin_bigrams %>%
  count(bigram, sort = TRUE)

## # A tibble: 206,416 × 2
##    bigram       n
##    <chr>    <int>
##  1 of the    9359
##  2 <NA>      7283
##  3 in the    4214
##  4 on the    3465
##  5 to the    2297
##  6 it is     1527
##  7 that the  1523
##  8 and the   1356
##  9 the same  1348
## 10 of a      1345
## # ℹ 206,406 more rows

Most of the common bigrams are stop-words. This can be good time to use tidyr’s seperate command which splits a column into multiple based on a delimiter. This will let us make a column for word one and word two.

library(tidyr)

bigrams_separated <- darwin_bigrams %>%
  separate(bigram, c("word1", "word2"), sep = " ")

bigram_filtered <- bigrams_separated %>%
  filter(!word1 %in% stop_words$word) %>%
  filter(!word2 %in% stop_words$word)

bigram_filtered

## # A tibble: 79,272 × 3
##    book                     word1   word2  
##    <chr>                    <chr>   <chr>  
##  1 The Voyage of the Beagle charles darwin 
##  2 The Voyage of the Beagle <NA>    <NA>   
##  3 The Voyage of the Beagle <NA>    <NA>   
##  4 The Voyage of the Beagle <NA>    <NA>   
##  5 The Voyage of the Beagle <NA>    <NA>   
##  6 The Voyage of the Beagle <NA>    <NA>   
##  7 The Voyage of the Beagle online  edition
##  8 The Voyage of the Beagle <NA>    <NA>   
##  9 The Voyage of the Beagle degree  symbol 
## 10 The Voyage of the Beagle degs    italics
## # ℹ 79,262 more rows

New bigram counts

bigram_counts <- bigram_filtered %>%
  unite(bigram, word1, word2, sep = " ")

bigram_counts

## # A tibble: 79,272 × 2
##    book                     bigram        
##    <chr>                    <chr>         
##  1 The Voyage of the Beagle charles darwin
##  2 The Voyage of the Beagle NA NA         
##  3 The Voyage of the Beagle NA NA         
##  4 The Voyage of the Beagle NA NA         
##  5 The Voyage of the Beagle NA NA         
##  6 The Voyage of the Beagle NA NA         
##  7 The Voyage of the Beagle online edition
##  8 The Voyage of the Beagle NA NA         
##  9 The Voyage of the Beagle degree symbol 
## 10 The Voyage of the Beagle degs italics  
## # ℹ 79,262 more rows

We may also be interested in trigrams, which are three word combos

trigrams <- darwin_books %>%
  unnest_tokens(trigram, text, token = "ngrams", n = 3) %>%
  separate(trigram, c("word1", "word2", "word3"), sep = " ") %>%
  filter(!word1 %in% stop_words$word,
         !word2 %in% stop_words$word,
         !word3 %in% stop_words$word) %>%
  count(word1, word2, word3, sort = TRUE)

trigrams

## # A tibble: 17,771 × 4
##    word1         word2  word3           n
##    <chr>         <chr>  <chr>       <int>
##  1 <NA>          <NA>   <NA>         7965
##  2 tierra        del    fuego          84
##  3 secondary     sexual characters     79
##  4 captain       fitz   roy            45
##  5 de            la     physionomie    30
##  6 domestication vol    ii             26
##  7 vol           ii     pp             22
##  8 vertebrates   vol    iii            21
##  9 proc          zoolog soc            18
## 10 proc          zool   soc            17
## # ℹ 17,761 more rows

Lets analyze some bigrams

bigram_filtered %>%
  filter(word2 == "selection") %>%
  count(book, word1, sort = TRUE)

## # A tibble: 24 × 3
##    book                                                 word1           n
##    <chr>                                                <chr>       <int>
##  1 The Descent of Man, and Selection in Relation to Sex sexual        254
##  2 The Descent of Man, and Selection in Relation to Sex natural       156
##  3 The Descent of Man, and Selection in Relation to Sex unconscious     6
##  4 The Descent of Man, and Selection in Relation to Sex continued       5
##  5 The Expression of the Emotions in Man and Animals    natural         4
##  6 The Descent of Man, and Selection in Relation to Sex artificial      2
##  7 The Descent of Man, and Selection in Relation to Sex ordinary        2
##  8 The Descent of Man, and Selection in Relation to Sex careful         1
##  9 The Descent of Man, and Selection in Relation to Sex consequent      1
## 10 The Descent of Man, and Selection in Relation to Sex la              1
## # ℹ 14 more rows

lets again look at tf-idf across Darwins works.

bigrams_tf_idf <- bigram_counts %>%
  count(book, bigram) %>%
  bind_tf_idf(bigram, book, n) %>%
  arrange(desc(tf_idf))

bigrams_tf_idf

## # A tibble: 51,213 × 6
##    book                                       bigram     n      tf   idf  tf_idf
##    <chr>                                      <chr>  <int>   <dbl> <dbl>   <dbl>
##  1 The Expression of the Emotions in Man and… nerve…    47 0.00350 1.10  0.00384
##  2 The Descent of Man, and Selection in Rela… sexua…   138 0.00315 1.10  0.00346
##  3 The Expression of the Emotions in Man and… la ph…    35 0.00260 1.10  0.00286
##  4 The Voyage of the Beagle                   bueno…    54 0.00245 1.10  0.00269
##  5 The Voyage of the Beagle                   capta…    53 0.00240 1.10  0.00264
##  6 The Descent of Man, and Selection in Rela… secon…   101 0.00231 1.10  0.00254
##  7 The Voyage of the Beagle                   fitz …    50 0.00227 1.10  0.00249
##  8 The Expression of the Emotions in Man and… muscl…    30 0.00223 1.10  0.00245
##  9 The Expression of the Emotions in Man and… orbic…    29 0.00216 1.10  0.00237
## 10 The Descent of Man, and Selection in Rela… sexua…   254 0.00580 0.405 0.00235
## # ℹ 51,203 more rows

bigrams_tf_idf %>%
  arrange(desc(tf_idf)) %>%
  group_by(book) %>%
  slice_max(tf_idf, n = 10) %>%
  ungroup() %>%
  mutate(bigram = reorder(bigram, tf_idf)) %>%
  ggplot(aes(tf_idf, bigram, fill = book)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~book, ncol = 2, scales = "free") +
  labs(x = "tf-idf of bigrams", y = NULL)

using bigrams to provide context in sentiment analysis

bigrams_separated %>%
  filter(word1 == "not") %>%
  count(word1, word2, sort = TRUE)

## # A tibble: 740 × 3
##    word1 word2      n
##    <chr> <chr>  <int>
##  1 not   be        90
##  2 not   only      89
##  3 not   have      80
##  4 not   a         78
##  5 not   to        74
##  6 not   the       63
##  7 not   at        56
##  8 not   been      54
##  9 not   appear    51
## 10 not   know      47
## # ℹ 730 more rows

By doing sentiment analysis on bigrams, we can examine how often sentiment-associated words are precedded by a modifier like “not” or other negating words.

AFINN <- get_sentiments("afinn")

AFINN

## # A tibble: 2,477 × 2
##    word       value
##    <chr>      <dbl>
##  1 abandon       -2
##  2 abandoned     -2
##  3 abandons      -2
##  4 abducted      -2
##  5 abduction     -2
##  6 abductions    -2
##  7 abhor         -3
##  8 abhorred      -3
##  9 abhorrent     -3
## 10 abhors        -3
## # ℹ 2,467 more rows

we can examine the most frequent words that were preceded by “not”, and associate with sentiment.

not_words <- bigrams_separated %>%
  filter(word1 == "not") %>%
  inner_join(AFINN, by = c(word2 = "word")) %>%
  count(word2, value, sort = TRUE)

not_words

## # A tibble: 97 × 3
##    word2     value     n
##    <chr>     <dbl> <int>
##  1 like          2    10
##  2 doubt        -1     9
##  3 wish          1     7
##  4 admit        -1     5
##  5 easy          1     5
##  6 pretend      -1     5
##  7 reach         1     5
##  8 difficult    -1     4
##  9 extend        1     4
## 10 help          2     4
## # ℹ 87 more rows

Lets visualize

library(ggplot2)

not_words %>%
  mutate(contribution = n * value) %>%
  arrange(desc(abs(contribution))) %>%
  head(20) %>%
  mutate(word2 = reorder(word2, contribution)) %>%
  ggplot(aes(n * value, word2, fill = n * value > 0 )) +
  geom_col(show.legend = FALSE) +
  labs(x = "sentiment value * number or occurences", y = "words preceded by \"not\"")

negation_words <- c("not", "no", "never", "non", "without")

negated_words <- bigrams_separated %>%
  filter(word1 %in% negation_words) %>%
  inner_join(AFINN, by = c(word2 = "word")) %>%
  count(word1, word2, value, sort = TRUE)

negated_words

## # A tibble: 182 × 4
##    word1   word2   value     n
##    <chr>   <chr>   <dbl> <int>
##  1 no      doubt      -1   173
##  2 no      great       3    14
##  3 not     like        2    10
##  4 not     doubt      -1     9
##  5 not     wish        1     7
##  6 without doubt      -1     7
##  7 not     admit      -1     5
##  8 not     easy        1     5
##  9 not     pretend    -1     5
## 10 not     reach       1     5
## # ℹ 172 more rows

Lets visualize the negation words

negated_words %>%
  mutate(contribution = n * value,
         word2 = reorder(paste(word2, word1, sep = "_"), contribution)) %>%
  group_by(word1) %>%
  slice_max(abs(contribution), n = 12, with_ties = FALSE) %>%
  ggplot(aes(word2, contribution, fill = n * value > 0)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~word1, scales = "free") +
  scale_x_discrete(labels = function(x) gsub("_.+$", "", x)) +
  xlab("words preceded by negation term") +
  ylab("sentiment value * # of occureneces") +
  coord_flip()

Visualize a network of bigrams with ggraph

library(igraph)

## 
## Attaching package: 'igraph'

## The following object is masked from 'package:mosaic':
## 
##     compare

## The following objects are masked from 'package:lubridate':
## 
##     %--%, union

## The following object is masked from 'package:plotly':
## 
##     groups

## The following object is masked from 'package:tidyr':
## 
##     crossing

## The following objects are masked from 'package:dplyr':
## 
##     as_data_frame, groups, union

## The following objects are masked from 'package:stats':
## 
##     decompose, spectrum

## The following object is masked from 'package:base':
## 
##     union

bigram_counts <- bigram_filtered %>%
  count(word1, word2, sort = TRUE)

bigram_graph <- bigram_counts %>%
  filter(n > 20) %>%
  graph_from_data_frame()

## Warning in graph_from_data_frame(.): In `d' `NA' elements were replaced with
## string "NA"

bigram_graph

## IGRAPH c0d8cc6 DN-- 158 106 -- 
## + attr: name (v/c), n (e/n)
## + edges from c0d8cc6 (vertex names):
##  [1] NA        ->NA          sexual    ->selection   vol       ->ii         
##  [4] natural   ->selection   lower     ->animals     sexual    ->differences
##  [7] breeding  ->season      secondary ->sexual      south     ->america    
## [10] sexual    ->characters  del       ->fuego       tierra    ->del        
## [13] vol       ->iii         de        ->la          bright    ->colours    
## [16] sexual    ->difference  distinct  ->species     tail      ->feathers   
## [19] closely   ->allied      vocal     ->organs      zoological->gardens    
## [22] natural   ->history     buenos    ->ayres       captain   ->fitz       
## + ... omitted several edges

library(ggraph)
set.seed(1234)

ggraph(bigram_graph, layout = "fr") +
  geom_edge_link() +
  geom_node_point() +
  geom_node_text(aes(label = name), vjust = 1, hjust = 1)

## Warning: Using the `size` aesthetic in this geom was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` in the `default_aes` field and elsewhere instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

we can also add directionality to this network

set.seed(1234)

a <- grid::arrow(type = "closed", length = unit(0.15, "inches"))

ggraph(bigram_graph, layout = "fr") +
  geom_edge_link(aes(edge_alpha = n), show.legend = FALSE, arrow = a, end_cap = circle(0.7, 'inches')) +
  geom_node_point(color = "lightblue", size = 5) +
  geom_node_text(aes(label = name), vjust = 1, hjust = 1) +
  theme_void()

###Word Frequencies A central question in text mining is how to quantify what a document is about. We can do this but looking at words that make up the document, and measuring term frequency.

There are a lot of words that may not be important, these are the stop words.

One way to remedy this is to look at inverse document frquency words, which decreases the weight for commonly used words and increases the weight for words that are not used very much.

Term frequency in Darwins works

library(dplyr)
library(tidytext)

book_words <- gutenberg_download(c(944, 1227, 1228, 2300), mirror = "https://gutenberg.nabasny.com/")

## Warning: ! Could not download a book at
##   https://gutenberg.nabasny.com//1/2/2/1228/1228.zip.
## ℹ The book may have been archived.
## ℹ Alternatively, You may need to select a different mirror.
## → See https://www.gutenberg.org/MIRRORS.ALL for options.

colnames(book_words)[1] <- "book"

book_words$book[book_words$book == 944] <- "The Voyage of the Beagle"
book_words$book[book_words$book == 1227] <- "The Expressionof the Emotions in Man and Animals"
book_words$book[book_words$book == 1228] <- "on the origin of species By Means of Natural selection"
book_words$book[book_words$book == 2300] <- "The Descent of Man, and selection in Relation to sex"

Now lets disect

book_words <- book_words %>%
  unnest_tokens(word, text) %>%
  count(book, word , sort = TRUE)

book_words

## # A tibble: 35,579 × 3
##    book                                                 word      n
##    <chr>                                                <chr> <int>
##  1 The Descent of Man, and selection in Relation to sex the   25490
##  2 The Voyage of the Beagle                             the   16930
##  3 The Descent of Man, and selection in Relation to sex of    16762
##  4 The Voyage of the Beagle                             of     9438
##  5 The Descent of Man, and selection in Relation to sex in     8882
##  6 The Expressionof the Emotions in Man and Animals     the    8045
##  7 The Descent of Man, and selection in Relation to sex and    7854
##  8 The Descent of Man, and selection in Relation to sex to     5901
##  9 The Voyage of the Beagle                             and    5768
## 10 The Voyage of the Beagle                             a      5328
## # ℹ 35,569 more rows

book_words$n <- as.numeric(book_words$n)

total_words <- book_words %>%
  group_by(book) %>%
  dplyr::summarize(total = sum(n))

book_words

## # A tibble: 35,579 × 3
##    book                                                 word      n
##    <chr>                                                <chr> <dbl>
##  1 The Descent of Man, and selection in Relation to sex the   25490
##  2 The Voyage of the Beagle                             the   16930
##  3 The Descent of Man, and selection in Relation to sex of    16762
##  4 The Voyage of the Beagle                             of     9438
##  5 The Descent of Man, and selection in Relation to sex in     8882
##  6 The Expressionof the Emotions in Man and Animals     the    8045
##  7 The Descent of Man, and selection in Relation to sex and    7854
##  8 The Descent of Man, and selection in Relation to sex to     5901
##  9 The Voyage of the Beagle                             and    5768
## 10 The Voyage of the Beagle                             a      5328
## # ℹ 35,569 more rows

book_words <- left_join(book_words, total_words)

## Joining with `by = join_by(book)`

book_words

## # A tibble: 35,579 × 4
##    book                                                 word      n  total
##    <chr>                                                <chr> <dbl>  <dbl>
##  1 The Descent of Man, and selection in Relation to sex the   25490 311041
##  2 The Voyage of the Beagle                             the   16930 208118
##  3 The Descent of Man, and selection in Relation to sex of    16762 311041
##  4 The Voyage of the Beagle                             of     9438 208118
##  5 The Descent of Man, and selection in Relation to sex in     8882 311041
##  6 The Expressionof the Emotions in Man and Animals     the    8045 110414
##  7 The Descent of Man, and selection in Relation to sex and    7854 311041
##  8 The Descent of Man, and selection in Relation to sex to     5901 311041
##  9 The Voyage of the Beagle                             and    5768 208118
## 10 The Voyage of the Beagle                             a      5328 208118
## # ℹ 35,569 more rows

you can see that the usual supspect are the most common words, but don’t tell us anything about what the books topic is.

library(ggplot2)

ggplot(book_words, aes(n/total, fill = book)) +
  geom_histogram(show.legend = FALSE) +
  xlim(NA, 0.0009) +
  facet_wrap(~book, ncol = 2, scales = "free_y")

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## Warning: Removed 370 rows containing non-finite values (`stat_bin()`).

## Warning: Removed 3 rows containing missing values (`geom_bar()`).

Zipf’s Law

The frequency that a words appears is inversely proportional to its rank when predicting a topic.

Lets apply Zipf’s law to Darwin’s work

freq_by_rank <- book_words %>%
  group_by(book) %>%
  dplyr::mutate(rank = row_number(),
         `term frequency` = n/total) %>%
  ungroup()

freq_by_rank

## # A tibble: 35,579 × 6
##    book                                word      n  total  rank `term frequency`
##    <chr>                               <chr> <dbl>  <dbl> <int>            <dbl>
##  1 The Descent of Man, and selection … the   25490 311041     1           0.0820
##  2 The Voyage of the Beagle            the   16930 208118     1           0.0813
##  3 The Descent of Man, and selection … of    16762 311041     2           0.0539
##  4 The Voyage of the Beagle            of     9438 208118     2           0.0453
##  5 The Descent of Man, and selection … in     8882 311041     3           0.0286
##  6 The Expressionof the Emotions in M… the    8045 110414     1           0.0729
##  7 The Descent of Man, and selection … and    7854 311041     4           0.0253
##  8 The Descent of Man, and selection … to     5901 311041     5           0.0190
##  9 The Voyage of the Beagle            and    5768 208118     3           0.0277
## 10 The Voyage of the Beagle            a      5328 208118     4           0.0256
## # ℹ 35,569 more rows

freq_by_rank %>%
  ggplot(aes(rank, `term frequency`, color = book)) +
  geom_line(size = 1.1, alpha = 0.8, show.legend = FALSE) +
  scale_x_log10() +
  scale_y_log10()

Lets us IF - IDF to find words for each document by decreasing the weight for commonly used and increasing the weight for words that are not used very much in a collection of documents.

book_tf_idf <- book_words %>%
  bind_tf_idf(word, book, n)

book_tf_idf

## # A tibble: 35,579 × 7
##    book                                   word      n  total     tf   idf tf_idf
##    <chr>                                  <chr> <dbl>  <dbl>  <dbl> <dbl>  <dbl>
##  1 The Descent of Man, and selection in … the   25490 311041 0.0820     0      0
##  2 The Voyage of the Beagle               the   16930 208118 0.0813     0      0
##  3 The Descent of Man, and selection in … of    16762 311041 0.0539     0      0
##  4 The Voyage of the Beagle               of     9438 208118 0.0453     0      0
##  5 The Descent of Man, and selection in … in     8882 311041 0.0286     0      0
##  6 The Expressionof the Emotions in Man … the    8045 110414 0.0729     0      0
##  7 The Descent of Man, and selection in … and    7854 311041 0.0253     0      0
##  8 The Descent of Man, and selection in … to     5901 311041 0.0190     0      0
##  9 The Voyage of the Beagle               and    5768 208118 0.0277     0      0
## 10 The Voyage of the Beagle               a      5328 208118 0.0256     0      0
## # ℹ 35,569 more rows

Lets look at terms with high tf-idf in Darwin’s works

book_tf_idf %>%
  select(-total) %>%
  arrange(desc(tf_idf))

## # A tibble: 35,579 × 6
##    book                                        word      n      tf   idf  tf_idf
##    <chr>                                       <chr> <dbl>   <dbl> <dbl>   <dbl>
##  1 The Expressionof the Emotions in Man and A… tears   126 1.14e-3 1.10  1.25e-3
##  2 The Expressionof the Emotions in Man and A… blush   114 1.03e-3 1.10  1.13e-3
##  3 The Descent of Man, and selection in Relat… sexu…   745 2.40e-3 0.405 9.71e-4
##  4 The Descent of Man, and selection in Relat… sele…   621 2.00e-3 0.405 8.10e-4
##  5 The Voyage of the Beagle                    sea     351 1.69e-3 0.405 6.84e-4
##  6 The Voyage of the Beagle                    degs    117 5.62e-4 1.10  6.18e-4
##  7 The Expressionof the Emotions in Man and A… eyeb…   149 1.35e-3 0.405 5.47e-4
##  8 The Voyage of the Beagle                    isla…   271 1.30e-3 0.405 5.28e-4
##  9 The Descent of Man, and selection in Relat… shewn   143 4.60e-4 1.10  5.05e-4
## 10 The Expressionof the Emotions in Man and A… frown    46 4.17e-4 1.10  4.58e-4
## # ℹ 35,569 more rows

Lets look at a visualization for these high tf-idf words

book_tf_idf %>%
  group_by(book) %>%
  slice_max(tf_idf, n = 15) %>%
  ungroup() %>%
  ggplot(aes(tf_idf, reorder(word, tf_idf), fill = book)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~book, ncol = 2, scales = "free") +
  labs(x = "tf-idf", y = NULL)