# Data

x <- -10:10
y <- -10:10
z <- sqrt(outer(x ^ 2, y ^ 2, "+"))

contour(x, y, z)

# You can also type, the following

# but the axes will be between 0 and 1
contour(z)

#=====
x <- -10:10
y <- -10:10
z <- sqrt(outer(x ^ 2, y ^ 2, "+"))

contour(x, y, z,
nlevels = 20)

############################################

# Libraries
library(tidyverse)
#install.packages('hrbrthemes')
library(hrbrthemes)
library(viridis)
#install.packages('patchwork')
library(patchwork)

# Dataset:
a <- data.frame( x=rnorm(20000, 10, 1.2),
y=rnorm(20000, 10, 1.2),
group=rep("A",20000))
b <- data.frame( x=rnorm(20000, 14.5, 1.2), y=rnorm(20000, 14.5, 1.2),
group=rep("B",20000))
c <- data.frame( x=rnorm(20000, 9.5, 1.5), y=rnorm(20000, 15.5, 1.5),
group=rep("C",20000))
data <- do.call(rbind, list(a,b,c))
View(data)
p1 <- data %>%
ggplot( aes(x=x, y=y)) +
geom_point(color="#69b3a2", size=2) +
theme_ipsum() +
theme( legend.position="non
e"
)
p2 <- ggplot(data, aes(x=x, y=y) ) +
stat_density_2d(aes(fill = ..density..), geom = "raster", contour = FALSE) +
scale_x_continuous(expand = c(0, 0)) +
scale_y_continuous(expand = c(0, 0)) +
scale_fill_viridis() +
theme( legend.position
='none'
)

p1 + p2

library(plotly)
library(MASS)

# Compute kde2d
kd <- with(data, MASS::kde2d(x, y, n = 50))

# Plot with plotly

plot_ly(x = kd$x, y = kd$y, z = kd$z) %>% add_surface()

#Node-Link Diagram
#https://krisrs1128.github.io/stat479/

library("dplyr")
library("knitr")
library("ggplot2")
#install.packages('ggraph')
library("ggraph")
library("gridExtra")
#install.packages("networkD3")
library("networkD3")
library("tidygraph")
theme_set(theme_graph())

#A node-link diagram
G_school <- as_tbl_graph(highschool) %>%
activate(edges) %>%
mutate(year = factor(year))

ggraph(G_school) +
geom_edge_link(aes(col = year), width = 0.1) +
geom_node_point()

#For Tree
G_flare <- tbl_graph(flare$vertices, flare$edges)
p1 <- ggraph(G_flare, 'tree') +
geom_edge_link() +
geom_node_label(aes(label = shortName), size = 3)

p2 <- ggraph(G_flare, 'tree', circular = TRUE) +

geom_edge_link() +
geom_node_label(aes(label = shortName), size = 3)

grid.arrange(p1, p2, ncol = 2)

############################################

#3D Network
school_edges <- G_school %>%
activate(edges) %>%
as.data.frame()
simpleNetwork(school_edges)

from <- match(flare$imports$from, flare$vertices$name)

to <- match(flare$imports$to, flare$vertices$name)
ggraph(G_flare, layout = 'dendrogram', circular = TRUE) +
geom_conn_bundle(data = get_con(from = from, to = to), alpha = 0.1) +
geom_node_label(aes(label = shortName), size = 2) +
coord_fixed()

############################################
#Shiny
#ui.R
library(shiny)
library(shinydashboard)

shinyServer( pageWithSidebar
( headerPanel("My First
App"), sidebarPanel(
selectInput("Distribution",
"Please Select Distribution Type",
choices = c("Normal", "Exponential")),
sliderInput("sampleSize",
"Please Select Sample Size",
min = 100, max=5000, value=1000,step=100),
conditionalPanel(condition ="input.Distribution=='Normal'",
textInput("mean","Please Select the mean:",10),
textInput("sd", "Please Select Std. Devivation",3)),
conditionalPanel(condition="input.Distribution=='Exponential'",
textInput("lambda","Pls. Select Exponential Lambda",1))
),
 mainPanel( plotOutput("myPl
ot")
)
)
)

#server.R
shinyServer(
function(input, output, session){
output$myPlot <- renderPlot({
distType <- input$Distribution
size <- input$sampleSize
if(distType == "Normal"){
randomVec <- rnorm(size, mean = as.numeric(input$mean),
sd = as.numeric(input$sd))
}
else{
randomVec <- rexp(size, rate = 1/as.numeric(input$lambda))
}
hist(randomVec, col="blue")
})
}
)

############################################
#igraph
#install.packages('igraph')
library(igraph)
nnodes <- 100
nnedges <- 200

nodes <- data.frame(id = 1:nnodes)

edges <- data.frame(from = sample(1:nnodes, nnedges, replace = T),
to = sample(1:nnodes, nnedges, replace = T))

# with defaut layout

visNetwork(nodes, edges, height = "500px") %>%
visIgraphLayout() %>%
visNodes(size = 10)

# in circle ?
visNetwork(nodes, edges, height = "500px") %>%
visIgraphLayout(layout = "layout_in_circle") %>%
visNodes(size = 10) %>%
visOptions(highlightNearest = list(enabled = T, hover = T),
nodesIdSelection = T)

library("igraph", quietly = TRUE, warn.conflicts = FALSE, verbose = FALSE)

igraph_network <- graph.famous("Walther")
igraph_network
plot(igraph_network)

#================

my_ui <- fluidPage(

sidebarLayout( si

debarPanel(

# Input: Selector for choosing dataset

selectInput(inputId = "my_variable", # internal ID name
label = "Choose a variable:", # your label
choices = c("Petal Length", "Petal Width", "Sepal Length", "Sepal
Width")),

# Input: Slider for choosing number of bins

sliderInput(inputId = "my_slider", # internal ID name
label = "Select number of bins:", # your label
min = 1, # Min value available
max = 30, # Max value available
value = 20)), # the starting value

mainPanel(
plotOutput(outputId = "hist_plot"))
)
)

# Define logic (functionality)

my_server <- function(input, output) {

# Return the requested variable

variableInput <- reactive({
switch(input$my_variable,
"Petal Length" = iris$Petal.Length,
"Petal Width" = iris$Petal.Width,
"Sepal Length" = iris$Sepal.Length,
"Sepal Width" = iris$Sepal.Width)
})

output$hist_plot <- renderPlot( {

x <- variableInput()
bins <- seq(min(x), max(x), length.out = input$my_slider + 1)
hist(x, breaks = bins, col = "lightgreen", border = "white",
xlab = "cm",
main = paste("Histogram of", input$my_variable ,"for the flowers of the iris
family"))
 }
)

# Run the app

shinyApp(ui = my_ui, server = my_server)

############################################

#Heat Map

# Load the library

library("lattice")

# Dummy data
data <- matrix(runif(100, 0, 5) , 10 , 10)
colnames(data) <- letters[c(1:10)]
rownames(data) <- paste( rep("row",10) , c(1:10) , sep=" ")

# plot it flipping the axis

levelplot( t(data[c(nrow(data):1) , ]),
col.regions=heat.colors(100))

#Heat Map
# Library
library(ggplot2)

# Dummy data
x <- LETTERS[1:20]
y <- paste0("var", seq(1,20))
data <- expand.grid(X=x, Y=y)
data$Z <- runif(400, 0, 5)
library(ggplot2)
ggplot(data, aes(X, Y, fill= Z)) +
geom_tile()

#Heapmap - Viridis
# Lattice package
require(lattice)

# The volcano dataset is provided, it looks like that:

#head(volcano)

# 1: native palette from R

levelplot(volcano, col.regions = terrain.colors(100)) # try cm.colors() or
terrain.colors()

# 2: Rcolorbrewer palette
library(RColorBrewer)
coul <- colorRampPalette(brewer.pal(8, "PiYG"))(25)
levelplot(volcano, col.regions = coul) # try cm.colors() or terrain.colors()

# 3: Viridis
library(viridisLite)
coul <- viridis(100)
levelplot(volcano, col.regions = coul)
#levelplot(volcano, col.regions = magma(100))

#Heatmap - mtcars
# The mtcars dataset:
data <- as.matrix(mtcars)

# Default Heatmap
heatmap(data)
#mtcars - Normalization
# Use 'scale' to normalize
heatmap(data, scale="column")

############################################

#Data Cleaning
data <- data.frame(x1 = c(1:4, 99999, 1, NA, 1, 1, NA), # Create example data
frame
x1 = c(1:5, 1, "NA", 1, 1, "NA"),
x1 = c(letters[c(1:3)], "x x", "x", " y y y", "x", "a", "a", NA),
x4 = "",
x5 = NA)
data # Print example data frame
#Example 1: Modify Column Names
colnames(data) # Print column names
colnames(data) <- paste0("col", 1:ncol(data)) # Modify all column names
data # Print updated data frame

#Format missing cell

data[data == ""] # Print blank data cells
data[data == ""] <- NA # Replace blanks by NA
data$col2 # Print column
data$col2[data$col2 == "NA"] <- NA # Replace character "NA"

#Example 3: Remove Empty Rows & Columns

data <- data[rowSums(is.na(data)) != ncol(data), ] # Drop empty rows
data # Print updated data frame
data <- data[ , colSums(is.na(data)) != nrow(data)] # Drop empty columns
data # Print updated data frame
#Example 4: Remove Rows with Missing Values
data <- na.omit(data) # Delete rows with missing values
data # Print updated data frame
#Example 5: Remove Duplicates
data <- unique(data) # Exclude duplicates
data # Print updated data frame
#Example 6: Modify Classes of Columns
sapply(data, class) # Print classes of all columns
#convert to approprate class name
data <- type.convert(data, as.is = TRUE)
data # Print updated data frame
sapply(data, class) # Print classes of updated columns
data$col1[data$col1 %in% boxplot.stats(data$col1)$out] # Identify outliers in
column
data <- data[! data$col1 %in% boxplot.stats(data$col1)$out, ] # Remove rows
with outliers
data # Print updated data frame
#Example 8: Remove Spaces in Character Strings
data$col3 <- gsub(" ", "", data$col3) # Delete white space in character
strings
data # Print updated data frame
#Example 9: Combine Categories
data$col3[data$col3 %in% c("b", "c")] <- "a" # Merge categories
data # Print updated data frame

############################################

#Time-Series
data(AirPassengers)
AirPassengers
str(AirPassengers)
class(AirPassengers)
#Check for missing values
sum(is.na(AirPassengers))
start(AirPassengers)
end(AirPassengers)
frequency(AirPassengers)
summary(AirPassengers)
par(mfrow=c(3,3))
plot(AirPassengers)
plot.ts(AirPassengers)
# This will fit in a line
abline(reg=lm(AirPassengers~time(AirPassengers)))
#This will print the cycle across years
cycle(AirPassengers)

#Step 3: Make it stationary

#stationary means there should be consitant mean and variance
plot(log(AirPassengers))
plot(diff(log(AirPassengers)))
#This will aggregate the cycles and display a year on year trend
plot(aggregate(AirPassengers,FUN=mean))
#Box plot across months will give us a sense on seasonal effect
boxplot(AirPassengers~cycle(AirPassengers))

plot(diff(log(AirPassengers)))
#Time Series Decomposition
#Decomposition break data into trend, seasonal, regular and random
plot(decompose(AirPassengers)) # time series decomposition
#The above figure shows the time series decomposition into trend, seasonal and
random (noise) . It is clear that the time series is non-stationary (has random
walks) because of seasonal effects and a trend (linear trend).

#Step 5: Model Identification and Estimation

#Autocorrelation function and partial autocorrelation function to determine
value of p and q
#AR I MA - Auto Regression Moving Average Integration
#p d q
acf(AirPassengers)
acf(diff(log(AirPassengers)))

pacf(diff(log(AirPassengers)))
#It determine value of p (value we got as 0)

#d is number of time you do the differentiations to make the mean

#We do diff only one time so value of d is 1
plot(diff(log(AirPassengers)))

#Stepn 6: ARIMA Model Prediction

fit <- arima(log(AirPassengers),c(0,1,1),seasonal =

list(order=c(0,1,1),period=12))
fit
#Predict for next 10 years
pred <- predict(fit,n.ahead=10*12) #10 years * 12 months
pred
#2.718 is e value and round them to 0 decimal
pred1<-round(2.718^pred$pred,0)
pred1 #give op of 1960 to 1970

#plot this model

#line type (lty) can be specified using either text ("blank", "solid", "dashed",
"dotted", "dotdash", "longdash", "twodash") or number (0, 1, 2, 3, 4, 5, 6). Note
that lty = "solid" is identical to lty=1.
ts.plot(AirPassengers,pred1,log="y",lty=c(1,3))
#Compare predicted values with original values
#Get only 1961 values
data1<-head(pred1,12)
data1
#Predicted Values
predicted_1960 <- round(data1)#head of Predicted
predicted_1960
#Original
original_1960 <- tail(AirPassengers,12) #tail of original
original_1960
#Lets Test this Model we are going to take a dataset till 1959, and then we
predict value of 1960, then validate that 1960 from alredy existing value we have
it in dataset
#Recreate model till 1959
datawide <- ts(AirPassengers, frequency = 12, start=c(1949,1), end=c(1959,12))
datawide
#Create model
fit1 <- arima(log(datawide),c(0,1,1),seasonal = list(order=c(0,1,1),period=12))
pred <- predict(fit1,n.ahead=10*12) # predictfor now 1960 to 1970
pred1<-2.718^pred$pred
pred1 #give op of 1960 to 1970

data11=round(head(pred1,12),0) #head of Predicted

data22=round(tail(AirPassengers,12),0) #tail of original

plot(data11,col="red", type="l")
lines(data22,col="blue")
#Step 7: Check normality using Q-Q plot
#qqnorm is a generic function the default method of which produces a normal
QQ plot of the values in y. qqline adds a line to a “theoretical”, by default normal,
quantile-quantile plot which passes through the probs quantiles, by default the
first and third quartiles.

qqnorm(residuals(fit))
qqline(residuals(fit))

############################################

#Text Analytics - Sentimental Analysis

#install.packages("tidytext")
#install.packages("tidyverse")
#install.packages("textdata")
# Load dplyr and tidytext
library(dplyr)
library(tidytext)
library(textdata)
# Choose the bing lexicon
get_sentiments("bing")

# Choose the nrc lexicon

get_sentiments("nrc") %>%
count(sentiment) # Count words by sentiment

#Geocoded Tweets
#The geocoded_tweets dataset contains three columns:
#1. state, a state in the United States
#2. word, a word used in tweets posted on Twitter
#3. freq, the average frequency of that word in that state (per billion words)

# geocoded_tweets has been pre-defined

load("geocoded_tweets.rda")
geocoded_tweets
# Use get_sentiments() to access the "bing" lexicon and assign it to bing.
bing <- get_sentiments("bing")
bing
# Use an inner_join() to implement sentiment analysis on the geocoded tweet
data using the bing lexicon.
tweets_nrc <- geocoded_tweets %>%
inner_join(bing)

#Test
#Access nrc lexicon: nrc
nrc <- get_sentiments("nrc")

# Use data frame with text data

tweets_nrc = geocoded_tweets %>%
# With inner join, implement sentiment analysis using `nrc`
inner_join(nrc)

head(tweets_nrc)

tweets_nrc %>%
# Filter to only choose the words associated with sadness
filter(sentiment=="sadness") %>%
# Group by word
group_by(word) %>%
# Use the summarize verb to find the mean frequency
summarize(freq = mean(freq)) %>%
# Arrange to sort in order of descending frequency
arrange(desc(freq))

joy_words <- tweets_nrc %>%

# Filter to choose only words associated with joy
filter(sentiment=="joy") %>%
# Group by each word
 group_by(word) %>%
# Use the summarize verb to find the mean frequency
summarize(freq = mean(freq)) %>%
# Arrange to sort in order of descending frequency
arrange(desc(freq))
joy_words
#install.packages("wordcloud")
library("wordcloud")
set.seed(100)
wordcloud(words = joy_words$word, freq = joy_words$freq,
random.order=TRUE)
wordcloud(words = joy_words$word, freq = joy_words$freq,
random.order=FALSE)
wordcloud(words = joy_words$word, freq = joy_words$freq,
min.freq = 3, max.words=250,
random.order=T,
rot.per=0.30,
colors=brewer.pal(8, "Dark2"))
# Load ggplot2
library(ggplot2)

joy_words %>%
top_n(20) %>%
mutate(word = reorder(word, freq)) %>%
# Use aes() to put words on the x-axis and frequency on the y-axis
ggplot(aes(x=word, y=freq)) +
# Make a bar chart with geom_col()
geom_col() +
coord_flip()
#install.packages('wordcloud2')
library(wordcloud2)
wordcloud2(joy_words, size = 1.5,
color='random-dark')
#circle, cardioid, diamond, triangle-forward
#triangle, pentagon, star

wordcloud2(joy_words, size = 0.7, shape = 'star')

text <- c("Because I could not stop for Death -",

"He kindly stopped for me -",
"The Carriage held but just Ourselves - * * ***",
"and Immortality?")
text
text_df <- tibble(line=1:4, text = text)
text_df %>%
unnest_tokens(word, text)
#Salaries Data - Visualization
library(ggplot2)
data(Salaries, package="carData")
View(Salaries)
# plot experience vs. salary
ggplot(Salaries,
aes(x = yrs.since.phd,
y = salary)) +
geom_point() +
labs(title = "Academic salary by years since degree")

# plot experience vs. salary (color represents rank)

ggplot(Salaries, aes(x = yrs.since.phd,
y = salary,
color=rank)) +
geom_point() +
labs(title = "Academic salary by rank and years since degree")

# (color represents rank, shape represents sex)

ggplot(Salaries,
aes(x = yrs.since.phd,
y = salary,
color = rank,
shape = sex)) +
geom_point(size = 3,
alpha = .6) +
labs(title = "Academic salary by rank, sex, and years since degree")

# plot experience vs. salary

# (color represents rank and size represents service)
ggplot(Salaries,
aes(x = yrs.since.phd,
y = salary,
color = rank,
size = yrs.service)) +
geom_point(alpha = .6) +
labs(title = "Academic salary by rank, years of service, and years since degree")

# plot salary histograms by rank

ggplot(Salaries, aes(x = salary)) +
geom_histogram(fill = "cornflowerblue",
color = "white") +
facet_wrap(~rank, ncol = 1) +
labs(title = "Salary histograms by rank")

# plot salary histograms by rank and sex

ggplot(Salaries, aes(x = salary / 1000)) +
geom_histogram(color = "white",
 fill = "cornflowerblue") +
facet_grid(sex ~ rank) +
labs(title = "Salary histograms by sex and rank",
x = "Salary ($1000)")

#$$$$$$$$# calculate means and standard erroes by sex, rank and discipline

library(dplyr)
plotdata <- Salaries %>%
group_by(sex, rank, discipline) %>%
summarize(n = n(),
mean = mean(salary),
sd = sd(salary),
se = sd / sqrt(n))

# create better labels for discipline

plotdata$discipline <- factor(plotdata$discipline,
labels = c("Theoretical",
"Applied"))
# create plot
ggplot(plotdata,
aes(x = sex,
y = mean,
color = sex)) +
geom_point(size = 3) +
geom_errorbar(aes(ymin = mean - se,
ymax = mean + se),
width = .1) +
scale_y_continuous(breaks = seq(70000, 140000, 10000),
label = scales::dollar) +
facet_grid(. ~ rank + discipline) +
theme_bw() +
theme(legend.position = "none",
panel.grid.major.x = element_blank(),
panel.grid.minor.y = element_blank()) +
labs(x="",
y="",
title="Nine month academic salaries by gender, discipline, and rank",
subtitle = "(Means and standard errors)") +
scale_color_brewer(palette="Set1")

###########################################
#library(MASS)
#install.packages("ISLR")
#library(ISLR)
#fix(Boston)

names(Boston)
head(Boston)
Bostondf<-data.frame(lstat=Boston$lstat,
age=Boston$age,
medv=Boston$medv)
plot(Bostondf)
pairs(Bostondf)
#install.packages("scatterplot3d") # Install
library("scatterplot3d")
scatterplot3d(Bostondf, angle=30)

#Parallel Coordinates
# Libraries
library(tidyverse)
library(hrbrthemes)
library(patchwork)
#install.packages('GGally')
library(GGally)
library(viridis)

diamonds %>%
sample_n(10) %>%
ggparcoord( column
s = c(1,5:7),
groupColumn = 2,
#order = "anyClass",
showPoints = TRUE,
title = "Diamonds features",
alphaLines = 0.3
)+
scale_color_viridis(discrete=TRUE) +
theme_ipsum()+
theme(
plot.title = element_text(size=10)
)

# Data set is provided by R natively

# Parallel plot or parallel coordinates plot allows to compare the feature of
several individual observations (series) on a set of numeric variables. Each
vertical bar represents a variable and often has its own scale. (The units can even
be different). Values are then plotted as series of lines connected across each
axis.

data <- iris

# Plot
data %>%
ggparcoord(
columns = 1:4, groupColumn = 5, order = "anyClass",
showPoints = TRUE,
title = "Parallel Coordinate Plot for the Iris Data",
 alphaLines = 0.3
)+
scale_color_viridis(discrete=TRUE) +
theme_ipsum()+
theme(
plot.title = element_text(size=10)
)

# Plot
p1 <- data %>%
ggparcoord(
columns = 1:4, groupColumn = 5, order = "anyClass",
scale="globalminmax",
showPoints = TRUE,
title = "No scaling",
alphaLines = 0.3
)+
scale_color_viridis(discrete=TRUE) +
theme_ipsum()+
theme( legend.position="none
",
plot.title = element_text(size=10)
)+
xlab("")

p2 <- data %>%

ggparcoord(
columns = 1:4, groupColumn = 5, order = "anyClass",
scale="uniminmax",
showPoints = TRUE,
title = "Standardize to Min = 0 and Max = 1",
alphaLines = 0.3
)+
scale_color_viridis(discrete=TRUE) +
theme_ipsum()+
theme( legend.position="none
",
plot.title = element_text(size=10)
)+
xlab("")

p3 <- data %>%

ggparcoord(
columns = 1:4, groupColumn = 5, order = "anyClass",
scale="std",
showPoints = TRUE,
 title = "Normalize univariately (substract mean & divide by sd)",
alphaLines = 0.3
)+
scale_color_viridis(discrete=TRUE) +
theme_ipsum()+
theme( legend.position="none
",
plot.title = element_text(size=10)
)+
xlab("")

p4 <- data %>%

ggparcoord(
columns = 1:4, groupColumn = 5, order = "anyClass",
scale="center",
showPoints = TRUE,
title = "Standardize and center variables",
alphaLines = 0.3
)+
scale_color_viridis(discrete=TRUE) +
theme_ipsum()+
theme( legend.position="none
",
plot.title = element_text(size=10)
)+
xlab("")

p1 + p2 + p3 + p4 + plot_layout(ncol = 2)

############################################
###########Tidying Shakespearean plays
#shakespeare dataset contains 3 colomns
#1. title, the title of a Shakespearean play
#2. type, the type of play, either tragedy or comedy
#3. text, a line from that play

#1. load shakespeare.rda into r environment

#2. Pipe the shakespeare data frame to the next line

# Use count to find out how many titles/types there are

#3. Load tidytext/ tidyverse

#4. create and object tidy_shakespeare

# Group by the titles of the plays
 # Define a new column linenumber
# Transform the non-tidy text data to tidy text data

#5. Pipe the tidy Shakespeare data frame to the next line
# Use count to find out how many times each word is used

#6. Sentiment analysis of tidy_shakespeare assin to object

shakespeare_sentiment
# Implement sentiment analysis with the "bing" lexicon

#7. shakespeare_sentiment
# Find how many positive/negative words each play has

#8. Tragedy or comedy from tidy_shakespeare assign to sentiment_counts

# Implement sentiment analysis using the "bing" lexicon
# Count the number of words by title, type, and sentiment

#9. from sentiment_counts

# Group by the titles of the plays
# Find the total number of words in each play
# Calculate the number of words divided by the total
# Filter the results for only negative sentiment then arrange percentage in asc
order

#10 Most common positive and negative words and assign to word_could
# Implement sentiment analysis using the "bing" lexicon
# Count by word and sentiment
#11. extract top 10 words from word_counts and assing to top_words
# Group by sentiment
# Take the top 10 for each sentiment and ungroup it
# Make word a factor in order of n

#12 Use aes() to put words on the x-axis and n on the y-axis
# Make a bar chart with geom_col()
# facet_wrap for sentiments and apply scales as free
#Move x to y and y to x

#13 from tidy_shakespeare Calculating a contribution score

# Count by title and word

# Implement sentiment analysis using the "afinn" lexicon

# Group by title

# Calculate a contribution for each word in each title