Unit-3

Unit-3
Data Reshaping
Joining multiple vectors to form a data frame and combining two data frames
name <- c("Naruto Shipudden", "Dragon Ball", "One Piece")

mc <- c("Naruto", "Goku", "Luffy")
## Join and form df

anime <- data.frame(name, mc)
anime2 <- data.frame(

name = c("Attack on Titan", "Death Note", "Bleach"),
mc = c("Eren", "Light", "Ichigo")
)
## Combine two dfs

combined_anime <- rbind(anime, anime2)
combined_anime
Merging two data frames based on a common column
## df1
df1 <- data.frame(
id = 1:5,
name = c("Yawar", "Zayed", "Hanan", "Ziya", "Paras")
)
## df2
df2 <- data.frame(
id = c(2, 5, 4, 1, 3),
address = c("Saraibal", "Tral", "Hyderpora", "Khanyar", "Rajbagh")
)
# Merge the two data frames based on the 'id' column

merged_df <- merge(df1, df2, by = "id")
# View the merged data frame

print(merged_df)
Melting
library("reshape2")
library("reshape")
n <- c(1, 1, 2, 2)
time <- c(1, 2, 1, 2)
x <- c(6, 3, 2, 5)
y <- c(1, 4, 6, 9)
df <- data.frame(n, time, x, y)

cat("===Original data===\\n")
df
cat("=== Organized by n and time ===\\n")

molten_data <- melt(df, id = c("n", "time"))
molten_data
CSV Files
## Write into a csv file
anime <- data.frame(
Name = c("Naruto", "Bleach", "One Piece", "Dragon Ball"),
Year = c(2002, 2004, 1999, 1986),
Episodes = c(220, 366, 900, 153),
Main_Character = c("Naruto", "Ichigo", "Luffy", "Goku"),
villains = c("Orochimaru", "Aizen", "Blackbeard", "Freeza")
)
write.csv(anime, "anime.csv", row.names = FALSE)
## Read from a csv file

anime <- read.csv("anime.csv")
anime
xlsx / xls Files
## Load library
library("xlsx")
## Create a data frame

creators <- data.frame(
"Creator" = c("Kishimoto", "Araki", "Oda", "Toriyama")
)
## Write the data frame into anime.xlsx Sheet2

write.xlsx(creators, "anime.xlsx",
sheetName = "Sheet2", append = TRUE,
row.names = FALSE
)
## Read data from the anime.xlsx

anime <- read.xlsx("anime.xlsx", sheetIndex = 3)
anime
Binary Files
Writing data into a binary file

## Load csv file
anime_csv <- read.csv("anime.csv")
## Create a con object in wb mode

write_filename <- file("anime.dat", "wb")
## Write the column names to the con object

writeBin(colnames(anime_csv), write_filename)
## Write the column values to the con object

writeBin(
c(
anime_csv$Name,
anime_csv$Year,
anime_csv$Episodes,
anime_csv$Main_Character,
anime_csv$villains
),
write_filename
)
## Close the con so the file can be used by other programs

close(write_filename)
Reading data into a binary file
## Create a con object in rb mode

read_filename <- file("anime.dat", "rb")
## Get the column names (n = 5, because we have 5 columns)

column_names <- readBin(read_filename, character(), n = 5)
## Get the column values (n = 25, because we have 20 values without cnames)
column_values <- readBin(read_filename, character(), n = 20)
## Read from 1 to 4th byte

anime_names <- column_values[1:4]
## Read from 5th to 8th byte

anime_years <- column_values[5:8]
## Combine into a data frame

final_data <- as.data.frame(cbind(anime_names, anime_years))
colnames(final_data) <- column_names[1:2]
final_data
class(final_data)
Xml Files
Read from an xml file

library("XML")
library("methods")
## xmlParse() parses an XML document

anime_xml <- xmlParse(file = "anime.xml")
## xmlRoot() returns the root node of the XML document

root_node <- xmlRoot(anime_xml)
## xmlSize() returns the number of children of a node

root_size <- xmlSize(root_node)
## 4th child of root node

root_node[[4]]
## 1st child of 4th child of root node

root_node[[4]][[1]]
## 1st child of 1st child of 4th child of root node

root_node[[4]][[1]][[1]]
## xmlToDataFrame() converts an XML document to a data frame

anime_dataframe <- xmlToDataFrame(anime_xml)
JSON Files
Reading from a json file
## Load the package

library("rjson")
## Read JSON file

anime_json <- fromJSON(file = "anime.json")
## Convert JSON to dataframe

anime_dataframe <- as.data.frame(anime_json)
anime_dataframe
Databases
## Load the package
library("RMySQL")
## Create a db connection
mysql_con <- dbConnect(
MySQL(),
user = "yuhao",
password = "huoyuhao",
dbname = "laragigs",
host = "localhost",
local.infile = TRUE
)
## List the tables in the db

dbListTables(mysql_con)
## Insert data into table

dbSendQuery(mysql_con,
"insert into friends(id, name, age)
values(5, 'Ziya', 25)"
)
####### CREATING A TABLE FROM DATA.FRAME ########
# Write the data.frame to a MySQL table

dbWriteTable(
conn = mysql_con,
name = "anime",
value = anime,
row.names = FALSE,
overwrite = TRUE
)
# Close the connection to the database

dbDisconnect(mysql_con)
R Charts
Pie chart
The basic syntax for creating a pie-chart using the R is −
pie(x, labels, radius, main, col, clockwise)
Following is the description of the parameters used −

x is a vector containing the numeric values used in the pie chart.
labels is used to give description to the slices.
radius indicates the radius of the circle of the pie chart.(value between −1 and +1).
main indicates the title of the chart.
col indicates the color palette.
clockwise is a logical value indicating if the slices are drawn clockwise or anti clockwise.
values <- c(78, 21, 1)

labels <- c("Nitrogen", "Oxygen", "Other gases")
colors <- c("green", "red", "cyan")
piepercent <- round(100 * values / sum(values), 1)
pie(values, labels = piepercent, main = "Atmospheric composition", col = colors)

legend("bottomleft", labels , cex = 0.5, fill = colors)
Bar chart
The basic syntax to create a bar-chart in R is −
barplot(H,names.arg,main,xlab,ylab,col)
H is a vector or matrix containing numeric values used in bar chart.

xlab is the label for x axis.
ylab is the label for y axis.
main is the title of the bar chart.
names.arg is a vector of names appearing under each bar.
col is used to give colors to the bars in the graph.
values <- c(10, 16, 18)

labels <- c("Football", "Cricket", "Basketball")
colors <- c("green", "red", "cyan")
barplot(
values,
names.arg = labels,
xlab="Sports",
ylab="No. of students",
main = "Popularity of sports",
col = c("red", "green", "blue")
)
Box plot
The basic syntax to create a boxplot in R is −
boxplot(x, data, notch, varwidth, names, main)
x is a vector or a formula.
data is the data frame.
notch is a logical value. Set as TRUE to draw a notch.
varwidth is a logical value. Set as true to draw width of the box proportionate to the sample size.
names are the group labels which will be printed under each boxplot.
main is used to give a title to the graph
dataset <- data.frame(

x = c(1, 2, 3, 4, 5),
y = c(1, 4, 9, 16, 25)
)
boxplot(
dataset$y ~ dataset$x^2,
data = dataset,
main = "Boxplot of x^2",
ylab = "x^2", xlab = "x",
names = c("1 sqr", "2 sqr", "3 sqr", "4 sqr", "5 sqr")
)
Histogram
The basic syntax for creating a histogram using R is −
hist(v,main,xlab,xlim,ylim,breaks,col,border)
v is a vector containing numeric values used in histogram.

main indicates title of the chart.
col is used to set color of the bars.
border is used to set border color of each bar.
xlab is used to give description of x-axis.
xlim is used to specify the range of values on the x-axis.
ylim is used to specify the range of values on the y-axis.
breaks is used to mention the width of each bar.
# Generate some sample data

weights <- c(69, 69, 66, 68, 68, 67, 75, 48, 43, 43, 49, 51, 53, 58, 63)
# Create a histogram using the hist() function

hist(
weights,
ylim=c(0, 8),
xlab="Weight of students",
ylab="Number of students",
main="Weight of students in class",
breaks = 3
)
Line Graphs
The basic syntax to create a line chart in R is −
plot(v,main,xlab,ylab,col,type)
v is a vector containing the numeric values.

type takes the value "p" to draw only the points, "l" to draw only the lines and "o" to draw both
points and lines.
xlab is the label for x axis.
ylab is the label for y axis.
main is the Title of the chart.
col is used to give colors to both the points and lines.
# Create the data for the chart.

v <- c(7,12,28,3,41)
t <- c(18, 32, 18, 20, 31)
# Plot the bar chart.

plot(v, type = "o", col = "red", xlab = "Month", ylab = "Rain fall (mm)",
main = "Rain fall chart")
lines(t, type="o", col="blue")

Scatter plot
The basic syntax for creating scatterplot in R is −
plot(x, y, main, xlab, ylab, xlim, ylim, axes)
x is the data set whose values are the horizontal coordinates.

y is the data set whose values are the vertical coordinates.
main is the tile of the graph.
xlab is the label in the horizontal axis.
ylab is the label in the vertical axis.
xlim is the limits of the values of x used for plotting.
ylim is the limits of the values of y used for plotting.
axes indicates whether both axes should be drawn on the plot.
weights <- c(53, 56, 69, 69, 75)
heights <- c(175, 182, 181, 190, 180)
plot(
weights,
heights,
xlab="Weight",
ylab="Height",
main="Weight and Height of students",
ylim=c(170, 195),
xlim=c(50, 80)
)

Unit-3

Uploaded by

Copyright:

Available Formats

Unit-3

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Unit-3

Uploaded by

Copyright:

Available Formats

Unit-3

name <- c("Naruto Shipudden", "Dragon Ball", "One Piece")

## Join and form df

anime2 <- data.frame(

## Combine two dfs

Merging two data frames based on a common column

# Merge the two data frames based on the 'id' column

# View the merged data frame

df <- data.frame(n, time, x, y)

cat("=== Organized by n and time ===\\n")

write.csv(anime, "anime.csv", row.names = FALSE)

## Read from a csv file

xlsx / xls Files

## Create a data frame

## Write the data frame into anime.xlsx Sheet2

## Read data from the anime.xlsx

Writing data into a binary file

## Create a con object in wb mode

## Write the column names to the con object

## Write the column values to the con object

## Close the con so the file can be used by other programs

Reading data into a binary file

## Create a con object in rb mode

## Get the column names (n = 5, because we have 5 columns)

## Read from 1 to 4th byte

## Read from 5th to 8th byte

## Combine into a data frame

Read from an xml file

## xmlParse() parses an XML document

## xmlRoot() returns the root node of the XML document

## xmlSize() returns the number of children of a node

## 4th child of root node

## 1st child of 4th child of root node

## 1st child of 1st child of 4th child of root node

## xmlToDataFrame() converts an XML document to a data frame

Reading from a json file

## Load the package

## Read JSON file

## Convert JSON to dataframe

## List the tables in the db

## Insert data into table

####### CREATING A TABLE FROM DATA.FRAME ########

# Write the data.frame to a MySQL table

# Close the connection to the database

The basic syntax for creating a pie-chart using the R is −

pie(x, labels, radius, main, col, clockwise)

Following is the description of the parameters used −

values <- c(78, 21, 1)

pie(values, labels = piepercent, main = "Atmospheric composition", col = colors)

The basic syntax to create a bar-chart in R is −

Following is the description of the parameters used −

H is a vector or matrix containing numeric values used in bar chart.

values <- c(10, 16, 18)

The basic syntax to create a boxplot in R is −

boxplot(x, data, notch, varwidth, names, main)

Following is the description of the parameters used −

dataset <- data.frame(

The basic syntax for creating a histogram using R is −

Following is the description of the parameters used −

v is a vector containing numeric values used in histogram.