clustering and classification #5
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# learning2014 is available # print out the column names of the data colnames(learning2014) [1] "gender" "Age" "attitude" "deep" "stra" "surf" "Points" # change the name of the second column colnames(learning2014)[2] <- "age" # change the name of "Points" to "points" colnames(learning2014)[7] <- "points" # print out the new column names of the data colnames(learning2014) [1] "gender" "age" "attitude" "deep" "stra" "surf" "points" >
# access the MASS package
library(MASS)
# load the data
data("Boston")
# explore the dataset
str(Boston)
'data.frame': 506 obs. of 14 variables:
$ crim : num 0.00632 0.02731 0.02729 0.03237 0.06905 ...
$ zn : num 18 0 0 0 0 0 12.5 12.5 12.5 12.5 ...
$ indus : num 2.31 7.07 7.07 2.18 2.18 2.18 7.87 7.87 7.87 7.87 ...
$ chas : int 0 0 0 0 0 0 0 0 0 0 ...
$ nox : num 0.538 0.469 0.469 0.458 0.458 0.458 0.524 0.524 0.524 0.524 ...
$ rm : num 6.58 6.42 7.18 7 7.15 ...
$ age : num 65.2 78.9 61.1 45.8 54.2 58.7 66.6 96.1 100 85.9 ...
$ dis : num 4.09 4.97 4.97 6.06 6.06 ...
$ rad : int 1 2 2 3 3 3 5 5 5 5 ...
$ tax : num 296 242 242 222 222 222 311 311 311 311 ...
$ ptratio: num 15.3 17.8 17.8 18.7 18.7 18.7 15.2 15.2 15.2 15.2 ...
$ black : num 397 397 393 395 397 ...
$ lstat : num 4.98 9.14 4.03 2.94 5.33 ...
$ medv : num 24 21.6 34.7 33.4 36.2 28.7 22.9 27.1 16.5 18.9 ...
summary(Boston)
crim zn indus chas
Min. : 0.00632 Min. : 0.00 Min. : 0.46 Min. :0.00000
1st Qu.: 0.08204 1st Qu.: 0.00 1st Qu.: 5.19 1st Qu.:0.00000
Median : 0.25651 Median : 0.00 Median : 9.69 Median :0.00000
Mean : 3.61352 Mean : 11.36 Mean :11.14 Mean :0.06917
3rd Qu.: 3.67708 3rd Qu.: 12.50 3rd Qu.:18.10 3rd Qu.:0.00000
Max. :88.97620 Max. :100.00 Max. :27.74 Max. :1.00000
nox rm age dis
Min. :0.3850 Min. :3.561 Min. : 2.90 Min. : 1.130
1st Qu.:0.4490 1st Qu.:5.886 1st Qu.: 45.02 1st Qu.: 2.100
Median :0.5380 Median :6.208 Median : 77.50 Median : 3.207
Mean :0.5547 Mean :6.285 Mean : 68.57 Mean : 3.795
3rd Qu.:0.6240 3rd Qu.:6.623 3rd Qu.: 94.08 3rd Qu.: 5.188
Max. :0.8710 Max. :8.780 Max. :100.00 Max. :12.127
rad tax ptratio black
Min. : 1.000 Min. :187.0 Min. :12.60 Min. : 0.32
1st Qu.: 4.000 1st Qu.:279.0 1st Qu.:17.40 1st Qu.:375.38
Median : 5.000 Median :330.0 Median :19.05 Median :391.44
Mean : 9.549 Mean :408.2 Mean :18.46 Mean :356.67
3rd Qu.:24.000 3rd Qu.:666.0 3rd Qu.:20.20 3rd Qu.:396.23
Max. :24.000 Max. :711.0 Max. :22.00 Max. :396.90
lstat medv
Min. : 1.73 Min. : 5.00
1st Qu.: 6.95 1st Qu.:17.02
Median :11.36 Median :21.20
Mean :12.65 Mean :22.53
3rd Qu.:16.95 3rd Qu.:25.00
Max. :37.97 Max. :50.00
# plot matrix of the variables
pairs(Boston)
Created a new RMarkdown file and save it as an empty file named ‘chapter4.Rmd’. Then included the file as a child file in your ‘index.Rmd’ file. Performed the following analysis in the file I created.
Loaded the Boston data from the MASS package. Explored the structure and the dimensions of the data and describe the dataset briefly, assuming the reader has no previous knowledge of it. Details about the Boston dataset can be seen for example here.
Show a graphical overview of the data and show summaries of the variables in the data. Describe and interpret the outputs, commenting on the distributions of the variables and the relationships between them.
# MASS, corrplot, tidyr and Boston dataset are available
# calculate the correlation matrix and round it
cor_matrix<-cor(Boston) %>% round(digits = 2)
# print the correlation matrix
cor_matrix
crim zn indus chas nox rm age dis rad tax ptratio
crim 1.00 -0.20 0.41 -0.06 0.42 -0.22 0.35 -0.38 0.63 0.58 0.29
zn -0.20 1.00 -0.53 -0.04 -0.52 0.31 -0.57 0.66 -0.31 -0.31 -0.39
indus 0.41 -0.53 1.00 0.06 0.76 -0.39 0.64 -0.71 0.60 0.72 0.38
chas -0.06 -0.04 0.06 1.00 0.09 0.09 0.09 -0.10 -0.01 -0.04 -0.12
nox 0.42 -0.52 0.76 0.09 1.00 -0.30 0.73 -0.77 0.61 0.67 0.19
rm -0.22 0.31 -0.39 0.09 -0.30 1.00 -0.24 0.21 -0.21 -0.29 -0.36
age 0.35 -0.57 0.64 0.09 0.73 -0.24 1.00 -0.75 0.46 0.51 0.26
dis -0.38 0.66 -0.71 -0.10 -0.77 0.21 -0.75 1.00 -0.49 -0.53 -0.23
rad 0.63 -0.31 0.60 -0.01 0.61 -0.21 0.46 -0.49 1.00 0.91 0.46
tax 0.58 -0.31 0.72 -0.04 0.67 -0.29 0.51 -0.53 0.91 1.00 0.46
ptratio 0.29 -0.39 0.38 -0.12 0.19 -0.36 0.26 -0.23 0.46 0.46 1.00
black -0.39 0.18 -0.36 0.05 -0.38 0.13 -0.27 0.29 -0.44 -0.44 -0.18
lstat 0.46 -0.41 0.60 -0.05 0.59 -0.61 0.60 -0.50 0.49 0.54 0.37
medv -0.39 0.36 -0.48 0.18 -0.43 0.70 -0.38 0.25 -0.38 -0.47 -0.51
black lstat medv
crim -0.39 0.46 -0.39
zn 0.18 -0.41 0.36
indus -0.36 0.60 -0.48
chas 0.05 -0.05 0.18
nox -0.38 0.59 -0.43
rm 0.13 -0.61 0.70
age -0.27 0.60 -0.38
dis 0.29 -0.50 0.25
rad -0.44 0.49 -0.38
tax -0.44 0.54 -0.47
ptratio -0.18 0.37 -0.51
black 1.00 -0.37 0.33
lstat -0.37 1.00 -0.74
medv 0.33 -0.74 1.00
# visualize the correlation matrix
corrplot(cor_matrix, method="circle", type="upper", cl.pos="b", tl.pos="d", tl.cex = 0.6)
>
create_human.R
# tidyr package and human are available # access the stringr package library(stringr) # look at the structure of the GNI column in 'human' str(human$GNI) # remove the commas from GNI and print out a numeric version of it str_replace(human$GNI, pattern=",", replace ="") %>% as.numeric
# dplyr is available
# read the RATS data
RATS <- read.table("https://raw.githubusercontent.com/KimmoVehkalahti/MABS/master/Examples/data/rats.txt", header = TRUE, sep = '\t')
# Factor variables ID and Group
RATS$ID <- factor(RATS$ID)
RATS$Group <- factor(RATS$Group)
# Glimpse the data
glimpse(RATS)
Observations: 16
Variables: 13
$ ID <fct> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16
$ Group <fct> 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3
$ WD1 <int> 240, 225, 245, 260, 255, 260, 275, 245, 410, 405, 445, 555, 4...
$ WD8 <int> 250, 230, 250, 255, 260, 265, 275, 255, 415, 420, 445, 560, 4...
$ WD15 <int> 255, 230, 250, 255, 255, 270, 260, 260, 425, 430, 450, 565, 4...
$ WD22 <int> 260, 232, 255, 265, 270, 275, 270, 268, 428, 440, 452, 580, 4...
$ WD29 <int> 262, 240, 262, 265, 270, 275, 273, 270, 438, 448, 455, 590, 4...
$ WD36 <int> 258, 240, 265, 268, 273, 277, 274, 265, 443, 460, 455, 597, 4...
$ WD43 <int> 266, 243, 267, 270, 274, 278, 276, 265, 442, 458, 451, 595, 4...
$ WD44 <int> 266, 244, 267, 272, 273, 278, 271, 267, 446, 464, 450, 595, 5...
$ WD50 <int> 265, 238, 264, 274, 276, 284, 282, 273, 456, 475, 462, 612, 5...
$ WD57 <int> 272, 247, 268, 273, 278, 279, 281, 274, 468, 484, 466, 618, 5...
$ WD64 <int> 278, 245, 269, 275, 280, 281, 284, 278, 478, 496, 472, 628, 5...
># dplyr, tidyr and RATSL are available
# Check the dimensions of the data
dim(RATSL)
[1] 176 5
# Plot the RATSL data
ggplot(RATSL, aes(x = Time, y = Weight, group = ID)) +
geom_line(aes(linetype = Group)) +
scale_x_continuous(name = "Time (days)", breaks = seq(0, 60, 10)) +
scale_y_continuous(name = "Weight (grams)") +
theme(legend.position = "top")
jmleppal
added a commit
to jmleppal/IODS-project
that referenced
this pull request
Nov 20, 2022
jmleppal
added a commit
to jmleppal/IODS-project
that referenced
this pull request
Nov 30, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
MASS, corrplot, tidyr and Boston dataset are available
calculate the correlation matrix and round it
cor_matrix<-cor(Boston) %>% round(digits = 2)
print the correlation matrix
cor_matrix
crim zn indus chas nox rm age dis rad tax ptratio
crim 1.00 -0.20 0.41 -0.06 0.42 -0.22 0.35 -0.38 0.63 0.58 0.29
zn -0.20 1.00 -0.53 -0.04 -0.52 0.31 -0.57 0.66 -0.31 -0.31 -0.39
indus 0.41 -0.53 1.00 0.06 0.76 -0.39 0.64 -0.71 0.60 0.72 0.38
chas -0.06 -0.04 0.06 1.00 0.09 0.09 0.09 -0.10 -0.01 -0.04 -0.12
nox 0.42 -0.52 0.76 0.09 1.00 -0.30 0.73 -0.77 0.61 0.67 0.19
rm -0.22 0.31 -0.39 0.09 -0.30 1.00 -0.24 0.21 -0.21 -0.29 -0.36
age 0.35 -0.57 0.64 0.09 0.73 -0.24 1.00 -0.75 0.46 0.51 0.26
dis -0.38 0.66 -0.71 -0.10 -0.77 0.21 -0.75 1.00 -0.49 -0.53 -0.23
rad 0.63 -0.31 0.60 -0.01 0.61 -0.21 0.46 -0.49 1.00 0.91 0.46
tax 0.58 -0.31 0.72 -0.04 0.67 -0.29 0.51 -0.53 0.91 1.00 0.46
ptratio 0.29 -0.39 0.38 -0.12 0.19 -0.36 0.26 -0.23 0.46 0.46 1.00
black -0.39 0.18 -0.36 0.05 -0.38 0.13 -0.27 0.29 -0.44 -0.44 -0.18
lstat 0.46 -0.41 0.60 -0.05 0.59 -0.61 0.60 -0.50 0.49 0.54 0.37
medv -0.39 0.36 -0.48 0.18 -0.43 0.70 -0.38 0.25 -0.38 -0.47 -0.51
black lstat medv
crim -0.39 0.46 -0.39
zn 0.18 -0.41 0.36
indus -0.36 0.60 -0.48
chas 0.05 -0.05 0.18
nox -0.38 0.59 -0.43
rm 0.13 -0.61 0.70
age -0.27 0.60 -0.38
dis 0.29 -0.50 0.25
rad -0.44 0.49 -0.38
tax -0.44 0.54 -0.47
ptratio -0.18 0.37 -0.51
black 1.00 -0.37 0.33
lstat -0.37 1.00 -0.74
medv 0.33 -0.74 1.00
visualize the correlation matrix
corrplot(cor_matrix, method="circle", type="upper", cl.pos="b", tl.pos="d", tl.cex = 0.6)
