Assignment
2023-11-13
R Markdown
Qn 1. Removing empty rows and columns using the janitor package
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(ggplot2)
library(dplyr)
library(dslabs)
library(janitor)##
## Attaching package: 'janitor'
##
## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.testdata("airquality")
as.data.frame(airquality)## Ozone Solar.R Wind Temp Month Day
## 1 41 190 7.4 67 5 1
## 2 36 118 8.0 72 5 2
## 3 12 149 12.6 74 5 3
## 4 18 313 11.5 62 5 4
## 5 NA NA 14.3 56 5 5
## 6 28 NA 14.9 66 5 6
## 7 23 299 8.6 65 5 7
## 8 19 99 13.8 59 5 8
## 9 8 19 20.1 61 5 9
## 10 NA 194 8.6 69 5 10
## 11 7 NA 6.9 74 5 11
## 12 16 256 9.7 69 5 12
## 13 11 290 9.2 66 5 13
## 14 14 274 10.9 68 5 14
## 15 18 65 13.2 58 5 15
## 16 14 334 11.5 64 5 16
## 17 34 307 12.0 66 5 17
## 18 6 78 18.4 57 5 18
## 19 30 322 11.5 68 5 19
## 20 11 44 9.7 62 5 20
## 21 1 8 9.7 59 5 21
## 22 11 320 16.6 73 5 22
## 23 4 25 9.7 61 5 23
## 24 32 92 12.0 61 5 24
## 25 NA 66 16.6 57 5 25
## 26 NA 266 14.9 58 5 26
## 27 NA NA 8.0 57 5 27
## 28 23 13 12.0 67 5 28
## 29 45 252 14.9 81 5 29
## 30 115 223 5.7 79 5 30
## 31 37 279 7.4 76 5 31
## 32 NA 286 8.6 78 6 1
## 33 NA 287 9.7 74 6 2
## 34 NA 242 16.1 67 6 3
## 35 NA 186 9.2 84 6 4
## 36 NA 220 8.6 85 6 5
## 37 NA 264 14.3 79 6 6
## 38 29 127 9.7 82 6 7
## 39 NA 273 6.9 87 6 8
## 40 71 291 13.8 90 6 9
## 41 39 323 11.5 87 6 10
## 42 NA 259 10.9 93 6 11
## 43 NA 250 9.2 92 6 12
## 44 23 148 8.0 82 6 13
## 45 NA 332 13.8 80 6 14
## 46 NA 322 11.5 79 6 15
## 47 21 191 14.9 77 6 16
## 48 37 284 20.7 72 6 17
## 49 20 37 9.2 65 6 18
## 50 12 120 11.5 73 6 19
## 51 13 137 10.3 76 6 20
## 52 NA 150 6.3 77 6 21
## 53 NA 59 1.7 76 6 22
## 54 NA 91 4.6 76 6 23
## 55 NA 250 6.3 76 6 24
## 56 NA 135 8.0 75 6 25
## 57 NA 127 8.0 78 6 26
## 58 NA 47 10.3 73 6 27
## 59 NA 98 11.5 80 6 28
## 60 NA 31 14.9 77 6 29
## 61 NA 138 8.0 83 6 30
## 62 135 269 4.1 84 7 1
## 63 49 248 9.2 85 7 2
## 64 32 236 9.2 81 7 3
## 65 NA 101 10.9 84 7 4
## 66 64 175 4.6 83 7 5
## 67 40 314 10.9 83 7 6
## 68 77 276 5.1 88 7 7
## 69 97 267 6.3 92 7 8
## 70 97 272 5.7 92 7 9
## 71 85 175 7.4 89 7 10
## 72 NA 139 8.6 82 7 11
## 73 10 264 14.3 73 7 12
## 74 27 175 14.9 81 7 13
## 75 NA 291 14.9 91 7 14
## 76 7 48 14.3 80 7 15
## 77 48 260 6.9 81 7 16
## 78 35 274 10.3 82 7 17
## 79 61 285 6.3 84 7 18
## 80 79 187 5.1 87 7 19
## 81 63 220 11.5 85 7 20
## 82 16 7 6.9 74 7 21
## 83 NA 258 9.7 81 7 22
## 84 NA 295 11.5 82 7 23
## 85 80 294 8.6 86 7 24
## 86 108 223 8.0 85 7 25
## 87 20 81 8.6 82 7 26
## 88 52 82 12.0 86 7 27
## 89 82 213 7.4 88 7 28
## 90 50 275 7.4 86 7 29
## 91 64 253 7.4 83 7 30
## 92 59 254 9.2 81 7 31
## 93 39 83 6.9 81 8 1
## 94 9 24 13.8 81 8 2
## 95 16 77 7.4 82 8 3
## 96 78 NA 6.9 86 8 4
## 97 35 NA 7.4 85 8 5
## 98 66 NA 4.6 87 8 6
## 99 122 255 4.0 89 8 7
## 100 89 229 10.3 90 8 8
## 101 110 207 8.0 90 8 9
## 102 NA 222 8.6 92 8 10
## 103 NA 137 11.5 86 8 11
## 104 44 192 11.5 86 8 12
## 105 28 273 11.5 82 8 13
## 106 65 157 9.7 80 8 14
## 107 NA 64 11.5 79 8 15
## 108 22 71 10.3 77 8 16
## 109 59 51 6.3 79 8 17
## 110 23 115 7.4 76 8 18
## 111 31 244 10.9 78 8 19
## 112 44 190 10.3 78 8 20
## 113 21 259 15.5 77 8 21
## 114 9 36 14.3 72 8 22
## 115 NA 255 12.6 75 8 23
## 116 45 212 9.7 79 8 24
## 117 168 238 3.4 81 8 25
## 118 73 215 8.0 86 8 26
## 119 NA 153 5.7 88 8 27
## 120 76 203 9.7 97 8 28
## 121 118 225 2.3 94 8 29
## 122 84 237 6.3 96 8 30
## 123 85 188 6.3 94 8 31
## 124 96 167 6.9 91 9 1
## 125 78 197 5.1 92 9 2
## 126 73 183 2.8 93 9 3
## 127 91 189 4.6 93 9 4
## 128 47 95 7.4 87 9 5
## 129 32 92 15.5 84 9 6
## 130 20 252 10.9 80 9 7
## 131 23 220 10.3 78 9 8
## 132 21 230 10.9 75 9 9
## 133 24 259 9.7 73 9 10
## 134 44 236 14.9 81 9 11
## 135 21 259 15.5 76 9 12
## 136 28 238 6.3 77 9 13
## 137 9 24 10.9 71 9 14
## 138 13 112 11.5 71 9 15
## 139 46 237 6.9 78 9 16
## 140 18 224 13.8 67 9 17
## 141 13 27 10.3 76 9 18
## 142 24 238 10.3 68 9 19
## 143 16 201 8.0 82 9 20
## 144 13 238 12.6 64 9 21
## 145 23 14 9.2 71 9 22
## 146 36 139 10.3 81 9 23
## 147 7 49 10.3 69 9 24
## 148 14 20 16.6 63 9 25
## 149 30 193 6.9 70 9 26
## 150 NA 145 13.2 77 9 27
## 151 14 191 14.3 75 9 28
## 152 18 131 8.0 76 9 29
## 153 20 223 11.5 68 9 30class(airquality)## [1] "data.frame"sum(is.na(airquality))## [1] 44##Remove empty rows and columns
airquality_df <-as.data.frame(airquality)
cleaned_data <- remove_empty(dat = airquality_df, which = c("rows", "cols"))- Explanations. The remove_empty() in the janitor package can be used to remove either rows or columns with missing values or both rows and columns with missing values. The basic syntax of how the remove_empty() does this is let us say Clean data <- remove_empty(dat = dataset, which = c(“rows”, “cols”)), the dat specifys the dataset to clean, the which, specifys whether you want to clean rows or coumns or both using the concatenate function c(). The dataset to be cleaned must be a dataframe.
Qn 2.
##Renaming colmns
Clean_names() in the janitor package
library(janitor)
library(VIM)## Warning: package 'VIM' was built under R version 4.3.2## Loading required package: colorspace## Loading required package: grid## VIM is ready to use.## Suggestions and bug-reports can be submitted at: https://github.com/statistikat/VIM/issues##
## Attaching package: 'VIM'## The following object is masked from 'package:datasets':
##
## sleepdata("SBS5242")
##clean and standardise column names
names_clean <- SBS5242 %>%
clean_names()- Explanations
The make_names_fully_unique() will ensure the the column names in a dataframe are actually unique. The duplicate column names will be made unique by adding a numeric suffix to these names. Here is an illustration of how the function works
unique_data <-make_names_fully_unique(data.frame). This will display the unique_data you desire.
Qn 3.
##Summarizing data
How to use the get_dupes() to identify duplicate rows in a dataframe. -Get the sample data with duplicate rows -Identify and retrieve the duplicate rows using the functions:
duplicates <-get-dupes(data.frame) print(duplicates) The duplicates object will contain the rows that are duplicates in the original data frame. To check for duplicates in specific columns, you can use the columns argument to specify the type of columns you want to check for duplicates.
- R code
##load the data set
data("food")
##convert into a data frame
food_df <-data.frame(food)
##generate a summary of the unique values for the real coffee column
unique_col <-food_df %>%
tabyl(Real.coffee)
##view the object
print(unique_col)## Real.coffee n percent
## 27 1 0.0625
## 30 1 0.0625
## 55 1 0.0625
## 70 1 0.0625
## 72 1 0.0625
## 73 1 0.0625
## 82 1 0.0625
## 88 1 0.0625
## 90 1 0.0625
## 92 1 0.0625
## 94 1 0.0625
## 96 2 0.1250
## 97 2 0.1250
## 98 1 0.0625Qn 4. ##Data visualization
- side by side violin plot
data("ToothGrowth")
head(ToothGrowth)## 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
## 5 6.4 VC 0.5
## 6 10.0 VC 0.5##Create a side by side violin plot
ggplot(ToothGrowth, aes(x = supp, y = len, fill = supp)) +
geom_violin(scale = "width", trim = FALSE) +
geom_boxplot(width = 0.1, fill = "white", color = "black") +
labs(title = "Side by Side Violin Plot", x = "Supplement", y = "Tooth_Length") +
scale_fill_manual(values = c("orange", "blue")) +
theme_minimal()
b) ##Scatter plot for the tooth Growth data set
## Scatter plot with dose on the x-axis and len on the y-axis
ggplot(ToothGrowth, aes(x = dose, y = len, color = supp, shape = supp)) +
geom_point(size = 3) +
labs(
title = "Scatter Plot of Dose vs Tooth Length",
x = "Dose",
y = "Tooth_Length",
color = "Supplement",
shape = "Supplement"
) +
scale_color_manual(values = c("orange", "blue")) +
scale_shape_manual(values = c(16, 17)) +
theme_minimal()
c) Chickweight line graph
data("ChickWeight")
head(ChickWeight)## weight Time Chick Diet
## 1 42 0 1 1
## 2 51 2 1 1
## 3 59 4 1 1
## 4 64 6 1 1
## 5 76 8 1 1
## 6 93 10 1 1# Create a line chart
ggplot(ChickWeight, aes(x = Time, y = weight, group = Diet, color = as.factor(Diet))) +
geom_line(size = 1) +
labs(
title = "Average_Weight Gain Over Time by Diet",
x = "Time",
y = "Weight",
color = "Diet"
) +
scale_color_manual(values = c("green", "blue", "red", "orange")) + # Custom line colors
theme_minimal()## 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.
##Create a faceted plot
# Create a faceted plot
ggplot(ChickWeight, aes(x = Time, y = weight, group = Diet, color = as.factor(Diet))) +
geom_line(size = 1) +
labs(
title = "Weight Gain Over Time by Diet",
x = "Time",
y = "Weight",
color = "Diet"
) +
scale_color_manual(values = c("blue", "green", "brown", "orange")) + # Custom line colors
theme_minimal() +
facet_wrap(~Diet, scales = "free_y", ncol = 2) # Facet by Diet with free y-axis scales