Data-Analysis-with-R/scripts.R at main · Abhi33-pharm/Data-Analysis-with-R · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
# install package
install.packages("tidyverse")
install.packages("skimr")
install.packages("openxlsx")
install.packages("readxl")
insta

# load package
library(tidyverse)
library(skimr)
library(openxlsx)
library(readxl)
library(dplyr)

# data
install.packages("gapminder")
library(gapminder)


# data exploration
# 1. dimension
dim(gapminder)
ncol(gapminder)
nrow(gapminder)

# 2. data structure
glimpse(gapminder)
str(gapminder)


# data inspection
# 1. first few rows
head(gapminder)
head(gapminder, n = 10)

# 2. last few rows
tail(gapminder)
tail(gapminder, n = 15)

# 3. sampling
sample_n(gapminder, 10)


# 4. fraction
sample_frac(gapminder, 0.30)


# missing value

is.na(gapminder)
is.na(airquality)

# How many?
sum(is.na(gapminder))
sum(is.na(airquality))

# Which columns?
colSums(is.na(gapminder))
colSums(is.na(airquality))

# Duplicated row
duplicated(gapminder)
duplicated(airquality)

# How many?
sum(duplicated(gapminder))
sum(duplicated(airquality))

# Summary
summary(gapminder)
skim(gapminder)

# Pick column
# 1. by name
select(gapminder, country)

select(gapminder, country, continent)


# by column number
select(gapminder, 1)
select(gapminder, 3)

select(gapminder, c(1,3,4))

select(gapminder, 1:3)


# by first letter
select(gapminder, starts_with("c"))

# by last letter
select(gapminder, ends_with("p"))


# Remove column
# 1. by name
select(gapminder, -country)

select(gapminder, -c(country, continent))


# by column number
select(gapminder, -1)
select(gapminder, -3)

select(gapminder, -c(1,3,4))

select(gapminder, -(1:3))


# filter
# equality
filter(gapminder, country == "Bangladesh")

# not equality
filter(gapminder, country != "Bangladesh")


# grater
filter(gapminder, lifeExp > 30)

# less
filter(gapminder, lifeExp < 25)

# grater or equal
filter(gapminder, lifeExp >= 30)

# less or equal
filter(gapminder, lifeExp <= 25)

# multiple condition

filter(gapminder, country %in% c("India", "Bangladesh", "Pakistan"))

# select & filter
select(gapminder, country, continent, lifeExp)
filter(gapminder, lifeExp > 30)

# How?
gapminder_new <- select(gapminder, country, continent, lifeExp)
filter(gapminder_new, lifeExp > 30)

# pipe operator (clt+shirt+M) |> (chaining method)

gapminder |>
  select(country, continent, lifeExp) |>
  filter(lifeExp > 30)

# mutate ~ creating new columns

gapminder |>
  mutate(gdp = gdpPercap * pop / 10^6 )


# rename
gapminder |>
  rename(population = pop)

# sort


gapminder