-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathapplication_data_mtcars.R
268 lines (235 loc) · 8.86 KB
/
application_data_mtcars.R
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
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
# Bibliotecas
library(tidyverse)
library(ggplot2)
# Database
## Motor Trend Car Road Tests
?mtcars
data(mtcars)
# Inspecionar estrutura Data Frame
str(mtcars)
head(mtcars,10)
tail(mtcars,10)
## Variáveis(v)
### V.categoricas nominais: vs e am
class(mtcars$vs)
unique(mtcars$vs)
mtcars$vs <- factor(mtcars$vs,
levels = c(0,1),
labels = c('v-shaped','straight'))
ggplot(mtcars$vs, aes(x = Categoria, y = Valores, fill = Categoria)) +
geom_bar(stat = "identity", color = "black") +
labs(
title = "Gráfico de Barras com ggplot2",
x = "Categorias",
y = "Valores"
) +
theme_minimal()
summary(mtcars$vs)
class(mtcars$am)
unique(mtcars$am)
mtcars$am <- factor(mtcars$am,
levels = c(0,1),
labels = c('automatic', 'manual'))
summary(mtcars$am)
# Tabelas Dados Categóricos
## Frequência Engine = vs
tabela_engine <- data.frame(mtcars$vs) %>%
rename(engine = mtcars.vs) %>%
count(engine) %>%
rename(count = n) %>%
add_row(engine = 'TOTAL', count = sum(.$count))
## Frequência Transmission = am
tabela_transmission <- data.frame(mtcars$am) %>%
rename(transmission = mtcars.am) %>%
count(transmission) %>%
rename(count = n) %>%
add_row(transmission = 'TOTAL', count = sum(.$count))
## Tabela com duas variaveis categoricas
tabela_vs_am <- data.frame(mtcars$vs,mtcars$am) %>%
rename(engine = mtcars.vs, transmission = mtcars.am) %>%
count(engine, transmission) %>%
rename(count = n)
## Tabela com duas variaveis categoricas e percentual
tbl_vs_am_percent <- tabela_vs_am %>%
mutate(percent = round(count/sum(count),5)*100) %>%
add_row(engine = 'TOTAL', count = sum(.$count), percent = floor(sum(.$percent)))
# V.numerica.discretas: cyl, hp, gear e carb.
class(mtcars$cyl)
unique(mtcars$cyl)
summary(mtcars$cyl)
## Frequência cylinders = cyl
tabela_cylinders <- data.frame(mtcars$cyl) %>%
rename(cylinders = mtcars.cyl) %>%
count(cylinders) %>%
rename(count = n) %>%
mutate(cylinders = as.character(cylinders)) %>%
add_row(cylinders = 'TOTAL', count = sum(.$count))
## Frequência horsepower = hp
class(mtcars$hp)
unique(mtcars$hp)
summary(mtcars$hp)
# Tabela distribuição de frequência hp
## 1º Rol dados
sort(mtcars$hp)
## 2º Amplitude total
ampli_total_hp <- max(mtcars$hp) - min(mtcars$hp)
## 3º nº de classes método Sturges
n.classes_hp <- nclass.Sturges(mtcars$hp)
### 4º Tamanho classes
t.classes_hp <- ceiling(ampli_total_hp/n.classes_hp)
#### 5º Limite Intervalo de classes
limit_inter_hp <- seq(min(mtcars$hp), (min(mtcars$hp) + (n.classes_hp * t.classes_hp)), by = t.classes_hp)
limit_inter_hp
## Histograma
### 1º Freq c/ intervalos
freq_hp <- cut(mtcars$hp, breaks = limit_inter_hp, right = FALSE)
table(freq_hp)
### 2º Tabela Histigrama
tbl_histograma_hp <- as.data.frame(table(freq_hp)) %>%
rename(horsepower = freq_hp) %>%
mutate(freq_rel_hp = round(Freq/sum(Freq),4)) %>%
add_row(horsepower = 'TOTAL', Freq = sum(.$Freq), freq_rel_hp = sum(.$freq_rel_hp))
## Frequência forward gears = gear
class(mtcars$gear)
unique(mtcars$gear)
summary(mtcars$gear)
tabela_gear <- data.frame(mtcars$gear) %>%
count(mtcars.gear) %>%
rename(n_forward_gears = mtcars.gear, count = n) %>%
mutate(n_forward_gears = as.character(n_forward_gears)) %>%
add_row(n_forward_gears = 'TOTAL', count = sum(.$count))
## Frequência carburetors = carb
class(mtcars$carb)
unique(mtcars$carb)
summary(mtcars$carb)
tabela_carb <- data.frame(mtcars$carb) %>%
count(mtcars.carb) %>%
rename(num_carb = mtcars.carb, count = n) %>%
mutate(num_carb = as.character(num_carb)) %>%
add_row(num_carb = 'TOTAL', count = sum(.$count))
summary(mtcars[, c('cyl', 'hp', 'gear', 'carb')])
###v.numerica.cont: mpg, disp, drat, wt e qsec.
class(mtcars$mpg)
summary(mtcars$mpg)
# Tabela distribuição de frequência mpg
## 1º Rol dados
sort(mtcars$mpg)
## 2º Amplitude total
ampli_total_mpg <- max(mtcars$mpg) - min(mtcars$mpg)
## 3º nº de classes método Sturges
n.classes_mpg <- nclass.Sturges(mtcars$mpg)
### 4º Tamanho classes
t.classes_mpg <- ceiling(ampli_total_mpg/n.classes_mpg)
#### 5º Limite Intervalo de classes
limit_inter_mpg <- seq(min(mtcars$mpg), (min(mtcars$mpg) + (n.classes_mpg * t.classes_mpg)), by = t.classes_mpg)
limit_inter_mpg
## Histograma
### 1º Freq c/ intervalos
freq_mpg <- cut(mtcars$mpg, breaks = limit_inter_mpg, right = FALSE)
table(freq_mpg)
### 2º Tabela Histigrama
tbl_histograma_mpg <- as.data.frame(table(freq_mpg)) %>%
rename(miles_gallon = freq_mpg, count_mpg = Freq) %>%
mutate(freq_rel_mpg = round(count_mpg/sum(count_mpg),5)*100) %>%
add_row(miles_gallon = 'TOTAL', count_mpg = sum(.$count_mpg), freq_rel_mpg = sum(.$freq_rel_mpg))
# Tabela distribuição de frequência disp
class(mtcars$disp)
unique(mtcars$disp)
summary(mtcars$disp)
## 1º Rol dados
sort(mtcars$disp)
## 2º Amplitude total
ampli_total_disp <- max(mtcars$disp) - min(mtcars$disp)
## 3º nº de classes método Sturges
n.classes_disp <- nclass.Sturges(mtcars$disp)
### 4º Tamanho classes
t.classes_disp <- ceiling(ampli_total_disp/n.classes_disp)
#### 5º Limite Intervalo de classes
limit_inter_disp <- seq(floor(min(mtcars$disp)), min(mtcars$disp) + (n.classes_disp * t.classes_disp), by = t.classes_disp)
limit_inter_disp
## Histograma
### 1º Freq c/ intervalos
freq_disp <- cut(mtcars$disp, breaks = limit_inter_disp, right = FALSE)
table(freq_disp)
### 2º Tabela Histigrama
tbl_histograma_disp <- as.data.frame(table(freq_disp)) %>%
rename(displacement = freq_disp, count_disp = Freq) %>%
mutate(freq_rel_disp = round(count_disp/sum(count_disp),4)*100) %>%
mutate(displacement = as.character(displacement)) %>%
add_row(displacement = 'TOTAL', count_disp = sum(.$count_disp), freq_rel_disp = sum(.$freq_rel_disp))
class(mtcars$drat)
unique(mtcars$drat)
summary(mtcars$drat)
## 1º Rol dados
sort(mtcars$drat)
## 2º Amplitude total
ampli_total_drat <- max(mtcars$drat) - min(mtcars$drat)
## 3º nº de classes método Sturges
n.classes_drat <- nclass.Sturges(mtcars$drat)
### 4º Tamanho classes
t.classes_drat <- round(ampli_total_drat / n.classes_drat, 1)
#### 5º Limite Intervalo de classes
limit_inter_drat <- seq(min(mtcars$drat), min(mtcars$drat) + (n.classes_drat * t.classes_drat), by = t.classes_drat)
limit_inter_drat
## Histograma
### 1º Freq c/ intervalos
freq_drat <- cut(mtcars$drat, breaks = limit_inter_drat, right = FALSE)
table(freq_drat)
### 2º Tabela Histograma
tbl_histograma_drat <- as.data.frame(table(freq_drat)) %>%
rename(rear_axle_ratio = freq_drat, count_drat = Freq) %>%
mutate(freq_rel_drat = round(count_drat/sum(count_drat),4)*100) %>%
mutate(rear_axle_ratio = as.character(rear_axle_ratio)) %>%
add_row(rear_axle_ratio = 'TOTAL', count_drat = sum(.$count_drat), freq_rel_drat = sum(.$freq_rel_drat))
# variavel wt
class(mtcars$wt)
summary(mtcars$wt)
## 1º Rol dados
sort(mtcars$wt)
## 2º Amplitude total
ampli_total_wt <- max(mtcars$wt) - min(mtcars$wt)
## 3º nº de classes método Sturges
n.classes_wt <- nclass.Sturges(mtcars$wt)
## 4º Tamanho classes
t.classes_wt <- round(ampli_total_wt/n.classes_wt,1)
## 5º Limites intervalo de classes
limit_inter_wt <- seq(from = min(mtcars$wt), to = min(mtcars$wt) + (n.classes_wt * t.classes_wt), by = t.classes_wt)
limit_inter_wt
### Histograma
#### 1º Freq c/ intervalos
freq_wt <- cut(mtcars$wt, breaks = limit_inter_wt, right = FALSE)
table(freq_wt)
#### 2º Tabela Histograma
tbl_histograma_wt <- as.data.frame(table(freq_wt)) %>%
rename(weight = freq_wt, count_wt = Freq) %>%
mutate(freq_rel_wt = round(count_wt/sum(count_wt),4)*100) %>%
mutate(weight = as.character(weight)) %>%
add_row(weight = 'TOTAL', count_wt = sum(.$count_wt), freq_rel_wt = sum(.$freq_rel_wt))
# variavel qsec
class(mtcars$qsec)
summary(mtcars$qsec)
## 1º Rol dados
sort(mtcars$qsec)
## 2º Amplitude total
ampli_total_qsec <- max(mtcars$qsec) - min(mtcars$qsec)
## 3º nº de classes método Sturges
n.classes_qsec <- nclass.Sturges(mtcars$qsec)
## 4º Tamanho classes
### Add vlr 0.1 para incluso do valor max na ultima classe, mantem uniformidade dos intervalos.
t.classes_qsec <- ((ampli_total_qsec/n.classes_qsec) + 0.1)
## 5º Limites intervalo de classes
limit_inter_qsec <- seq(from = min(mtcars$qsec),
to = min(mtcars$qsec) + (n.classes_qsec * t.classes_qsec),
by = t.classes_qsec)
limit_inter_qsec
### Histograma
#### 1º Freq c/ intervalos
freq_qsec <- cut(mtcars$qsec, breaks = limit_inter_qsec, right = FALSE)
#### 2º Tabela Histograma
tbl_histograma_qsec <- as.data.frame((table(freq_qsec))) %>%
rename(quarter_mile_time = freq_qsec, count_wt = Freq) %>%
mutate(freq_rel_qsec = round(count_wt/sum(count_wt),5)*100) %>%
mutate(quarter_mile_time = as.character(quarter_mile_time)) %>%
add_row(quarter_mile_time = "TOTAL", count_wt = sum(.$count_wt), freq_rel_qsec = sum(.$freq_rel_qsec))
str(mtcars[, c('mpg', 'disp', 'drat', 'wt', 'qsec')])
summary(mtcars[, c('mpg', 'disp', 'drat', 'wt', 'qsec')])