# Cargamos el conjunto de datos
# En Python: 
# import seaborn as sns
# df1 = sns.load_dataset('iris')
df1 <- iris
df1

A data.frame: 150 × 5

Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
<dbl>	<dbl>	<dbl>	<dbl>	<fct>
5.1	3.5	1.4	0.2	setosa
4.9	3.0	1.4	0.2	setosa
4.7	3.2	1.3	0.2	setosa
4.6	3.1	1.5	0.2	setosa
5.0	3.6	1.4	0.2	setosa
5.4	3.9	1.7	0.4	setosa
4.6	3.4	1.4	0.3	setosa
5.0	3.4	1.5	0.2	setosa
4.4	2.9	1.4	0.2	setosa
4.9	3.1	1.5	0.1	setosa
5.4	3.7	1.5	0.2	setosa
4.8	3.4	1.6	0.2	setosa
4.8	3.0	1.4	0.1	setosa
4.3	3.0	1.1	0.1	setosa
5.8	4.0	1.2	0.2	setosa
5.7	4.4	1.5	0.4	setosa
5.4	3.9	1.3	0.4	setosa
5.1	3.5	1.4	0.3	setosa
5.7	3.8	1.7	0.3	setosa
5.1	3.8	1.5	0.3	setosa
5.4	3.4	1.7	0.2	setosa
5.1	3.7	1.5	0.4	setosa
4.6	3.6	1.0	0.2	setosa
5.1	3.3	1.7	0.5	setosa
4.8	3.4	1.9	0.2	setosa
5.0	3.0	1.6	0.2	setosa
5.0	3.4	1.6	0.4	setosa
5.2	3.5	1.5	0.2	setosa
5.2	3.4	1.4	0.2	setosa
4.7	3.2	1.6	0.2	setosa
⋮	⋮	⋮	⋮	⋮
6.9	3.2	5.7	2.3	virginica
5.6	2.8	4.9	2.0	virginica
7.7	2.8	6.7	2.0	virginica
6.3	2.7	4.9	1.8	virginica
6.7	3.3	5.7	2.1	virginica
7.2	3.2	6.0	1.8	virginica
6.2	2.8	4.8	1.8	virginica
6.1	3.0	4.9	1.8	virginica
6.4	2.8	5.6	2.1	virginica
7.2	3.0	5.8	1.6	virginica
7.4	2.8	6.1	1.9	virginica
7.9	3.8	6.4	2.0	virginica
6.4	2.8	5.6	2.2	virginica
6.3	2.8	5.1	1.5	virginica
6.1	2.6	5.6	1.4	virginica
7.7	3.0	6.1	2.3	virginica
6.3	3.4	5.6	2.4	virginica
6.4	3.1	5.5	1.8	virginica
6.0	3.0	4.8	1.8	virginica
6.9	3.1	5.4	2.1	virginica
6.7	3.1	5.6	2.4	virginica
6.9	3.1	5.1	2.3	virginica
5.8	2.7	5.1	1.9	virginica
6.8	3.2	5.9	2.3	virginica
6.7	3.3	5.7	2.5	virginica
6.7	3.0	5.2	2.3	virginica
6.3	2.5	5.0	1.9	virginica
6.5	3.0	5.2	2.0	virginica
6.2	3.4	5.4	2.3	virginica
5.9	3.0	5.1	1.8	virginica

# En Python: df1.head(10)
# En R:
head(df1, 10)

A data.frame: 10 × 5

	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
	<dbl>	<dbl>	<dbl>	<dbl>	<fct>
1	5.1	3.5	1.4	0.2	setosa
2	4.9	3.0	1.4	0.2	setosa
3	4.7	3.2	1.3	0.2	setosa
4	4.6	3.1	1.5	0.2	setosa
5	5.0	3.6	1.4	0.2	setosa
6	5.4	3.9	1.7	0.4	setosa
7	4.6	3.4	1.4	0.3	setosa
8	5.0	3.4	1.5	0.2	setosa
9	4.4	2.9	1.4	0.2	setosa
10	4.9	3.1	1.5	0.1	setosa

tail(df1, 5)

A data.frame: 5 × 5

	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
	<dbl>	<dbl>	<dbl>	<dbl>	<fct>
146	6.7	3.0	5.2	2.3	virginica
147	6.3	2.5	5.0	1.9	virginica
148	6.5	3.0	5.2	2.0	virginica
149	6.2	3.4	5.4	2.3	virginica
150	5.9	3.0	5.1	1.8	virginica

# En Python: df1.info()
# Factor--> categorica (variable que tiene categorias)
str(df1)

'data.frame':	150 obs. of  5 variables:
 $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
 $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
 $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
 $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
 $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

# En Python: df1.describe()
summary(df1)

  Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
 Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100  
 1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300  
 Median :5.800   Median :3.000   Median :4.350   Median :1.300  
 Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199  
 3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800  
 Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500  
       Species  
 setosa    :50  
 versicolor:50  
 virginica :50  
                
                
                

# En Python: df1.columns
names(df1)

1. 'Sepal.Length'
2. 'Sepal.Width'
3. 'Petal.Length'
4. 'Petal.Width'
5. 'Species'

# En Python df1['nombre_columna']
# En Python df1.nombre_columna
df1$Petal.Width

1. 0.2
2. 0.2
3. 0.2
4. 0.2
5. 0.2
6. 0.4
7. 0.3
8. 0.2
9. 0.2
10. 0.1
11. 0.2
12. 0.2
13. 0.1
14. 0.1
15. 0.2
16. 0.4
17. 0.4
18. 0.3
19. 0.3
20. 0.3
21. 0.2
22. 0.4
23. 0.2
24. 0.5
25. 0.2
26. 0.2
27. 0.4
28. 0.2
29. 0.2
30. 0.2
31. 0.2
32. 0.4
33. 0.1
34. 0.2
35. 0.2
36. 0.2
37. 0.2
38. 0.1
39. 0.2
40. 0.2
41. 0.3
42. 0.3
43. 0.2
44. 0.6
45. 0.4
46. 0.3
47. 0.2
48. 0.2
49. 0.2
50. 0.2
51. 1.4
52. 1.5
53. 1.5
54. 1.3
55. 1.5
56. 1.3
57. 1.6
58. 1
59. 1.3
60. 1.4
61. 1
62. 1.5
63. 1
64. 1.4
65. 1.3
66. 1.4
67. 1.5
68. 1
69. 1.5
70. 1.1
71. 1.8
72. 1.3
73. 1.5
74. 1.2
75. 1.3
76. 1.4
77. 1.4
78. 1.7
79. 1.5
80. 1
81. 1.1
82. 1
83. 1.2
84. 1.6
85. 1.5
86. 1.6
87. 1.5
88. 1.3
89. 1.3
90. 1.3
91. 1.2
92. 1.4
93. 1.2
94. 1
95. 1.3
96. 1.2
97. 1.3
98. 1.3
99. 1.1
100. 1.3
101. 2.5
102. 1.9
103. 2.1
104. 1.8
105. 2.2
106. 2.1
107. 1.7
108. 1.8
109. 1.8
110. 2.5
111. 2
112. 1.9
113. 2.1
114. 2
115. 2.4
116. 2.3
117. 1.8
118. 2.2
119. 2.3
120. 1.5
121. 2.3
122. 2
123. 2
124. 1.8
125. 2.1
126. 1.8
127. 1.8
128. 1.8
129. 2.1
130. 1.6
131. 1.9
132. 2
133. 2.2
134. 1.5
135. 1.4
136. 2.3
137. 2.4
138. 1.8
139. 1.8
140. 2.1
141. 2.4
142. 2.3
143. 1.9
144. 2.3
145. 2.5
146. 2.3
147. 1.9
148. 2
149. 2.3
150. 1.8

# En Python df1[ ['nombre_columna1', 'nombre_columna2'] ]
# En Python df1[ ['Sepal.Length', 'Sepal.Width'] ]
# En R: df1[filas, columnas]
# quiero todas las filas
head(df1[, c('Sepal.Length', 'Sepal.Width')])

A data.frame: 6 × 2

	Sepal.Length	Sepal.Width
	<dbl>	<dbl>
1	5.1	3.5
2	4.9	3.0
3	4.7	3.2
4	4.6	3.1
5	5.0	3.6
6	5.4	3.9

1:10
c(1:10)
seq(1,10)

1. 1
2. 2
3. 3
4. 4
5. 5
6. 6
7. 7
8. 8
9. 9
10. 10

1. 1
2. 2
3. 3
4. 4
5. 5
6. 6
7. 7
8. 8
9. 9
10. 10

1. 1
2. 2
3. 3
4. 4
5. 5
6. 6
7. 7
8. 8
9. 9
10. 10

df1[1:6, c('Sepal.Length', 'Sepal.Width')]

A data.frame: 6 × 2

	Sepal.Length	Sepal.Width
	<dbl>	<dbl>
1	5.1	3.5
2	4.9	3.0
3	4.7	3.2
4	4.6	3.1
5	5.0	3.6
6	5.4	3.9

• 0 es un número natural

• 0 no es natural

• Python: 0 es natural, las numeraciones comienzan con el 0

• R: 0 no es natural, las numeraciones comienzan con el 1

# En R: las numeraciones comienzan en 1
df1[c(1,90, 149), c('Sepal.Length', 'Sepal.Width')]

A data.frame: 3 × 2

	Sepal.Length	Sepal.Width
	<dbl>	<dbl>
1	5.1	3.5
90	5.5	2.5
149	6.2	3.4

Filtros

# df1[filas, columnas]
# df1[mascara booleana, ]
df1[df1$Petal.Width > 2, ]

A data.frame: 23 × 5

	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
	<dbl>	<dbl>	<dbl>	<dbl>	<fct>
101	6.3	3.3	6.0	2.5	virginica
103	7.1	3.0	5.9	2.1	virginica
105	6.5	3.0	5.8	2.2	virginica
106	7.6	3.0	6.6	2.1	virginica
110	7.2	3.6	6.1	2.5	virginica
113	6.8	3.0	5.5	2.1	virginica
115	5.8	2.8	5.1	2.4	virginica
116	6.4	3.2	5.3	2.3	virginica
118	7.7	3.8	6.7	2.2	virginica
119	7.7	2.6	6.9	2.3	virginica
121	6.9	3.2	5.7	2.3	virginica
125	6.7	3.3	5.7	2.1	virginica
129	6.4	2.8	5.6	2.1	virginica
133	6.4	2.8	5.6	2.2	virginica
136	7.7	3.0	6.1	2.3	virginica
137	6.3	3.4	5.6	2.4	virginica
140	6.9	3.1	5.4	2.1	virginica
141	6.7	3.1	5.6	2.4	virginica
142	6.9	3.1	5.1	2.3	virginica
144	6.8	3.2	5.9	2.3	virginica
145	6.7	3.3	5.7	2.5	virginica
146	6.7	3.0	5.2	2.3	virginica
149	6.2	3.4	5.4	2.3	virginica

mascara <- df1$Petal.Width > 2 & df1$Species == 'virginica'
df1[mascara, ]

A data.frame: 23 × 5

	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
	<dbl>	<dbl>	<dbl>	<dbl>	<fct>
101	6.3	3.3	6.0	2.5	virginica
103	7.1	3.0	5.9	2.1	virginica
105	6.5	3.0	5.8	2.2	virginica
106	7.6	3.0	6.6	2.1	virginica
110	7.2	3.6	6.1	2.5	virginica
113	6.8	3.0	5.5	2.1	virginica
115	5.8	2.8	5.1	2.4	virginica
116	6.4	3.2	5.3	2.3	virginica
118	7.7	3.8	6.7	2.2	virginica
119	7.7	2.6	6.9	2.3	virginica
121	6.9	3.2	5.7	2.3	virginica
125	6.7	3.3	5.7	2.1	virginica
129	6.4	2.8	5.6	2.1	virginica
133	6.4	2.8	5.6	2.2	virginica
136	7.7	3.0	6.1	2.3	virginica
137	6.3	3.4	5.6	2.4	virginica
140	6.9	3.1	5.4	2.1	virginica
141	6.7	3.1	5.6	2.4	virginica
142	6.9	3.1	5.1	2.3	virginica
144	6.8	3.2	5.9	2.3	virginica
145	6.7	3.3	5.7	2.5	virginica
146	6.7	3.0	5.2	2.3	virginica
149	6.2	3.4	5.4	2.3	virginica

head(df1)

A data.frame: 6 × 5

	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
	<dbl>	<dbl>	<dbl>	<dbl>	<fct>
1	5.1	3.5	1.4	0.2	setosa
2	4.9	3.0	1.4	0.2	setosa
3	4.7	3.2	1.3	0.2	setosa
4	4.6	3.1	1.5	0.2	setosa
5	5.0	3.6	1.4	0.2	setosa
6	5.4	3.9	1.7	0.4	setosa

# En Python: df1.iloc[0,0]

# df1[fila, columna]
# acceder a un solo elemento
# fila 1, columna 1
df1[1,1]

5.1

# En Python: df1.iloc[0,0] = 3.0

# igualito a iloc
df1[1,1] <- 3.0
df1[1,1]

3

head(df1)

A data.frame: 6 × 5

	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
	<dbl>	<dbl>	<dbl>	<dbl>	<fct>
1	3.0	3.5	1.4	0.2	setosa
2	4.9	3.0	1.4	0.2	setosa
3	4.7	3.2	1.3	0.2	setosa
4	4.6	3.1	1.5	0.2	setosa
5	5.0	3.6	1.4	0.2	setosa
6	5.4	3.9	1.7	0.4	setosa

Creación de un dataframe

# Creamos dos vectores:
# Un vector de nombres
nombre <- c("Ana", "Luna", "Fernando")

# Un vector de edades
edad <- c(32, 17, 40)

# Procederemos a crear el dataframe con la funcion data.frame
df_new  <- data.frame(
  "Nombres" = nombre,
  "Edades"  = edad 
)

df_new

A data.frame: 3 × 2

Nombres	Edades
<chr>	<dbl>
Ana	32
Luna	17
Fernando	40

# agregamos una columna nueva
df_new$Col.Nueva <- c(1,2,3)
df_new

A data.frame: 3 × 3

Nombres	Edades	Col.Nueva
<chr>	<dbl>	<dbl>
Ana	32	1
Luna	17	2
Fernando	40	3

nombre <- c("Ana2")
edad <- c(32)
colnueva <- c(24)

# Procederemos a crear el dataframe con la funcion data.frame
df_new2  <- data.frame(
  "Nombres" = nombre,
  "Edades"  = edad,
  "Col.Nueva" = colnueva
)

df_New  <- rbind(df_new, df_new2)
df_New

A data.frame: 4 × 3

Nombres	Edades	Col.Nueva
<chr>	<dbl>	<dbl>
Ana	32	1
Luna	17	2
Fernando	40	3
Ana2	32	24

Funciones en R

Recordemos en Python

def <nombre funcion>(<nombre parametros>):
    # instrucciones
    return <lo que regresa la funcion>

---

En R

<nombre funcion> <- function(<nombres parametros>){
    # instrucciones
    return(<lo que regresa la funcion>)
}

$$ f(x)=x^{2} $$

f <- function(x){
    return (x^2)
}

f(4)

16

Graficación

# plot()
plot(x=df1$Petal.Length, y=df1$Petal.Width)

plot(x=df1$Petal.Length, y=df1$Petal.Width, col='red', pch = 19,
    cex=1.5)

plot(x=df1$Petal.Length, y=df1$Petal.Width, col=df1$Species, 
     # puntos gruesos
     pch = 19,
     # titulo
     main = "Diagrama de dispersión")

plot(x=df1$Petal.Length, y=df1$Petal.Width, col=df1$Species, 
     # puntos gruesos
     pch = 19,
     # titulo
     main = "Diagrama de dispersión")

# x: posicion
legend(x="topleft", 
       # Texto que queremos que se vea
       legend = c("Set", "Versi", "Virgi"), 
       fill=c("black", "red", "green"))

# Podemos agregar una cuadricula al grafico
grid()

Gráfica de funciones matemáticas

$$ f(x)=x^{2} $$

rango <- seq(-5,5,0.002)

plot(x=rango, y=f(rango),
     main = "Gráfico de una función", pch=19)

# Podemos agregar una cuadricula al grafico
grid()

f3 <- function(x){
    return(x^3)
}

plot(x=rango, y=f3(rango),
     main = "función cúbica", pch=19, col='red')

# Podemos agregar una cuadricula al grafico
grid()