3 Encuentro
Jessica
2024-11-08
# INSTALACIÓN
install.packages("tidyverse")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.4'
## (as 'lib' is unspecified)library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ 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(readxl)# Instalamos y/o cargamos paquetes.
library("tidyverse")
library("readxl")Función read_csv()
ALUMNOS_2024 <- read_csv("https://docs.google.com/spreadsheets/d/e/2PACX-1vTwVt48G81FHfD_K9jcVmhjN3otTkR0-5Y8mC23oaEOTmhiG4So0kjw6I0b2tkU5ilpehvlhqBjId9i/pub?output=csv")## Rows: 24 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Marca temporal, Género, ¿Qué tan difícil le resulta el aprendizaje ...
## dbl (2): Edad, ¿Cuántas asignaturas rendiste y aprobaste este año?
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.# Copiar el link de la encuesta del AV.
names(ALUMNOS_2024)## [1] "Marca temporal"
## [2] "Género"
## [3] "Edad"
## [4] "¿Qué tan difícil le resulta el aprendizaje del software R y RStudio?"
## [5] "¿Cuántas asignaturas rendiste y aprobaste este año?"Función read_excel()
# crear objeto- falta base de datos- tenemos todo en el mismo proyecto- UPLOAD MANDARINAS_2024.
MANDARINAS <- read_excel("MANDARINAS_2024.xlsx")glimpse(MANDARINAS)## Rows: 419
## Columns: 8
## $ N <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 1…
## $ GRUPO <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
## $ VARIEDAD <chr> "Clementina", "Clementina", "Clementina", "Clementina", …
## $ N_DE_FRUTO <dbl> 19, 9, 21, 8, 4, 30, 22, 23, 17, 27, 29, 14, 16, 13, 25,…
## $ PESO <dbl> 101, 122, 127, 126, 37, 139, 140, 130, 138, 142, 121, 15…
## $ DIAM_ECUAT <dbl> 64.2, 64.2, 64.7, 64.9, 65.9, 66.4, 67.1, 67.5, 68.2, 68…
## $ NIVEL_DE_DAÑO <dbl> 1, 0, 3, 3, 2, 2, 3, 1, 2, 2, 2, 1, 1, 2, 1, 1, 0, 1, 0,…
## $ COLOR <dbl> 4, 5, 4, 1, 5, 4, 4, 3, 3, 4, 4, 1, 1, 3, 4, 1, 4, 1, 5,…Ordenamos la base de datos
cambiamos de nombre a las variables
IRIS <- iris %>%
rename(Longitud.Sepalo = Sepal.Length,
Ancho.Sepalo = Sepal.Width,
Longitud.Petalo = Petal.Length,
Ancho.Petalo = Petal.Width,
ESPECIE = Species)como esta constituida la base de datos
glimpse(IRIS)## Rows: 150
## Columns: 5
## $ Longitud.Sepalo <dbl> 5.1, 4.9, 4.7, 4.6, 5.0, 5.4, 4.6, 5.0, 4.4, 4.9, 5.4,…
## $ Ancho.Sepalo <dbl> 3.5, 3.0, 3.2, 3.1, 3.6, 3.9, 3.4, 3.4, 2.9, 3.1, 3.7,…
## $ Longitud.Petalo <dbl> 1.4, 1.4, 1.3, 1.5, 1.4, 1.7, 1.4, 1.5, 1.4, 1.5, 1.5,…
## $ Ancho.Petalo <dbl> 0.2, 0.2, 0.2, 0.2, 0.2, 0.4, 0.3, 0.2, 0.2, 0.1, 0.2,…
## $ ESPECIE <fct> setosa, setosa, setosa, setosa, setosa, setosa, setosa…Diagramas de dispersión
comenzamos con ggplot luego la data, la estetica y por ultimo la geometria
ggplot(IRIS, aes(Longitud.Petalo, Ancho.Petalo)) +
geom_point()
# shape es la forma que le doy a la gráfica, fill que es el relleno el
color
ggplot(IRIS, aes(Longitud.Petalo, Ancho.Petalo)) +
geom_point(shape = 25, fill = "yellow") # Para las formas 21 a 25, `fill =` controla el color de relleno de la forma.
También es posible modificar el tamaño de la forma seleccionada con
“size =”
ggplot(IRIS, aes(Longitud.Petalo, Ancho.Petalo)) +
geom_point(size = 4)
ggplot(IRIS, aes(Longitud.Petalo, Ancho.Petalo)) +
geom_point(color = "red")
Combinamos atributos
ggplot(IRIS, aes(Longitud.Petalo, Ancho.Petalo, shape = ESPECIE, color = ESPECIE)) +
geom_point(size= 3)
# Gráfico de líneas.
# PP de precipitaciones y en el añ0 1977-2022.
PP_77_22 <- read_excel("PP_77_22.xlsx")glimpse(PP_77_22)## Rows: 46
## Columns: 2
## $ ANIO <dbl> 1977, 1978, 1979, 1980, 1981, 1982, 1983, 1984, 1985, 1986, 1987,…
## $ PP <dbl> 666.4, 553.2, 675.7, 532.4, 528.7, 410.9, 569.2, 484.0, 610.2, 37…# La pp mas alta no llego a 600mm y la mas baja no supero los 100mm.
ggplot(PP_77_22, aes(ANIO, PP)) +
geom_line()
Renombramos variables
PP_77_22 <- PP_77_22 %>%
rename(AÑO = ANIO,
PRECIPITACION = PP)Visualizamos
PP_77_22## # A tibble: 46 × 2
## AÑO PRECIPITACION
## <dbl> <dbl>
## 1 1977 666.
## 2 1978 553.
## 3 1979 676.
## 4 1980 532.
## 5 1981 529.
## 6 1982 411.
## 7 1983 569.
## 8 1984 484
## 9 1985 610.
## 10 1986 379.
## # ℹ 36 more rowsCombinamos ambos argumentos…
# se puede cambiar ancho de linea y el color, la estetica en el eje x=año y=pp
ggplot(PP_77_22, aes(AÑO, PRECIPITACION)) +
geom_line(color = "red", linetype = 2, lwd = 1 )
Histogramas
# como se distribuyen las frecuencias de una sola variable que es la ppciones.
ggplot(PP_77_22, aes(PRECIPITACION)) +
geom_histogram()## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Cambiamos color de los contenedores.
ggplot(PP_77_22, aes(PRECIPITACION)) +
geom_histogram(color = "yellow")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Modificamos color y relleno de los contenedores.
ggplot(PP_77_22, aes(PRECIPITACION)) +
geom_histogram(color = "yellow", fill = "brown1")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
A continuación pueden ver los nombres de algunos colores con la
función colors()
colors()## [1] "white" "aliceblue" "antiquewhite"
## [4] "antiquewhite1" "antiquewhite2" "antiquewhite3"
## [7] "antiquewhite4" "aquamarine" "aquamarine1"
## [10] "aquamarine2" "aquamarine3" "aquamarine4"
## [13] "azure" "azure1" "azure2"
## [16] "azure3" "azure4" "beige"
## [19] "bisque" "bisque1" "bisque2"
## [22] "bisque3" "bisque4" "black"
## [25] "blanchedalmond" "blue" "blue1"
## [28] "blue2" "blue3" "blue4"
## [31] "blueviolet" "brown" "brown1"
## [34] "brown2" "brown3" "brown4"
## [37] "burlywood" "burlywood1" "burlywood2"
## [40] "burlywood3" "burlywood4" "cadetblue"
## [43] "cadetblue1" "cadetblue2" "cadetblue3"
## [46] "cadetblue4" "chartreuse" "chartreuse1"
## [49] "chartreuse2" "chartreuse3" "chartreuse4"
## [52] "chocolate" "chocolate1" "chocolate2"
## [55] "chocolate3" "chocolate4" "coral"
## [58] "coral1" "coral2" "coral3"
## [61] "coral4" "cornflowerblue" "cornsilk"
## [64] "cornsilk1" "cornsilk2" "cornsilk3"
## [67] "cornsilk4" "cyan" "cyan1"
## [70] "cyan2" "cyan3" "cyan4"
## [73] "darkblue" "darkcyan" "darkgoldenrod"
## [76] "darkgoldenrod1" "darkgoldenrod2" "darkgoldenrod3"
## [79] "darkgoldenrod4" "darkgray" "darkgreen"
## [82] "darkgrey" "darkkhaki" "darkmagenta"
## [85] "darkolivegreen" "darkolivegreen1" "darkolivegreen2"
## [88] "darkolivegreen3" "darkolivegreen4" "darkorange"
## [91] "darkorange1" "darkorange2" "darkorange3"
## [94] "darkorange4" "darkorchid" "darkorchid1"
## [97] "darkorchid2" "darkorchid3" "darkorchid4"
## [100] "darkred" "darksalmon" "darkseagreen"
## [103] "darkseagreen1" "darkseagreen2" "darkseagreen3"
## [106] "darkseagreen4" "darkslateblue" "darkslategray"
## [109] "darkslategray1" "darkslategray2" "darkslategray3"
## [112] "darkslategray4" "darkslategrey" "darkturquoise"
## [115] "darkviolet" "deeppink" "deeppink1"
## [118] "deeppink2" "deeppink3" "deeppink4"
## [121] "deepskyblue" "deepskyblue1" "deepskyblue2"
## [124] "deepskyblue3" "deepskyblue4" "dimgray"
## [127] "dimgrey" "dodgerblue" "dodgerblue1"
## [130] "dodgerblue2" "dodgerblue3" "dodgerblue4"
## [133] "firebrick" "firebrick1" "firebrick2"
## [136] "firebrick3" "firebrick4" "floralwhite"
## [139] "forestgreen" "gainsboro" "ghostwhite"
## [142] "gold" "gold1" "gold2"
## [145] "gold3" "gold4" "goldenrod"
## [148] "goldenrod1" "goldenrod2" "goldenrod3"
## [151] "goldenrod4" "gray" "gray0"
## [154] "gray1" "gray2" "gray3"
## [157] "gray4" "gray5" "gray6"
## [160] "gray7" "gray8" "gray9"
## [163] "gray10" "gray11" "gray12"
## [166] "gray13" "gray14" "gray15"
## [169] "gray16" "gray17" "gray18"
## [172] "gray19" "gray20" "gray21"
## [175] "gray22" "gray23" "gray24"
## [178] "gray25" "gray26" "gray27"
## [181] "gray28" "gray29" "gray30"
## [184] "gray31" "gray32" "gray33"
## [187] "gray34" "gray35" "gray36"
## [190] "gray37" "gray38" "gray39"
## [193] "gray40" "gray41" "gray42"
## [196] "gray43" "gray44" "gray45"
## [199] "gray46" "gray47" "gray48"
## [202] "gray49" "gray50" "gray51"
## [205] "gray52" "gray53" "gray54"
## [208] "gray55" "gray56" "gray57"
## [211] "gray58" "gray59" "gray60"
## [214] "gray61" "gray62" "gray63"
## [217] "gray64" "gray65" "gray66"
## [220] "gray67" "gray68" "gray69"
## [223] "gray70" "gray71" "gray72"
## [226] "gray73" "gray74" "gray75"
## [229] "gray76" "gray77" "gray78"
## [232] "gray79" "gray80" "gray81"
## [235] "gray82" "gray83" "gray84"
## [238] "gray85" "gray86" "gray87"
## [241] "gray88" "gray89" "gray90"
## [244] "gray91" "gray92" "gray93"
## [247] "gray94" "gray95" "gray96"
## [250] "gray97" "gray98" "gray99"
## [253] "gray100" "green" "green1"
## [256] "green2" "green3" "green4"
## [259] "greenyellow" "grey" "grey0"
## [262] "grey1" "grey2" "grey3"
## [265] "grey4" "grey5" "grey6"
## [268] "grey7" "grey8" "grey9"
## [271] "grey10" "grey11" "grey12"
## [274] "grey13" "grey14" "grey15"
## [277] "grey16" "grey17" "grey18"
## [280] "grey19" "grey20" "grey21"
## [283] "grey22" "grey23" "grey24"
## [286] "grey25" "grey26" "grey27"
## [289] "grey28" "grey29" "grey30"
## [292] "grey31" "grey32" "grey33"
## [295] "grey34" "grey35" "grey36"
## [298] "grey37" "grey38" "grey39"
## [301] "grey40" "grey41" "grey42"
## [304] "grey43" "grey44" "grey45"
## [307] "grey46" "grey47" "grey48"
## [310] "grey49" "grey50" "grey51"
## [313] "grey52" "grey53" "grey54"
## [316] "grey55" "grey56" "grey57"
## [319] "grey58" "grey59" "grey60"
## [322] "grey61" "grey62" "grey63"
## [325] "grey64" "grey65" "grey66"
## [328] "grey67" "grey68" "grey69"
## [331] "grey70" "grey71" "grey72"
## [334] "grey73" "grey74" "grey75"
## [337] "grey76" "grey77" "grey78"
## [340] "grey79" "grey80" "grey81"
## [343] "grey82" "grey83" "grey84"
## [346] "grey85" "grey86" "grey87"
## [349] "grey88" "grey89" "grey90"
## [352] "grey91" "grey92" "grey93"
## [355] "grey94" "grey95" "grey96"
## [358] "grey97" "grey98" "grey99"
## [361] "grey100" "honeydew" "honeydew1"
## [364] "honeydew2" "honeydew3" "honeydew4"
## [367] "hotpink" "hotpink1" "hotpink2"
## [370] "hotpink3" "hotpink4" "indianred"
## [373] "indianred1" "indianred2" "indianred3"
## [376] "indianred4" "ivory" "ivory1"
## [379] "ivory2" "ivory3" "ivory4"
## [382] "khaki" "khaki1" "khaki2"
## [385] "khaki3" "khaki4" "lavender"
## [388] "lavenderblush" "lavenderblush1" "lavenderblush2"
## [391] "lavenderblush3" "lavenderblush4" "lawngreen"
## [394] "lemonchiffon" "lemonchiffon1" "lemonchiffon2"
## [397] "lemonchiffon3" "lemonchiffon4" "lightblue"
## [400] "lightblue1" "lightblue2" "lightblue3"
## [403] "lightblue4" "lightcoral" "lightcyan"
## [406] "lightcyan1" "lightcyan2" "lightcyan3"
## [409] "lightcyan4" "lightgoldenrod" "lightgoldenrod1"
## [412] "lightgoldenrod2" "lightgoldenrod3" "lightgoldenrod4"
## [415] "lightgoldenrodyellow" "lightgray" "lightgreen"
## [418] "lightgrey" "lightpink" "lightpink1"
## [421] "lightpink2" "lightpink3" "lightpink4"
## [424] "lightsalmon" "lightsalmon1" "lightsalmon2"
## [427] "lightsalmon3" "lightsalmon4" "lightseagreen"
## [430] "lightskyblue" "lightskyblue1" "lightskyblue2"
## [433] "lightskyblue3" "lightskyblue4" "lightslateblue"
## [436] "lightslategray" "lightslategrey" "lightsteelblue"
## [439] "lightsteelblue1" "lightsteelblue2" "lightsteelblue3"
## [442] "lightsteelblue4" "lightyellow" "lightyellow1"
## [445] "lightyellow2" "lightyellow3" "lightyellow4"
## [448] "limegreen" "linen" "magenta"
## [451] "magenta1" "magenta2" "magenta3"
## [454] "magenta4" "maroon" "maroon1"
## [457] "maroon2" "maroon3" "maroon4"
## [460] "mediumaquamarine" "mediumblue" "mediumorchid"
## [463] "mediumorchid1" "mediumorchid2" "mediumorchid3"
## [466] "mediumorchid4" "mediumpurple" "mediumpurple1"
## [469] "mediumpurple2" "mediumpurple3" "mediumpurple4"
## [472] "mediumseagreen" "mediumslateblue" "mediumspringgreen"
## [475] "mediumturquoise" "mediumvioletred" "midnightblue"
## [478] "mintcream" "mistyrose" "mistyrose1"
## [481] "mistyrose2" "mistyrose3" "mistyrose4"
## [484] "moccasin" "navajowhite" "navajowhite1"
## [487] "navajowhite2" "navajowhite3" "navajowhite4"
## [490] "navy" "navyblue" "oldlace"
## [493] "olivedrab" "olivedrab1" "olivedrab2"
## [496] "olivedrab3" "olivedrab4" "orange"
## [499] "orange1" "orange2" "orange3"
## [502] "orange4" "orangered" "orangered1"
## [505] "orangered2" "orangered3" "orangered4"
## [508] "orchid" "orchid1" "orchid2"
## [511] "orchid3" "orchid4" "palegoldenrod"
## [514] "palegreen" "palegreen1" "palegreen2"
## [517] "palegreen3" "palegreen4" "paleturquoise"
## [520] "paleturquoise1" "paleturquoise2" "paleturquoise3"
## [523] "paleturquoise4" "palevioletred" "palevioletred1"
## [526] "palevioletred2" "palevioletred3" "palevioletred4"
## [529] "papayawhip" "peachpuff" "peachpuff1"
## [532] "peachpuff2" "peachpuff3" "peachpuff4"
## [535] "peru" "pink" "pink1"
## [538] "pink2" "pink3" "pink4"
## [541] "plum" "plum1" "plum2"
## [544] "plum3" "plum4" "powderblue"
## [547] "purple" "purple1" "purple2"
## [550] "purple3" "purple4" "red"
## [553] "red1" "red2" "red3"
## [556] "red4" "rosybrown" "rosybrown1"
## [559] "rosybrown2" "rosybrown3" "rosybrown4"
## [562] "royalblue" "royalblue1" "royalblue2"
## [565] "royalblue3" "royalblue4" "saddlebrown"
## [568] "salmon" "salmon1" "salmon2"
## [571] "salmon3" "salmon4" "sandybrown"
## [574] "seagreen" "seagreen1" "seagreen2"
## [577] "seagreen3" "seagreen4" "seashell"
## [580] "seashell1" "seashell2" "seashell3"
## [583] "seashell4" "sienna" "sienna1"
## [586] "sienna2" "sienna3" "sienna4"
## [589] "skyblue" "skyblue1" "skyblue2"
## [592] "skyblue3" "skyblue4" "slateblue"
## [595] "slateblue1" "slateblue2" "slateblue3"
## [598] "slateblue4" "slategray" "slategray1"
## [601] "slategray2" "slategray3" "slategray4"
## [604] "slategrey" "snow" "snow1"
## [607] "snow2" "snow3" "snow4"
## [610] "springgreen" "springgreen1" "springgreen2"
## [613] "springgreen3" "springgreen4" "steelblue"
## [616] "steelblue1" "steelblue2" "steelblue3"
## [619] "steelblue4" "tan" "tan1"
## [622] "tan2" "tan3" "tan4"
## [625] "thistle" "thistle1" "thistle2"
## [628] "thistle3" "thistle4" "tomato"
## [631] "tomato1" "tomato2" "tomato3"
## [634] "tomato4" "turquoise" "turquoise1"
## [637] "turquoise2" "turquoise3" "turquoise4"
## [640] "violet" "violetred" "violetred1"
## [643] "violetred2" "violetred3" "violetred4"
## [646] "wheat" "wheat1" "wheat2"
## [649] "wheat3" "wheat4" "whitesmoke"
## [652] "yellow" "yellow1" "yellow2"
## [655] "yellow3" "yellow4" "yellowgreen"Ajuste de los contenedores
- Ajustando el número de bins a través del argumento
bins. Usando este método especificamos el número de contenedores.
# baffer 350 mm ppciones nosotros valores frecuentes son de 300 a 400 mm
# años que voy a poder tener esas pasturas por las ppciones
# con esta base de datos de ppciones tenemos argumentos para tomar decisiones.
ggplot(PP_77_22, aes(PRECIPITACION)) +
geom_histogram(bins = 8, color = "gray", fill = "lightblue") +
theme_classic()
- Ajustando el ancho de los contenedores a través del argumento
binwidth. Con el segundo método, en lugar de especificar el número de bins, especificamos el ancho de los bins. Por ejemplo, establezcamos el ancho de cada contenedor en cien milímetros.
ggplot(PP_77_22, aes(PRECIPITACION)) +
geom_histogram(binwidth = 100, color = "red", fill = "blue") +
theme_classic()
Polígono de frecuencias
# el grafico es mas o menos simetrico
ggplot(PP_77_22, aes(PRECIPITACION)) +
geom_freqpoly(binwidth = 100)
Combinamos un histograma con un polígono de frecuencias
ggplot(PP_77_22, aes(PRECIPITACION)) +
geom_histogram(binwidth = 100, color = "orange") +
geom_freqpoly(binwidth = 100, color = "blue", linewidth = 1)
Gráfico de cajas
MANDARINAS <- read_excel("MANDARINAS_2024.xlsx")str(MANDARINAS)## tibble [419 × 8] (S3: tbl_df/tbl/data.frame)
## $ N : num [1:419] 1 2 3 4 5 6 7 8 9 10 ...
## $ GRUPO : num [1:419] 1 1 1 1 1 1 1 1 1 1 ...
## $ VARIEDAD : chr [1:419] "Clementina" "Clementina" "Clementina" "Clementina" ...
## $ N_DE_FRUTO : num [1:419] 19 9 21 8 4 30 22 23 17 27 ...
## $ PESO : num [1:419] 101 122 127 126 37 139 140 130 138 142 ...
## $ DIAM_ECUAT : num [1:419] 64.2 64.2 64.7 64.9 65.9 66.4 67.1 67.5 68.2 68.2 ...
## $ NIVEL_DE_DAÑO: num [1:419] 1 0 3 3 2 2 3 1 2 2 ...
## $ COLOR : num [1:419] 4 5 4 1 5 4 4 3 3 4 ...#los valores atipicos tambien pueden ser errores, por comas o mal escritos etc.instrumental.
ggplot(MANDARINAS, aes(DIAM_ECUAT, VARIEDAD)) +
geom_boxplot()
ggplot(MANDARINAS, aes(DIAM_ECUAT, VARIEDAD, color = VARIEDAD)) +
geom_boxplot()
¿Y si agregamos la media muestral?
# Clementina con diámetros más homogeneos por la caja mas chica, la md simetria criolla es asimetrica, y en clementina es una distribucion normal, los valores de la criolla son un poco mas altos.
ggplot(MANDARINAS, aes(DIAM_ECUAT, VARIEDAD, color = VARIEDAD)) +
geom_boxplot() +
stat_summary(fun = mean, color = "black") # función para agregar la media muestral y asignarle color## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_segment()`).
```