#Complementaria 4 2023-20
# Importar datos ----------------------------------------------------------
#Opcion 1
Datos<-read.csv(file="AAPL.csv",sep=",")
View(Datos)
getwd()
## [1] "C:/Users/mayer/OneDrive - Universidad de los Andes/2 SEMESTRE MAESTRIA/Modelos/Complementaria 4"
#Opcion 2
library(readr)
AAPL <- read_csv("AAPL.csv")
## Rows: 21 Columns: 7
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## dbl (6): Open, High, Low, Close, Adj Close, Volume
## date (1): Date
##
## 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.
View(AAPL)
class(Datos)
## [1] "data.frame"
# Dataframes --------------------------------------------------------------
#Convertir datos en dataframes
datos<-as.data.frame(AAPL)
#Acceder a datos
datos[3,4]
## [1] 149.95
datos[1,"Low"]
## [1] 148.57
#Cantidad filas y columnas
ncol(datos)
## [1] 7
nrow(datos)
## [1] 21
#Informacion relevante
summary(datos)
## Date Open High Low
## Min. :2017-07-17 Min. :148.8 Min. :150.1 Min. :147.3
## 1st Qu.:2017-07-24 1st Qu.:150.0 1st Qu.:150.9 1st Qu.:148.9
## Median :2017-07-31 Median :153.4 Median :153.9 Median :151.8
## Mean :2017-07-30 Mean :153.9 Mean :155.0 Mean :152.6
## 3rd Qu.:2017-08-07 3rd Qu.:157.1 3rd Qu.:158.9 3rd Qu.:156.1
## Max. :2017-08-14 Max. :159.9 Max. :161.8 Max. :159.1
## Close Adj Close Volume
## Min. :148.7 Min. :148.1 Min. :15781000
## 1st Qu.:150.3 1st Qu.:149.7 1st Qu.:19845900
## Median :152.7 Median :152.1 Median :22028200
## Mean :153.8 Mean :153.3 Mean :26571690
## 3rd Qu.:157.1 3rd Qu.:156.5 3rd Qu.:27097300
## Max. :161.1 Max. :160.4 Max. :69936800
#Acceder a columnas
datos[["Close"]]
## [1] 149.56 150.08 151.02 150.34 150.27 152.09 152.74 153.46 150.56 149.50
## [11] 148.73 150.05 157.14 155.57 156.39 158.81 160.08 161.06 155.32 157.48
## [21] 159.85
datos[[3]]
## [1] 150.90 150.13 151.42 151.74 150.44 152.44 153.84 153.93 153.99 150.23
## [11] 150.33 150.22 159.75 157.21 157.40 158.92 161.83 161.27 160.00 158.57
## [21] 160.21
datos[,"Close"]
## [1] 149.56 150.08 151.02 150.34 150.27 152.09 152.74 153.46 150.56 149.50
## [11] 148.73 150.05 157.14 155.57 156.39 158.81 160.08 161.06 155.32 157.48
## [21] 159.85
datos$Low
## [1] 148.57 148.67 149.95 150.19 148.88 149.90 151.80 153.06 147.30 149.19
## [11] 148.13 148.41 156.16 155.02 155.69 156.67 158.27 159.11 154.63 156.07
## [21] 158.75
#Acceder a filas
datos[4,]
## Date Open High Low Close Adj Close Volume
## 4 2017-07-20 151.5 151.74 150.19 150.34 149.7519 17243700
#Pedir mas datos
datos[c(3,4),]
## Date Open High Low Close Adj Close Volume
## 3 2017-07-19 150.48 151.42 149.95 151.02 150.4293 20923000
## 4 2017-07-20 151.50 151.74 150.19 150.34 149.7519 17243700
datos[c(1,2),c("Low","Close")]
## Low Close
## 1 148.57 149.56
## 2 148.67 150.08
#Sacar datos con condicones
datos[datos$Close>155 & datos$Open<157,"Volume"]
## [1] 20559900 26257100
#Crear nuevas columnas
datos$logAdj<-log10(datos$`Adj Close`)
#Eliminar columnas
datos<-datos[,-ncol(datos)]
#Eliminar filas
datos<-datos[-1,]
# Graficas ----------------------------------------------------------------
#Histograma del precio ajustado de la accion
hist(x=datos$`Adj Close`,
main = "Histograma del Precio Cierre Ajustado",
xlab="Precio de cierre ajustado",
ylab = "Frecuencia",
col='red')
#Grafico de dispersion
ejeX<-log10(x = datos$`Adj Close`)[-nrow(datos)]
ejeY<-log10(x = datos$`Adj Close`)[-1]
plot(x=ejeX,y = ejeY,
main="Grafica de dispersion del precio ajustado de cierre",
xlab="Precio ajustado en t-1",
ylab="Precio ajustado en t",
col="deepskyblue")
# Fechas ------------------------------------------------------------------
as.Date(datos$Date,"%Y-%m-%d")
## [1] "2017-07-18" "2017-07-19" "2017-07-20" "2017-07-21" "2017-07-24"
## [6] "2017-07-25" "2017-07-26" "2017-07-27" "2017-07-28" "2017-07-31"
## [11] "2017-08-01" "2017-08-02" "2017-08-03" "2017-08-04" "2017-08-07"
## [16] "2017-08-08" "2017-08-09" "2017-08-10" "2017-08-11" "2017-08-14"
datos$Date<-as.Date(datos$Date,"%Y-%m-%d")
datos$Date2<-as.POSIXct(datos$Date,"%Y-%m-%d")
# Ajuste de datos ---------------------------------------------------------
#Paquetes
library(rriskDistributions)
library(fitdistrplus)
## Loading required package: MASS
## Loading required package: survival
library(MASS)
#Variable continua
#Exponenciales, Normal, t, gamma,...
#Crear datos de tiempos entre llegadas de estudiantes
tEstudiantes<-rexp(n = 300,rate = 3)
#Intui comporatmiento
hist(tEstudiantes)
#Ajuste de los datos
ajuste<-fitdist(tEstudiantes,"exp")
#Parametros de el ajuste
ajuste$estimate
## rate
## 3.090185
plot(ajuste)
#Prueba de bondad de ajuste
rta<-gofstat(ajuste)
rta$chisqpvalue #Pvalue
## [1] 0.5321226
#Se ajustan los datos
#Distribuciones discretas
#Cantidad estudiantes en una hora
nEstudiantes<-rpois(n=300,lambda = 25)
ajuste2<-fitdist(nEstudiantes,"pois")
#Parametro
summary(ajuste2)
## Fitting of the distribution ' pois ' by maximum likelihood
## Parameters :
## estimate Std. Error
## lambda 25.23 0.29
## Loglikelihood: -909.6629 AIC: 1821.326 BIC: 1825.03
#Prueba de bondad de ajuste
rta2<-gofstat(ajuste2)
rta2$chisqpvalue #Pvalue
## [1] 0.6905788
#Datos si se ajustan