Actividad Integradora

Instalar paquetes y cargar librerías

# install.packages("forecast")
library(forecast)

## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo

# install.packages("tidyverse")
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ 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 errors

Importar la base de datos

df <- read.csv("C:\\Users\\raulc\\OneDrive\\Escritorio\\population.csv")

Entender la base de datos

summary(df)

##     state                year        population      
##  Length:6020        Min.   :1900   Min.   :   43000  
##  Class :character   1st Qu.:1930   1st Qu.:  901483  
##  Mode  :character   Median :1960   Median : 2359000  
##                     Mean   :1960   Mean   : 3726003  
##                     3rd Qu.:1990   3rd Qu.: 4541883  
##                     Max.   :2019   Max.   :39512223

str(df)

## 'data.frame':    6020 obs. of  3 variables:
##  $ state     : chr  "AK" "AK" "AK" "AK" ...
##  $ year      : int  1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 ...
##  $ population: int  135000 158000 189000 205000 215000 222000 224000 231000 224000 224000 ...

Serie de Tiempo 1: Texas

df_texas <- df %>% filter(state == "TX")
ts_texas <- ts(df_texas$population, start=1900, frequency=1) # Serie de Tiempo Anual
# ts_texas <- ts(df_texas$population, start=c(1900,4), frequency=4) # Serie de Tiempo Trimestral
# ts_texas <- ts(df_texas$population, start=c(1900,8), frequency=12) # Serie de Tiempo Mensual
arima_texas <- auto.arima(ts_texas)
arima_texas

## Series: ts_texas 
## ARIMA(0,2,2) 
## 
## Coefficients:
##           ma1      ma2
##       -0.5950  -0.1798
## s.e.   0.0913   0.0951
## 
## sigma^2 = 1.031e+10:  log likelihood = -1527.14
## AIC=3060.28   AICc=3060.5   BIC=3068.6

summary(arima_texas)

## Series: ts_texas 
## ARIMA(0,2,2) 
## 
## Coefficients:
##           ma1      ma2
##       -0.5950  -0.1798
## s.e.   0.0913   0.0951
## 
## sigma^2 = 1.031e+10:  log likelihood = -1527.14
## AIC=3060.28   AICc=3060.5   BIC=3068.6
## 
## Training set error measures:
##                    ME     RMSE      MAE       MPE      MAPE      MASE
## Training set 12147.62 99818.31 59257.39 0.1046163 0.5686743 0.2672197
##                     ACF1
## Training set -0.02136734

pronostico_texas <- forecast(arima_texas, level=c(95), h=51)
pronostico_texas

##      Point Forecast    Lo 95    Hi 95
## 2020       29398472 29199487 29597457
## 2021       29806827 29463665 30149990
## 2022       30215183 29742956 30687410
## 2023       30623538 30024100 31222977
## 2024       31031894 30303359 31760429
## 2025       31440249 30579246 32301253
## 2026       31848605 30851090 32846119
## 2027       32256960 31118581 33395339
## 2028       32665316 31381587 33949044
## 2029       33073671 31640070 34507272
## 2030       33482027 31894047 35070007
## 2031       33890382 32143561 35637204
## 2032       34298738 32388674 36208801
## 2033       34707093 32629456 36784730
## 2034       35115449 32865983 37364914
## 2035       35523804 33098330 37949278
## 2036       35932160 33326573 38537746
## 2037       36340515 33550788 39130242
## 2038       36748871 33771046 39726695
## 2039       37157226 33987418 40327034
## 2040       37565581 34199972 40931191
## 2041       37973937 34408774 41539100
## 2042       38382292 34613887 42150698
## 2043       38790648 34815371 42765925
## 2044       39199003 35013284 43384723
## 2045       39607359 35207682 44007036
## 2046       40015714 35398618 44632810
## 2047       40424070 35586145 45261995
## 2048       40832425 35770311 45894540
## 2049       41240781 35951163 46530399
## 2050       41649136 36128748 47169524
## 2051       42057492 36303110 47811874
## 2052       42465847 36474290 48457405
## 2053       42874203 36642330 49106076
## 2054       43282558 36807269 49757848
## 2055       43690914 36969145 50412683
## 2056       44099269 37127994 51070544
## 2057       44507625 37283853 51731396
## 2058       44915980 37436755 52395205
## 2059       45324336 37586734 53061937
## 2060       45732691 37733822 53731560
## 2061       46141047 37878050 54404044
## 2062       46549402 38019447 55079357
## 2063       46957758 38158044 55757471
## 2064       47366113 38293868 56438358
## 2065       47774469 38426948 57121989
## 2066       48182824 38557310 57808338
## 2067       48591180 38684979 58497380
## 2068       48999535 38809982 59189088
## 2069       49407891 38932343 59883438
## 2070       49816246 39052086 60580406

plot(pronostico_texas, main = "Población en Texas")