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 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4     
## ── 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

library(skimr)
library(fpp3)

## Registered S3 method overwritten by 'tsibble':
##   method               from 
##   as_tibble.grouped_df dplyr
## ── Attaching packages ──────────────────────────────────────────── fpp3 1.0.1 ──
## ✔ tsibble     1.1.6     ✔ feasts      0.4.1
## ✔ tsibbledata 0.4.1     ✔ fable       0.4.1
## ── Conflicts ───────────────────────────────────────────────── fpp3_conflicts ──
## ✖ lubridate::date()    masks base::date()
## ✖ dplyr::filter()      masks stats::filter()
## ✖ tsibble::intersect() masks base::intersect()
## ✖ tsibble::interval()  masks lubridate::interval()
## ✖ dplyr::lag()         masks stats::lag()
## ✖ tsibble::setdiff()   masks base::setdiff()
## ✖ tsibble::union()     masks base::union()

# Cargue de datos
dique = read_table("Dique.txt", col_names = c("año", "mes", "dia", "altura"))

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   año = col_double(),
##   mes = col_character(),
##   dia = col_character(),
##   altura = col_double()
## )

## Warning: 9224 parsing failures.
## row col  expected    actual        file
##   1  -- 4 columns 5 columns 'Dique.txt'
##   2  -- 4 columns 5 columns 'Dique.txt'
##   3  -- 4 columns 5 columns 'Dique.txt'
##   4  -- 4 columns 5 columns 'Dique.txt'
##   5  -- 4 columns 5 columns 'Dique.txt'
## ... ... ......... ......... ...........
## See problems(...) for more details.

guajaro = read_table("Guajaro.txt", col_names = c("año", "mes", "dia", "altura"))

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   año = col_double(),
##   mes = col_character(),
##   dia = col_character(),
##   altura = col_double()
## )

## Warning: 6597 parsing failures.
## row col  expected    actual          file
##   1  -- 4 columns 5 columns 'Guajaro.txt'
##   2  -- 4 columns 5 columns 'Guajaro.txt'
##   3  -- 4 columns 5 columns 'Guajaro.txt'
##   4  -- 4 columns 5 columns 'Guajaro.txt'
##   5  -- 4 columns 5 columns 'Guajaro.txt'
## ... ... ......... ......... .............
## See problems(...) for more details.

inkora = read_table("Inkora.txt", col_names = c("año", "mes", "dia", "altura"))

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   año = col_double(),
##   mes = col_character(),
##   dia = col_character(),
##   altura = col_double()
## )

Bomba = read_table("Casa_Bomba.txt", col_names = c("año", "mes", "dia", "altura"))

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   año = col_double(),
##   mes = col_character(),
##   dia = col_character(),
##   altura = col_double()
## )

## Warning: 6224 parsing failures.
## row col  expected    actual             file
##   1  -- 4 columns 5 columns 'Casa_Bomba.txt'
##   2  -- 4 columns 5 columns 'Casa_Bomba.txt'
##   3  -- 4 columns 5 columns 'Casa_Bomba.txt'
##   4  -- 4 columns 5 columns 'Casa_Bomba.txt'
##   5  -- 4 columns 5 columns 'Casa_Bomba.txt'
## ... ... ......... ......... ................
## See problems(...) for more details.

Conversión de data.frame a time serie

### Dique 

ts_dique = dique %>% 
  mutate(fecha = as.Date(paste(año, mes, dia, sep = "-"), format = "%Y-%m-%d")) %>% 
  select(fecha, altura) %>% 
  as_tsibble(index = fecha)

### Guajaro

ts_guajaro = guajaro %>% 
  mutate(fecha = as.Date(paste(año, mes, dia, sep = "-"), format = "%Y-%m-%d")) %>% 
  select(fecha, altura) %>% 
  as_tsibble(index = fecha)

### Inkora

ts_inkora = inkora %>% 
  mutate(fecha = as.Date(paste(año, mes, dia, sep = "-"), format = "%Y-%m-%d")) %>% 
  select(fecha, altura) %>% 
  as_tsibble(index = fecha)
### Inkora

ts_bomba = Bomba %>% 
  mutate(fecha = as.Date(paste(año, mes, dia, sep = "-"), format = "%Y-%m-%d")) %>% 
  select(fecha, altura) %>% 
  as_tsibble(index = fecha)

Incompletitud en la secuencia temporal

Los datos presentan incosistencias temporales en la fecha y su contituidad. Es decir, la serie temporal no es continua ya que salta periodos de tiempo. Para solucionar esto se emplea un código que asigna la fecha que sigue la secuecuencia siguiendo el orden cronológico correcto y asina a la columna de altura un NA.

## Secuencia adecuada 

## Dique 

ts_dique = ts_dique %>% 
  fill_gaps()

## Guajaro

ts_guajaro = ts_guajaro %>% 
  fill_gaps()

## CRA

ts_bomba = ts_bomba %>% 
  fill_gaps()


## Inkora

ts_inkora = ts_inkora %>% 
  fill_gaps()

#Bomba

Estadísticas generales

skim(ts_bomba$altura)

Data summary
Name	ts_bomba$altura
Number of rows	8128
Number of columns	1
_______________________
Column type frequency:
numeric	1
________________________
Group variables	None

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
data	1903	0.77	375.6	64.88	218	328	371	425	547	▂▇▇▆▁

##Grafica

ggplot(ts_bomba, aes(x = fecha, y = altura)) +
  geom_line(color = "black", size = 0.6) +
  geom_hline(yintercept = 375.6039, color = "red", linetype = "solid", linewidth = 0.8) +
  geom_hline(yintercept = 375.6039 + 64.88179, color = "blue", linetype = "dashed", linewidth = 0.8) +
  labs(
    title = "Altura del Agua - Estación Casa Bomba",
    x = "Fecha",
    y = "Altura (cm)"
  ) +
  theme_bw(base_size = 12)

## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

#Dique ## Estadísticas generales

skim(ts_dique$altura)

Data summary
Name	ts_dique$altura
Number of rows	13516
Number of columns	1
_______________________
Column type frequency:
numeric	1
________________________
Group variables	None

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
data	4292	0.68	398.5	132.59	0	318	414	500	704	▁▂▇▇▁

Grafica

ggplot(ts_dique, aes(x = fecha, y = altura)) +
  geom_line(color = "black", size = 0.6) +
  geom_hline(yintercept = 398.4978, color = "red", linetype = "solid", linewidth = 0.8) +
  geom_hline(yintercept = 398.4978 + 132.5882, color = "blue", linetype = "dashed", linewidth = 0.8) +
  labs(
    title = "Altura del Agua - Estación Dique",
    x = "Fecha",
    y = "Altura (cm)"
  ) +
  theme_bw(base_size = 12)

Guajaro

Estadísticas generales

skim(ts_guajaro$altura)

Data summary
Name	ts_guajaro$altura
Number of rows	7794
Number of columns	1
_______________________
Column type frequency:
numeric	1
________________________
Group variables	None

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
data	1197	0.85	397.64	69.52	200	353	401	448	587	▁▅▇▆▁

Series de tiempo

Grafica

ggplot(ts_guajaro, aes(x = fecha, y = altura)) +
  geom_line(color = "black", size = 0.6) +
  geom_hline(yintercept = 397.6359, color = "red", linetype = "solid", linewidth = 0.8) +
  geom_hline(yintercept = 397.6359 + 69.51968, color = "blue", linetype = "dashed", linewidth = 0.8) +
  labs(
    title = "Altura del Agua - Estación Guájaro",
    x = "Fecha",
    y = "Altura (cm)"
  ) +
  theme_bw(base_size = 12)

Inkora

Estadísticas generales

skim(ts_inkora$altura)

Data summary
Name	ts_inkora$altura
Number of rows	11689
Number of columns	1
_______________________
Column type frequency:
numeric	1
________________________
Group variables	None

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
data	1180	0.9	528	158.31	73	420	533	648	896	▁▃▇▇▂

head(ts_inkora)

## # A tsibble: 6 x 2 [1D]
##   fecha      altura
##   <date>      <dbl>
## 1 1980-01-01    652
## 2 1980-01-02    643
## 3 1980-01-03    634
## 4 1980-01-04    625
## 5 1980-01-05    614
## 6 1980-01-06    607

ggplot(ts_inkora, aes(x = fecha, y = altura)) +
  geom_line(color = "black", size = 0.6) +
  geom_hline(yintercept = 527.9994, color = "red", linetype = "solid", linewidth = 0.8) +
  geom_hline(yintercept = 527.9994 + 158.3073, color = "blue", linetype = "dashed", linewidth = 0.8) +
  labs(
    title = "Altura del Agua - Estación Inkora",
    x = "Fecha",
    y = "Altura (cm)"
  ) +
  theme_bw(base_size = 12)

Dique, Guajaro, Inkora

Serie de tiempo

# Combinar todas las series temporales
ts_estaciones_completas <- ts_dique %>%
  rename(dique = altura) %>%
  full_join(ts_guajaro %>% rename(guajaro = altura), by = "fecha") %>%
  full_join(ts_inkora %>% rename(inkora = altura), by = "fecha") %>%
  full_join(ts_bomba %>% rename(bomba = altura), by = "fecha") %>%
  pivot_longer(cols = c(dique, guajaro, inkora, bomba),
               names_to = "estacion", values_to = "altura")

# Graficar en formato científico
ggplot(ts_estaciones_completas, aes(x = fecha, y = altura, color = estacion)) +
  geom_line(size = 0.7, na.rm = TRUE) +
  scale_color_manual(
    values = c("dique" = "#1f77b4", "guajaro" = "#ff7f0e", "inkora" = "#2ca02c", "bomba" = "#d62728"),
    labels = c("Dique", "Guájaro", "Inkora", "Casa Bomba")
  ) +
  labs(
    title = "Altura del agua en estaciones del Embalse del Guájaro",
    x = "Fecha",
    y = "Altura (cm)",
    color = "Estación"
  ) +
  theme_bw(base_size = 12) +
  theme(
    plot.title = element_text(hjust = 0.5, face = "bold"),
    legend.title = element_text(face = "bold"),
    legend.position = "bottom"
  )

# Combinar todas las series temporales en un solo tibble largo
ts_estaciones_completas <- ts_dique %>%
  rename(dique = altura) %>%
  full_join(ts_guajaro %>% rename(guajaro = altura), by = "fecha") %>%
  full_join(ts_inkora %>% rename(inkora = altura), by = "fecha") %>%
  full_join(ts_bomba %>% rename(bomba = altura), by = "fecha") %>%
  pivot_longer(
    cols = c(dique, guajaro, inkora, bomba),
    names_to = "estacion",
    values_to = "altura"
  )

# Renombrar estaciones para mostrar nombres más legibles
ts_estaciones_completas$estacion <- recode(
  ts_estaciones_completas$estacion,
  dique = "Dique",
  guajaro = "Guájaro",
  inkora = "Inkora",
  bomba = "Casa Bomba"
)

# Crear gráfico con facetas
ggplot(ts_estaciones_completas, aes(x = fecha, y = altura)) +
  geom_line(color = "black", size = 0.6, na.rm = TRUE) +
  facet_wrap(~ estacion, scales = "free_y", ncol = 2) +
  labs(
    title = "Altura del agua por estación - Embalse del Guájaro",
    x = "Fecha",
    y = "Altura (cm)"
  ) +
  theme_bw(base_size = 12) +
  theme(
    strip.text = element_text(face = "bold"),
    plot.title = element_text(hjust = 0.5, face = "bold")
  )