gistfile1.txt

rm(list = ls())
options("scipen"=100, "digits"=10)

#### LIBRARIES ####
library(readr)
library(readxl)
library(DataExplorer)
library(tidyverse)
library(ggExtra)
library(gridExtra)
library(grid)
library(AzureStor)
library(caret)
library(car)
library(skimr)
library(forecast)
library(lubridate)
library(xgboost)
library(tidymodels)
library(modeltime)
library(tidyverse)
library(timetk)
library(modelr)
library(data.table)
library(sweep)
library(zoo)
library(dynlm)
library(ggfortify)
library(tsDyn)
library(vars)
library(doParallel)
library(lattice)
library(pdp)
library(ggfortify)
library(xgboost)
library(DT)
library(forecastML)
pacman::p_load(tidyverse, magrittr) # data wrangling packages
pacman::p_load(lubridate, tsintermittent, fpp3, modeltime, timetk, modeltime.gluonts, tidymodels, modeltime.ensemble, modeltime.resample) # time series model packages
pacman::p_load(foreach, future) # parallel functions
pacman::p_load(viridis, plotly) # visualizations packages
theme_set(hrbrthemes::theme_ipsum()) # set default themes

#### IMPORT DATA ####
day <- read_csv("Location860_day.csv")
View(day)
names(day)
str(day)
dim(day)
hour <- read_csv("Location860_hour.csv")
View(hour)
names(hour)
str(hour)
dim(hour)
Norm <- read_excel("Norm.xlsx")
names(Norm)
str(Norm)
dim(Norm)

folder<-setwd(getwd())
name="/DATA.csv"
download_from_url("https://xxxxx.blob.core.windows.net/xxx/xxxx.csv",
                  dest      = paste0(folder,name),
                  overwrite = TRUE,
                  key       = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")
day <- read_csv("DATA.csv")

day$average_weight_eggs <- if_else(day$average_weight_eggs < 1,
                                   day$average_weight_eggs * 100,
                                   day$average_weight_eggs)
options("scipen"=100, "digits"=4)
day %>%
  group_by(location_identification, date_interval) %>%
  filter(location_identification == "2" &
           date_interval > "2021-12-05" & date_interval < "2021-12-12") %>%
  summarise_by_time(date_interval,
                    .by = "week",
                    Leg_perc_dag               =  egg_count/animals_actual, 
                    Leg_perc_week              =  (cumsum(egg_count) / 7) / (animals_start - (2 / 2)), 
                    Totaal_ei_week_tel         =  sum(egg_count, na.rm = TRUE), 
                    Totaal_twee_ei_week_tel    =  sum(eggs_second_quality, na.rm = TRUE), 
                    Totaal_twee_ei_week_perc   =  (sum(eggs_second_quality, na.rm = TRUE) / Totaal_ei_week_tel) * 100, 
                    Leg_Perc                   =  (cumsum(egg_count) / 7) / (animals_start - (2 / 2)), 
                    Leg_Perc_Incre             =  sum(egg_count / animals_actual, na.rm = TRUE) / 7, 
                    Leg_Perc_Totaal            =  (sum(egg_count, na.rm = TRUE) / sum(animals_actual, na.rm = TRUE)), 
                    Eiggewicht_dag             =  average_weight_eggs,
                    Eiggewicht_week_abs        =  abs(average_weight_eggs),         
                    Eiggewicht_week_gem_incr   =  mean(average_weight_eggs, na.rm=TRUE),
                    Eiggewicht_week_gem_totaal =  sum(average_weight_eggs, na.rm = TRUE) / 7, 
                    Eimassa_dag                =  (Eiggewicht_dag * Leg_perc_dag),
                    Eimassa_week               =  (Eiggewicht_week_gem_totaal * Leg_perc_week),
                    Totaal_ei_kg               =  (Totaal_ei_week_tel * Eiggewicht_week_gem_totaal) / 1000000,
                    Begin_hennen               =  sum(animals_start, na.rm = TRUE),
                    Uitval_hennen              =  sum(animals_out, na.rm = TRUE),
                    Uitval_hennen_Perc         =  sum(Uitval_hennen / Begin_hennen) * 100) %>% 
  mutate(
                    Week_Eimassa               =  cumsum(Eiggewicht_dag * Leg_perc_dag),
                    Totaal_ei_cum              =  cumsum(Totaal_ei_week_tel), 
                    Totaal_ei_kg_cum           =  cumsum(Totaal_ei_kg), 
                    Uitval_hennen_cum          =  cumsum(Uitval_hennen_Perc), 
                    Eimassa_cum                =  cumsum(Eimassa_dag)
  ) %>% # Eimassa POH cum
  reshape2::melt(., id.vars=1:2)%>%
  print.data.frame()


newdf<-day %>%
  group_by(location_identification, date_interval) %>%
  summarise_by_time(date_interval,
                    .by = "week",
                    Eieren                     =  egg_count,
                    Hennen                     =  animals_actual,    
                    Leg_perc_dag               =  egg_count/animals_actual, 
                    Leg_perc_week              =  (cumsum(egg_count) / 7) / (animals_start - (2 / 2)), 
                    Totaal_ei_week_tel         =  sum(egg_count, na.rm = TRUE), 
                    Totaal_twee_ei_week_tel    =  sum(eggs_second_quality, na.rm = TRUE), 
                    Totaal_twee_ei_week_perc   =  (sum(eggs_second_quality, na.rm = TRUE) / Totaal_ei_week_tel) * 100, 
                    Leg_Perc_Incre             =  sum(egg_count / animals_actual, na.rm = TRUE) / 7, 
                    Leg_Perc_Totaal            =  (sum(egg_count, na.rm = TRUE) / sum(animals_actual, na.rm = TRUE)), 
                    Eiggewicht_dag             =  average_weight_eggs,
                    Eiggewicht_week_abs        =  abs(sum(average_weight_eggs)),         
                    Eiggewicht_week_gem_incr   =  mean(average_weight_eggs, na.rm=TRUE),
                    Eiggewicht_week_gem_totaal =  sum(average_weight_eggs, na.rm = TRUE) / 7, 
                    Eimassa_dag                =  (Eiggewicht_dag * Leg_perc_dag),
                    Eimassa_week               =  (Eiggewicht_week_gem_totaal * Leg_perc_week),
                    Totaal_ei_kg               =  (Totaal_ei_week_tel * Eiggewicht_week_gem_incr) / 1000000,
                    Begin_hennen               =  sum(animals_start, na.rm = TRUE),
                    Uitval_hennen              =  sum(animals_out, na.rm = TRUE),
                    Uitval_hennen_Perc         =  sum(Uitval_hennen / Begin_hennen) * 100) %>% 
  mutate(
    Week_Eimassa               =  cumsum(Eiggewicht_dag * Leg_perc_dag),
    Totaal_ei_cum              =  cumsum(Totaal_ei_week_tel), 
    Totaal_ei_kg_cum           =  cumsum(Totaal_ei_kg), 
    Uitval_hennen_cum          =  cumsum(Uitval_hennen_Perc), 
    Eimassa_cum                =  cumsum(Eimassa_dag))
day$date_interval_day<-day$date_interval
newdf$date_interval_week<-newdf$date_interval
newdf$date_interval_day<-day$date_interval_day
newdf$week=week(newdf$date_interval_day)