read_wapData.R

#Reading in the data and necessary libraries and data for RPI StudySafe App
#Created by Kara Kniss

################################################################################################################
#READING IN THE NECESSARY LIBRARIES
################################################################################################################
library(shiny)
library(shinydashboard)
library(shinyjs)
library(ggplot2)
library(shinyWidgets)
library(tidyverse)
library(tidyr)
library(lubridate)
library(plyr)
library(scales)
library(zoo)
library(ggalt)
library(leaflet)
library(plotly)
library(wesanderson)
library(reactable)

################################################################################################################
###READING IN NECESSARY FILES
################################################################################################################
#rpi_wap_raw: Min_30, devname, maccount, usercount, datetime, date_time, Date, Building, Floor, Room, latitude, longitude, buldingType, abbrev, time
rpi_wap_raw <- readRDS("../../COVID_RPI_WiFi_Data/rpi_wap_raw.rds")

#combined_wap_data: building, time, Date, latitude, longitude, buildingType, abbrev, users, macs, 
combined_wap_data <- readRDS("../../COVID_RPI_WiFi_Data/combined_wap_data.rds")

#rpi_wap_stats: devname, Day, maccount_mean, maccount_med, maccount_max, usrecount_mean, usercount_med, usercount_max
rpi_wap_stats <- readRDS("../../COVID_RPI_WiFi_Data/rpi_wifi_semester_day_summary.rds")

#rpi_wap_week: devname, maccount, usercount, datetime, date_time, Date, Day
rpi_wap_week <- readRDS("../../COVID_RPI_WiFi_Data/rpi_wifi_semester_extended.rds")

#buildinginfo: Building, latitude, longitude, buildingType, abbrev
#buildinginfo <- readRDS("../../COVID_RPI_WiFi_Data/buildinginfo.rds")

################################################################################################################
###CLEANING DATA
################################################################################################################
#rpi_wap_raw: devname, users, Date, Building, Hour, lat, lng, BuildingType
rpi_wap_raw <- rpi_wap_raw %>% mutate(Hour = hour(as.POSIXct(time))) %>% select(devname, usercount, Date, Building, Hour, latitude, longitude, buildingType)
colnames(rpi_wap_raw) <- c('devname', 'users', 'Date', 'Building', 'Hour', 'lat', 'lng', 'BuildingType')

#combined_wap_data: Building,  Hour, lat, lng, BuildingType
rpi_wap_last7 <- combined_wap_data %>% mutate(Hour = hour(as.POSIXct(time))) %>% select(Building, users, Date, Building, Hour, latitude, longitude, buildingType)
rpi_wap_last7 <- rpi_wap_last7 %>% group_by(Building, Date, Hour, latitude, longitude, buildingType) %>% summarise_all(funs(max)) %>% ungroup() 
colnames(rpi_wap_last7) <- c('Building', 'Date', 'Hour','lat','lng', 'BuildingType', 'users' )

#Building Tagging, Use Later for whatever categories we have
#combined_wap_data$BuildingType <- ''
#combined_wap_data[combined_wap_data$Building %in% Academic == TRUE, ]$BuildingType <- 'Academic'
#combined_wap_data[combined_wap_data$Building %in% Greek == TRUE, ]$BuildingType <- 'Greek'
#combined_wap_data[combined_wap_data$Building %in% Housing == TRUE, ]$BuildingType <- 'Housing'
#combined_wap_data[combined_wap_data$Building %in% OtherOnCampus == TRUE, ]$BuildingType <- 'OtherOnCampus'
#combined_wap_data[combined_wap_data$Building %in% OtherOffCampus == TRUE, ]$BuildingType <- 'OtherOffCampus'

#bldgs(getting buildings to append to devnames): devname, Building
bldgs <- rpi_wap_raw %>% filter(Date == min(rpi_wap_last7$Date)+1) %>% filter(Hour==12) %>% select(devname, Building)

# hits_per_wap_semester_by_building_max(getting maximum number of users for each building): Building, capacity
hits_per_wap_semester_by_building_max <- merge(rpi_wap_stats, bldgs, by.x= "devname", by.y="devname")
hits_per_wap_semester_by_building_max <- hits_per_wap_semester_by_building_max %>% group_by(devname, Building, Day) %>% summarise_all(funs(max)) %>% ungroup() %>% select(devname, Day, usercount_max, Building)
hits_per_wap_semester_by_building_max <- hits_per_wap_semester_by_building_max[,2:ncol(hits_per_wap_semester_by_building_max)]
hits_per_wap_semester_by_building_max <- hits_per_wap_semester_by_building_max %>% group_by(Building, Day) %>% summarise_all(funs(sum)) %>% ungroup()
hits_per_wap_semester_by_building_max <- hits_per_wap_semester_by_building_max %>% group_by(Building) %>% summarise_all(funs(max)) %>% ungroup() %>% select(Building, usercount_max)
colnames(hits_per_wap_semester_by_building_max) <- c('Building', 'capacity')

################################################################################################################
## DEFININING LISTS AND DATA FRAMES FOR CONVENIENCE
################################################################################################################

#Possible tagging for later
#placesOfInterest <- c('CII', 'DCC', 'Folsom Library', 'Rensselaer Union', 'Voorhees Computing Center')
#placesOfWellness <- c('ASRC', 'ECAV arena', 'ECAV stadium', 'Houston Field House', 'Fitness Center', '87 Gym', 'Robison Pool')
#placesOfDeliciousness <- c('Moes, College Ave', 'Commons Dining Hall', 'Russell Sage Dining Hall')
#BuildingTypes <- c('Academic','Housing','placesOfInterest', 'placesOfWellness', 'placesOfDeliciousness',  'Greek',  'OtherOnCampus', 'OtherOffCampus')

#creating a time list for the graphs so they aren't in military time
time <- list('12:00am'= 0,'1:00am'=1, '2:00am'=2, '3:00am'=3, '4:00am'=4, '5:00am'=5, '6:00am'=6, '7:00am'=7, '8:00am'=8, '9:00am'=9, '10:00am'=10, "11:00am"=11, "12:00pm"=12, "1:00pm"=13, "2:00pm"=14, "3:00pm"=15, "4:00pm"=16, "5:00pm"=17, "6:00pm"=18, "7:00pm"=19, "8:00pm"=20, "9:00pm"=21,"10:00pm"=22, "11:00pm"=23)
Time_num <- c(0:23)
Time_AMPM <- c('12am', '1am', '2am', '3am', '4am', '5am', '6am', '7am', '8am', '9am', '10am', '11am', '12pm', '1pm', '2pm','3pm', '4pm', '5pm', '6pm', '7pm', '8pm', '9pm', '10pm', '11pm' )
Time_noLabel <- c(12,1,2,3,4,5,6,7,8,9,10,11,12,1,2,3,4,5,6,7,8,9,10,11)
time.data <- data.frame(Time_num, Time_AMPM, Time_noLabel, stringsAsFactors=FALSE)

#defining the max date and min date info
min_date <- min(rpi_wap_last7$Date)
max_date <- max(rpi_wap_last7$Date)
max_time_of_max_date <- max(rpi_wap_last7[rpi_wap_last7$Date == max(rpi_wap_last7$Date),]$Hour)+1
min_time_of_min_date <- min(rpi_wap_last7[rpi_wap_last7$Date == min(rpi_wap_last7$Date),]$Hour)+1

#weekday information
#getting selected weekday
day <- c("Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday" )
dayVal<- c(1,2,3,4,5,6,7)
weekpair <- data.frame(day,dayVal, stringsAsFactors=FALSE)

#weekly3_stats(Getting average devname users of the last three weeks by day): devname, Day, Hour, users 
weekly3_stats <- rpi_wap_week %>% filter(Date >= min(rpi_wap_last7$Date)-21) %>% mutate(Hour = hour(as.POSIXct(date_time))) 
weekly3_stats <- weekly3_stats %>% select(devname, usercount, Day, Hour) %>% group_by(devname, Day, Hour) %>% summarise_all(funs(max)) %>% ungroup()
colnames(weekly3_stats) <- c('devname', 'Day', 'Hour', 'users')