transitDelays
Siddhartha Baghel
2022-11-30
R Markdown
Final Project for Intro To Urban Analytics: Chunk 1: Read csv files, test code for delays per specific train number (*Not Used), calculate delays for specific days in March 2018. Chunk 2: Calculate/Summarize and Display train delays for overall months per season. Chunk 3: Display and Summarize delays for specific days in March.
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.9
## ✔ tidyr 1.2.0 ✔ stringr 1.4.0
## ✔ readr 2.1.2 ✔ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()library(tidycensus)
library(osmdata)## Data (c) OpenStreetMap contributors, ODbL 1.0. https://www.openstreetmap.org/copyrightlibrary(sfnetworks)
library(units)## udunits database from C:/Program Files/R/R-4.2.1/library/units/share/udunits/udunits2.xmllibrary(sf)## Linking to GEOS 3.9.1, GDAL 3.4.3, PROJ 7.2.1; sf_use_s2() is TRUElibrary(tidygraph)##
## Attaching package: 'tidygraph'
##
## The following object is masked from 'package:stats':
##
## filterlibrary(tmap)
library(dotenv)
library(viridis)## Loading required package: viridisLitelibrary(dplyr)
library(ggplot2)
library(units)
library(leaflet)
library(leafsync)
library(dbscan)
library(tigris)## To enable caching of data, set `options(tigris_use_cache = TRUE)`
## in your R script or .Rprofile.library(plotly)##
## Attaching package: 'plotly'
##
## The following object is masked from 'package:ggplot2':
##
## last_plot
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following object is masked from 'package:graphics':
##
## layoutlibrary(here)## here() starts at C:/Users/sbaghel3/OneDrive - Georgia Institute of Technology/Desktop/transitDelayslibrary(patchwork)
library(rgdal)## Loading required package: sp
## Please note that rgdal will be retired by the end of 2023,
## plan transition to sf/stars/terra functions using GDAL and PROJ
## at your earliest convenience.
##
## rgdal: version: 1.5-32, (SVN revision 1176)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 3.4.3, released 2022/04/22
## Path to GDAL shared files: C:/Program Files/R/R-4.2.1/library/rgdal/gdal
## GDAL binary built with GEOS: TRUE
## Loaded PROJ runtime: Rel. 7.2.1, January 1st, 2021, [PJ_VERSION: 721]
## Path to PROJ shared files: C:/Program Files/R/R-4.2.1/library/rgdal/proj
## PROJ CDN enabled: FALSE
## Linking to sp version:1.5-0
## To mute warnings of possible GDAL/OSR exportToProj4() degradation,
## use options("rgdal_show_exportToProj4_warnings"="none") before loading sp or rgdal.library(mapview)
library(tidyr)
library(lubridate)##
## Attaching package: 'lubridate'
##
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionlocal3861Data <-
read.csv("3861.csv")
head(local3861Data)## date train_id stop_sequence from from_id
## 1 3/1/2018 3861 1 New York Penn Station 105
## 2 3/1/2018 3861 2 New York Penn Station 105
## 3 3/1/2018 3861 3 Secaucus Upper Lvl 38187
## 4 3/1/2018 3861 4 Newark Penn Station 107
## 5 3/1/2018 3861 5 Newark Airport 37953
## 6 3/1/2018 3861 6 North Elizabeth 109
## to to_id scheduled_time actual_time delay_minutes
## 1 New York Penn Station 105 3/1/2018 16:29 3/1/2018 16:29 0.2833333
## 2 Secaucus Upper Lvl 38187 3/1/2018 16:38 3/1/2018 16:41 3.2833333
## 3 Newark Penn Station 107 3/1/2018 16:50 3/1/2018 16:50 0.2333333
## 4 Newark Airport 37953 3/1/2018 16:56 3/1/2018 16:56 0.3000000
## 5 North Elizabeth 109 3/1/2018 16:59 3/1/2018 16:59 0.3000000
## 6 Elizabeth 41 3/1/2018 17:02 3/1/2018 17:02 0.2000000
## status line type
## 1 departed Northeast Corrdr NJ Transit
## 2 departed Northeast Corrdr NJ Transit
## 3 departed Northeast Corrdr NJ Transit
## 4 departed Northeast Corrdr NJ Transit
## 5 departed Northeast Corrdr NJ Transit
## 6 departed Northeast Corrdr NJ Transittypeof(local3861Data)## [1] "list"local3861Data$delay_minutes## [1] 0.28333333 3.28333333 0.23333333 0.30000000 0.30000000 0.20000000
## [7] 0.20000000 0.23333333 1.21666667 1.20000000 0.21666667 0.20000000
## [13] 0.00000000 0.00000000 0.00000000 0.00000000 0.16666667 0.00000000
## [19] 0.21666667 0.33333333 0.23333333 0.33333333 0.18333333 1.28333333
## [25] 1.28333333 0.33333333 0.23333333 0.00000000 0.00000000 0.00000000
## [31] 0.00000000 0.21666667 0.21666667 0.11666667 1.11666667 0.20000000
## [37] 1.18333333 0.06666667 2.13333333 1.18333333 0.10000000 1.15000000
## [43] 0.00000000 0.00000000 0.00000000 0.00000000 0.18333333 0.00000000
## [49] 0.00000000 0.13333333 0.20000000 0.15000000 0.23333333 1.15000000
## [55] 0.23333333 0.16666667 0.25000000 0.00000000 0.00000000 0.00000000local3861DelayinMinutesforMarch1 <- with(local3861Data, sum(delay_minutes[date == '3/1/2018']))
local3861DelayinMinutesforMarch1## [1] 7.866667with(local3861Data, sum(delay_minutes[date == '3/1/2018' & (stop_sequence == '1' | stop_sequence == '2')]))## [1] 3.566667local3861DelayinMinutesforMarch15 <- with(local3861Data, sum(delay_minutes[date == '3/15/2018']))
local3861DelayinMinutesforMarch22 <- with(local3861Data, sum(delay_minutes[date == '3/22/2018']))
local3861DelayinMinutesforMarch29 <- with(local3861Data, sum(delay_minutes[date == '3/29/2018']))
delayinMinutesofTrain <- c(local3861DelayinMinutesforMarch1, local3861DelayinMinutesforMarch15, local3861DelayinMinutesforMarch22, local3861DelayinMinutesforMarch29)
dateOfTrain <- c("March 1", "March 15", "March 22", "March 29")
png(file = "barchart_delay3861Local.png")
barplot(delayinMinutesofTrain, names.arg=dateOfTrain, xlab="Date", ylab="Delay In Min", col="red", main="Delay Chart for Local 3861", border="blue")
dev.off## function (which = dev.cur())
## {
## if (which == 1)
## stop("cannot shut down device 1 (the null device)")
## .External(C_devoff, as.integer(which))
## dev.cur()
## }
## <bytecode: 0x0000028ba4d6fdd0>
## <environment: namespace:grDevices>allTrainsMarch2018Data <- read.csv("march2018Delays.csv")
allTrainsApril2018Data <- read.csv("april2018Delays.csv")
allTrainsAugust2018Data <- read.csv("august2018Delays.csv")
allTrainsJune2018Data <- read.csv("june2018Delays.csv")
allTrainsSeptember2018Data <- read.csv("september2018Delays.csv")
allTrainsDecember2018Data <- read.csv("december2018Delays.csv")
#totalinMinutesforMarch <- "totalDelayinMinutesforMarch"
totalDelayperDayinMinutes <- c()
totalMarchDelaydf <- data.frame(totalDelayperDayinMinutes)
totalMarchDelaydf## data frame with 0 columns and 0 rowsx = 1
paste0('3/',as.character(x),'/2018')## [1] "3/1/2018"with(allTrainsMarch2018Data, sum(delay_minutes[date == paste0('3/',as.character(x),'/2018')]))## [1] 9190.117#delayStore <- numeric(31)
sumofMarch1Delays <- with(allTrainsMarch2018Data, sum(delay_minutes[date == '3/1/2018']))
typeof(sumofMarch1Delays)## [1] "double"totalrowsMarch12018 <- allTrainsMarch2018Data %>% select(delay_minutes, date) %>% filter(date == "3/1/2018")
totalrowsMarch152018 <- allTrainsMarch2018Data %>% select(delay_minutes, date) %>% filter(date == "3/15/2018")
totalrowsMarch222018 <- allTrainsMarch2018Data %>% select(delay_minutes, date) %>% filter(date == "3/22/2018")
totalrowsMarch292018 <- allTrainsMarch2018Data %>% select(delay_minutes, date) %>% filter(date == "3/29/2018")
totalrowsMarch212018 <- allTrainsMarch2018Data %>% select(delay_minutes, date) %>% filter(date == "3/21/2018")
totalrowsMarch22018 <- allTrainsMarch2018Data %>% select(delay_minutes, date) %>% filter(date == "3/2/2018")
totalrowsMarch72018 <- allTrainsMarch2018Data %>% select(delay_minutes, date) %>% filter(date == "3/7/2018")
#totalrowsMarch12018
mean(totalrowsMarch12018$delay_minutes)## [1] 6.277402mean(totalrowsMarch152018$delay_minutes)## [1] 3.909953mean(totalrowsMarch222018$delay_minutes)## [1] 3.862648mean(totalrowsMarch292018$delay_minutes)## [1] 2.848815marchDaysCombined <- rbind(totalrowsMarch12018,totalrowsMarch152018,totalrowsMarch222018,totalrowsMarch292018,totalrowsMarch212018,totalrowsMarch22018, totalrowsMarch72018)
#marchDaysCombined
mean(totalrowsMarch152018$delay_minutes)## [1] 3.909953mean(totalrowsMarch222018$delay_minutes)## [1] 3.862648mean(totalrowsMarch292018$delay_minutes)## [1] 2.848815marchDaysCombined$date <- factor(marchDaysCombined$date, levels=c("3/1/2018", "3/2/2018", "3/7/2018", "3/15/2018", "3/21/2018", "3/22/2018", "3/29/2018"))##Plots for Monthly Delays
#plot(pressure)
delayStore <- list()
delayStoreApril2018 <- list()
delayStoreAugust2018 <- list()
delayStoreJune2018 <- list()
delayStoreSeptember2018 <- list()
delayStoreDecember2018 <- list()
typeof(delayStore)## [1] "list"for( i in 1:31){
delayStore[i] <- with(allTrainsMarch2018Data, sum(delay_minutes[date == paste0('3/',as.character(i),'/2018')]))
}
for( i in 1:30){
delayStoreApril2018[i] <- with(allTrainsApril2018Data, sum(delay_minutes[date == paste0('4/',as.character(i),'/2018')]))
}
for( i in 1:31){
delayStoreAugust2018[i] <- with(allTrainsAugust2018Data, sum(delay_minutes[date == paste0('8/',as.character(i),'/2018')]))
}
for( i in 1:30){
delayStoreJune2018[i] <- with(allTrainsJune2018Data, sum(delay_minutes[date == paste0('6/',as.character(i),'/2018')]))
}
for( i in 1:30){
delayStoreSeptember2018[i] <- with(allTrainsSeptember2018Data, sum(delay_minutes[date == paste0('9/',as.character(i),'/2018')]))
}
for( i in 1:31){
delayStoreDecember2018[i] <- with(allTrainsDecember2018Data, sum(delay_minutes[date == paste0('12/',as.character(i),'/2018')]))
}
do.call(rbind, delayStoreApril2018)## [,1]
## [1,] 1376.350
## [2,] 4502.483
## [3,] 4172.800
## [4,] 9157.350
## [5,] 8168.667
## [6,] 5657.267
## [7,] 3713.733
## [8,] 3779.683
## [9,] 5164.817
## [10,] 5214.100
## [11,] 3692.283
## [12,] 6017.033
## [13,] 7226.850
## [14,] 2645.267
## [15,] 2184.267
## [16,] 6047.333
## [17,] 5854.350
## [18,] 4680.267
## [19,] 4656.650
## [20,] 6193.667
## [21,] 2718.883
## [22,] 2766.917
## [23,] 10752.400
## [24,] 8108.917
## [25,] 5242.883
## [26,] 6436.033
## [27,] 4392.317
## [28,] 2875.817
## [29,] 3345.650
## [30,] 4844.867delayCheckApril2018 <- do.call(rbind, delayStoreApril2018)
colnames(delayCheckApril2018)[1] <- "DelayinMin"
data_delayCheckApril2018 <- as.data.frame(delayCheckApril2018)
data_delayCheckApril2018$Month <- ("April")
#head(data_delayCheckApril2018)
do.call(rbind, delayStoreAugust2018)## [,1]
## [1,] 6116.917
## [2,] 5436.050
## [3,] 6485.200
## [4,] 3275.867
## [5,] 3538.000
## [6,] 5870.083
## [7,] 5115.717
## [8,] 4399.233
## [9,] 12797.483
## [10,] 7003.783
## [11,] 2866.017
## [12,] 2780.700
## [13,] 5663.867
## [14,] 4921.450
## [15,] 5689.933
## [16,] 4902.033
## [17,] 6486.000
## [18,] 2953.833
## [19,] 3068.433
## [20,] 4981.683
## [21,] 4919.650
## [22,] 9248.350
## [23,] 5448.533
## [24,] 6558.667
## [25,] 4684.500
## [26,] 5892.817
## [27,] 4131.767
## [28,] 5864.983
## [29,] 4347.300
## [30,] 3581.617
## [31,] 4588.233delayCheckAugust2018 <- do.call(rbind, delayStoreAugust2018)
colnames(delayCheckAugust2018)[1] <- "DelayinMin"
data_delayCheckAugust2018 <- as.data.frame(delayCheckAugust2018)
data_delayCheckAugust2018$Month <- ("August")
#head(data_delayCheckAugust2018)
do.call(rbind, delayStoreJune2018)## [,1]
## [1,] 7953.150
## [2,] 2422.250
## [3,] 2454.067
## [4,] 4954.817
## [5,] 4644.067
## [6,] 3649.200
## [7,] 3856.150
## [8,] 5093.917
## [9,] 2493.467
## [10,] 2082.733
## [11,] 4613.333
## [12,] 5453.117
## [13,] 3890.450
## [14,] 4442.817
## [15,] 4760.650
## [16,] 2698.733
## [17,] 2596.617
## [18,] 6079.967
## [19,] 7197.050
## [20,] 4570.867
## [21,] 4674.567
## [22,] 4440.450
## [23,] 2657.983
## [24,] 2669.500
## [25,] 4426.517
## [26,] 3421.717
## [27,] 5777.850
## [28,] 5488.583
## [29,] 6605.117
## [30,] 2647.583delayCheckJune2018 <- do.call(rbind, delayStoreJune2018)
colnames(delayCheckJune2018)[1] <- "DelayinMin"
data_delayCheckJune2018 <- as.data.frame(delayCheckJune2018)
data_delayCheckJune2018$Month <- ("June")
#head(data_delayCheckJune2018)
do.call(rbind, delayStoreSeptember2018)## [,1]
## [1,] 2184.150
## [2,] 1998.067
## [3,] 3131.483
## [4,] 4263.833
## [5,] 12103.000
## [6,] 4247.000
## [7,] 7552.167
## [8,] 3489.200
## [9,] 5826.100
## [10,] 7387.383
## [11,] 5296.333
## [12,] 4144.283
## [13,] 4897.000
## [14,] 4682.417
## [15,] 2322.367
## [16,] 2933.400
## [17,] 5439.917
## [18,] 4148.667
## [19,] 5102.317
## [20,] 5780.800
## [21,] 3868.450
## [22,] 3181.617
## [23,] 2300.283
## [24,] 5347.333
## [25,] 5182.967
## [26,] 4320.583
## [27,] 4180.833
## [28,] 5717.100
## [29,] 2377.333
## [30,] 2639.667delayCheckSeptember2018 <- do.call(rbind, delayStoreSeptember2018)
colnames(delayCheckSeptember2018)[1] <- "DelayinMin"
data_delayCheckSeptember2018 <- as.data.frame(delayCheckSeptember2018)
data_delayCheckSeptember2018$Month <- ("September")
#head(data_delayCheckSeptember2018)
do.call(rbind, delayStoreDecember2018)## [,1]
## [1,] 3099.517
## [2,] 3824.100
## [3,] 5335.083
## [4,] 5334.167
## [5,] 7374.283
## [6,] 6724.917
## [7,] 11893.800
## [8,] 7758.600
## [9,] 6290.250
## [10,] 14459.150
## [11,] 6025.633
## [12,] 6701.533
## [13,] 7259.517
## [14,] 6510.267
## [15,] 3588.083
## [16,] 5029.700
## [17,] 7328.017
## [18,] 7155.933
## [19,] 6740.667
## [20,] 6060.100
## [21,] 5634.783
## [22,] 4211.650
## [23,] 3184.667
## [24,] 4867.667
## [25,] 2876.150
## [26,] 4221.783
## [27,] 4178.767
## [28,] 4785.667
## [29,] 3875.267
## [30,] 2787.850
## [31,] 4293.333delayCheckDecember2018 <- do.call(rbind, delayStoreDecember2018)
colnames(delayCheckDecember2018)[1] <- "DelayinMin"
data_delayCheckDecember2018 <- as.data.frame(delayCheckDecember2018)
data_delayCheckDecember2018$Month <- ("December")
#head(data_delayCheckDecember2018)
print(delayStore)## [[1]]
## [1] 9190.117
##
## [[2]]
## [1] 12944.98
##
## [[3]]
## [1] 2235
##
## [[4]]
## [1] 3433.717
##
## [[5]]
## [1] 4316.183
##
## [[6]]
## [1] 5415.733
##
## [[7]]
## [1] 6528.033
##
## [[8]]
## [1] 1996.367
##
## [[9]]
## [1] 12790.55
##
## [[10]]
## [1] 3357.1
##
## [[11]]
## [1] 3524.217
##
## [[12]]
## [1] 7172.55
##
## [[13]]
## [1] 5945.95
##
## [[14]]
## [1] 3745.683
##
## [[15]]
## [1] 5775
##
## [[16]]
## [1] 11008.83
##
## [[17]]
## [1] 3255.317
##
## [[18]]
## [1] 2272.35
##
## [[19]]
## [1] 5044.833
##
## [[20]]
## [1] 5342.967
##
## [[21]]
## [1] 2817.983
##
## [[22]]
## [1] 5878.95
##
## [[23]]
## [1] 4142.2
##
## [[24]]
## [1] 4017.633
##
## [[25]]
## [1] 3999.833
##
## [[26]]
## [1] 3997.95
##
## [[27]]
## [1] 4286.5
##
## [[28]]
## [1] 3695.867
##
## [[29]]
## [1] 4207.7
##
## [[30]]
## [1] 5123.317
##
## [[31]]
## [1] 2721.417do.call(rbind.data.frame, delayStore)## c.9190.116666678..12944.983333328..2234.999999982..3433.71666668..
## 1 9190.117
## 2 12944.983
## 3 2235.000
## 4 3433.717
## 5 4316.183
## 6 5415.733
## 7 6528.033
## 8 1996.367
## 9 12790.550
## 10 3357.100
## 11 3524.217
## 12 7172.550
## 13 5945.950
## 14 3745.683
## 15 5775.000
## 16 11008.833
## 17 3255.317
## 18 2272.350
## 19 5044.833
## 20 5342.967
## 21 2817.983
## 22 5878.950
## 23 4142.200
## 24 4017.633
## 25 3999.833
## 26 3997.950
## 27 4286.500
## 28 3695.867
## 29 4207.700
## 30 5123.317
## 31 2721.417do.call(rbind, delayStore)## [,1]
## [1,] 9190.117
## [2,] 12944.983
## [3,] 2235.000
## [4,] 3433.717
## [5,] 4316.183
## [6,] 5415.733
## [7,] 6528.033
## [8,] 1996.367
## [9,] 12790.550
## [10,] 3357.100
## [11,] 3524.217
## [12,] 7172.550
## [13,] 5945.950
## [14,] 3745.683
## [15,] 5775.000
## [16,] 11008.833
## [17,] 3255.317
## [18,] 2272.350
## [19,] 5044.833
## [20,] 5342.967
## [21,] 2817.983
## [22,] 5878.950
## [23,] 4142.200
## [24,] 4017.633
## [25,] 3999.833
## [26,] 3997.950
## [27,] 4286.500
## [28,] 3695.867
## [29,] 4207.700
## [30,] 5123.317
## [31,] 2721.417delayCheck <- do.call(rbind, delayStore)
colnames(delayCheck)[1] <- "DelayinMin"
data_delayCheck <- as.data.frame(delayCheck)
data_delayCheck## DelayinMin
## 1 9190.117
## 2 12944.983
## 3 2235.000
## 4 3433.717
## 5 4316.183
## 6 5415.733
## 7 6528.033
## 8 1996.367
## 9 12790.550
## 10 3357.100
## 11 3524.217
## 12 7172.550
## 13 5945.950
## 14 3745.683
## 15 5775.000
## 16 11008.833
## 17 3255.317
## 18 2272.350
## 19 5044.833
## 20 5342.967
## 21 2817.983
## 22 5878.950
## 23 4142.200
## 24 4017.633
## 25 3999.833
## 26 3997.950
## 27 4286.500
## 28 3695.867
## 29 4207.700
## 30 5123.317
## 31 2721.417data_delayCheck$Month <- ("March")
#head(data_delayCheck)
#head(data_delayCheckApril2018)
summarise(data_delayCheck, mean(DelayinMin))## mean(DelayinMin)
## 1 5167.253summarise(data_delayCheckApril2018, mean(DelayinMin))## mean(DelayinMin)
## 1 5052.997#head(delayCheck)
#delayCheck$DelayinMin
#summarise(delayCheck, mean(DelainMin))
median(data_delayCheck$DelayinMin)## [1] 4207.7median(data_delayCheckJune2018$DelayinMin)## [1] 4441.633median(data_delayCheckSeptember2018$DelayinMin)## [1] 4255.417median(data_delayCheckDecember2018$DelayinMin)## [1] 5335.083median(data_delayCheckApril2018$DelayinMin)## [1] 4762.567median(data_delayCheckAugust2018$DelayinMin)## [1] 4981.683allMonthsCombined2018 <- rbind(data_delayCheck,data_delayCheckApril2018,data_delayCheckAugust2018)
allSeasonsCombined2018 <- rbind(data_delayCheck,data_delayCheckJune2018,data_delayCheckSeptember2018,data_delayCheckDecember2018)
#head(allMonthsCombined2018)
#allMonthsCombined2018
allMonthsCombined2018$Month <- factor(allMonthsCombined2018$Month, levels=c("March", "April", "August"))
allSeasonsCombined2018$Month <- factor(allSeasonsCombined2018$Month, levels=c("March", "June", "September", "December"))
allMonthsCombined2018 %>%
aov(DelayinMin ~ Month, data = .) %>%
summary()## Df Sum Sq Mean Sq F value Pr(>F)
## Month 2 772002 386001 0.07 0.932
## Residuals 89 490102846 5506774allMonthsCombined2018 %>%
aov(DelayinMin ~ Month, data = .) %>%
TukeyHSD() #%>%## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = DelayinMin ~ Month, data = .)
##
## $Month
## diff lwr upr p adj
## April-March -114.2560 -1546.762 1318.250 0.9802769
## August-March 110.7699 -1309.945 1531.485 0.9811446
## August-April 225.0259 -1207.480 1657.532 0.9257036 # plot()
allSeasonsCombined2018 %>%
aov(DelayinMin ~ Month, data = .) %>%
TukeyHSD()## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = DelayinMin ~ Month, data = .)
##
## $Month
## diff lwr upr p adj
## June-March -876.6766 -2397.10687 643.7537 0.4391922
## September-March -632.3844 -2152.81465 888.0459 0.7000249
## December-March 620.1957 -887.72055 2128.1119 0.7073185
## September-June 244.2922 -1288.54995 1777.1344 0.9757542
## December-June 1496.8723 -23.55802 3017.3026 0.0553515
## December-September 1252.5801 -267.85024 2773.0103 0.1444953allSeasonsCombined2018 %>%
aov(DelayinMin ~ Month, data = .) %>%
summary()## Df Sum Sq Mean Sq F value Pr(>F)
## Month 3 41417572 13805857 2.66 0.0514 .
## Residuals 118 612368054 5189560
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1ggplot(allSeasonsCombined2018, aes(x = Month, y = DelayinMin, fill = Month)) +
geom_violin(show.legend = FALSE)+
geom_boxplot(width = .5, show.legend = FALSE)
ggplot(allMonthsCombined2018, aes(x = Month, y = DelayinMin, fill = Month)) +
geom_violin(show.legend = FALSE)+
geom_boxplot(width = .5, show.legend = FALSE)
Delays by days in March 2018
marchDaysCombined %>%
aov(delay_minutes ~ date, data = .) %>%
summary()## Df Sum Sq Mean Sq F value Pr(>F)
## date 6 38654 6442 69.87 <2e-16 ***
## Residuals 9273 855053 92
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1marchDaysCombined %>%
aov(delay_minutes ~ date, data = .) %>%
TukeyHSD()## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = delay_minutes ~ date, data = .)
##
## $date
## diff lwr upr p adj
## 3/2/2018-3/1/2018 2.11752873 1.0842002 3.15085723 0.0000000
## 3/7/2018-3/1/2018 1.04102092 -0.1617733 2.24381511 0.1410963
## 3/15/2018-3/1/2018 -2.36744949 -3.4117930 -1.32310598 0.0000000
## 3/21/2018-3/1/2018 -3.16704521 -4.3640508 -1.97003962 0.0000000
## 3/22/2018-3/1/2018 -2.41475426 -3.4513840 -1.37812448 0.0000000
## 3/29/2018-3/1/2018 -3.42858693 -4.4729304 -2.38424342 0.0000000
## 3/7/2018-3/2/2018 -1.07650781 -2.2677287 0.11471313 0.1073709
## 3/15/2018-3/2/2018 -4.48497822 -5.5159713 -3.45398510 0.0000000
## 3/21/2018-3/2/2018 -5.28457395 -6.4699498 -4.09919812 0.0000000
## 3/22/2018-3/2/2018 -4.53228299 -5.5554617 -3.50910424 0.0000000
## 3/29/2018-3/2/2018 -5.54611566 -6.5771088 -4.51512254 0.0000000
## 3/15/2018-3/7/2018 -3.40847041 -4.6092589 -2.20768197 0.0000000
## 3/21/2018-3/7/2018 -4.20806614 -5.5437539 -2.87237833 0.0000000
## 3/22/2018-3/7/2018 -3.45577519 -4.6498610 -2.26168942 0.0000000
## 3/29/2018-3/7/2018 -4.46960785 -5.6703963 -3.26881941 0.0000000
## 3/21/2018-3/15/2018 -0.79959573 -1.9945859 0.39539441 0.4318976
## 3/22/2018-3/15/2018 -0.04730477 -1.0816066 0.98699708 0.9999995
## 3/29/2018-3/15/2018 -1.06113744 -2.1031703 -0.01910463 0.0427170
## 3/22/2018-3/21/2018 0.75229095 -0.4359638 1.94054571 0.5024870
## 3/29/2018-3/21/2018 -0.26154171 -1.4565318 0.93344842 0.9952607
## 3/29/2018-3/22/2018 -1.01383267 -2.0481345 0.02046919 0.0590118ggplot(marchDaysCombined, aes(x = date, y = delay_minutes, fill = date)) +
geom_violin(show.legend = FALSE)+
geom_boxplot(width = .5, show.legend = FALSE)