DATA 607 Project 2
Ahsanul Choudhury
October 7, 2016
Install packages
##install.packages("dplyr")
##install.packages("tidyr")
##install.packages("ggplot2")Load packages
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(tidyr)
library(ggplot2)Dataset 1
Engilsh Premier League Data, Source Provided by Ravi Kothari
objective: To find if there is any home advantage during a match by analyzing home and away goals
##.csv was created and uploaded to Github
Load data
epl <- read.csv("https://raw.githubusercontent.com/choudhury1023/Data-607/gh-pages/epl_data.csv", header = TRUE, stringsAsFactors = FALSE)
epl## Team P W D L GF GA GD Pts PPG Wh Dh Lh GFh GAh Wa Da La
## 1 Manchester City 7 6 0 1 18 7 11 18 2.57 3 0 0 9 2 3 0 1
## 2 Tottenham 7 5 2 0 12 3 9 17 2.43 3 1 0 5 1 2 1 0
## 3 Arsenal 7 5 1 1 16 7 9 16 2.29 2 0 1 8 5 3 1 0
## 4 Liverpool 7 5 1 1 18 10 8 16 2.29 2 0 0 9 2 3 1 1
## 5 Everton 7 4 2 1 11 5 6 14 2.00 2 2 0 6 3 2 0 1
## 6 Manchester Utd 7 4 1 2 13 8 5 13 1.86 2 1 1 8 4 2 0 1
## 7 Chelsea 7 4 1 2 12 9 3 13 1.86 2 0 1 6 3 2 1 1
## 8 Crystal Palace 7 3 2 2 11 8 3 11 1.57 1 1 1 5 3 2 1 1
## 9 West Bromwich 7 2 3 2 8 7 1 9 1.29 1 1 1 5 4 1 2 1
## 10 Southampton 7 2 3 2 7 6 1 9 1.29 1 2 0 3 2 1 1 2
## 11 Watford 7 2 2 3 12 13 -1 8 1.14 1 1 2 7 8 1 1 1
## 12 Leicester City 7 2 2 3 8 11 -3 8 1.14 2 2 0 5 1 0 0 3
## 13 Bournemouth 7 2 2 3 6 11 -5 8 1.14 2 0 1 3 3 0 2 2
## 14 Burnley 7 2 1 4 5 9 -4 7 1.00 2 1 2 5 3 0 0 2
## 15 Hull City 7 2 1 4 7 14 -7 7 1.00 1 0 3 3 8 1 1 1
## 16 Middlesbrough 7 1 3 3 7 10 -3 6 0.86 0 1 2 3 5 1 2 1
## 17 Swansea City 7 1 1 5 6 12 -6 4 0.57 0 1 3 4 9 1 0 2
## 18 West Ham Utd 7 1 1 5 8 17 -9 4 0.57 1 1 2 4 8 0 0 3
## 19 Stoke City 7 0 3 4 5 16 -11 3 0.43 0 1 2 2 9 0 2 2
## 20 Sunderland 7 0 2 5 6 13 -7 2 0.29 0 1 3 4 9 0 1 2
## GFa GAa X
## 1 9 5 NA
## 2 7 2 NA
## 3 8 2 NA
## 4 9 8 NA
## 5 5 2 NA
## 6 5 4 NA
## 7 6 6 NA
## 8 6 5 NA
## 9 3 3 NA
## 10 4 4 NA
## 11 5 5 NA
## 12 3 10 NA
## 13 3 8 NA
## 14 0 6 NA
## 15 4 6 NA
## 16 4 5 NA
## 17 2 3 NA
## 18 4 9 NA
## 19 3 7 NA
## 20 2 4 NAFind Column Names
names(epl)## [1] "Team" "P" "W" "D" "L" "GF" "GA" "GD" "Pts" "PPG"
## [11] "Wh" "Dh" "Lh" "GFh" "GAh" "Wa" "Da" "La" "GFa" "GAa"
## [21] "X"Select required columns and rename
epl1<- epl %>%
select(Team, GFh, GAh, GFa, GAa) %>%
rename(team = Team, goal_for_home = GFh, goal_against_home = GAh, goal_for_away = GFa, goal_against_away = GAa)
epl1## team goal_for_home goal_against_home goal_for_away
## 1 Manchester City 9 2 9
## 2 Tottenham 5 1 7
## 3 Arsenal 8 5 8
## 4 Liverpool 9 2 9
## 5 Everton 6 3 5
## 6 Manchester Utd 8 4 5
## 7 Chelsea 6 3 6
## 8 Crystal Palace 5 3 6
## 9 West Bromwich 5 4 3
## 10 Southampton 3 2 4
## 11 Watford 7 8 5
## 12 Leicester City 5 1 3
## 13 Bournemouth 3 3 3
## 14 Burnley 5 3 0
## 15 Hull City 3 8 4
## 16 Middlesbrough 3 5 4
## 17 Swansea City 4 9 2
## 18 West Ham Utd 4 8 4
## 19 Stoke City 2 9 3
## 20 Sunderland 4 9 2
## goal_against_away
## 1 5
## 2 2
## 3 2
## 4 8
## 5 2
## 6 4
## 7 6
## 8 5
## 9 3
## 10 4
## 11 5
## 12 10
## 13 8
## 14 6
## 15 6
## 16 5
## 17 3
## 18 9
## 19 7
## 20 4Summary analysis
summary(epl1)## team goal_for_home goal_against_home goal_for_away
## Length:20 Min. :2.00 Min. :1.00 Min. :0.0
## Class :character 1st Qu.:3.75 1st Qu.:2.75 1st Qu.:3.0
## Mode :character Median :5.00 Median :3.50 Median :4.0
## Mean :5.20 Mean :4.60 Mean :4.6
## 3rd Qu.:6.25 3rd Qu.:8.00 3rd Qu.:6.0
## Max. :9.00 Max. :9.00 Max. :9.0
## goal_against_away
## Min. : 2.00
## 1st Qu.: 3.75
## Median : 5.00
## Mean : 5.20
## 3rd Qu.: 6.25
## Max. :10.00Tidy data, convert form wide to long
epl_tidy <- gather(epl1,"type", "goals", 2:5)
epl_tidy## team type goals
## 1 Manchester City goal_for_home 9
## 2 Tottenham goal_for_home 5
## 3 Arsenal goal_for_home 8
## 4 Liverpool goal_for_home 9
## 5 Everton goal_for_home 6
## 6 Manchester Utd goal_for_home 8
## 7 Chelsea goal_for_home 6
## 8 Crystal Palace goal_for_home 5
## 9 West Bromwich goal_for_home 5
## 10 Southampton goal_for_home 3
## 11 Watford goal_for_home 7
## 12 Leicester City goal_for_home 5
## 13 Bournemouth goal_for_home 3
## 14 Burnley goal_for_home 5
## 15 Hull City goal_for_home 3
## 16 Middlesbrough goal_for_home 3
## 17 Swansea City goal_for_home 4
## 18 West Ham Utd goal_for_home 4
## 19 Stoke City goal_for_home 2
## 20 Sunderland goal_for_home 4
## 21 Manchester City goal_against_home 2
## 22 Tottenham goal_against_home 1
## 23 Arsenal goal_against_home 5
## 24 Liverpool goal_against_home 2
## 25 Everton goal_against_home 3
## 26 Manchester Utd goal_against_home 4
## 27 Chelsea goal_against_home 3
## 28 Crystal Palace goal_against_home 3
## 29 West Bromwich goal_against_home 4
## 30 Southampton goal_against_home 2
## 31 Watford goal_against_home 8
## 32 Leicester City goal_against_home 1
## 33 Bournemouth goal_against_home 3
## 34 Burnley goal_against_home 3
## 35 Hull City goal_against_home 8
## 36 Middlesbrough goal_against_home 5
## 37 Swansea City goal_against_home 9
## 38 West Ham Utd goal_against_home 8
## 39 Stoke City goal_against_home 9
## 40 Sunderland goal_against_home 9
## 41 Manchester City goal_for_away 9
## 42 Tottenham goal_for_away 7
## 43 Arsenal goal_for_away 8
## 44 Liverpool goal_for_away 9
## 45 Everton goal_for_away 5
## 46 Manchester Utd goal_for_away 5
## 47 Chelsea goal_for_away 6
## 48 Crystal Palace goal_for_away 6
## 49 West Bromwich goal_for_away 3
## 50 Southampton goal_for_away 4
## 51 Watford goal_for_away 5
## 52 Leicester City goal_for_away 3
## 53 Bournemouth goal_for_away 3
## 54 Burnley goal_for_away 0
## 55 Hull City goal_for_away 4
## 56 Middlesbrough goal_for_away 4
## 57 Swansea City goal_for_away 2
## 58 West Ham Utd goal_for_away 4
## 59 Stoke City goal_for_away 3
## 60 Sunderland goal_for_away 2
## 61 Manchester City goal_against_away 5
## 62 Tottenham goal_against_away 2
## 63 Arsenal goal_against_away 2
## 64 Liverpool goal_against_away 8
## 65 Everton goal_against_away 2
## 66 Manchester Utd goal_against_away 4
## 67 Chelsea goal_against_away 6
## 68 Crystal Palace goal_against_away 5
## 69 West Bromwich goal_against_away 3
## 70 Southampton goal_against_away 4
## 71 Watford goal_against_away 5
## 72 Leicester City goal_against_away 10
## 73 Bournemouth goal_against_away 8
## 74 Burnley goal_against_away 6
## 75 Hull City goal_against_away 6
## 76 Middlesbrough goal_against_away 5
## 77 Swansea City goal_against_away 3
## 78 West Ham Utd goal_against_away 9
## 79 Stoke City goal_against_away 7
## 80 Sunderland goal_against_away 4Plot all “for” and “against” goal for both home and away match
ggplot(data = epl_tidy, aes(x = team, y = goals, fill = type))+ geom_bar(stat="identity", position="dodge") + ggtitle("Home and Away Goals") + ylab("Goals") + coord_flip()
##unable to reach a conclusion from the plot, further analysis requiredSeperate “for” goals from “against” and create new tables
“for” table for both home and away match with percent scored at home
epl_pct_home_for <- epl1 %>%
select(team, total_for_home = sum(goal_for_home), total_for_away = sum(goal_for_away)) %>%
mutate(pct_for_home = round(( total_for_home/ (total_for_home + total_for_away)) * 100))
epl_pct_home_for## team total_for_home total_for_away pct_for_home
## 1 Manchester City 9 9 50
## 2 Tottenham 5 7 42
## 3 Arsenal 8 8 50
## 4 Liverpool 9 9 50
## 5 Everton 6 5 55
## 6 Manchester Utd 8 5 62
## 7 Chelsea 6 6 50
## 8 Crystal Palace 5 6 45
## 9 West Bromwich 5 3 62
## 10 Southampton 3 4 43
## 11 Watford 7 5 58
## 12 Leicester City 5 3 62
## 13 Bournemouth 3 3 50
## 14 Burnley 5 0 100
## 15 Hull City 3 4 43
## 16 Middlesbrough 3 4 43
## 17 Swansea City 4 2 67
## 18 West Ham Utd 4 4 50
## 19 Stoke City 2 3 40
## 20 Sunderland 4 2 67Summary of the “for” table
summary(epl_pct_home_for)## team total_for_home total_for_away pct_for_home
## Length:20 Min. :2.00 Min. :0.0 Min. : 40.00
## Class :character 1st Qu.:3.75 1st Qu.:3.0 1st Qu.: 44.50
## Mode :character Median :5.00 Median :4.0 Median : 50.00
## Mean :5.20 Mean :4.6 Mean : 54.45
## 3rd Qu.:6.25 3rd Qu.:6.0 3rd Qu.: 62.00
## Max. :9.00 Max. :9.0 Max. :100.00nrow(filter(epl_pct_home_for, pct_for_home > 50))## [1] 8##8 teams out of 20 scores more than 50% of the goals at home with one team scoring all their goals at homePlot percentage of “for”" scored goal at home
ggplot(data = epl_pct_home_for, aes(x = team, y = pct_for_home, fill = pct_for_home))+ geom_bar(stat="identity", position="dodge") + ggtitle("For Home Goal Percentage") + ylab("Percent")+ coord_flip()
percentage of total “for” goal scored at home by all team
epl_total_pct_home_for <- epl1 %>%
summarise(total_for_home = sum(goal_for_home), total_for_away = sum(goal_for_away)) %>%
mutate(pct_for_home = round(( total_for_home/ (total_for_home + total_for_away)) * 100))
epl_total_pct_home_for## total_for_home total_for_away pct_for_home
## 1 104 92 53##53% of the total "for" goals were scored at home“against” table for both home and away match with percent conceded at home
epl_pct_home_against <- epl1 %>%
select(team, total_against_home = sum(goal_against_home), total_against_away = sum(goal_against_away)) %>%
mutate(pct_against_home = round(( total_against_home/ (total_against_home + total_against_away)) * 100))
epl_pct_home_against## team total_against_home total_against_away
## 1 Manchester City 2 5
## 2 Tottenham 1 2
## 3 Arsenal 5 2
## 4 Liverpool 2 8
## 5 Everton 3 2
## 6 Manchester Utd 4 4
## 7 Chelsea 3 6
## 8 Crystal Palace 3 5
## 9 West Bromwich 4 3
## 10 Southampton 2 4
## 11 Watford 8 5
## 12 Leicester City 1 10
## 13 Bournemouth 3 8
## 14 Burnley 3 6
## 15 Hull City 8 6
## 16 Middlesbrough 5 5
## 17 Swansea City 9 3
## 18 West Ham Utd 8 9
## 19 Stoke City 9 7
## 20 Sunderland 9 4
## pct_against_home
## 1 29
## 2 33
## 3 71
## 4 20
## 5 60
## 6 50
## 7 33
## 8 38
## 9 57
## 10 33
## 11 62
## 12 9
## 13 27
## 14 33
## 15 57
## 16 50
## 17 75
## 18 47
## 19 56
## 20 69Summary of the “against” table
summary(epl_pct_home_against)## team total_against_home total_against_away pct_against_home
## Length:20 Min. :1.00 Min. : 2.00 Min. : 9.00
## Class :character 1st Qu.:2.75 1st Qu.: 3.75 1st Qu.:33.00
## Mode :character Median :3.50 Median : 5.00 Median :48.50
## Mean :4.60 Mean : 5.20 Mean :45.45
## 3rd Qu.:8.00 3rd Qu.: 6.25 3rd Qu.:57.75
## Max. :9.00 Max. :10.00 Max. :75.00nrow(filter(epl_pct_home_against, pct_against_home < 50))## [1] 10##10 out of 20 or 50% of the teams conceded less than 50% of the goals at homePlot percentage of “against” goal conceded at home
ggplot(data = epl_pct_home_against, aes(x = team, y = pct_against_home, fill = pct_against_home))+ geom_bar(stat="identity", position="dodge") + ggtitle("For Home Goal Percentage") + ylab("Percent")+ coord_flip()
epl_total_pct_home_against <- epl1 %>%
summarise(total_against_home = sum(goal_against_home), total_against_away = sum(goal_against_away)) %>%
mutate(pct_against_home = round(( total_against_home/ (total_against_home + total_against_away)) * 100))
epl_total_pct_home_against## total_against_home total_against_away pct_against_home
## 1 92 104 47##47% of the against goals were conceded at homeconclusion: From the data set we can not reach to a strong conclusion that playing at home has significant advatage for the home team
Dataset 2
Citizenship provided by regions, source provided by Jose Zuniga
[Source: Tips for Simplifying Crosstab Query Statements, Rob Gravelle, Database Journal, 2010}
Objective: to compare monthly citizenship for the given regions
##.csv was created and uploaded to Github
Load Data
citizenship <- read.csv("https://raw.githubusercontent.com/choudhury1023/Data-607/gh-pages/monthly_citizenship.csv", header = TRUE, stringsAsFactors = FALSE)
citizenship## Month REGION.1 REGION.2 REGION.3 REGION.4 REGION.5 TOTAL
## 1 April 13 33 76 2 47 171
## 2 May 17 55 209 1 143 425
## 3 June 8 63 221 1 127 420
## 4 July 13 104 240 6 123 486
## 5 August 18 121 274 9 111 533
## 6 September 25 160 239 2 88 514
## 7 October 9 88 295 2 127 521
## 8 November 2 86 292 2 120 502
## 9 December 1 128 232 6 155 522
## 10 TOTAL 106 838 2078 31 1041 4094Tidy wide format data and convert to long format
tidy_citizenship <- citizenship %>%
gather("region","month_total",2:6) %>%
select(Month, region, month_total,TOTAL)
tidy_citizenship## Month region month_total TOTAL
## 1 April REGION.1 13 171
## 2 May REGION.1 17 425
## 3 June REGION.1 8 420
## 4 July REGION.1 13 486
## 5 August REGION.1 18 533
## 6 September REGION.1 25 514
## 7 October REGION.1 9 521
## 8 November REGION.1 2 502
## 9 December REGION.1 1 522
## 10 TOTAL REGION.1 106 4094
## 11 April REGION.2 33 171
## 12 May REGION.2 55 425
## 13 June REGION.2 63 420
## 14 July REGION.2 104 486
## 15 August REGION.2 121 533
## 16 September REGION.2 160 514
## 17 October REGION.2 88 521
## 18 November REGION.2 86 502
## 19 December REGION.2 128 522
## 20 TOTAL REGION.2 838 4094
## 21 April REGION.3 76 171
## 22 May REGION.3 209 425
## 23 June REGION.3 221 420
## 24 July REGION.3 240 486
## 25 August REGION.3 274 533
## 26 September REGION.3 239 514
## 27 October REGION.3 295 521
## 28 November REGION.3 292 502
## 29 December REGION.3 232 522
## 30 TOTAL REGION.3 2078 4094
## 31 April REGION.4 2 171
## 32 May REGION.4 1 425
## 33 June REGION.4 1 420
## 34 July REGION.4 6 486
## 35 August REGION.4 9 533
## 36 September REGION.4 2 514
## 37 October REGION.4 2 521
## 38 November REGION.4 2 502
## 39 December REGION.4 6 522
## 40 TOTAL REGION.4 31 4094
## 41 April REGION.5 47 171
## 42 May REGION.5 143 425
## 43 June REGION.5 127 420
## 44 July REGION.5 123 486
## 45 August REGION.5 111 533
## 46 September REGION.5 88 514
## 47 October REGION.5 127 521
## 48 November REGION.5 120 502
## 49 December REGION.5 155 522
## 50 TOTAL REGION.5 1041 4094Making Month an ordered factor so that ggplot does not rearrnge
tidy_citizenship$Month <- factor(tidy_citizenship$Month, levels = tidy_citizenship$Month)## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecatedPlot data
ggplot(data = tidy_citizenship, aes(x = region, y = month_total, fill = Month))+ geom_bar(stat="identity", position="dodge") + ggtitle("Citizenship by Month") + ylab("Citizenship")## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
Region 3 issues the most citizenzip by far and region 4 issues the least.
Another plot
ggplot(data = tidy_citizenship, aes(x = Month, y = TOTAL, fill = month_total)) + geom_bar(stat="identity", position="dodge") + ggtitle("Citizenship by Month") + ylab("Citizenship")## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
Citizenship issuance is consitant in all five region troughout the given month hovering aroud 420 to 533 with the exception of month of April where citizenship issuance was the least (171).
Dataset 3
Income by Religion, source provided by Marco Siqueira Campos
Objective: Analyse the income by religion
##.csv was created and uploaded to Github
Load Data
income <- read.csv("https://raw.githubusercontent.com/choudhury1023/Data-607/gh-pages/Income_distribution_by_religious_group.csv", header = TRUE, stringsAsFactors = FALSE)
income## Religious.tradition Less.than..30.000 X.30.000..49.999
## 1 Buddhist 36% 18%
## 2 Catholic 36% 19%
## 3 Evangelical Protestant 35% 22%
## 4 Hindu 17% 13%
## 5 Historically Black Protestant 53% 22%
## 6 Jehovah's Witness 48% 25%
## 7 Jewish 16% 15%
## 8 Mainline Protestant 29% 20%
## 9 Mormon 27% 20%
## 10 Muslim 34% 17%
## 11 Orthodox Christian 18% 17%
## 12 Unaffiliated (religious "nones") 33% 20%
## X.50.000..99.999 X.100.000.or.more Sample.Size
## 1 32% 13% 233
## 2 26% 19% 6,137
## 3 28% 14% 7,462
## 4 34% 36% 172
## 5 17% 8% 1,704
## 6 22% 4% 208
## 7 24% 44% 708
## 8 28% 23% 5,208
## 9 33% 20% 594
## 10 29% 20% 205
## 11 36% 29% 155
## 12 26% 21% 6,790Get names of the column
names(income)## [1] "Religious.tradition" "Less.than..30.000" "X.30.000..49.999"
## [4] "X.50.000..99.999" "X.100.000.or.more" "Sample.Size"Rename Columns
income1 <-rename(income, religion = Religious.tradition,smple_size = Sample.Size)
income1## religion Less.than..30.000 X.30.000..49.999
## 1 Buddhist 36% 18%
## 2 Catholic 36% 19%
## 3 Evangelical Protestant 35% 22%
## 4 Hindu 17% 13%
## 5 Historically Black Protestant 53% 22%
## 6 Jehovah's Witness 48% 25%
## 7 Jewish 16% 15%
## 8 Mainline Protestant 29% 20%
## 9 Mormon 27% 20%
## 10 Muslim 34% 17%
## 11 Orthodox Christian 18% 17%
## 12 Unaffiliated (religious "nones") 33% 20%
## X.50.000..99.999 X.100.000.or.more smple_size
## 1 32% 13% 233
## 2 26% 19% 6,137
## 3 28% 14% 7,462
## 4 34% 36% 172
## 5 17% 8% 1,704
## 6 22% 4% 208
## 7 24% 44% 708
## 8 28% 23% 5,208
## 9 33% 20% 594
## 10 29% 20% 205
## 11 36% 29% 155
## 12 26% 21% 6,790names(income1)[2] <- "<30k"
names(income1)[3] <- "30k-49,999"
names(income1)[4] <- "50k-99.999"
names(income1)[5] <- "100k+"
income1## religion <30k 30k-49,999 50k-99.999 100k+
## 1 Buddhist 36% 18% 32% 13%
## 2 Catholic 36% 19% 26% 19%
## 3 Evangelical Protestant 35% 22% 28% 14%
## 4 Hindu 17% 13% 34% 36%
## 5 Historically Black Protestant 53% 22% 17% 8%
## 6 Jehovah's Witness 48% 25% 22% 4%
## 7 Jewish 16% 15% 24% 44%
## 8 Mainline Protestant 29% 20% 28% 23%
## 9 Mormon 27% 20% 33% 20%
## 10 Muslim 34% 17% 29% 20%
## 11 Orthodox Christian 18% 17% 36% 29%
## 12 Unaffiliated (religious "nones") 33% 20% 26% 21%
## smple_size
## 1 233
## 2 6,137
## 3 7,462
## 4 172
## 5 1,704
## 6 208
## 7 708
## 8 5,208
## 9 594
## 10 205
## 11 155
## 12 6,790##I was having problem renaming the column using dplyr, so had use basic r function for part of the renamingTidy data, convert from long format and getting rid of “%” symbol
tidy_income <- income1 %>%
gather("income_bracket", "percentage_raw", 2:5 )%>%
mutate(percentage = as.numeric(gsub("%", "", percentage_raw)))%>%
select(religion, income_bracket, percentage)
tidy_income## religion income_bracket percentage
## 1 Buddhist <30k 36
## 2 Catholic <30k 36
## 3 Evangelical Protestant <30k 35
## 4 Hindu <30k 17
## 5 Historically Black Protestant <30k 53
## 6 Jehovah's Witness <30k 48
## 7 Jewish <30k 16
## 8 Mainline Protestant <30k 29
## 9 Mormon <30k 27
## 10 Muslim <30k 34
## 11 Orthodox Christian <30k 18
## 12 Unaffiliated (religious "nones") <30k 33
## 13 Buddhist 30k-49,999 18
## 14 Catholic 30k-49,999 19
## 15 Evangelical Protestant 30k-49,999 22
## 16 Hindu 30k-49,999 13
## 17 Historically Black Protestant 30k-49,999 22
## 18 Jehovah's Witness 30k-49,999 25
## 19 Jewish 30k-49,999 15
## 20 Mainline Protestant 30k-49,999 20
## 21 Mormon 30k-49,999 20
## 22 Muslim 30k-49,999 17
## 23 Orthodox Christian 30k-49,999 17
## 24 Unaffiliated (religious "nones") 30k-49,999 20
## 25 Buddhist 50k-99.999 32
## 26 Catholic 50k-99.999 26
## 27 Evangelical Protestant 50k-99.999 28
## 28 Hindu 50k-99.999 34
## 29 Historically Black Protestant 50k-99.999 17
## 30 Jehovah's Witness 50k-99.999 22
## 31 Jewish 50k-99.999 24
## 32 Mainline Protestant 50k-99.999 28
## 33 Mormon 50k-99.999 33
## 34 Muslim 50k-99.999 29
## 35 Orthodox Christian 50k-99.999 36
## 36 Unaffiliated (religious "nones") 50k-99.999 26
## 37 Buddhist 100k+ 13
## 38 Catholic 100k+ 19
## 39 Evangelical Protestant 100k+ 14
## 40 Hindu 100k+ 36
## 41 Historically Black Protestant 100k+ 8
## 42 Jehovah's Witness 100k+ 4
## 43 Jewish 100k+ 44
## 44 Mainline Protestant 100k+ 23
## 45 Mormon 100k+ 20
## 46 Muslim 100k+ 20
## 47 Orthodox Christian 100k+ 29
## 48 Unaffiliated (religious "nones") 100k+ 21Making income_bracket an ordered factor so that ggplot does not rearrnge
tidy_income$income_bracket <- factor(tidy_income$income_bracket, levels = tidy_income$income_bracket)## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecatedplot income data by religion
ggplot(data = tidy_income, aes(x = income_bracket, y = percentage, fill = religion))+ geom_bar(stat="identity", position="dodge") + ggtitle("Income by religion") + ylab("percentage")## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
plot income data by religion <30k
ggplot(data = filter(tidy_income, income_bracket %in% c("<30k")), aes(x = income_bracket, y = percentage, fill = religion))+ geom_bar(stat="identity", position="dodge") + ggtitle("Income by religion") + ylab("percentage")## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
Historically Black Protestant has the most representation and Jewish has the least rpresentation in under 30k bracket
plot income data by religion 30k-49,999
ggplot(data = filter(tidy_income, income_bracket %in% c("30k-49,999")), aes(x = income_bracket, y = percentage, fill = religion))+ geom_bar(stat="identity", position="dodge") + ggtitle("Income by religion") + ylab("percentage")## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
Jehovah’s Witness has the most representation and Hindu has the least representaton in 30k-49,999 bracket
plot income data by religion 50k-99.999
ggplot(data = filter(tidy_income, income_bracket %in% c("50k-99.999")), aes(x = income_bracket, y = percentage, fill = religion))+ geom_bar(stat="identity", position="dodge") + ggtitle("Income by religion") + ylab("percentage")## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
Orthodox Christian has the most representation and Historically Black Protestant has the most representation in 50k-99,99 bracket
plot income data by religion 100k+
ggplot(data = filter(tidy_income, income_bracket %in% c("100k+")), aes(x = income_bracket, y = percentage, fill = religion))+ geom_bar(stat="identity", position="dodge") + ggtitle("Income by religion") + ylab("percentage")## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated
## Warning in `levels<-`(`*tmp*`, value = if (nl == nL) as.character(labels)
## else paste0(labels, : duplicated levels in factors are deprecated