data607 project 2
Richard
3/14/2021
Loading Packages
library(tidyverse)## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --## v ggplot2 3.3.3 v purrr 0.3.4
## v tibble 3.0.5 v dplyr 1.0.3
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()Untidy datasets
squirrel_url = "https://raw.githubusercontent.com/schoolkidrich/R/main/DATA%20607/project2/2018_Central_Park_Squirrel_Census_-_Squirrel_Data.csv"
gdp_url = "https://raw.githubusercontent.com/schoolkidrich/R/main/DATA%20607/project2/gdp.csv"
candy_url = "https://raw.githubusercontent.com/schoolkidrich/R/main/DATA%20607/project2/candyhierarchy2017.csv"1) Squirrel dataset
squirrel_df = read.csv(squirrel_url)
head(squirrel_df)## X Y Unique.Squirrel.ID Hectare Shift Date
## 1 -73.95613 40.79408 37F-PM-1014-03 37F PM 10142018
## 2 -73.96886 40.78378 21B-AM-1019-04 21B AM 10192018
## 3 -73.97428 40.77553 11B-PM-1014-08 11B PM 10142018
## 4 -73.95964 40.79031 32E-PM-1017-14 32E PM 10172018
## 5 -73.97027 40.77621 13E-AM-1017-05 13E AM 10172018
## 6 -73.96836 40.77259 11H-AM-1010-03 11H AM 10102018
## Hectare.Squirrel.Number Age Primary.Fur.Color Highlight.Fur.Color
## 1 3
## 2 4
## 3 8 Gray
## 4 14 Adult Gray
## 5 5 Adult Gray Cinnamon
## 6 3 Adult Cinnamon White
## Combination.of.Primary.and.Highlight.Color
## 1 +
## 2 +
## 3 Gray+
## 4 Gray+
## 5 Gray+Cinnamon
## 6 Cinnamon+White
## Color.notes
## 1
## 2
## 3
## 4 Nothing selected as Primary. Gray selected as Highlights. Made executive adjustments.
## 5
## 6
## Location Above.Ground.Sighter.Measurement Specific.Location Running
## 1 FALSE
## 2 FALSE
## 3 Above Ground 10 FALSE
## 4 FALSE
## 5 Above Ground on tree stump FALSE
## 6 FALSE
## Chasing Climbing Eating Foraging Other.Activities Kuks Quaas Moans
## 1 FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## 2 FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## 3 TRUE FALSE FALSE FALSE FALSE FALSE FALSE
## 4 FALSE FALSE TRUE TRUE FALSE FALSE FALSE
## 5 FALSE FALSE FALSE TRUE FALSE FALSE FALSE
## 6 FALSE FALSE FALSE TRUE FALSE FALSE FALSE
## Tail.flags Tail.twitches Approaches Indifferent Runs.from Other.Interactions
## 1 FALSE FALSE FALSE FALSE FALSE
## 2 FALSE FALSE FALSE FALSE FALSE
## 3 FALSE FALSE FALSE FALSE FALSE
## 4 FALSE FALSE FALSE FALSE TRUE
## 5 FALSE FALSE FALSE FALSE FALSE
## 6 FALSE TRUE FALSE TRUE FALSE
## Lat.Long
## 1 POINT (-73.9561344937861 40.7940823884086)
## 2 POINT (-73.9688574691102 40.7837825208444)
## 3 POINT (-73.97428114848522 40.775533619083)
## 4 POINT (-73.9596413903948 40.7903128889029)
## 5 POINT (-73.9702676472613 40.7762126854894)
## 6 POINT (-73.9683613516225 40.7725908847499)There are a lot of unesseccary data and seperate rows for various actions. I will drop columns I think are unessecary and pivot the action colu1ms into one “Action” column
# dropping columns
squirrel_sightings = squirrel_df[c('Unique.Squirrel.ID','Hectare','Shift','Age','Primary.Fur.Color','Running','Chasing','Climbing','Eating','Foraging')]
# pivoting dataframe
squirrel_sightings = squirrel_sightings %>%
pivot_longer(names(squirrel_sightings)[6:dim(squirrel_sightings)[2]], names_to = "Action")
# dropping FALSE (N/A) values
squirrel_clean = squirrel_sightings[squirrel_sightings['value'] == TRUE,]## Warning: The `i` argument of ``[`()` can't be a matrix as of tibble 3.0.0.
## Convert to a vector.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.squirrel_clean = squirrel_clean[names(squirrel_clean)[1:dim(squirrel_clean)[2]-1]]
head(squirrel_clean)## # A tibble: 6 x 6
## Unique.Squirrel.ID Hectare Shift Age Primary.Fur.Color Action
## <chr> <chr> <chr> <chr> <chr> <chr>
## 1 11B-PM-1014-08 11B PM "" Gray Chasing
## 2 32E-PM-1017-14 32E PM "Adult" Gray Eating
## 3 32E-PM-1017-14 32E PM "Adult" Gray Foraging
## 4 13E-AM-1017-05 13E AM "Adult" Gray Foraging
## 5 11H-AM-1010-03 11H AM "Adult" Cinnamon Foraging
## 6 36H-AM-1010-02 36H AM "Adult" Gray ForagingWhat are squirrels at Central Park up to?
squirrel_clean %>%
group_by(Action) %>%
summarise(Percentage = n()/dim(squirrel_clean)[1]) %>%
ggplot(mapping = aes(x = reorder(Action,-Percentage),y = Percentage)) +geom_bar(stat = 'identity') + labs(x = 'Actions', title = "What are Squirrels at Central Park up to?")
Which location has the most squirrels?
squirrel_clean %>%
group_by(Hectare) %>%
summarise(Count = n()) %>%
arrange(desc(Count))%>%
head(10) %>%
ggplot(mapping = aes(x = reorder(Hectare,-Count),y = Count))+geom_bar(stat = 'identity') + labs(x = 'Location', title = 'Locations with the Most Squirrel Sightings')
Conclusion:
Squirrels at central park are usually either looking for or eating food. If you want to see squirrels I suggest you go to location 14E as most of the sightings are from there
2) GDP dataset
gdp_df = read.csv(gdp_url)
head(gdp_df)## Country.Name Country.Code Indicator.Name Indicator.Code X1960 X1961
## 1 Aruba ABW GDP growth (annual %) NY.GDP.MKTP.KD.ZG NA NA
## 2 Afghanistan AFG GDP growth (annual %) NY.GDP.MKTP.KD.ZG NA NA
## 3 Angola AGO GDP growth (annual %) NY.GDP.MKTP.KD.ZG NA NA
## 4 Albania ALB GDP growth (annual %) NY.GDP.MKTP.KD.ZG NA NA
## 5 Andorra AND GDP growth (annual %) NY.GDP.MKTP.KD.ZG NA NA
## 6 Arab World ARB GDP growth (annual %) NY.GDP.MKTP.KD.ZG NA NA
## X1962 X1963 X1964 X1965 X1966 X1967 X1968 X1969 X1970 X1971 X1972
## 1 NA NA NA NA NA NA NA NA NA NA NA
## 2 NA NA NA NA NA NA NA NA NA NA NA
## 3 NA NA NA NA NA NA NA NA NA NA NA
## 4 NA NA NA NA NA NA NA NA NA NA NA
## 5 NA NA NA NA NA NA NA NA NA 4.649465 8.149743
## 6 NA NA NA NA NA NA NA NA NA NA NA
## X1973 X1974 X1975 X1976 X1977 X1978 X1979 X1980
## 1 NA NA NA NA NA NA NA NA
## 2 NA NA NA NA NA NA NA NA
## 3 NA NA NA NA NA NA NA NA
## 4 NA NA NA NA NA NA NA NA
## 5 7.788467 5.61879 0.5422057 3.303787 2.838576 1.4630002 0.04155719 2.208728
## 6 NA NA NA 15.740326 8.243803 -0.6817728 11.68988215 9.082873
## X1981 X1982 X1983 X1984 X1985 X1986 X1987
## 1 NA NA NA NA NA NA 16.0784314
## 2 NA NA NA NA NA NA NA
## 3 -4.4000012 0.000000 4.200001 6.000002 3.499999 2.900002 4.0827486
## 4 5.7456353 2.948597 1.104938 -1.251597 1.780644 5.637243 -0.7878427
## 5 -0.1324745 1.246461 1.770118 1.784687 2.321433 3.253322 5.5471222
## 6 3.0386015 -9.078660 -6.896081 1.326049 -2.366242 4.684686 -0.5397674
## X1988 X1989 X1990 X1991 X1992 X1993 X1994
## 1 18.648649 12.12984055 3.961402 7.9628725 5.882353 7.307692 8.203903
## 2 NA NA NA NA NA NA NA
## 3 6.128890 0.04162146 -3.450099 0.9913593 -5.838281 -23.983417 1.339363
## 4 -1.420040 9.83654897 -9.575640 -28.0021417 -7.187111 9.559412 8.302867
## 5 5.094326 4.82703424 3.781388 2.5460029 0.929212 -1.031484 2.383188
## 6 5.671389 2.37715021 13.126828 1.5030680 4.938746 3.267514 3.203914
## X1995 X1996 X1997 X1998 X1999 X2000 X2001
## 1 2.547144 1.185788 7.046874 1.991986 1.238042 7.616588 -2.971257
## 2 NA NA NA NA NA NA NA
## 3 15.000000 13.544370 7.274277 4.691146 2.181490 3.054624 4.205999
## 4 13.322333 9.099999 -10.919984 8.830088 12.889897 6.950036 8.290070
## 5 2.757499 4.649740 9.067672 3.194790 4.099081 3.528361 8.119358
## 6 2.748955 4.592264 4.224988 5.265799 1.800874 5.496228 1.563740
## X2002 X2003 X2004 X2005 X2006 X2007 X2008
## 1 -3.2736464 1.975547 7.911563 1.214349 1.050608 1.800226 -0.09070805
## 2 NA 8.832278 1.414118 11.229715 5.357403 13.826320 3.92498382
## 3 13.6656865 2.989850 10.952862 15.028915 11.547683 14.010018 11.16613833
## 4 4.5399606 5.530051 5.509999 5.529915 5.900084 5.979982 7.49996956
## 5 4.5463622 8.694204 8.135676 5.397796 4.808689 1.553188 -5.55918637
## 6 0.5699665 5.318673 9.373925 5.747402 6.501691 4.523806 5.81119882
## X2009 X2010 X2011 X2012 X2013 X2014 X2015
## 1 -10.5197485 -3.685029 3.446054750 -1.369863 4.198232 0.300000 5.7000009
## 2 21.3905284 14.362441 0.426354793 12.752287 5.600745 2.724543 1.4513147
## 3 0.8587126 4.403933 3.471976345 8.542188 4.954545 4.822628 0.9435716
## 4 3.3500665 3.706892 2.545321845 1.417526 1.001987 1.774487 2.2187522
## 5 -5.3028465 -1.974958 -0.008069753 -4.974444 -3.547597 2.504466 1.4341404
## 6 0.4199733 4.668194 3.748900536 6.662222 3.287271 2.505076 3.2433121
## X2016 X2017 X2018 X2019 X2020
## 1 2.100000 1.9999991 NA NA NA
## 2 2.260314 2.6470032 1.189228 3.9116034 NA
## 3 -2.580050 -0.1472129 -2.003630 -0.6246443 NA
## 4 3.314805 3.8021975 4.071301 2.2400703 NA
## 5 3.709678 0.3460719 1.588765 1.8492383 NA
## 6 3.507128 0.8208465 2.079469 1.4876330 NAI want to remove rename columns to remove the “X” and then pivot all the year columns into one ‘Year’ column. Afterwards I will remove NA values
# removing "x" from year strings
cols = names(gdp_df)
len = dim(gdp_df)[2]
for (col in cols[5:len]){
cols[cols == col] = substr(col,2,5)
}
names(gdp_df) = cols
# pivoting year columns to a single 'Year' column
gdp_clean = gdp_df %>%
pivot_longer(cols = cols[5:len],names_to = "Year", values_to = 'percent_growth') %>%
drop_na()
# separate df for country codes
country_code = unique(gdp_clean[c('Country.Name','Country.Code')])
# drop unwanted columns from gdp df
gdp_clean = gdp_clean[c('Country.Name','Year','percent_growth')]
head(gdp_clean)## # A tibble: 6 x 3
## Country.Name Year percent_growth
## <chr> <chr> <dbl>
## 1 Aruba 1987 16.1
## 2 Aruba 1988 18.6
## 3 Aruba 1989 12.1
## 4 Aruba 1990 3.96
## 5 Aruba 1991 7.96
## 6 Aruba 1992 5.88Country with the highest change in GDP
gdp_clean %>%
group_by(Country.Name) %>%
summarize(Avg_Growth = sum(percent_growth)/n())%>%
arrange(desc(Avg_Growth)) %>%
head(10) %>%
ggplot(mapping = aes(x = reorder(Country.Name,Avg_Growth),y = Avg_Growth))+geom_bar(stat = 'identity') + coord_flip() +labs(x = 'Countries', title = 'Largest Average Change in GDP (1960-2020)')
Change in GDP (United States) since I was born
# subset df into united states only
us_gdp = gdp_clean[gdp_clean['Country.Name'] == 'United States' & gdp_clean['Year']>= 1997,]
us_gdp %>%
ggplot(mapping = aes(x = Year, y = percent_growth, group = Country.Name))+geom_line() + theme(axis.text.x = element_text(angle = 90)) + labs(title = 'Change in GDP since 1997')
Colclusion
The country with the greatest average growth in GDP is Guinea. This was surprising to me especially since other countries such as China and Japan have grown so much but I believe its because they are a relatively poorer country which means higher potential growth (%) wise.
For the United States, I noticed that growth was more volatile prior to 2011. I also notice a sharp decline in growth leading into 2009 (Great Recession)
3) Candy Dataset
candy_df = read.csv(candy_url)
head(candy_df)## Internal.ID Q1..GOING.OUT. Q2..GENDER Q3..AGE Q4..COUNTRY
## 1 90258773
## 2 90272821 No Male 44 USA
## 3 90272829 Male 49 USA
## 4 90272840 No Male 40 us
## 5 90272841 No Male 23 usa
## 6 90272852 No Male
## Q5..STATE..PROVINCE..COUNTY..ETC Q6...100.Grand.Bar
## 1
## 2 NM MEH
## 3 Virginia
## 4 or MEH
## 5 exton pa JOY
## 6 JOY
## Q6...Anonymous.brown.globs.that.come.in.black.and.orange.wrappers..a.k.a..Mary.Janes.
## 1
## 2 DESPAIR
## 3
## 4 DESPAIR
## 5 DESPAIR
## 6 DESPAIR
## Q6...Any.full.sized.candy.bar Q6...Black.Jacks Q6...Bonkers..the.candy.
## 1
## 2 JOY MEH DESPAIR
## 3
## 4 JOY MEH MEH
## 5 JOY DESPAIR MEH
## 6 JOY
## Q6...Bonkers..the.board.game. Q6...Bottle.Caps Q6...Box.o.Raisins
## 1
## 2 DESPAIR DESPAIR DESPAIR
## 3
## 4 DESPAIR MEH DESPAIR
## 5 DESPAIR MEH DESPAIR
## 6 MEH MEH
## Q6...Broken.glow.stick Q6...Butterfinger Q6...Cadbury.Creme.Eggs
## 1
## 2 DESPAIR DESPAIR MEH
## 3
## 4 DESPAIR MEH MEH
## 5 DESPAIR MEH MEH
## 6 DESPAIR JOY DESPAIR
## Q6...Candy.Corn
## 1
## 2 MEH
## 3
## 4 DESPAIR
## 5 DESPAIR
## 6 MEH
## Q6...Candy.that.is.clearly.just.the.stuff.given.out.for.free.at.restaurants
## 1
## 2 DESPAIR
## 3
## 4 DESPAIR
## 5 DESPAIR
## 6 MEH
## Q6...Caramellos Q6...Cash..or.other.forms.of.legal.tender Q6...Chardonnay
## 1
## 2 MEH JOY MEH
## 3
## 4 MEH JOY MEH
## 5 JOY MEH JOY
## 6 JOY JOY JOY
## Q6...Chick.o.Sticks..we.donÕt.know.what.that.is. Q6...Chiclets
## 1
## 2 DESPAIR DESPAIR
## 3
## 4 JOY MEH
## 5 DESPAIR DESPAIR
## 6 MEH MEH
## Q6...Coffee.Crisp Q6...Creepy.Religious.comics.Chick.Tracts
## 1
## 2 DESPAIR DESPAIR
## 3
## 4 DESPAIR DESPAIR
## 5 MEH DESPAIR
## 6 JOY DESPAIR
## Q6...Dental.paraphenalia Q6...Dots Q6...Dove.Bars Q6...Fuzzy.Peaches
## 1
## 2 DESPAIR MEH JOY DESPAIR
## 3
## 4 DESPAIR JOY JOY MEH
## 5 DESPAIR MEH JOY DESPAIR
## 6 MEH MEH JOY
## Q6...Generic.Brand.Acetaminophen Q6...Glow.sticks Q6...Goo.Goo.Clusters
## 1
## 2 DESPAIR DESPAIR DESPAIR
## 3
## 4 MEH JOY JOY
## 5 DESPAIR DESPAIR MEH
## 6 DESPAIR MEH JOY
## Q6...Good.N..Plenty Q6...Gum.from.baseball.cards Q6...Gummy.Bears.straight.up
## 1
## 2 MEH DESPAIR MEH
## 3
## 4 MEH DESPAIR JOY
## 5 MEH DESPAIR JOY
## 6 MEH DESPAIR MEH
## Q6...Hard.Candy Q6...Healthy.Fruit Q6...Heath.Bar
## 1
## 2 MEH DESPAIR MEH
## 3
## 4 MEH MEH DESPAIR
## 5 MEH DESPAIR DESPAIR
## 6 MEH MEH JOY
## Q6...Hershey.s.Dark.Chocolate Q6...HersheyÕs.Milk.Chocolate
## 1
## 2 JOY JOY
## 3
## 4 MEH MEH
## 5 JOY MEH
## 6 JOY MEH
## Q6...Hershey.s.Kisses Q6...Hugs..actual.physical.hugs.
## 1
## 2 MEH DESPAIR
## 3
## 4 MEH MEH
## 5 MEH DESPAIR
## 6 MEH MEH
## Q6...Jolly.Rancher..bad.flavor. Q6...Jolly.Ranchers..good.flavor.
## 1
## 2 DESPAIR MEH
## 3
## 4 MEH MEH
## 5 MEH JOY
## 6 MEH MEH
## Q6...JoyJoy..Mit.Iodine.. Q6...Junior.Mints Q6...Senior.Mints
## 1
## 2 DESPAIR DESPAIR DESPAIR
## 3
## 4 DESPAIR DESPAIR DESPAIR
## 5 MEH JOY DESPAIR
## 6 JOY
## Q6...Kale.smoothie Q6...Kinder.Happy.Hippo Q6...Kit.Kat Q6...LaffyTaffy
## 1
## 2 DESPAIR DESPAIR JOY DESPAIR
## 3
## 4 DESPAIR MEH MEH JOY
## 5 DESPAIR JOY JOY JOY
## 6 DESPAIR JOY MEH
## Q6...LemonHeads Q6...Licorice..not.black. Q6...Licorice..yes.black.
## 1
## 2 MEH MEH JOY
## 3
## 4 JOY MEH JOY
## 5 JOY MEH DESPAIR
## 6 MEH MEH MEH
## Q6...Lindt.Truffle Q6...Lollipops Q6...Mars Q6...Maynards Q6...Mike.and.Ike
## 1
## 2 MEH DESPAIR DESPAIR DESPAIR MEH
## 3
## 4 JOY DESPAIR JOY MEH MEH
## 5 JOY MEH MEH DESPAIR MEH
## 6 JOY MEH JOY JOY
## Q6...Milk.Duds Q6...Milky.Way Q6...Regular.M.Ms Q6...Peanut.M.MÕs
## 1
## 2 MEH JOY JOY MEH
## 3
## 4 DESPAIR JOY MEH JOY
## 5 MEH JOY JOY JOY
## 6 JOY JOY JOY JOY
## Q6...Blue.M.M.s Q6...Red.M.M.s Q6...Green.Party.M.M.s Q6...Independent.M.M.s
## 1
## 2 JOY JOY JOY JOY
## 3
## 4 MEH MEH MEH MEH
## 5 JOY JOY JOY JOY
## 6 JOY JOY
## Q6...Abstained.from.M.M.ing. Q6...Minibags.of.chips Q6...Mint.Kisses
## 1
## 2 DESPAIR DESPAIR MEH
## 3
## 4 MEH DESPAIR DESPAIR
## 5 MEH DESPAIR JOY
## 6 JOY JOY
## Q6...Mint.Juleps Q6...Mr..Goodbar Q6...Necco.Wafers Q6...Nerds
## 1
## 2 DESPAIR DESPAIR DESPAIR DESPAIR
## 3
## 4 MEH MEH DESPAIR MEH
## 5 JOY MEH DESPAIR JOY
## 6 JOY JOY MEH JOY
## Q6...Nestle.Crunch Q6...Now.n.Laters Q6...Peeps Q6...Pencils Q6...Pixy.Stix
## 1
## 2 JOY DESPAIR DESPAIR DESPAIR DESPAIR
## 3
## 4 MEH MEH DESPAIR DESPAIR DESPAIR
## 5 JOY JOY MEH DESPAIR JOY
## 6 MEH MEH DESPAIR DESPAIR MEH
## Q6...Real.Housewives.of.Orange.County.Season.9.Blue.Ray
## 1
## 2 DESPAIR
## 3
## 4 DESPAIR
## 5 DESPAIR
## 6 DESPAIR
## Q6...ReeseÕs.Peanut.Butter.Cups Q6...Reese.s.Pieces Q6...Reggie.Jackson.Bar
## 1
## 2 JOY JOY DESPAIR
## 3
## 4 JOY MEH MEH
## 5 JOY JOY MEH
## 6 JOY JOY DESPAIR
## Q6...Rolos Q6...Sandwich.sized.bags.filled.with.BooBerry.Crunch Q6...Skittles
## 1
## 2 JOY DESPAIR DESPAIR
## 3
## 4 MEH DESPAIR DESPAIR
## 5 JOY JOY
## 6 JOY DESPAIR JOY
## Q6...Smarties..American. Q6...Smarties..Commonwealth. Q6...Snickers
## 1
## 2 DESPAIR DESPAIR MEH
## 3
## 4 DESPAIR MEH JOY
## 5 JOY DESPAIR
## 6 JOY JOY JOY
## Q6...Sourpatch.Kids..i.e..abominations.of.nature. Q6...Spotted.Dick
## 1
## 2 DESPAIR DESPAIR
## 3
## 4 MEH DESPAIR
## 5 MEH DESPAIR
## 6 DESPAIR DESPAIR
## Q6...Starburst Q6...Sweet.Tarts Q6...Swedish.Fish
## 1
## 2 MEH DESPAIR MEH
## 3
## 4 MEH MEH JOY
## 5 JOY JOY MEH
## 6 MEH MEH MEH
## Q6...Sweetums..a.friend.to.diabetes. Q6...Take.5 Q6...Tic.Tacs
## 1
## 2 DESPAIR DESPAIR DESPAIR
## 3
## 4 MEH JOY MEH
## 5 DESPAIR MEH DESPAIR
## 6 MEH
## Q6...Those.odd.marshmallow.circus.peanut.things Q6...Three.Musketeers
## 1
## 2 DESPAIR JOY
## 3
## 4 DESPAIR DESPAIR
## 5 DESPAIR JOY
## 6 DESPAIR JOY
## Q6...Tolberone.something.or.other Q6...Trail.Mix Q6...Twix
## 1
## 2 JOY DESPAIR JOY
## 3
## 4 JOY MEH JOY
## 5 JOY DESPAIR JOY
## 6 JOY MEH JOY
## Q6...Vials.of.pure.high.fructose.corn.syrup..for.main.lining.into.your.vein
## 1
## 2 DESPAIR
## 3
## 4 DESPAIR
## 5 MEH
## 6 DESPAIR
## Q6...Vicodin Q6...Whatchamacallit.Bars Q6...White.Bread
## 1
## 2 DESPAIR DESPAIR DESPAIR
## 3
## 4 JOY JOY DESPAIR
## 5 JOY JOY DESPAIR
## 6 DESPAIR JOY DESPAIR
## Q6...Whole.Wheat.anything Q6...York.Peppermint.Patties
## 1
## 2 DESPAIR DESPAIR
## 3
## 4 DESPAIR DESPAIR
## 5 DESPAIR JOY
## 6 DESPAIR JOY
## Q7..JOY.OTHER
## 1
## 2 Mounds
## 3
## 4 Reese's crispy crunchy bars, 5th avenue bars, ferrero rocher, dries fruit other than raisins
## 5
## 6
## Q8..DESPAIR.OTHER Q9..OTHER.COMMENTS
## 1
## 2 Bottom line is Twix is really the only candy worth eating.
## 3
## 4 Raisins can go to hell
## 5
## 6
## Q10..DRESS X Q11..DAY Q12..MEDIA..Daily.Dish. Q12..MEDIA..Science.
## 1 NA NA
## 2 White and gold Sunday NA 1
## 3 NA NA
## 4 White and gold Sunday NA 1
## 5 White and gold Friday NA 1
## 6 NA 1
## Q12..MEDIA..ESPN. Q12..MEDIA..Yahoo. Click.Coordinates..x..y.
## 1 NA NA
## 2 NA NA (84, 25)
## 3 NA NA
## 4 NA NA (75, 23)
## 5 NA NA (70, 10)
## 6 NA NA (75, 23)Noticed that there are a lot of characters such as “Q#” and “.” in column names and I want to remove those
length = dim(candy_df)[2]
columns = names(candy_df)
pattern = '^[a-z][0-9]$'
# removing "Q#" from strings
for (column in columns){
new_str = ""
for (item in strsplit(column,"\\.")[[1]]){
if (grepl(pattern, item, ignore.case = TRUE) == FALSE){
new_str = paste(new_str,item)
}
}
columns[columns == column] = trimws(new_str)
}
names(candy_df) = columns
head(candy_df)## Internal ID GOING OUT GENDER AGE COUNTRY STATE PROVINCE COUNTY ETC
## 1 90258773
## 2 90272821 No Male 44 USA NM
## 3 90272829 Male 49 USA Virginia
## 4 90272840 No Male 40 us or
## 5 90272841 No Male 23 usa exton pa
## 6 90272852 No Male
## 100 Grand Bar
## 1
## 2 MEH
## 3
## 4 MEH
## 5 JOY
## 6 JOY
## Anonymous brown globs that come in black and orange wrappers a k a Mary Janes
## 1
## 2 DESPAIR
## 3
## 4 DESPAIR
## 5 DESPAIR
## 6 DESPAIR
## Any full sized candy bar Black Jacks Bonkers the candy
## 1
## 2 JOY MEH DESPAIR
## 3
## 4 JOY MEH MEH
## 5 JOY DESPAIR MEH
## 6 JOY
## Bonkers the board game Bottle Caps Box o Raisins Broken glow stick
## 1
## 2 DESPAIR DESPAIR DESPAIR DESPAIR
## 3
## 4 DESPAIR MEH DESPAIR DESPAIR
## 5 DESPAIR MEH DESPAIR DESPAIR
## 6 MEH MEH DESPAIR
## Butterfinger Cadbury Creme Eggs Candy Corn
## 1
## 2 DESPAIR MEH MEH
## 3
## 4 MEH MEH DESPAIR
## 5 MEH MEH DESPAIR
## 6 JOY DESPAIR MEH
## Candy that is clearly just the stuff given out for free at restaurants
## 1
## 2 DESPAIR
## 3
## 4 DESPAIR
## 5 DESPAIR
## 6 MEH
## Caramellos Cash or other forms of legal tender Chardonnay
## 1
## 2 MEH JOY MEH
## 3
## 4 MEH JOY MEH
## 5 JOY MEH JOY
## 6 JOY JOY JOY
## Chick o Sticks we donÕt know what that is Chiclets Coffee Crisp
## 1
## 2 DESPAIR DESPAIR DESPAIR
## 3
## 4 JOY MEH DESPAIR
## 5 DESPAIR DESPAIR MEH
## 6 MEH MEH JOY
## Creepy Religious comics Chick Tracts Dental paraphenalia Dots Dove Bars
## 1
## 2 DESPAIR DESPAIR MEH JOY
## 3
## 4 DESPAIR DESPAIR JOY JOY
## 5 DESPAIR DESPAIR MEH JOY
## 6 DESPAIR MEH MEH JOY
## Fuzzy Peaches Generic Brand Acetaminophen Glow sticks Goo Goo Clusters
## 1
## 2 DESPAIR DESPAIR DESPAIR DESPAIR
## 3
## 4 MEH MEH JOY JOY
## 5 DESPAIR DESPAIR DESPAIR MEH
## 6 DESPAIR MEH JOY
## Good N Plenty Gum from baseball cards Gummy Bears straight up Hard Candy
## 1
## 2 MEH DESPAIR MEH MEH
## 3
## 4 MEH DESPAIR JOY MEH
## 5 MEH DESPAIR JOY MEH
## 6 MEH DESPAIR MEH MEH
## Healthy Fruit Heath Bar Hershey s Dark Chocolate HersheyÕs Milk Chocolate
## 1
## 2 DESPAIR MEH JOY JOY
## 3
## 4 MEH DESPAIR MEH MEH
## 5 DESPAIR DESPAIR JOY MEH
## 6 MEH JOY JOY MEH
## Hershey s Kisses Hugs actual physical hugs Jolly Rancher bad flavor
## 1
## 2 MEH DESPAIR DESPAIR
## 3
## 4 MEH MEH MEH
## 5 MEH DESPAIR MEH
## 6 MEH MEH MEH
## Jolly Ranchers good flavor JoyJoy Mit Iodine Junior Mints Senior Mints
## 1
## 2 MEH DESPAIR DESPAIR DESPAIR
## 3
## 4 MEH DESPAIR DESPAIR DESPAIR
## 5 JOY MEH JOY DESPAIR
## 6 MEH JOY
## Kale smoothie Kinder Happy Hippo Kit Kat LaffyTaffy LemonHeads
## 1
## 2 DESPAIR DESPAIR JOY DESPAIR MEH
## 3
## 4 DESPAIR MEH MEH JOY JOY
## 5 DESPAIR JOY JOY JOY JOY
## 6 DESPAIR JOY MEH MEH
## Licorice not black Licorice yes black Lindt Truffle Lollipops Mars
## 1
## 2 MEH JOY MEH DESPAIR DESPAIR
## 3
## 4 MEH JOY JOY DESPAIR JOY
## 5 MEH DESPAIR JOY MEH MEH
## 6 MEH MEH JOY MEH JOY
## Maynards Mike and Ike Milk Duds Milky Way Regular M Ms Peanut M MÕs
## 1
## 2 DESPAIR MEH MEH JOY JOY MEH
## 3
## 4 MEH MEH DESPAIR JOY MEH JOY
## 5 DESPAIR MEH MEH JOY JOY JOY
## 6 JOY JOY JOY JOY JOY
## Blue M M s Red M M s Green Party M M s Independent M M s
## 1
## 2 JOY JOY JOY JOY
## 3
## 4 MEH MEH MEH MEH
## 5 JOY JOY JOY JOY
## 6 JOY JOY
## Abstained from M M ing Minibags of chips Mint Kisses Mint Juleps Mr Goodbar
## 1
## 2 DESPAIR DESPAIR MEH DESPAIR DESPAIR
## 3
## 4 MEH DESPAIR DESPAIR MEH MEH
## 5 MEH DESPAIR JOY JOY MEH
## 6 JOY JOY JOY JOY
## Necco Wafers Nerds Nestle Crunch Now n Laters Peeps Pencils Pixy Stix
## 1
## 2 DESPAIR DESPAIR JOY DESPAIR DESPAIR DESPAIR DESPAIR
## 3
## 4 DESPAIR MEH MEH MEH DESPAIR DESPAIR DESPAIR
## 5 DESPAIR JOY JOY JOY MEH DESPAIR JOY
## 6 MEH JOY MEH MEH DESPAIR DESPAIR MEH
## Real Housewives of Orange County Season 9 Blue Ray ReeseÕs Peanut Butter Cups
## 1
## 2 DESPAIR JOY
## 3
## 4 DESPAIR JOY
## 5 DESPAIR JOY
## 6 DESPAIR JOY
## Reese s Pieces Reggie Jackson Bar Rolos
## 1
## 2 JOY DESPAIR JOY
## 3
## 4 MEH MEH MEH
## 5 JOY MEH JOY
## 6 JOY DESPAIR JOY
## Sandwich sized bags filled with BooBerry Crunch Skittles Smarties American
## 1
## 2 DESPAIR DESPAIR DESPAIR
## 3
## 4 DESPAIR DESPAIR DESPAIR
## 5 JOY JOY
## 6 DESPAIR JOY JOY
## Smarties Commonwealth Snickers Sourpatch Kids i e abominations of nature
## 1
## 2 DESPAIR MEH DESPAIR
## 3
## 4 MEH JOY MEH
## 5 DESPAIR MEH
## 6 JOY JOY DESPAIR
## Spotted Dick Starburst Sweet Tarts Swedish Fish
## 1
## 2 DESPAIR MEH DESPAIR MEH
## 3
## 4 DESPAIR MEH MEH JOY
## 5 DESPAIR JOY JOY MEH
## 6 DESPAIR MEH MEH MEH
## Sweetums a friend to diabetes Take 5 Tic Tacs
## 1
## 2 DESPAIR DESPAIR DESPAIR
## 3
## 4 MEH JOY MEH
## 5 DESPAIR MEH DESPAIR
## 6 MEH
## Those odd marshmallow circus peanut things Three Musketeers
## 1
## 2 DESPAIR JOY
## 3
## 4 DESPAIR DESPAIR
## 5 DESPAIR JOY
## 6 DESPAIR JOY
## Tolberone something or other Trail Mix Twix
## 1
## 2 JOY DESPAIR JOY
## 3
## 4 JOY MEH JOY
## 5 JOY DESPAIR JOY
## 6 JOY MEH JOY
## Vials of pure high fructose corn syrup for main lining into your vein
## 1
## 2 DESPAIR
## 3
## 4 DESPAIR
## 5 MEH
## 6 DESPAIR
## Vicodin Whatchamacallit Bars White Bread Whole Wheat anything
## 1
## 2 DESPAIR DESPAIR DESPAIR DESPAIR
## 3
## 4 JOY JOY DESPAIR DESPAIR
## 5 JOY JOY DESPAIR DESPAIR
## 6 DESPAIR JOY DESPAIR DESPAIR
## York Peppermint Patties
## 1
## 2 DESPAIR
## 3
## 4 DESPAIR
## 5 JOY
## 6 JOY
## JOY OTHER
## 1
## 2 Mounds
## 3
## 4 Reese's crispy crunchy bars, 5th avenue bars, ferrero rocher, dries fruit other than raisins
## 5
## 6
## DESPAIR OTHER OTHER COMMENTS
## 1
## 2 Bottom line is Twix is really the only candy worth eating.
## 3
## 4 Raisins can go to hell
## 5
## 6
## Q10 DRESS X Q11 DAY Q12 MEDIA Daily Dish Q12 MEDIA Science
## 1 NA NA
## 2 White and gold Sunday NA 1
## 3 NA NA
## 4 White and gold Sunday NA 1
## 5 White and gold Friday NA 1
## 6 NA 1
## Q12 MEDIA ESPN Q12 MEDIA Yahoo Click Coordinates x y
## 1 NA NA
## 2 NA NA (84, 25)
## 3 NA NA
## 4 NA NA (75, 23)
## 5 NA NA (70, 10)
## 6 NA NA (75, 23)Similar to the last dataset this one is very wide and I want to pivot all the candy columns into one with a rating column that has the values: “MEH”, “JOY”, “DESPAIR”
# pivoting candy data
candy_clean = candy_df %>%
pivot_longer(columns[7:(length-11)],names_to = "Candy", values_to = "Mood")
# Separate out repeated information
candy_id = unique(candy_clean[c('Internal ID','GOING OUT','GENDER','AGE','COUNTRY')])
# Drop columns not needed for analysis
candy_clean = candy_clean[c('Internal ID','Candy','Mood')]
candy_clean = candy_clean[candy_clean["Mood"] != "",]
head(candy_clean)## # A tibble: 6 x 3
## `Internal ID` Candy Mood
## <int> <chr> <chr>
## 1 90272821 100 Grand Bar MEH
## 2 90272821 Anonymous brown globs that come in black and orange wrap~ DESPA~
## 3 90272821 Any full sized candy bar JOY
## 4 90272821 Black Jacks MEH
## 5 90272821 Bonkers the candy DESPA~
## 6 90272821 Bonkers the board game DESPA~Joy vs Despair
candy_clean%>%
group_by(Mood)%>%
summarise(Percent = n()/dim(candy_clean)[1]) %>%
ggplot(mapping = aes(x = Mood, y = Percent)) + geom_bar(stat = 'identity') + labs(title = "")
Which candy do people like the most?
joy = candy_clean[candy_clean['Mood'] == 'JOY',]
joy %>%
group_by(Candy)%>%
summarize(Count = n())%>%
arrange(desc(Count))%>%
head(10) %>%
ggplot(mapping = aes(x = reorder(Candy,Count),y = Count))+geom_bar(stat = 'identity') +coord_flip() + labs(x = 'Candy', title = "Which Candy Brings People Joy?")