Part 1: Temperature Analysis (15 total points)

 

1.1 Create initial data frame

date <- c(as.Date("9/24/2016","%m/%d/%Y"),
          as.Date("9/25/2016","%m/%d/%Y"),
          as.Date("9/26/2016","%m/%d/%Y"),
          as.Date("9/27/2016","%m/%d/%Y"),
          as.Date("9/28/2016","%m/%d/%Y"),
          as.Date("9/29/2016","%m/%d/%Y"),
          as.Date("9/30/2016","%m/%d/%Y"))

nash_temp <- c(92,94,78,79,84,67,68)
tor_temp <- c(18,16,19,21,21,19,18)
temp.diff.df <- data.frame(date,nash_temp,tor_temp)

# View(temp.diff.df)

 

1.2 Add to existing data frame

temp.diff.df <- mutate(temp.diff.df,
                       tor_temp_f = tor_temp * 1.8 + 32,
                       temp_diff = nash_temp - tor_temp_f,
                       pct_temp_diff = temp_diff/tor_temp_f)

# View(temp.diff.df)


# Do not modify the following code:
knitr::kable(temp.diff.df, format = "markdown")
date nash_temp tor_temp tor_temp_f temp_diff pct_temp_diff
2016-09-24 92 18 64.4 27.6 0.4285714
2016-09-25 94 16 60.8 33.2 0.5460526
2016-09-26 78 19 66.2 11.8 0.1782477
2016-09-27 79 21 69.8 9.2 0.1318052
2016-09-28 84 21 69.8 14.2 0.2034384
2016-09-29 67 19 66.2 0.8 0.0120846
2016-09-30 68 18 64.4 3.6 0.0559006

 

1.3 Calculate mean percentage difference

avg = round(mean(temp.diff.df$pct_temp_diff) *100,digits=4)
avg
## [1] 22.23

The mean temperature difference was 22.23%.

 

1.4 Plot the percent difference per day

ggplot(temp.diff.df, aes(x=date,y=pct_temp_diff)) +
  geom_bar(stat="identity",color="black", fill="gray")+
  labs(x="date", y="Percent Defference",
       title= "Nashville vs Toronto Temperature")

maxDiff = max(temp.diff.df$pct_temp_diff)
highestDate = subset(temp.diff.df,pct_temp_diff==maxDiff,select = date)

The percent difference was greatest on 2016-09-25.

 

Part 2: Analysis of Fish Data (35 total points)

 

2.1 Import the data

fish <- read.csv("https://ww2.amstat.org/publications/jse/datasets/fishcatch.dat.txt",
                          header = FALSE, 
                          sep = '')
colnames(fish) <- c('obs', 'species', 'weight', 'len1', 'len2', 'len3', 'height.pct', 'width.pct', 'sex')
# View(fish)

 

2.2 Change ‘sex’ to be a factor

fish$sex <- factor(fish$sex, labels = c("female","male"))

 

2.3 Change ‘species’ to be a factor and add labels

fish$species <- factor(fish$species, labels = c(
  'Common Bream','Whitefish','Roach','Silver Bream','Smelt','Pike','Perch')
)


# Do not modify the following code:
fish.sub <- filter(fish, sex != "NA")
knitr::kable(head(fish.sub), format = "markdown")
obs species weight len1 len2 len3 height.pct width.pct sex
14 Common Bream NA 29.5 32 37.3 37.3 13.6 male
15 Common Bream 600 29.4 32 37.2 40.2 13.9 male
17 Common Bream 700 30.4 33 38.3 38.8 13.8 male
21 Common Bream 575 31.3 34 39.5 38.3 14.1 male
26 Common Bream 725 31.8 35 40.9 40.0 14.8 male
30 Common Bream 1000 33.5 37 42.6 44.5 15.5 female

 

2.4 Determine mean weight for each species

by_species <- group_by(fish,species)
mean.wt <- summarise(by_species,
                   average.weight = mean(weight, na.rm = TRUE)
                  )

minWeight <- min(mean.wt$average.weight)

minspecies <- subset(mean.wt,average.weight == minWeight)[,1]




# Do not modify the following code:
knitr::kable(mean.wt, format = "markdown")
species average.weight
Common Bream 626.00000
Whitefish 531.00000
Roach 152.05000
Silver Bream 154.81818
Smelt 11.17857
Pike 718.70588
Perch 382.23929

The species with the smallest mean weight is Smelt with a weight of 11.1785714g.

 

2.5 Plot the mean weights for each species

ggplot(mean.wt, aes(x=species,y=average.weight)) +
  geom_bar(stat="identity",color="black", fill="gray")+
  labs(x="Species", y="Weight",
       title= "Mean Weight per Species")

maxDiff = max(temp.diff.df$pct_temp_diff)
highestDate = subset(temp.diff.df,pct_temp_diff==maxDiff,select = date)

mean.wt
## # A tibble: 7 × 2
##        species average.weight
##         <fctr>          <dbl>
## 1 Common Bream      626.00000
## 2    Whitefish      531.00000
## 3        Roach      152.05000
## 4 Silver Bream      154.81818
## 5        Smelt       11.17857
## 6         Pike      718.70588
## 7        Perch      382.23929

 

Part 3: Analysis of Forbes Global 2000 Data (50 total points)

 

3.1 Import the dataset

library(readr)
library(dplyr)

Forbes <- read_csv("2014 Forbes Global 2000.csv")
## Parsed with column specification:
## cols(
##   Rank = col_integer(),
##   Company = col_character(),
##   Sector = col_character(),
##   Industry = col_character(),
##   Continent = col_character(),
##   Country = col_character(),
##   Sales = col_double(),
##   Profits = col_double(),
##   Assets = col_double(),
##   Market_Value = col_double()
## )

 

3.2 Exclude specified records

Forbes <-
  filter(Forbes,is.na(Forbes$Sector)==FALSE,Sales!=0)

 

3.3 Convert four variables to factors

Forbes$Sector <- factor(Forbes$Sector)
Forbes$Industry <- factor(Forbes$Industry)
Forbes$Continent <- factor(Forbes$Continent)
Forbes$Country <- factor(Forbes$Country)

 

3.4 Create mosaic plot

# ggplot(data = Forbes) +
#   geom_mosaic(aes(x=Sector,y=Continent))

SectorContinent <- table(Forbes$Sector, Forbes$Continent)
mosaicplot(SectorContinent, color = c("red","green","blue","yellow","brown","purple"), main = "Sector by Continent")

Forbes.CC <- Forbes %>%
  dplyr::select(Sector) %>%
  group_by(Sector) %>%
  summarise(CompanyCount = n()) 


answer1 <- subset(Forbes.CC,CompanyCount==max(Forbes.CC$CompanyCount))[,1]

Forbes.NACC <- Forbes %>%
  dplyr::select(Sector,Continent) %>%
  group_by(Sector) %>%
  filter(Continent == "North America") %>%
  summarise(CompanyCount = n()) 

answer2 <- subset(Forbes.NACC,CompanyCount == max(Forbes.NACC$CompanyCount))[,1]

The Financials sector contains the largest number of companies.
North America’s largest sector (in terms of the number of companies) is Financials.

 

3.5 Create Profit Margin variable

Forbes <- mutate(Forbes, ProfMgn = Profits/Sales)


# Do not modify the following code:
knitr::kable(head(Forbes), format = "markdown")
Rank Company Sector Industry Continent Country Sales Profits Assets Market_Value ProfMgn
1 ICBC Financials Major Banks Asia China 148.7 42.7 3124.9 215.6 0.2871553
2 China Construction Bank Financials Regional Banks Asia China 121.3 34.2 2449.5 174.4 0.2819456
3 Agricultural Bank of China Financials Regional Banks Asia China 136.4 27.0 2405.4 141.1 0.1979472
4 JPMorgan Chase Financials Major Banks North America United States 105.7 17.3 2435.3 229.7 0.1636708
5 Berkshire Hathaway Financials Investment Services North America United States 178.8 19.5 493.4 309.1 0.1090604
6 Exxon Mobil Energy Oil & Gas Operations North America United States 394.0 32.6 346.8 422.3 0.0827411

 

3.6 Create boxplot of Profit Margin by Sector

p <- ggplot(Forbes, aes(Sector,ProfMgn)) 
  p + coord_flip() +  geom_boxplot()

The sector that appears to have the greatest standard deviation is Consumer Discretionary.

 

3.7 Calculate the SD for each sector

Forbes.SD <- Forbes %>%
  dplyr::select(Sector,ProfMgn) %>%
  group_by(Sector) %>%
  # filter(Year.Built >= 2000) %>%
  # mutate(totalObs = 93) %>%
  summarise(StDev = sd(ProfMgn)) #%>%
  # filter(count >= 10) %>%
  # arrange(desc(meanPricePerSqFt))

SDanswer <- subset(Forbes.SD, StDev == max(Forbes.SD$StDev))[,1]

# Do not modify the following code:
knitr::kable(Forbes.SD, format = "markdown")
Sector StDev
Consumer Discretionary 0.6289455
Consumer Staples 0.1000578
Energy 0.1058560
Financials 0.4052307
Health Care 0.1074421
Industrials 0.0993903
Information Technology 0.2345233
Materials 0.2154817
Telecommunication Services 0.1022383
Utilities 0.1623265

The sector that has the greatest standard deviation is Consumer Discretionary. Consumer Discretionary looks to have one strong outlier that pulls that standard deviation above the Financials sector.