Unit 3.Rmd

---
title: "Unit 3 backup"
output: html_document
editor_options: 
  chunk_output_type: console
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

## R Markdown

```

# Install packages and libraries used
# install.packages("GGally")
library(GGally)
library(tidyverse)

# library(ggplot2)
# library(lubridate)

# Import CSV file for FIFA data
fifa = read.csv(file="03-School/DS 6306/Unit3/FIFA Players.csv", header=TRUE, sep=",")

# Create only Left Mid-fielder and Left Forward data only
LMLF <- fifa %>% filter(Position == "LF" | Position == "LM")

# LMLF$Position = as.factor(as.character(LMLF$Position))

# LMLF<-as.data.frame(LMLF)
# summary(LMLF$Position)
# class(LMLF$Position)

LMLF %>% select(Acceleration, Agility, Position) %>% ggpairs(aes(color = Position))


# LMLF %>% select(Acceleration, Agility) %>% ggpairs()


# Filter by individual position of either Left Mid-fielder or Left Forward
LM <- LMLF %>% filter(Position == "LM")
LF <- LMLF %>% filter(Position == "LF")

# Compute the mean, standard deviation and count for Left Forwards
MALF <- fifa %>%
filter(Position == "LF") %>%
summarize(mean = mean(Agility), sd = sd(Agility), count = n())

# Compute the mean, standard deviation and count for Left Mid-fielders
MALM <- fifa %>%
filter(Position == "LM") %>%
summarize(mean = mean(Agility), sd = sd(Agility), count = n())

# Create only the agility values of each position
LMAgility <- LM$Agility
LFAgility <- LF$Agility

# Create histograms for each position LF or LM

hist(LFAgility, col = "firebrick3")
hist(LMAgility, col = "skyblue2")


############################################################

# Import car data
cars = mtcars %>% rownames_to_column()

# Calculate the expected elapsed time
Expected <- cars %>% mutate(expect = (6.290*'^'((wt*1000 / hp),1/3)))

# Plot the first graph showing the data and performance ratio
Expected %>% ggplot(aes(x = expect, y = qsec)) + geom_point() + geom_smooth(method = "lm") + ggtitle("Plot of Calculated E.T. vs Observed E.T.") +
xlab("Calculated Elapsed Time") + ylab("Observed Elapsed Time")

# Begin to see if the car will be over performing (fast) or under performing (slower)
performance <- Expected %>% mutate(perfratio = expect / qsec)

# Show a histogram of performance ratio
hist(performance$perfratio, col = "red") 

# compute the breaks / cuts in the data for slower than expected, expected and faster than expected
performance <- performance %>%
mutate(perfcar = cut(perfratio, breaks = c(0,0.97,1.03,2), labels =
c("Slower Performance","Expected", "Faster Peformance"))) 

# plot the new data points with slow, expected and faster
performance %>% ggplot(aes(x = expect, y = qsec, fill = perfcar)) + geom_point() + geom_smooth(method = "lm") + ggtitle("Plot of Calculated E.T. vs Observed E.T.") +
xlab("Calculated Elapsed Time") + ylab("Observed Elapsed Time")

# plot the performance vs cylinders
performance %>%
ggplot(aes(x = perfcar, y = cyl)) +
geom_boxplot(fill='lightblue', color="darkred")

# plot the performance vs carburetors
performance %>%
ggplot(aes(x = perfcar, y = carb)) +
geom_boxplot(fill='lightblue', color="darkred")

```