initial commit

Author: DoubleD1994

.DS_Store

@@ -0,0 +1,33 @@
+"Name","Transmission","Cylinders","Fuel.Economy"
+"Mazda RX4","Manual",6,21
+"Mazda RX4 Wag","Manual",6,21
+"Datsun 710","Manual",4,22.8
+"Hornet 4 Drive","Automatic",6,21.4
+"Hornet Sport","Automatic",8,18.7
+"Valiant","Automatic",6,18.1
+"Duster 360","Automatic",8,14.3
+"Merc 240D","Automatic",4,24.4
+"Merc 230","Automatic",4,22.8
+"Merc 280","Automatic",6,19.2
+"Merc 280C","Automatic",6,17.8
+"Merc 450SE","Automatic",8,16.4
+"Merc 450SL","Automatic",8,17.3
+"Merc 450SLC","Automatic",8,15.2
+"Cadillac Fleetwood","Automatic",8,10.4
+"Lincoln Continental","Automatic",8,10.4
+"Chrysler Imperial","Automatic",8,14.7
+"Fiat 128","Manual",4,32.4
+"Honda Civic","Manual",4,30.4
+"Toyota Corolla","Manual",4,33.9
+"Toyota Corona","Automatic",4,21.5
+"Dodge Challenger","Automatic",8,15.5
+"AMC Javelin","Automatic",8,15.2
+"Camaro Z28","Automatic",8,13.3
+"Pontiac Firebird","Automatic",8,19.2
+"Fiat X1-9","Manual",4,27.3
+"Porsche 914-2","Manual",4,26
+"Lotus Europa","Manual",4,30.4
+"Ford Pantera L","Manual",8,15.8
+"Ferrari Dino","Manual",6,19.7
+"Maserati Bora","Manual",8,15
+"Volvo 142E","Manual",4,21.4

Cars.csv

@@ -0,0 +1,50 @@
+# Creating Statistical Model
+
+# Set working directory
+setwd("/Users/daviddryburgh/Documents/R_Programming")
+
+# Load CSV file
+iris <- read.csv("Iris.csv")
+
+# Peak at data
+head(iris)
+
+# Create a scatterplot
+plot(
+  x = iris$Petal.Length,
+  y = iris$Petal.Width,
+  main = "Iris Petal Length vs. Width",
+  xlab = "Petal Length (cm)",
+  ylab = "Petal width (cm)"
+)
+
+# Create a linear regression model
+model <- lm(
+  formula = Petal.Width ~ Petal.Length,
+  data = iris
+)
+
+# Summarize the model
+summary(model)
+
+# Draw a regression line on plot
+lines(
+  x = iris$Petal.Length,
+  y = model$fitted,
+  col = "red",
+  lwd = 3
+)
+
+# Get correlation coefficient
+cor(
+  x = iris$Petal.Length,
+  y = iris$Petal.Width
+)
+
+# Predict new values from the model
+predict(
+  object = model,
+  newdata = data.frame(
+    Petal.Length = c(2, 5, 7)
+  )
+)

CreateStatisticalModels.R

@@ -0,0 +1,52 @@
+#Creating Data Visualisation
+
+# Set the working directory
+setwd("/Users/daviddryburgh/Documents/R_Programming")
+
+# Read the CSV file
+cars <- read.csv("Cars.csv")
+
+# Load the ggplot2 library
+library(ggplot2)
+
+# Create a frequency bar chart
+ggplot(
+  data = cars,
+  aes(x = Transmission)) +
+  geom_bar() +
+  ggtitle("Count of Cars by Transmission Type") + 
+  xlab("Transmission Type") +
+  ylab("Count of Cars")
+
+# Create a histogram
+ggplot(
+  data = cars,
+  aes(x = Fuel.Economy)) +
+  geom_histogram(
+    bins = 10
+  ) +
+  ggtitle("Distribution of Fuel Economy") + 
+  xlab("Fuel Economy") +
+  ylab("Count of Cars")
+
+# Create a density plot
+ggplot(
+  data = cars,
+  aes(x = Fuel.Economy)) +
+  geom_density() +
+  ggtitle("Distribution of Fuel Economy") + 
+  xlab("Fuel Economy (mpg)") +
+  ylab("Density")
+
+# Create a scatterplot
+ggplot(
+  data = cars,
+  aes(
+    x = Cylinders,
+    y = Fuel.Economy)) +
+  geom_point() +
+  ggtitle("Fuel Economy by Cylinders") + 
+  xlab("Number of Cylinders") +
+  ylab("Fuel Economy (mpg)")
+
+

CreatingDataVisualisations.R

@@ -0,0 +1,42 @@
+# Creating Data Visualization
+
+# Set the working directory
+setwd("/Users/daviddryburgh/Documents/R_Programming")
+
+# Read the CSV file
+cars <- read.csv("Cars.csv")
+
+# Peek at the data
+head(cars)
+
+# Create a frequency table
+table(cars$Transmission)
+
+# Get the minimum value
+min(cars$Fuel.Economy)
+
+# Get the maximum value
+max(cars$Fuel.Economy)
+# Get the average vale
+mean(cars$Fuel.Economy)
+
+# Get the median value
+median(cars$Fuel.Economy)
+
+# Get the quartiles
+quantile(cars$Fuel.Economy)
+
+# Get the standard deviation
+sd(cars$Fuel.Economy)
+
+# Get the total value
+sum(cars$Fuel.Economy)
+
+# Get the correlation coefficient
+cor(
+  x = cars$Cylinders,
+  y = cars$Fuel.Economy
+)
+
+# Summarize and entire table
+summary(cars)

CreatingDescriptiveStatistics.R

@@ -0,0 +1,4 @@
+"Cylinders","Avg.Consumption"
+4,9.7325
+6,8.128125
+8,6.39625

Fuel Efficiency.csv

@@ -0,0 +1,65 @@
+# Handling Big Data
+
+# set working directory
+setwd("/Users/daviddryburgh/Documents/R_Programming")
+
+# Load the ff package
+library(ff)
+
+# Read a CSV file as ff data frame
+irisff <- read.table.ffdf(
+  file = "Iris.csv",
+  FUN = "read.csv"
+)
+
+# Inspect the class
+class(irisff)
+
+# Inspect the column names
+names(irisff)
+
+# Inspect the first few rows
+irisff[1:5,]
+
+# Load the biglm package
+library(biglm)
+
+model <- biglm(
+  formula = Petal.Width ~ Petal.Length,
+  data = irisff
+)
+
+# Summarize the model
+summary(model)
+
+# Create a scatterplot
+plot(
+  x = irisff$Petal.Length[],
+  y = irisff$Petal.Width[],
+  main = "Iris Petal Length vs. Width",
+  xlab = "Petal Length(cm)",
+  ylab = "Petal Width (cm)"
+)
+
+# Get y-intercept from model
+b <- summary(model)$mat[1,1]
+
+# Get slope from model
+m <- summary(model)$mat[2,1]
+
+# Draw a regression line on plot
+lines(
+  x = irisff$Petal.Length[],
+  y = m * irisff$Petal.Length[] + b,
+  col = "red",
+  lwd = 3
+)
+
+# Predict new values with the model
+predict(
+  object = model,
+  newdata = data.frame(
+    Petal.Length = c(2, 5, 7),
+    Petal.Width = c(0, 0, 0)
+  )
+)

HandlingBigData.R

@@ -0,0 +1,5 @@
+# Assign a character string to a variable
+x <- "Hello World!"
+
+#Print the variable
+prit(x)