posting eda notes

lec02/.Rhistory

@@ -0,0 +1,81 @@
+mpg <- read.csv(file = "https://github.com/math430-lu/data/raw/master/mpg.csv", as.is = TRUE)
+library(ggplot2)
+mpg <- read.csv(file = "https://github.com/math430-lu/data/raw/master/mpg.csv")
+library(ggplot2)
+dim(mpg)
+head(mpg)
+ggplot(data = mpg, mapping = aes(x = weight, y = mpg)) +
+geom_point()
+ggplot(data = mpg, mapping = aes(x = weight, y = mpg)) +
+geom_point() +
+labs(x = "weight (lbs.)", y = "fuel economy (mpg)")
+cor(mpg$weight, mpg$mpg)
+x <- -5:5
+y <- x^2
+cor(x, y)
+ggplot(data = data.frame(x, y), mapping = aes(x, y)) +
+geom_point() +
+geom_smooth(method = "lm", se = FALSE)
+qplot(x3, y3, data = anscombe) +
+xlab("x") + ylab("y") + scale_y_continuous(limits=c(5,13)) +
+annotate("text", label = "r = 0.816", x = 6, y = 12, size = 6)
+qplot(x3, y3, data = filter(anscombe, y3 < 9)) +
+xlab("x") + ylab("y") + scale_y_continuous(limits=c(5,13)) +
+annotate("text", label = "r = 0.999", x = 6, y = 12, size = 6)
+qplot(x3, y3, data = anscombe) +
+xlab("x") + ylab("y") + scale_y_continuous(limits=c(5,13)) +
+annotate("text", label = "r = 0.816", x = 6, y = 12, size = 6)
+qplot(x3, y3, data = subset(anscombe, y3 < 9)) +
+xlab("x") + ylab("y") + scale_y_continuous(limits=c(5,13)) +
+annotate("text", label = "r = 0.999", x = 6, y = 12, size = 6)
+grid.arrange(p1, p2, nrow = 1)
+qplot(x3, y3, data = anscombe) +
+xlab("x") + ylab("y") + scale_y_continuous(limits=c(5,13)) +
+annotate("text", label = "r = 0.816", x = 6, y = 12, size = 6)
+qplot(x3, y3, data = subset(anscombe, y3 < 9)) +
+xlab("x") + ylab("y") + scale_y_continuous(limits=c(5,13)) +
+annotate("text", label = "r = 0.999", x = 6, y = 12, size = 6)
+library(gridExtra)
+p1 <- qplot(x3, y3, data = anscombe) +
+xlab("x") + ylab("y") + scale_y_continuous(limits=c(5,13)) +
+annotate("text", label = "r = 0.816", x = 6, y = 12, size = 6)
+p2 <- qplot(x3, y3, data = subset(anscombe, y3 < 9)) +
+xlab("x") + ylab("y") + scale_y_continuous(limits=c(5,13)) +
+annotate("text", label = "r = 0.999", x = 6, y = 12, size = 6)
+grid.arrange(p1, p2, nrow = 1)
+1:10
+# You will need to load the package in each R markdown notebook
+library(tidyverse)
+# Load the data and assign it a name
+mpg <- read.csv("https://github.com/math430-lu/data/raw/master/mpg.csv")
+# Printing the first 6 rows
+# Note that missing values are denoted by NA
+head(mpg)
+# Printing the last 6 rows
+tail(mpg)
+# Looking at the number of rows and columns
+dim(mpg)
+# Looking at the structure
+str(mpg)
+# Getting a glimpse of the structure
+glimpse(mpg)
+# looking at the summary
+summary(mpg)
+ggplot(data = mpg, mapping = aes(x = weight, y = mpg)) +
+geom_point() +
+labs(x = "weight (lbs.)", y = "fuel economy (mpg)")
+cor(mpg$weight, mpg$mpg)
+x <- -5:5
+y <- x^2
+cor(x, y)
+ggplot(data = data.frame(x, y), mapping = aes(x, y)) +
+geom_point() +
+geom_smooth(method = "lm", se = FALSE)
+library(gridExtra)
+p1 <- qplot(x3, y3, data = anscombe) +
+xlab("x") + ylab("y") + scale_y_continuous(limits=c(5,13)) +
+annotate("text", label = "r = 0.816", x = 6, y = 12, size = 6)
+p2 <- qplot(x3, y3, data = subset(anscombe, y3 < 9)) +
+xlab("x") + ylab("y") + scale_y_continuous(limits=c(5,13)) +
+annotate("text", label = "r = 0.999", x = 6, y = 12, size = 6)
+grid.arrange(p1, p2, nrow = 1)