--- title: "Homework Chapter 10" author: "Dr. Paul Pearson" date: "2024-11-01" output: html_document --- ```{r setup, include=FALSE} knitr::opts_chunk$set(echo = TRUE, comment = "", warning = FALSE, message = FALSE) library(ggplot2) # ggsave(ggplot_object) can save svg files without xml annotations library(BrailleR) # VI(ggplot_object) for annotations for in text graph annotations # MakeAccessibleSVG(ggplot_object) to save accessible standalone html (=svg + xml annotations) library(tactileR) # Use braille in graphs for embossed printing # brl_begin(file='tactile_histogram_SWL.pdf', pt=14, paper='special', font='SWL') # base or lattice plot code here # brl_end() library(infer) #library(tibble) library(tidyr) # for reshaping data, etc. library(car) # for fancy scatterplots set.seed(1) options(digits = 4) ``` # Define helper functions ```{r} make_graphs <- function(df, explanatory, response, title_string, xlab_string, ylab_string, filename) { formula_string <- paste(substitute(response), "~", substitute(explanatory)) # winner: https://win-vector.com/2019/07/06/programming-over-lm-in-r/ # https://stackoverflow.com/questions/27261232/passing-argument-to-lm-in-r-within-function model <- eval(bquote( lm( as.formula(formula_string), data = df) )) # ggplot scatterplot without line sp <- ggplot(df, aes( x = {{ explanatory }}, y = {{ response }} )) + geom_point(size = 4) + ggtitle( title_string ) + xlab( xlab_string ) + ylab( ylab_string ) + theme_bw(base_size = 18) print(sp) # generates both graph and VI(ts) automatically # ggplot scatterplot with line sp <- sp + geom_smooth(method='lm', se=FALSE, size=2, color = "black") print(sp) # generates both graph and VI(ts) automatically MakeAccessibleSVG.ggplot(sp, file = paste0("reader-", filename)) # tactile scatterplot with no line brl_begin(paste0( 'tactile-', filename, '-scatterplot.pdf'), pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') # to get the variable values, use data[[substitute(varname)]] instead of data$varname plot(df[[substitute(explanatory)]], df[[substitute(response)]], main = title_string, xlab = xlab_string, ylab = ylab_string ) brl_end() # tactile scatterplot with line brl_begin(paste0( 'tactile-', filename, '-scatterplot-and-line.pdf'), pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') # to get the variable values, use data[[substitute(varname)]] instead of data$varname plot(df[[substitute(explanatory)]], df[[substitute(response)]], main = title_string, xlab = xlab_string, ylab = ylab_string ) abline( model, col = "black", lwd = 3 ) brl_end() # tactile scatterplot with line and ellipses and boxplots brl_begin(paste0( 'tactile-', filename, '-scatterplot-and-line-and-ellipses-and-boxplots.pdf'), pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') scatterplot( as.formula(formula_string), data = df, main = title_string, xlab = xlab_string, ylab = ylab_string, pch = 16, cex = 2, col = "black", smooth = FALSE, grid = FALSE, frame = TRUE, ellipse = list(levels=c(.25, .75), robust=TRUE, fill=FALSE, fill.alpha=0, lwd = 3) ) brl_end() } ``` # HW 10.1.1 ```{r} hike <- read.table(text= "distance_mi time_min 0.6097186336 20.32467532 0.9050679996 30.35714286 1.013197929 40.98678108 1.510114442 60.29637592 1.509591285 45.40584416 1.80488472 60.28733766 2.107534689 60.43194981 2.211915266 90.18752081 2.560801906 89.99002023 2.512130856 60.29637592 2.812892859 89.99458874 3.009500625 89.99458874 3.208011736 90.12263075 3.453380132 90.16378711 3.803841346 119.8133117 4.009197009 149.9107143 4.010004961 120.1477273 4.557401918 120.1099707 4.61306372 149.9107143 5.013472219 149.9107143 5.513155229 180.0081169 5.567220817 149.9107143 5.800632131 180.0081169 6.01152509 180.0081169 7.010177463 179.882711 7.41944808 419.1152597 9.516062599 299.5616883", header=TRUE, check.names=FALSE) #print(hike, row.names=FALSE) ``` ```{r, fig.cap="This scatter plot has title ‘Hiking distance versus time’ with x-axis ‘distance (miles)’ that has values from 0 to 10, and y-axis ‘time (minutes)’ with values from 0 to 400. There are 27 big solid circle points. The points are concentrated tightly around a straight path (except for one outlier) that is increasing at a constant rate of about 30 minutes for every mile."} make_graphs( df = hike, explanatory = distance_mi, response = time_min, title = "HW 10.1 #1 hiking distance vs time", xlab_string = "distance (miles)", ylab_string = "time (minutes)", filename = "HW_10.1.1" ) ``` ```{r, echo=FALSE, fig.cap="This scatter plot has title ‘Hiking distance versus time’ with x-axis ‘distance (miles)’ that has values from 0 to 10, and y-axis ‘time (minutes)’ with values from 0 to 400. There are 27 big solid circle points. The points are concentrated tightly around a straight path (except for one outlier) that is increasing at a constant rate of about 30 minutes for every mile."} # time series plot sp <- ggplot(hike, aes(distance_mi, time_min)) + geom_point(size = 4) + ggtitle("HW 10.1 #1: Hiking distance versus time") + xlab("Distance (miles)") + ylab("Time (minutes)") + theme_bw(base_size = 18) sp # generates both graph and VI(ts) automatically lm(time_min ~ distance_mi, hike) ``` ```{r, echo=FALSE, fig.cap="This scatter plot has title ‘Hiking distance versus time’ with x-axis ‘distance (miles)’ that has values from 0 to 10, and y-axis ‘time (minutes)’ with values from 0 to 400. There are 27 big solid circle points. The points are concentrated tightly around a straight path (except for one outlier) that is increasing at a constant rate of about 30 minutes for every mile. The graph also has a line of best fit."} # time series plot sp <- ggplot(hike, aes(distance_mi, time_min)) + geom_point(size = 4) + ggtitle("HW 10.1 #1: Hiking distance versus time") + xlab("Distance (miles)") + ylab("Time (minutes)") + theme_bw(base_size = 18) + geom_smooth(method='lm', se=FALSE, size=2, color = "black") sp # generates both graph and VI(ts) automatically lm(time_min ~ distance_mi, hike) ``` ```{r, include=FALSE, fig.cap="This scatter plot has title ‘Hiking distance versus time’ with x-axis ‘distance (miles)’ that has values from 0 to 10, and y-axis ‘time (minutes)’ with values from 0 to 400. There are 27 big solid circle points. The points are concentrated tightly around a straight path (except for one outlier) that is increasing at a constant rate of about 30 minutes for every mile."} #MakeAccessibleSVG.ggplot(sp, file = "reader-HW_10_1_1") ``` ```{r, include=FALSE} # brl_begin('tactile-HW_10_1_1_scatterplot.pdf', # pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') # plot(hike$distance_mi, # hike$time_min, # main = "HW 10.1.1 hiking distance vs time", # xlab = "Distance (miles)", # ylab = "Time (minutes)"#, # #ylim = c(0,0.5) # #type = "o", # both points p and lines l # #lwd = 3, # line width = 3 # #pch = 16, # ) # brl_end() ``` ```{r, include=FALSE} # brl_begin('tactile-HW_10_1_1_scatterplot_and_line.pdf', # pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') # plot(hike$distance_mi, # hike$time_min, # main = "HW 10.1.1 hiking distance vs time", # xlab = "Distance (miles)", # ylab = "Time (minutes)"#, # #ylim = c(0,0.5) # #type = "o", # both points p and lines l # #lwd = 3, # line width = 3 # #pch = 16, # ) # abline(lm(time_min ~ distance_mi, data = hike), col = "black", lwd = 3) # brl_end() ``` ```{r, echo=FALSE} #plot(hike$distance_mi, hike$time_min) #ScatterPlot(hike, x=hike$distance_mi, y=hike$time_min) ``` # HW 10.1.3 about glycemic loads and mean rating ```{r} foods <- read.table(text= "MeanRating GlycemicLoad 4.01 22 3.73 14 3.73 12 3.71 7 3.68 14 3.6 21 3.51 17 3.29 16 3.26 24 3.22 0 3.03 0 2.97 7 2.73 15 2.64 26 2.56 22 2.57 22 2.54 0 2.5 29 2.47 3 2.18 0 2.16 0 2.13 15 2.07 11 1.94 0 1.93 10 1.88 1 1.87 8 1.84 0 1.77 12 1.74 0 1.74 20 1.66 4 1.63 7 1.6 2 1.53 0", header=TRUE, check.names=FALSE) ``` ```{r, echo=FALSE, fig.cap="This scatter plot has title ‘Glycemic load versus mean rating’ with x-axis ‘glycemic load’ that has values from 0 to 30, and y-axis ‘mean rating’ with values from 1.5 to 4. There are 35 big solid circle points. The points are quite spread out horizontally and vertically but they do show a general slight increase in mean rating as glycemic load increases."} sp <- ggplot(foods, aes(GlycemicLoad, MeanRating)) + geom_point(size = 4) + ggtitle("HW 10.1 #3: glycemic load vs mean rating") + xlab("glycemic load") + ylab("mean rating") + theme_bw(base_size = 18) sp ``` ```{r, echo=FALSE, fig.cap="This scatter plot has title ‘Glycemic load versus mean rating’ with x-axis ‘glycemic load’ that has values from 0 to 30, and y-axis ‘mean rating’ with values from 1.5 to 4. There are 35 big solid circle points. The points are quite spread out horizontally and vertically but they do show a general slight increase in mean rating as glycemic load increases."} sp <- ggplot(foods, aes(GlycemicLoad, MeanRating)) + geom_point(size = 4) + ggtitle("HW 10.1 #3: glycemic load vs mean rating") + xlab("glycemic load") + ylab("mean rating") + theme_bw(base_size = 18) + geom_smooth(data = foods, method='lm', se=FALSE, size=2, color = "black") sp # generates both graph and VI(ts) automatically lm(MeanRating ~ GlycemicLoad, foods) ``` ```{r, echo=FALSE, fig.cap="This scatter plot has title ‘Glycemic load versus mean rating’ with x-axis ‘glycemic load’ that has values from 0 to 30, and y-axis ‘mean rating’ with values from 1.5 to 4. There are 35 big solid circle points. The points are quite spread out horizontally and vertically but they do show a general slight increase in mean rating as glycemic load increases."} MakeAccessibleSVG.ggplot(sp, file = "reader-HW_10_1_3") ``` ```{r, include=FALSE} brl_begin('tactile-HW_10_1_3_scatterplot.pdf', pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') plot(foods$GlycemicLoad, foods$MeanRating, main = "HW 10.1.3 glycemic load vs mean rating", xlab = "glycemic load", ylab = "mean rating" ) brl_end() ``` ```{r, include=FALSE} brl_begin('tactile-HW_10_1_3_scatterplot_and_line.pdf', pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') plot(foods$GlycemicLoad, foods$MeanRating, main = "HW 10.1.3 glycemic load vs mean rating", xlab = "glycemic load", ylab = "mean rating" ) abline(lm(MeanRating ~ GlycemicLoad, data = foods), col = "black", lwd = 3) brl_end() ``` ```{r} brl_begin('tactile-HW_10_1_3_scatterplot_and_line_and_ellipse.pdf', pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') scatterplot(MeanRating ~ GlycemicLoad, data = foods, main = "HW 10.1.3 glycemic load vs mean rating", xlab = "glycemic load", ylab = "mean rating", pch = 16, cex = 2, col = "black", smooth = FALSE, grid = FALSE, frame = TRUE, ellipse = list(levels=c(.25, .75), robust=TRUE, fill=FALSE, fill.alpha=0, lwd = 3) ) brl_end() ``` # HW 10.1.4 on housing prices and location ```{r} houses <- read.table(text= "sqft price location 900.4245641 121.4827342 notlakefront 1332.911007 202.2002959 notlakefront 1664.055598 182.3960118 notlakefront 2236.790998 241.6676939 notlakefront 2272.71276 213.7819329 notlakefront 2407.247765 328.0687403 notlakefront 3165.875711 314.1584852 notlakefront 1597.275542 412.0484081 lakefront 1736.981082 532.1023415 lakefront 1904.070236 497.9171293 lakefront 2695.003193 643.0897783 lakefront 3258.721474 754.0413121 lakefront 3351.031211 901.4073519 lakefront", header=TRUE, check.names=FALSE) notlakefront <- subset(houses, location == "notlakefront") lakefront <- subset(houses, location == "lakefront") print(houses, row.names=FALSE) ``` ## House prices ```{r, echo=FALSE, fig.cap="This scatter plot has title ‘Housing price versus square footage of home’ with x-axis ‘square footage’ that has values from 500 to 3500, and y-axis ‘price / 1000’ with values from 100 to 900 (in units thousands of dollars). There are 12 big solid circle points. The points are spread out but do show a general increase in price as square footage increases."} # time series plot sp <- ggplot(houses, aes(sqft, price)) + geom_point(size = 4) + ggtitle("HW 10.1 #4: House price versus sq ft") + xlab("sq ft") + ylab("Price/1000") + theme_bw(base_size = 18) + geom_smooth(data = houses, method='lm', se=FALSE, size=2, color = "black") sp # generates both graph and VI(ts) automatically lm(price ~ sqft, houses) ``` ```{r, include=FALSE, fig.cap="This scatter plot has title ‘Hiking distance versus time’ with x-axis ‘distance (miles)’ that has values from 0 to 10, and y-axis ‘time (minutes)’ with values from 0 to 400. There are 27 big solid circle points. The points are concentrated tightly around a straight path (except for one outlier) that is increasing at a constant rate of about 30 minutes for every mile."} MakeAccessibleSVG.ggplot(sp, file = "reader-HW_10_1_4") ``` ```{r, include=FALSE} brl_begin('tactile-HW_10_1_4.pdf', pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') plot(houses$sqft, houses$price, main = "HW 10.1.4 house price vs sq ft", xlab = "sq ft", ylab = "Price/1000"#, #ylim = c(0,0.5) #type = "o", # both points p and lines l #lwd = 3, # line width = 3 #pch = 16, ) brl_end() ``` ## Lakefront house prices ```{r, echo=FALSE, fig.cap="This scatter plot has title ‘Housing price versus square footage of home’ with x-axis ‘square footage’ that has values from 500 to 3500, and y-axis ‘price / 1000’ with values from 100 to 900 (in units thousands of dollars). There are 12 big solid circle points. The points are spread out but do show a general increase in price as square footage increases."} # time series plot sp <- ggplot(houses, aes(sqft, price)) + geom_point(size = 4) + ggtitle("HW 10.1 #4: House price versus sq ft") + xlab("sq ft") + ylab("Price/1000") + theme_bw(base_size = 18) + # https://stackoverflow.com/questions/42132442/ggplot-adding-regression-line-of-different-subsets geom_smooth(data = subset(houses, location == "lakefront"), method='lm', se=FALSE, size=2, color = "black") + geom_smooth(data = subset(houses, location == "notlakefront"), method='lm', se=FALSE, size=2, color = "black") sp # generates both graph and VI(ts) automatically lm(price ~ sqft, houses) ```