--- title: "Homework Chapter 10.1" author: "Dr. Paul Pearson" date: "2024-11-01" output: html_document --- ```{r setup, include=FALSE} knitr::opts_chunk$set(echo = TRUE, comment = "", warning = FALSE, message = FALSE) library(ggplot2) # ggsave(ggplot_object) can save svg files without xml annotations library(BrailleR) # VI(ggplot_object) for annotations for in text graph annotations # MakeAccessibleSVG(ggplot_object) to save accessible standalone html (=svg + xml annotations) library(tactileR) # Use braille in graphs for embossed printing # brl_begin(file='tactile_histogram_SWL.pdf', pt=14, paper='special', font='SWL') # base or lattice plot code here # brl_end() library(infer) #library(tibble) library(tidyr) # for reshaping data, etc. library(car) # for fancy scatterplots set.seed(1) options(digits = 4) ``` # Define helper functions ```{r} make_graphs <- function(df, explanatory, response, title_string, xlab_string, ylab_string, filename) { formula_string <- paste(substitute(response), "~", substitute(explanatory)) # winner: https://win-vector.com/2019/07/06/programming-over-lm-in-r/ # https://stackoverflow.com/questions/27261232/passing-argument-to-lm-in-r-within-function model <- eval(bquote( lm( as.formula(formula_string), data = df) )) print(model) # ggplot scatterplot without line sp <- ggplot(df, aes( x = {{ explanatory }}, y = {{ response }} )) + geom_point(size = 4) + ggtitle( title_string ) + xlab( xlab_string ) + ylab( ylab_string ) + theme_bw(base_size = 18) print(sp) # generates both graph and VI(ts) automatically # ggplot scatterplot with line sp <- sp + geom_smooth(method='lm', se=FALSE, size=2, color = "black") print(sp) # generates both graph and VI(ts) automatically MakeAccessibleSVG.ggplot(sp, file = paste0("reader-", filename)) # tactile scatterplot with no line brl_begin(paste0( 'tactile-', filename, '-scatterplot.pdf'), pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') # to get the variable values, use data[[substitute(varname)]] instead of data$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 hiking distance vs time ```{r, echo=FALSE} 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(round(hike,2), 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" ) ``` # 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."} make_graphs( df = foods, explanatory = GlycemicLoad, response = MeanRating, title = "HW 10.1 #3 glycemic load vs mean rating", xlab_string = "glycemic load", ylab_string = "mean rating", filename = "HW_10.1.3" ) ``` # HW 10.1.4 on housing sq ft vs prices by 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 sq ft vs price ```{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."} make_graphs( df = houses, explanatory = sqft, response = price, title = "HW 10.1 #4 house sq ft vs price", xlab_string = "square feet", ylab_string = "price/1000", filename = "HW_10.1.4" ) ``` ## House sq ft vs price by location ```{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) ``` ## Plot with two lines (one line per group) ```{r} model_lakefront <- lm( price ~ sqft, data = lakefront) print(model_lakefront) model_notlakefront <- lm( price ~ sqft, data = notlakefront) print(model_notlakefront) # tactile scatterplot with line brl_begin(paste0( 'tactile-HW_10.1.4-scatterplot-and-two-lines.pdf'), pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') plot(houses$sqft, houses$price, main = "HW 10.1 #4: House price versus sq ft by location", xlab = "sq ft", ylab = "Price/1000" ) abline( model_lakefront, col = "black", lwd = 3 ) abline( model_notlakefront, col = "black", lwd = 3 ) brl_end() ``` # HW 10.1.5 cricket chirps per minute ```{r, echo = FALSE} crickets <- read.table(text= "temperature_Celsius chirps_per_second cricket_type 12.71682406 0.9277767901 Karschi 13.0057562 0.9808195347 Karschi 13.10031581 1.072372765 Karschi 14.28231093 1.073306982 Karschi 14.43006032 1.031664275 Karschi 15.41702624 1.03220145 Karschi 18.49546685 1.266741726 Karschi 18.79538319 1.254587474 Karschi 19.01029139 1.687087312 Karschi 18.86845198 1.232590918 Karschi 19.104851 1.503980851 Karschi 19.29922353 1.384453023 Karschi 19.43580963 1.8043315 Karschi 19.71948846 1.667468763 Karschi 19.74312836 1.804798608 Karschi 19.81404807 1.897286055 Karschi 19.86920784 1.391900805 Karschi 20.00316729 1.275097775 Karschi 20.02680719 1.437495767 Karschi 20.19753982 1.64094739 Karschi 20.52324514 1.575292721 Karschi 20.63553467 1.534021755 Karschi 20.81217728 1.758658687 Karschi 20.94876338 1.577316857 Karschi 21.15561253 1.786814938 Karschi 21.42156143 1.556296983 Karschi 21.44520133 1.811338125 Karschi 21.61068065 1.64878443 Karschi 21.80505318 1.483998995 Karschi 22.31987772 1.811805233 Karschi 22.31987772 1.719784894 Karschi 22.41443732 1.582455049 Karschi 22.41443732 1.374124739 Karschi 22.51425025 2.039494588 Karschi 22.93451518 1.742361796 Karschi 22.93451518 1.629165881 Karschi 23.02907478 1.698297912 Karschi 23.12363439 1.791096764 Karschi 23.36003342 1.700166345 Karschi 23.86119935 1.704417031 Karschi 24.09287039 1.726324411 Karschi 24.30562951 1.817877641 Karschi 24.40018912 1.980431336 Karschi 24.92026697 1.865055581 Karschi 25.53490443 2.306940051 Karschi 25.72402365 2.491447836 Karschi 26.01295579 2.326870005 Karschi 10.49992656 1.324144149 Fultoni 10.49992656 1.180274787 Fultoni 11.13482679 1.34049294 Fultoni 11.59681802 1.343762698 Fultoni 12.04440017 1.360838102 Fultoni 13.0057562 1.421146976 Fultoni 13.50219415 1.50670565 Fultoni 13.49431418 1.438040727 Fultoni 14.01439203 1.601528638 Fultoni 14.01439203 1.480123726 Fultoni 14.52816591 1.658095456 Fultoni 14.50295001 1.563381459 Fultoni 15.03203354 1.668870088 Fultoni 14.991508 1.590302469 Fultoni 15.0151479 1.528504038 Fultoni 15.51158585 1.721964733 Fultoni 15.51158585 1.631501422 Fultoni 15.51158585 1.527232465 Fultoni 15.99113815 1.791719575 Fultoni 16.5162817 1.714471537 Fultoni 16.50446174 1.567974691 Fultoni 17.01103108 1.854000684 Fultoni 17.04480237 1.76727424 Fultoni 17.00680967 1.682455155 Fultoni 18.01741549 1.915970388 Fultoni 18.01741549 1.840765949 Fultoni 18.01741549 1.781256349 Fultoni 20.04369283 2.089267574 Fultoni 21.01968309 2.156706338 Fultoni 23.02907478 2.397714767 Fultoni 23.50862709 2.416243397 Fultoni 15.5108055 1.5625 Fultoni 16.01178782 1.725543478 Fultoni 16.01178782 1.684782609 Fultoni 16.01178782 1.611413043 Fultoni 16.01178782 1.566576087 Fultoni 16.51277014 1.774456522 Fultoni 16.51277014 1.815217391 Fultoni 16.51277014 1.595108696 Fultoni 17.01375246 1.729619565 Fultoni 17.01375246 1.815217391 Fultoni 14.00785855 1.50951087 Fultoni", header=TRUE, check.names=FALSE) print(crickets, row.names=TRUE) karschi <- subset(crickets, cricket_type == "Karschi") fultoni <- subset(crickets, cricket_type == "Fultoni") ``` ## Crickets temperature vs chirps/sec ```{r, echo=FALSE, fig.cap="This scatter plot has title ‘African crickets: temperature versus chirps per second’ with x-axis ‘temperature (Celsius)’ that has values from 10 to 30, and y-axis ‘chirps per second’ with values from 0.5 to 2.5. There are 89 big solid circle points. The points are somewhat spread out but do show a clear increase in chirps per second as temperature increases."} make_graphs( df = crickets, explanatory = temperature_Celsius, response = chirps_per_second, title = "HW 10.1 #5 crickets temp vs chirps/second", xlab_string = "temperature (Celsius)", ylab_string = "chirps per second", filename = "HW_10.1.5" ) ``` ## Plot with two lines (one line per group) ```{r} model_karschi <- lm( chirps_per_second ~ temperature_Celsius, data = karschi) print(model_karschi) model_fultoni <- lm( chirps_per_second ~ temperature_Celsius, data = fultoni) print(model_fultoni) # tactile scatterplot with line brl_begin(paste0( 'tactile-HW_10.1.5-scatterplot-and-line-karschi-only.pdf'), pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') plot(karschi$temperature_Celsius, karschi$chirps_per_second, main = "HW 10.1 #5: Karschi", xlab = "temperature (Celsius)", ylab = "chirps per second" ) abline( model_karschi, col = "black", lwd = 3 ) brl_end() # tactile scatterplot with line brl_begin(paste0( 'tactile-HW_10.1.5-scatterplot-and-line-fultoni-only.pdf'), pt=12, paper='special', font='SWL') #, font='BRL' or 'SWL') plot(fultoni$temperature_Celsius, fultoni$chirps_per_second, main = "HW 10.1 #5: Fultoni", xlab = "temperature (Celsius)", ylab = "chirps per second" ) abline( model_fultoni, col = "black", lwd = 3 ) brl_end() ```