library(tidyverse)
library(dplyr)
library(tidyr)
library(knitr)
library(ggplot2)
library(tools)
library(gmodels)Week 6 Workbook
mpg %>%
group_by(class, cyl) %>% #Groups by class then cyl
summarise(n=n()) %>% #Summarises by number of observations
spread(cyl, n) %>% #Creates a crosstab/contingency table where class is arranged in rows and cyl in columns.
kable() #Creates a basic table| class | 4 | 5 | 6 | 8 |
|---|---|---|---|---|
| 2seater | NA | NA | NA | 5 |
| compact | 32 | 2 | 13 | NA |
| midsize | 16 | NA | 23 | 2 |
| minivan | 1 | NA | 10 | NA |
| pickup | 3 | NA | 10 | 20 |
| subcompact | 21 | 2 | 7 | 5 |
| suv | 8 | NA | 16 | 38 |
mpg%>%
group_by(class, cyl)%>% #Groups by class
summarise(mean_cty=mean(cty))%>% #Summarises by average number of city miles
spread(cyl, mean_cty) %>% #Creates a crosstab/contingency table where class is arranged in rows and cyl in columns, returning the mean value.
kable() #Creates a basic table| class | 4 | 5 | 6 | 8 |
|---|---|---|---|---|
| 2seater | NA | NA | NA | 15.40000 |
| compact | 21.37500 | 21 | 16.92308 | NA |
| midsize | 20.50000 | NA | 17.78261 | 16.00000 |
| minivan | 18.00000 | NA | 15.60000 | NA |
| pickup | 16.00000 | NA | 14.50000 | 11.80000 |
| subcompact | 22.85714 | 20 | 17.00000 | 14.80000 |
| suv | 18.00000 | NA | 14.50000 | 12.13158 |
mpg %>%
group_by(class, cyl) %>% #Groups by class then cyl
summarise(max_cty=max(cty)) %>% #Summarises by max cty
spread(cyl, max_cty) %>% #Creates a crosstab/contingency table where class is arranged in rows and cyl in columns, returning the max value.
kable() #Creates a basic table| class | 4 | 5 | 6 | 8 |
|---|---|---|---|---|
| 2seater | NA | NA | NA | 16 |
| compact | 33 | 21 | 18 | NA |
| midsize | 23 | NA | 19 | 16 |
| minivan | 18 | NA | 17 | NA |
| pickup | 17 | NA | 16 | 14 |
| subcompact | 35 | 20 | 18 | 15 |
| suv | 20 | NA | 17 | 14 |
mpg%>%
group_by(class)%>% #Groups by class
summarise(n=n())%>% #Summarises by number of observations
mutate(prop=n/sum(n))%>% #Creates a new field and calculates proportion
kable() #Creates a basic table| class | n | prop |
|---|---|---|
| 2seater | 5 | 0.0213675 |
| compact | 47 | 0.2008547 |
| midsize | 41 | 0.1752137 |
| minivan | 11 | 0.0470085 |
| pickup | 33 | 0.1410256 |
| subcompact | 35 | 0.1495726 |
| suv | 62 | 0.2649573 |
mpg%>%
group_by(class, cyl)%>% #Groups by class then cyl
summarize(n=n())%>% #Summarises by number of observations
mutate(prop=n/sum(n))%>% #Creates a new field and calculates proportion
subset(select=c("class","cyl","prop"))%>% #Retains only class, cyl and prop columns (does not display frequency value)
spread(class, prop)%>% #Creates a crosstab/contingency table where class is arranged in rows and prop in columns.
kable() #Creates a basic table| cyl | 2seater | compact | midsize | minivan | pickup | subcompact | suv |
|---|---|---|---|---|---|---|---|
| 4 | NA | 0.6808511 | 0.3902439 | 0.0909091 | 0.0909091 | 0.6000000 | 0.1290323 |
| 5 | NA | 0.0425532 | NA | NA | NA | 0.0571429 | NA |
| 6 | NA | 0.2765957 | 0.5609756 | 0.9090909 | 0.3030303 | 0.2000000 | 0.2580645 |
| 8 | 1 | NA | 0.0487805 | NA | 0.6060606 | 0.1428571 | 0.6129032 |
table(mpg$class, mpg$cyl) #Creates a table showing vehicle class by number of cylinders
4 5 6 8
2seater 0 0 0 5
compact 32 2 13 0
midsize 16 0 23 2
minivan 1 0 10 0
pickup 3 0 10 20
subcompact 21 2 7 5
suv 8 0 16 38mpg_table<-table(mpg$class, mpg$cyl)
ftable(mpg_table) #Creates a frequency table by class and cyl 4 5 6 8
2seater 0 0 0 5
compact 32 2 13 0
midsize 16 0 23 2
minivan 1 0 10 0
pickup 3 0 10 20
subcompact 21 2 7 5
suv 8 0 16 38margin.table(mpg_table, 1) #Creates a frequency table by rows
2seater compact midsize minivan pickup subcompact suv
5 47 41 11 33 35 62 margin.table(mpg_table, 2) #Creates a frequency table by columns
4 5 6 8
81 4 79 70 prop.table(mpg_table) #Creates a proportions table for the entire table
4 5 6 8
2seater 0.000000000 0.000000000 0.000000000 0.021367521
compact 0.136752137 0.008547009 0.055555556 0.000000000
midsize 0.068376068 0.000000000 0.098290598 0.008547009
minivan 0.004273504 0.000000000 0.042735043 0.000000000
pickup 0.012820513 0.000000000 0.042735043 0.085470085
subcompact 0.089743590 0.008547009 0.029914530 0.021367521
suv 0.034188034 0.000000000 0.068376068 0.162393162prop.table(mpg_table, 1) #Creates a proportion table by entire row
4 5 6 8
2seater 0.00000000 0.00000000 0.00000000 1.00000000
compact 0.68085106 0.04255319 0.27659574 0.00000000
midsize 0.39024390 0.00000000 0.56097561 0.04878049
minivan 0.09090909 0.00000000 0.90909091 0.00000000
pickup 0.09090909 0.00000000 0.30303030 0.60606061
subcompact 0.60000000 0.05714286 0.20000000 0.14285714
suv 0.12903226 0.00000000 0.25806452 0.61290323prop.table(mpg_table, 2) #Creates a proportion table by entire column
4 5 6 8
2seater 0.00000000 0.00000000 0.00000000 0.07142857
compact 0.39506173 0.50000000 0.16455696 0.00000000
midsize 0.19753086 0.00000000 0.29113924 0.02857143
minivan 0.01234568 0.00000000 0.12658228 0.00000000
pickup 0.03703704 0.00000000 0.12658228 0.28571429
subcompact 0.25925926 0.50000000 0.08860759 0.07142857
suv 0.09876543 0.00000000 0.20253165 0.54285714CrossTable(mpg$class, mpg$cyl) #Creates a frequencies and table, row and column proportions in one command (requires gmodels)
Cell Contents
|-------------------------|
| N |
| Chi-square contribution |
| N / Row Total |
| N / Col Total |
| N / Table Total |
|-------------------------|
Total Observations in Table: 234
| mpg$cyl
mpg$class | 4 | 5 | 6 | 8 | Row Total |
-------------|-----------|-----------|-----------|-----------|-----------|
2seater | 0 | 0 | 0 | 5 | 5 |
| 1.731 | 0.085 | 1.688 | 8.210 | |
| 0.000 | 0.000 | 0.000 | 1.000 | 0.021 |
| 0.000 | 0.000 | 0.000 | 0.071 | |
| 0.000 | 0.000 | 0.000 | 0.021 | |
-------------|-----------|-----------|-----------|-----------|-----------|
compact | 32 | 2 | 13 | 0 | 47 |
| 15.210 | 1.782 | 0.518 | 14.060 | |
| 0.681 | 0.043 | 0.277 | 0.000 | 0.201 |
| 0.395 | 0.500 | 0.165 | 0.000 | |
| 0.137 | 0.009 | 0.056 | 0.000 | |
-------------|-----------|-----------|-----------|-----------|-----------|
midsize | 16 | 0 | 23 | 2 | 41 |
| 0.230 | 0.701 | 6.059 | 8.591 | |
| 0.390 | 0.000 | 0.561 | 0.049 | 0.175 |
| 0.198 | 0.000 | 0.291 | 0.029 | |
| 0.068 | 0.000 | 0.098 | 0.009 | |
-------------|-----------|-----------|-----------|-----------|-----------|
minivan | 1 | 0 | 10 | 0 | 11 |
| 2.070 | 0.188 | 10.641 | 3.291 | |
| 0.091 | 0.000 | 0.909 | 0.000 | 0.047 |
| 0.012 | 0.000 | 0.127 | 0.000 | |
| 0.004 | 0.000 | 0.043 | 0.000 | |
-------------|-----------|-----------|-----------|-----------|-----------|
pickup | 3 | 0 | 10 | 20 | 33 |
| 6.211 | 0.564 | 0.117 | 10.391 | |
| 0.091 | 0.000 | 0.303 | 0.606 | 0.141 |
| 0.037 | 0.000 | 0.127 | 0.286 | |
| 0.013 | 0.000 | 0.043 | 0.085 | |
-------------|-----------|-----------|-----------|-----------|-----------|
subcompact | 21 | 2 | 7 | 5 | 35 |
| 6.515 | 3.284 | 1.963 | 2.858 | |
| 0.600 | 0.057 | 0.200 | 0.143 | 0.150 |
| 0.259 | 0.500 | 0.089 | 0.071 | |
| 0.090 | 0.009 | 0.030 | 0.021 | |
-------------|-----------|-----------|-----------|-----------|-----------|
suv | 8 | 0 | 16 | 38 | 62 |
| 8.444 | 1.060 | 1.162 | 20.403 | |
| 0.129 | 0.000 | 0.258 | 0.613 | 0.265 |
| 0.099 | 0.000 | 0.203 | 0.543 | |
| 0.034 | 0.000 | 0.068 | 0.162 | |
-------------|-----------|-----------|-----------|-----------|-----------|
Column Total | 81 | 4 | 79 | 70 | 234 |
| 0.346 | 0.017 | 0.338 | 0.299 | |
-------------|-----------|-----------|-----------|-----------|-----------|