misc-data-tables.Rmd

---
title: "Other datasets"
author: "John D. Smith"
date: "`r Sys.Date()`"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```



## A classic dataset from Tukey, 1977
```{r}

leptinotarsa_d <- read.csv(header = TRUE, text = "
treat, a1, a2, a3, a4, a5, a6
one, 492, 410, 475, 895, 401, 330
two, 111, 67, 233, 218, 28, 18
three, 58, 267, 283, 279, 392, 141
four, 4, 1, 53, 14, 138, 11")

long_lept <- pivot_longer(leptinotarsa_d, cols = where(is.numeric), names_to = "area", values_to = "original_count")
```


Newsletter subscriptions

```{r  SN participation}
table <- data.frame(
  stringsAsFactors = FALSE,
  subscription.type = c(
    "new topics", "all emails", "weekly summary",
    "daily digest", "none"
  ),
  Sangha.Talk = c(22, 51, 434, 1620, 8638),
  Sangha.Announce = c(30, 83, 6611, 1691, 2479)
)
x <- as.matrix(c(
  22, 30,
  51, 83,
  434, 6611,
  1620, 1691,
  8638, 2479
))

dim(x) <- c(2, 5)
medpolish(x)
mp <- medpolish(x)
str(mp)
t(mp$residuals)
plot(mp)
```

Religious participation

```{r}

# data from http://religions.pewforum.org/pdf/comparison-Income20Distribution20of20Religious20Traditions.pdf
# cited in Hadley Wickam's article on Tidy data

(rel.income <- read.table(sep = " ", header = TRUE, text = "
religion LT10k 10.20k 20.30k 30.40k 40.50k 50.75k 75.100k
1 Agnostic 27 34 60 81 76 137 122
2 Atheist 12 27 37 52 35 70 73
3 Buddhist 27 21 30 34 33 58 62
4 Catholic 418 617 732 670 638 1116 949
5 DK_refused 15 14 15 11 10 35 21
6 Evangelical_Prot 575 869 1064 982 881 1486 949
7 Hindu 1 9 7 9 11 34 47
8 Black_Prot 228 244 236 238 197 223 131
9 Jehovahs_Witness 20 27 24 24 21 30 15
10 Jewish 19 19 25 25 30 95 69
"))
nums <- select(rel.income, -religion)
med <- medpolish(nums)
med
row.names <- med$row
names(row.names) <- rel.income$religion
row.names

row.length <- length(med$row)
col.length <- length(med$col)
resid_df <- tibble(
  resids = c(med$residuals),
  row_fit = rep(med$row, each = col.length),
  row_names = rep(row.names, each = col.length),
  col_fit = rep(med$col, times = row.length)
)

resid_df >
  ggplot(aes(col_fit, row_fit)) +
    geom_point() +
    geom_text(aes(row_fit, col_fit, label = names(row_names)))
```


Pew data from: https://www.pewforum.org/religious-landscape-study/income-distribution/

```{r}
# income level by religious tradition

religious <- data.frame(
  stringsAsFactors = FALSE,
  check.names = FALSE,
  Religious_tradition = c(
    "Buddhist", "Catholic",
    "Evangelical Protestant", "Hindu",
    "Historically Black Protestant", "Jehovah's Witness", "Jewish",
    "Mainline Protestant", "Mormon", "Muslim", "Orthodox Christian",
    "Unaffiliated (religious \"nones\")"
  ),
  `Less.than.$30,000` = c(
    "36", "36", "35",
    "17", "53", "48", "16", "29", "27", "34", "18",
    "33"
  ),
  `$30,000-$49,999` = c(
    "18", "19", "22",
    "13", "22", "25", "15", "20", "20", "17", "17",
    "20"
  ),
  `$50,000-$99,999` = c(
    "32", "26", "28",
    "34", "17", "22", "24", "28", "33", "29", "36",
    "26"
  ),
  `$100,000.or.more` = c(
    "13", "19", "14",
    "36", "8", "4", "44", "23", "20", "20", "29",
    "21"
  ),
  sample_size = c(
    233, 6137, 7462, 172,
    1704, 208, 708, 5208, 594, 205, 155, 6790
  )
) %>%
  select(-sample_size) %>%
  pivot_longer(
    cols = c(
      "Less.than.$30,000",
      "$30,000-$49,999",
      "$50,000-$99,999",
      "$100,000.or.more"
    ),
    values_to = "percent"
  ) %>%
  mutate(percent = as.numeric(percent))
```


```{r}
religious %>% ggplot(aes(Religious_tradition, y = name)) +
  geom_point(aes(size = percent)) +
  coord_flip()
```

```{r}
# Frequency of meditation by household income
#  of adults who meditate…

data.frame(
  stringsAsFactors = FALSE,
  check.names = FALSE,
  income = c(
    "Less than $30,000",
    "$30,000-$49,999", "$50,000-$99,999",
    "$100,000 or more"
  ),
  At.least.once.a.week = c("45", "41", "37", "34"),
  Once.or.twice.a.month = c("9", "8", "9", "9"),
  Several.times.a.year = c("4", "4", "4", "5"),
  `Seldom/never` = c("40", "46", "49", "51"),
  `Don't.know` = c("2", "1", "1", "1"),
  Sample.Size = c(8845, 5920, 8723, 7002)
)
```