nyc-pizza.Rmd

---
title: "Pizza"
output: html_document
editor_options: 
  chunk_output_type: console
---

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

## R Markdown

```{r}
library(tidyverse)
theme_set(theme_light())\
```

```{r}
pizza_jared <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-10-01/pizza_jared.csv")
pizza_barstool <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-10-01/pizza_barstool.csv")
pizza_datafiniti <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-10-01/pizza_datafiniti.csv")
```

```{r}
answer_orders <- c("Never Again", "Poor", "Average", "Good", "Excellent")

by_place_answer <- pizza_jared %>%
  mutate(time = as.POSIXct(time, origin = "1970-01-01"),
         date = as.Date(time),
         answer = fct_relevel(answer, answer_orders)) %>%
  group_by(place, answer) %>%
  summarize(votes = sum(votes)) %>%
  mutate(total = sum(votes),
         percent = votes / total,
         answer_integer = as.integer(answer),
         average = sum(answer_integer * percent)) %>%
  ungroup()

by_place <- by_place_answer %>%
  distinct(place, total, average)
```

```{r}
by_place_answer %>%
  filter(as.integer(fct_reorder(place, total, .desc = TRUE)) <= 16,
         answer != "Fair") %>%
  mutate(place = glue::glue("{ place } ({ total })"),
         place = fct_reorder(place, average)) %>%
  ggplot(aes(answer, percent)) +
  geom_col() +
  facet_wrap(~ place) +
  scale_y_continuous(labels = scales::percent) +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  labs(x = "",
       y = "% of respondents",
       title = "What is the most popular pizza place in Open Stats meetup?",
       subtitle = "Only the 16 pizza places with the most respondents. # respondents shown in parentheses.")
```

```{r}
library(broom)

# THIS TRICK DOESN'T WORK
# tidy(lm(c(1, 2, 3, 4, 5) ~ 1, weights = c(100, 300, 100, 200, 150)), conf.int = TRUE)

t_test_repeated <- function(x, frequency) {
  tidy(t.test(rep(x, frequency)))
}

by_place_answer %>%
  filter(total >= 3) %>%
  group_by(place, total) %>%
  summarize(t_test_result = list(t_test_repeated(answer_integer, votes))) %>%
  ungroup() %>%
  unnest(t_test_result) %>%
  select(place, total, average = estimate, low = conf.low, high = conf.high) %>%
  top_n(16, total) %>%
  mutate(place = fct_reorder(place, average)) %>%
  ggplot(aes(average, place)) +
  geom_point(aes(size = total)) +
  geom_errorbarh(aes(xmin = low, xmax = high)) +
  labs(x = "Average score (1-5 Likert Scale)",
       y = "",
       title = "What is the most popular pizza place in Open Stats meetup?",
       subtitle = "Only the 16 pizza places with the most respondents.",
       size = "# of respondents")
```

```{r}
# Don't bother comparing them, this is a bad graph
pizza_barstool %>%
  select(place = name,
         barstool_total = review_stats_all_count,
         barstool_average = review_stats_all_average_score) %>%
  inner_join(by_place, by = "place") %>%
  group_by(place) %>%
  filter(n() == 1) %>%
  ungroup() %>%
  filter(barstool_total >= 5,
         total >= 5) %>%
  ggplot(aes(average, barstool_average)) +
  geom_point() +
  labs(x = "Meetup",
       y = "Barstool")
```

```{r}
pizza_barstool %>%
  top_n(50, review_stats_all_count) %>%
  ggplot(aes(price_level, review_stats_all_average_score, group = price_level)) +
  geom_boxplot()

pizza_barstool %>%
  filter(review_stats_all_count >= 50) %>%
  mutate(name = fct_reorder(name, review_stats_all_average_score)) %>%
  ggplot(aes(review_stats_all_average_score, name, size = review_stats_all_count)) +
  geom_point() +
  labs(x = "Average rating",
       y = "",
       size = "# of reviews",
       title = "Barstool Sports ratings of pizza places",
       subtitle = "Only places with at least 50 reviews")
```

```{r}
pizza_barstool %>%
  filter(review_stats_all_count >= 20) %>%
  mutate(city = fct_lump(city, 3)) %>%
  add_count(city) %>%
  mutate(city = glue::glue("{ city } ({ n })")) %>%
  ggplot(aes(city, review_stats_all_average_score)) +
  geom_boxplot() +
  labs(title = "Do pizza ratings differ across cities?",
       subtitle = "Only pizza places with at least 20 reviews")
```

```{r}
pizza_cleaned <- pizza_barstool %>%
  select(place = name,
         price_level,
         contains("review")) %>%
  rename_all(~ str_remove(., "review_stats_")) %>%
  select(-contains("provider"))

pizza_cleaned %>%
  filter(critic_count > 0) %>%
  ggplot(aes(critic_average_score, dave_average_score)) +
  geom_point() +
  geom_abline(color = "red") +
  geom_smooth(method = "lm") +
  labs(title = "Does Barstool Sports' Dave agree with the critics?",
       x = "Critic average score",
       y = "Dave score")
```

```{r}
pizza_cleaned %>%
  filter(community_count >= 20) %>%
  ggplot(aes(community_average_score, dave_average_score)) +
  geom_point(aes(size = community_count)) +
  geom_abline(color = "red") +
  geom_smooth(method = "lm") +
  labs(size = "# of community reviews",
       x = "Community score",
       y = "Dave score")
```