library(devtools)Warning: package 'devtools' was built under R version 4.3.2Loading required package: usethisWarning: package 'usethis' was built under R version 4.3.2Wikipedia API
devtools::install_github("ironholds/pageviews")Skipping install of 'pageviews' from a github remote, the SHA1 (d32c629c) has not changed since last install.
Use `force = TRUE` to force installationlibrary(tidyverse)Warning: package 'tidyverse' was built under R version 4.3.2Warning: package 'lubridate' was built under R version 4.3.2── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr 1.1.2 ✔ readr 2.1.4
✔ forcats 1.0.0 ✔ stringr 1.5.0
✔ ggplot2 3.4.2 ✔ tibble 3.2.1
✔ lubridate 1.9.3 ✔ tidyr 1.3.0
✔ purrr 1.0.1
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag() masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(pageviews) # This package gets data on Wikipedia viewing
library(DT) # DT stands for datatable, and creates interactive tablesWarning: package 'DT' was built under R version 4.3.2library(infer) # for some stats like t_testWarning: package 'infer' was built under R version 4.3.2library(devtools)This is stats stuff, telling me what libraries to use.
gun_control <- article_pageviews(article = "Gun control", start = as.Date("2017-1-1"), end = as.Date("2023-12-31"))
glimpse(gun_control)Rows: 2,556
Columns: 8
$ project <chr> "wikipedia", "wikipedia", "wikipedia", "wikipedia", "wikip…
$ language <chr> "en", "en", "en", "en", "en", "en", "en", "en", "en", "en"…
$ article <chr> "Gun_control", "Gun_control", "Gun_control", "Gun_control"…
$ access <chr> "all-access", "all-access", "all-access", "all-access", "a…
$ agent <chr> "all-agents", "all-agents", "all-agents", "all-agents", "a…
$ granularity <chr> "daily", "daily", "daily", "daily", "daily", "daily", "dai…
$ date <dttm> 2017-01-01, 2017-01-02, 2017-01-03, 2017-01-04, 2017-01-0…
$ views <dbl> 285, 393, 434, 544, 635, 620, 431, 464, 610, 595, 686, 688…This is me telling the program to look at the number of views of the “gun control” article on Wikipedia from the last few years.
gun_control |>
ggplot(aes(x = date, y = views)) +
geom_line()
This is those views charted by frequency.
violence <- article_pageviews(article = "Gun violence in the United States", start = as.Date("2017-1-1"), end = as.Date("2023-12-31"))
glimpse(violence)Rows: 2,556
Columns: 8
$ project <chr> "wikipedia", "wikipedia", "wikipedia", "wikipedia", "wikip…
$ language <chr> "en", "en", "en", "en", "en", "en", "en", "en", "en", "en"…
$ article <chr> "Gun_violence_in_the_United_States", "Gun_violence_in_the_…
$ access <chr> "all-access", "all-access", "all-access", "all-access", "a…
$ agent <chr> "all-agents", "all-agents", "all-agents", "all-agents", "a…
$ granularity <chr> "daily", "daily", "daily", "daily", "daily", "daily", "dai…
$ date <dttm> 2017-01-01, 2017-01-02, 2017-01-03, 2017-01-04, 2017-01-0…
$ views <dbl> 877, 1033, 1173, 1186, 1298, 2281, 2275, 1491, 1503, 2460,…This is me telling the program to look at the number of views of the “gun violence in the United States” article on Wikipedia from the last few years.
violence |>
ggplot(aes(x = date, y = views)) +
geom_line()
This is those views charted by frequency.
guns <- bind_rows(gun_control, violence) This is me turning the gun control article and the gun violence article into one term, “guns”.
guns |>
ggplot(aes(x = date, y = views, color = article)) +
geom_line()
This is a graph of views of the “gun control” article (red) against the “gun violence in the United States” article (teal).
guns |>
pivot_wider(names_from = article, values_from = views)# A tibble: 2,556 × 8
project language access agent granularity date Gun_control
<chr> <chr> <chr> <chr> <chr> <dttm> <dbl>
1 wikipedia en all-acc… all-… daily 2017-01-01 00:00:00 285
2 wikipedia en all-acc… all-… daily 2017-01-02 00:00:00 393
3 wikipedia en all-acc… all-… daily 2017-01-03 00:00:00 434
4 wikipedia en all-acc… all-… daily 2017-01-04 00:00:00 544
5 wikipedia en all-acc… all-… daily 2017-01-05 00:00:00 635
6 wikipedia en all-acc… all-… daily 2017-01-06 00:00:00 620
7 wikipedia en all-acc… all-… daily 2017-01-07 00:00:00 431
8 wikipedia en all-acc… all-… daily 2017-01-08 00:00:00 464
9 wikipedia en all-acc… all-… daily 2017-01-09 00:00:00 610
10 wikipedia en all-acc… all-… daily 2017-01-10 00:00:00 595
# ℹ 2,546 more rows
# ℹ 1 more variable: Gun_violence_in_the_United_States <dbl>This is the combined “guns” pageviews every day for the past few years.
guns |>
pivot_wider(names_from = article, values_from = views) |>
ggplot(aes(x = Gun_violence_in_the_United_States, y = Gun_control)) + # create scatterplot
geom_point() +
geom_smooth(method = lm) + # create regression line
labs(x = "Views of the Wikipedia Gun violence in the US article",
y = "Views of the Wikipedia Gun control article",
title = "Relationship between Wikipedia article views")`geom_smooth()` using formula = 'y ~ x'
This is a scatterplot showing the correlation of views of the violence (bottom) and control (side) articles.
top <- top_articles(start = as.Date("2023-07-03"))top |>
select(article, views) |>
filter(!article == "Main_Page", !article == "Special:Search") |>
slice_max(views, n = 10) |>
datatable()This is showing me what the top 10 most searched Wikipedia articles were on the day after the Baltimore shooting, which was July 2nd, 2023.
top |>
select(article, views) |>
filter(!article == "Main_Page", !article == "Special:Search") |>
top_n(10, views) |>
ggplot(aes(x = fct_rev(as_factor(article)), y = views)) +
geom_col(fill = "purple") +
coord_flip() +
scale_y_continuous(labels = scales::comma) +
labs(y = "Number of Views", x = "Article", title = "Top Wikipedia articles, Jul.3, 2023")
This purple graph is a visual representation of the same information.
top <- top_articles(start = as.Date("2023-10-30"))top |>
select(article, views) |>
filter(!article == "Main_Page", !article == "Special:Search") |>
slice_max(views, n = 10) |>
datatable()This is showing me what the top 10 most searched Wikipedia articles were on the day after the Ybor City (Tampa) shooting, which was October 29th, 2023.
top |>
select(article, views) |>
filter(!article == "Main_Page", !article == "Special:Search") |>
top_n(10, views) |>
ggplot(aes(x = fct_rev(as_factor(article)), y = views)) +
geom_col(fill = "pink") +
coord_flip() +
scale_y_continuous(labels = scales::comma) +
labs(y = "Number of Views", x = "Article", title = "Top Wikipedia articles, Oct. 30, 2023")
This pink graph is a visual representation of the same information.
ybor <- article_pageviews(article = "Gun_control",
start = as.Date("2023-10-22"),
end = as.Date("2023-11-5"))
ybor <- ybor |>
mutate(day = -7:7) |>
mutate(event = "Tampa")
ybor |>
ggplot(aes(x = day, y = views)) +
geom_line()
This is a graph of views of the Gun Control article for seven days before and after the Ybor City shooting.
mary <- article_pageviews(article = "Gun_control",
start = as.Date("2023-6-25"),
end = as.Date("2023-7-9"))
mary <- mary |>
mutate(day = -7:7) |>
mutate(event = "Baltimore")
mary |>
ggplot(aes(x = day, y = views)) +
geom_line()
This is a graph of views of the Gun Control article for seven days before and after the Ybor City shooting.
shootings <- bind_rows(ybor, mary)
shootings |>
ggplot(aes(x = day, y = views, color = event)) +
geom_line() +
theme_minimal() +
labs(x = "Days before/after Shooting",
y = "Wikipedia Views",
color = "Event",
title = "Views of the Wikipedia Gun Control Article before and after Two Mass Shootings")
This is a graph of views of the Gun Control article for seven days before and after the Ybor City shooting (teal) and the Baltimore shooting (red).
shootings |>
mutate(after_event = (day > 0)) project language article access agent granularity date
1 wikipedia en Gun_control all-access all-agents daily 2023-10-22
2 wikipedia en Gun_control all-access all-agents daily 2023-10-23
3 wikipedia en Gun_control all-access all-agents daily 2023-10-24
4 wikipedia en Gun_control all-access all-agents daily 2023-10-25
5 wikipedia en Gun_control all-access all-agents daily 2023-10-26
6 wikipedia en Gun_control all-access all-agents daily 2023-10-27
7 wikipedia en Gun_control all-access all-agents daily 2023-10-28
8 wikipedia en Gun_control all-access all-agents daily 2023-10-29
9 wikipedia en Gun_control all-access all-agents daily 2023-10-30
10 wikipedia en Gun_control all-access all-agents daily 2023-10-31
11 wikipedia en Gun_control all-access all-agents daily 2023-11-01
12 wikipedia en Gun_control all-access all-agents daily 2023-11-02
13 wikipedia en Gun_control all-access all-agents daily 2023-11-03
14 wikipedia en Gun_control all-access all-agents daily 2023-11-04
15 wikipedia en Gun_control all-access all-agents daily 2023-11-05
16 wikipedia en Gun_control all-access all-agents daily 2023-06-25
17 wikipedia en Gun_control all-access all-agents daily 2023-06-26
18 wikipedia en Gun_control all-access all-agents daily 2023-06-27
19 wikipedia en Gun_control all-access all-agents daily 2023-06-28
20 wikipedia en Gun_control all-access all-agents daily 2023-06-29
21 wikipedia en Gun_control all-access all-agents daily 2023-06-30
22 wikipedia en Gun_control all-access all-agents daily 2023-07-01
23 wikipedia en Gun_control all-access all-agents daily 2023-07-02
24 wikipedia en Gun_control all-access all-agents daily 2023-07-03
25 wikipedia en Gun_control all-access all-agents daily 2023-07-04
26 wikipedia en Gun_control all-access all-agents daily 2023-07-05
27 wikipedia en Gun_control all-access all-agents daily 2023-07-06
28 wikipedia en Gun_control all-access all-agents daily 2023-07-07
29 wikipedia en Gun_control all-access all-agents daily 2023-07-08
30 wikipedia en Gun_control all-access all-agents daily 2023-07-09
views day event after_event
1 351 -7 Tampa FALSE
2 417 -6 Tampa FALSE
3 492 -5 Tampa FALSE
4 548 -4 Tampa FALSE
5 778 -3 Tampa FALSE
6 651 -2 Tampa FALSE
7 484 -1 Tampa FALSE
8 553 0 Tampa FALSE
9 620 1 Tampa TRUE
10 524 2 Tampa TRUE
11 559 3 Tampa TRUE
12 435 4 Tampa TRUE
13 372 5 Tampa TRUE
14 366 6 Tampa TRUE
15 381 7 Tampa TRUE
16 315 -7 Baltimore FALSE
17 364 -6 Baltimore FALSE
18 318 -5 Baltimore FALSE
19 331 -4 Baltimore FALSE
20 371 -3 Baltimore FALSE
21 322 -2 Baltimore FALSE
22 343 -1 Baltimore FALSE
23 335 0 Baltimore FALSE
24 336 1 Baltimore TRUE
25 373 2 Baltimore TRUE
26 308 3 Baltimore TRUE
27 360 4 Baltimore TRUE
28 330 5 Baltimore TRUE
29 304 6 Baltimore TRUE
30 293 7 Baltimore TRUEshootings |>
mutate(after_event = (day > 0)) |>
t_test(views ~ after_event)Warning: The statistic is based on a difference or ratio; by default, for
difference-based statistics, the explanatory variable is subtracted in the
order "TRUE" - "FALSE", or divided in the order "TRUE" / "FALSE" for
ratio-based statistics. To specify this order yourself, supply `order =
c("TRUE", "FALSE")`.# A tibble: 1 × 7
statistic t_df p_value alternative estimate lower_ci upper_ci
<dbl> <dbl> <dbl> <chr> <dbl> <dbl> <dbl>
1 -0.883 27.3 0.385 two.sided -38.6 -128. 51.1shootings |>
mutate(after_event = (day > 0)) |>
group_by(after_event) |>
summarize(Mean = mean(views),
StdDev = sd(views),
N = n())# A tibble: 2 × 4
after_event Mean StdDev N
<lgl> <dbl> <dbl> <int>
1 FALSE 436. 137. 16
2 TRUE 397. 101. 14This t-test showed that the average number of views of the Wikipedia Gun Control article in the seven days prior to the two shootings (M = 435.81, SD = 137.43) was not statistically significantly different from the average number of views in the seven days after the shooting (M = 397.21, SD = 101.12), t(27.26) = -0.88, p = .38.