install.packages("pageviews_0.5.0.tar", repos = NULL, type = "source")Installing package into 'C:/Users/msubstudent/AppData/Local/R/win-library/4.3'
(as 'lib' is unspecified)Warning in install.packages("pageviews_0.5.0.tar", repos = NULL, type =
"source"): installation of package 'pageviews_0.5.0.tar' had non-zero exit
statuslibrary(tidyverse)── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr 1.1.4 ✔ readr 2.1.5
✔ forcats 1.0.0 ✔ stringr 1.5.1
✔ ggplot2 3.4.4 ✔ tibble 3.2.1
✔ lubridate 1.9.3 ✔ tidyr 1.3.0
✔ purrr 1.0.2
── 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 tables
library(infer) # for some stats like t_test
library(devtools)Loading required package: usethisdevtools::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 installationgun_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…topLV <- top_articles(start = as.Date("2017-10-2"))topM <- top_articles(start = as.Date("2017-4-19"))Las_Vegas_shooting <- article_pageviews(article = "2017 Las Vegas shooting", start = as.Date("2017-1-1"), end = as.Date("2023-12-31"))
glimpse(Las_Vegas_shooting)Rows: 2,282
Columns: 8
$ project <chr> "wikipedia", "wikipedia", "wikipedia", "wikipedia", "wikip…
$ language <chr> "en", "en", "en", "en", "en", "en", "en", "en", "en", "en"…
$ article <chr> "2017_Las_Vegas_shooting", "2017_Las_Vegas_shooting", "201…
$ 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> 2017-10-02, 2017-10-03, 2017-10-04, 2017-10-05, 2017-10-0…
$ views <dbl> 6994, 314, 414, 233, 238, 235, 40, 22, 2844, 35329, 31019,…Fresno_shootings <- article_pageviews(article = "Fresno shootings", start = as.Date("2017-1-1"), end = as.Date("2023-12-31"))
glimpse(Fresno_shootings)Rows: 1,284
Columns: 8
$ project <chr> "wikipedia", "wikipedia", "wikipedia", "wikipedia", "wikip…
$ language <chr> "en", "en", "en", "en", "en", "en", "en", "en", "en", "en"…
$ article <chr> "Fresno_shootings", "Fresno_shootings", "Fresno_shootings"…
$ 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> 2017-11-03, 2017-11-04, 2017-11-05, 2017-11-06, 2017-11-0…
$ views <dbl> 73, 33, 89, 226, 84, 73, 70, 49, 53, 40, 51, 82, 99, 56, 6…gun_control |>
slice_max(views, n = 10) project language article access agent granularity date
1 wikipedia en Gun_control all-access all-agents daily 2022-05-25
2 wikipedia en Gun_control all-access all-agents daily 2018-02-16
3 wikipedia en Gun_control all-access all-agents daily 2018-02-15
4 wikipedia en Gun_control all-access all-agents daily 2022-05-26
5 wikipedia en Gun_control all-access all-agents daily 2018-02-22
6 wikipedia en Gun_control all-access all-agents daily 2017-10-03
7 wikipedia en Gun_control all-access all-agents daily 2018-02-20
8 wikipedia en Gun_control all-access all-agents daily 2018-02-19
9 wikipedia en Gun_control all-access all-agents daily 2018-02-21
10 wikipedia en Gun_control all-access all-agents daily 2018-02-18
views
1 9666
2 6549
3 6117
4 5587
5 5142
6 4342
7 4233
8 4229
9 3914
10 3760Mass_shootings_in_the_United_States <- article_pageviews(article = "Mass shootings in the United States", start = as.Date("2017-1-1"), end = as.Date("2023-12-31"))
glimpse(Mass_shootings_in_the_United_States)Rows: 2,554
Columns: 8
$ project <chr> "wikipedia", "wikipedia", "wikipedia", "wikipedia", "wikip…
$ language <chr> "en", "en", "en", "en", "en", "en", "en", "en", "en", "en"…
$ article <chr> "Mass_shootings_in_the_United_States", "Mass_shootings_in_…
$ 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> 13, 9, 7, 13, 21, 54, 49, 32, 16, 19, 24, 14, 9, 11, 6, 21…gun_Mass <- bind_rows(gun_control, Mass_shootings_in_the_United_States) Mass_shootings_in_the_United_States |>
ggplot(aes(x = date, y = views)) +
geom_line()
gun_control |>
ggplot(aes(x = date, y = views)) +
geom_line()
gun_Mass |>
ggplot(aes(x = date, y = views, color = article)) +
geom_line()
gun_Mass |>
pivot_wider(names_from = article, values_from = views) |>
ggplot(aes(x = Mass_shootings_in_the_United_States, y = Gun_control)) + # create scatterplot
geom_point() +
geom_smooth(method = lm) + # create regression line
labs(x = "Views of the Wikipedia Mass shootings in the United States article",
y = "Views of the Wikipedia Gun control article",
title = "Relationship between Wikipedia article views")`geom_smooth()` using formula = 'y ~ x'Warning: Removed 2 rows containing non-finite values (`stat_smooth()`).Warning: Removed 2 rows containing missing values (`geom_point()`).
topLV |>
select(article, views) |>
filter(!article == "Main_Page", !article == "Special:Search") |>
slice_max(views, n = 10) |>
datatable()topLV |>
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 = "blue") +
coord_flip() +
scale_y_continuous(labels = scales::comma) +
labs(y = "Number of Views",
x = "Article",
title = "Top Wikipedia articles, Oct. 2, 2017")
topM |>
select(article, views) |>
filter(!article == "Main_Page", !article == "Special:Search") |>
slice_max(views, n = 10) |>
datatable()topM |>
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 = "blue") +
coord_flip() +
scale_y_continuous(labels = scales::comma) +
labs(y = "Number of Views",
x = "Article",
title = "Top Wikipedia articles, Apl. 19, 2017")
Las_Vegas_shooting <- article_pageviews(article = "Gun_control",
start = as.Date("2017-9-17"),
end = as.Date("2017-10-15"))Las_Vegas_shooting <- Las_Vegas_shooting |>
mutate(day = -14:14) |>
mutate(event = "Las Vegas shooting")Las_Vegas_shooting |>
ggplot(aes(x = day, y = views)) +
geom_line()
Fresno_shootings <- article_pageviews(article = "Gun_control",
start = as.Date("2017-4-4"),
end = as.Date("2017-5-2"))
Fresno_shootings <- Fresno_shootings |>
mutate(day = -14:14) |>
mutate(event = "Fresno shootings")
Fresno_shootings |>
ggplot(aes(x = day, y = views)) +
geom_line()
shootings <- bind_rows(Las_Vegas_shooting, Fresno_shootings)
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")
shootings |>
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 3.84 27.6 0.000651 two.sided 778. 363. 1193.shootings |>
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 459. 119. 30
2 TRUE 1237. 1065. 28The average number of views of the Wikipedia Gun Control article in the 7 days prior to the two shootings (M = 458.7, SD = 118.57) was statistically significant and different from the average number of views in the 7 days after the shooting (M = 1236.7, SD = 1065.25), t(27.6) = 3.84, p < .001.