The goal of this document is to describe how and why we created The Generality Widget and how we made it, focusing on:
- What data we used
- How we coded the data
- How we prepared the data
- How we analyzed the data
from facebook_scraper import get_posts | |
import pandas as pd | |
import time | |
import json | |
# param | |
n_pages_to_iterate = 100 # number of pages to scrape within one FB page | |
# reading data with page names | |
district_data = pd.read_csv("2020-2021-critical-race-posts-schools-districts.csv") |
from facebook_scraper import * | |
import pandas as pd | |
set_user_agent("Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)") | |
page = pd.DataFrame() | |
for post in get_posts('245937932251091/posts/2129192957258903', pages=10 ,options={"comments": True}, credentials = ("jrosenb8@utk.edu","025021")): | |
page = page.append(post, ignore_index = True) |
library(tidyverse) | |
library(googlesheets4) | |
# this is an example Google Sheet | |
d <- read_sheet("https://docs.google.com/spreadsheets/d/1kz2LlLgXkN_HaBEAiFETl59b09u9AwMIgrwQx6DCv8A/edit#gid=0", col_names = FALSE) | |
prep_otter_transcript <- function(d, length_less_than_100_min) { | |
d <- d %>% rename(x1 = 1) |
# apply for access to Twitter's academic program: https://developer.twitter.com/en/solutions/academic-research | |
library(academictwitteR) | |
library(rtweet) | |
library(tidytags) # must be installed first with: remotes::install_github("ropensci/tidytags") | |
bearer_token <- "xxx" # Insert bearer token from developer.twitter.com from the your academic account | |
trial <- get_all_tweets("#BAmazonUnion OR #UnionizeAmazon", "2020-01-01T00:00:00Z", "2021-05-01T00:00:00Z", bearer_token, data_path = NULL) |
library(tidyverse) | |
library(tidytuesdayR) | |
library(janitor) | |
tt_output <- tt_load_gh(last_tuesday()) | |
list_of_d <- tt_download(tt_output) | |
d <- list_of_d$animal_complaints | |
d %>% |
library(tidyverse) | |
library(readxl) | |
d <- read_excel("Downloads/Public-Dataset-Age.xlsx") | |
d %>% | |
mutate(month = lubridate::month(DATE, label = TRUE)) %>% | |
group_by(month, AGE_RANGE) %>% | |
summarize(total_cases = sum(NEW_ARCASES)) %>% | |
filter(AGE_RANGE != "Pending") %>% | |
mutate(total_cases_prop = total_cases / sum(total_cases)) %>% | |
ggplot(aes(y = total_cases_prop, x = AGE_RANGE, fill = as.factor(month))) + |
library(shiny) | |
ui <- fluidPage( | |
titlePanel("How Many Reviewers?"), | |
sidebarLayout( | |
sidebarPanel( | |
numericInput("n_papers", "Number of Anticipated Papers", 100), | |
numericInput("n_reviews", "Number of Reviews Per Paper", 3), |
library(shiny) | |
library(tidyverse) | |
d <- read_csv("https://raw.githubusercontent.com/nytimes/covid-19-data/master/us-counties.csv") | |
states <- d %>% | |
pull(state) %>% | |
unique() %>% | |
sort() |
# | |
# This is a Shiny web application. You can run the application by clicking | |
# the 'Run App' button above. | |
# | |
# Find out more about building applications with Shiny here: | |
# | |
# http://shiny.rstudio.com/ | |
# | |
library(shiny) |