Merge pull request #5 from nrosed/main

pipeline QC markdown analysis added

.gitignore

@@ -7,3 +7,4 @@
 .DS_Store
 .Rhistory
 .Rproj.user
+*.Rproj

analysis_scripts/analyze_quote_data/location-analysis_all_years.Rmd

@@ -0,0 +1,31 @@
+---
+title: "location_analysis"
+author: "Natalie Davidson"
+date: "1/22/2021"
+output: github_document
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+
+require(data.table)
+require(here)
+require(ggplot2)
+require(caret)
+
+proj_dir = here()
+source(paste(proj_dir, "/analysis_scripts/analysis_utils.R", sep=""))
+source(paste(proj_dir, "/utils/plotting_utils.R", sep=""))
+```
+
+## Nature News Location Bias
+
+This document is a working analysis of the quotes extracted from Nature News content to see if there are differences in gender representation.
+The data we will be working with are the following:
+
+1) `./data/benchmark_data/benchmark_quote_table_raw.tsv` is the output after scraping a randomly selected set of 10 articles from 2010, 2015, or 2020 (`./nature_news_scraper/run_scrape_benchmark.sh`) then running it through coreNLP with additional processing (`./process_scraped_data/run_process_target_year.sh`)
+2) `./data/scraped_data/quote_table_raw_20*.tsv` are the output after scraping all articles from a year between 2001 2020 (`./nature_news_scraper/run_scrape_benchmark.sh`) then running it through coreNLP with additional processing (`./process_scraped_data/run_process_target_year.sh`)
+
+
+**All analysis shown below depends on the functions described in `/analysis_scripts/analysis_utils.R`**
+