Created
May 21, 2020 19:32
-
-
Save erdavis1/e4d24c8acf736ccb6fbf96272937a096 to your computer and use it in GitHub Desktop.
Process all books code outline
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| library(reticulate) | |
| library(cleanNLP) | |
| library(dplyr) | |
| library(stringr) | |
| library(tidyr) | |
| library(textstem) | |
| setwd("C:/Users/Erin/Documents/DataViz/Adjectives/") | |
| options(stringsAsFactors = FALSE) | |
| #-----spaCy | |
| use_python("C:/Users/Erin/Anaconda3") | |
| cnlp_init_spacy() | |
| #---get basic data | |
| body <- read.csv("./Data/bodyparts.csv") | |
| files <- read.csv('PotentialBooks.csv') | |
| lim <- 900000 | |
| final <- NULL | |
| for (i in 1:nrow(files)) { | |
| mastertext <- readLines(files$Link[i]) %>% paste(collapse = " ") #readLines('test.txt') %>% paste(collapse = " ") #t | |
| #---spacy can only process 900k characters at once, or thereabouts | |
| loops <- ceiling(nchar(mastertext)/lim) | |
| for (j in 1:loops) { | |
| #body <- read.csv("./Data/bodyparts.csv") | |
| text <- substr(mastertext, (j-1)*lim+1, j*lim) #readLines('felurian.txt') %>% paste(collapse = " ") # | |
| #------annotate. this will take a bit | |
| obj <- cnlp_annotate(text) | |
| #----------extract body parts | |
| <BODY PART EXTRACTION CODE HERE> | |
| #----------bind in results to final dataframe | |
| book_results <- bind_rows(simpleposs, hadadj) %>% bind_rows(poss) %>% unique() | |
| book_results$id <- files$ID[i] | |
| final <- bind_rows(final, book_results) | |
| } | |
| } | |
| <SKEW CALCULATIONS PROCEED AS NORMAL HERE> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment