In f0nzie/petro.One: Statistics and Text Mining for Oil and Gas Papers from OnePetro Metadata

library(petro.One)
library(dplyr)

major   <- c("PUNQ-S3")
minor   <- c("machine-learning", "machine learning")

search_result <- run_papers_search(major, minor, get_papers = TRUE , 
                                   verbose = TRUE, len_keywords = 4)

papers <- search_result$papers
papers

# no need of this because now is built in into the function run_papers_search()

# eliminate duplicates
# papers <- papers %>% 
#     distinct(paper_id, .keep_all = TRUE) %>% 
#     distinct(book_title, .keep_all = TRUE) %>%  
#     print

# 54 vs 26

papers %>% 
    group_by(year) %>%
    summarize(n  = n()) %>% 
    print

papers %>%
    filter(year == 2003)

what papers have machine learning in the title

papers %>%
    # machine learning OR machine-learning
    filter(grepl(pattern = "machine[-\\s]learning", 
                 x = book_title, ignore.case = TRUE, perl = TRUE))

what papers have PUNQ-S3 in the title

papers %>%
    # machine learning OR machine-learning
    filter(grepl(pattern = "PUNQ-S3", 
                 x = book_title, ignore.case = TRUE, perl = TRUE))

f0nzie/petro.One documentation built on May 29, 2019, 12:05 a.m.