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

Article LinkedIn: https://www.linkedin.com/pulse/paper-research-petroleum-engineering-do-you-know-how-spell-reyes/

We try the same technique with "gas lift temperature"

library(petro.One)

# provide the list of keywords
keywords <- "    
    gas lift
    gas-lift
    GasLift
    gas-lifted
    gas lifted
    lift gas
    lift-gas
    gas.lift
    gas_lift"
# convert the text to a dataframe
# read text table and split rows at carriage return
kw_tbl <- read.table(text = keywords, header = FALSE, sep = "\n", 
                     stringsAsFactors = FALSE, strip.white = TRUE, 
                     col.names = "keyword")
kw_tbl

Build iteration loop

# iterate through the keywords dataframe
rec <- vector("list")
i <- 1
for (k in kw_tbl$keyword) {
    url_all  <- make_search_url(query = k, how = "all")    # create search query
    count    <- get_papers_count(url_all)                  # paper count
    rec[[i]] <- list(keyword = k, count = count)           # add observation
    cat(sprintf("%30s %5d \n", k, count))                  # print it
    i <-  i + 1                                            # increment counter
    Sys.sleep(5)                          # do not bug OnePetro website too much
}                                         # be a good internet citizen
data.table::rbindlist(rec)                # final data table

using join_keywords

major <- c("gas lift", "gas-lift", "GasLift", "gas-lifted", "gas lifted", 
           "lift gas", "lift-gas", "gas.lift", "gas_lift")
gas_lift <- join_keywords(major, 
                                   get_papers = TRUE, sleep = 3, verbose = TRUE)

# "gas lift" is the same as "gas-lift"

library(rNodal.utils)
save_to_project(gas_lift, name = "gas_lift_L1")

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