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

# provide different set of keywords to combine as vectors
major  <- c("water injection", "water flooding")
minor  <- c("machine-learning", "intelligent")
lesser <- c("neural network", "SVM", "genetic", "algorithm")
df <- expand.grid(major, minor, lesser, stringsAsFactors = FALSE)
df

Function using algorithm that joins multiple composite keywords

library(petro.One)

#' @param ...     input character vectors
#' @param bool_op boolean operator. It can be AND or OR
join_keywords <- function(..., bool_op = "AND", sleep = 3) {
    rec <- vector("list")
    ##sleep <- 3
    # works for "n" columns or "n" keyword character vectors
    df <- expand.grid(..., stringsAsFactors = FALSE)   # combine keywords
    sep     <- paste0("'", bool_op, "'")               # add apostrophes to operator
    # iterate through the rows of keyword combinations dataframe
    for (i in 1:nrow(df)) {
        sf <- NULL
        # iterate through columns of keywords
        for (j in 1:ncol(df)) {
            s     <- unlist(strsplit(df[i, j], " "))   # split keyword if space
            splus <- paste(s, collapse = "+")          # join keywords with + sign
            if (!is.null(sf)) {                        
                sf <- paste(sf, splus, sep = sep)      # if not the 1st keyword add AND
            } else {                                   # else
                sf <- paste0("'", sf, splus)           # just join 1st with next kword
            }
        }
        sf <- paste0(sf, "'")                          # close with apostrophe
        url <- make_search_url(sf, how = "all")        # search in OnePetro
        paper_count <- get_papers_count(url)           # paper count
        cat(sprintf("%3d %5d %60s \n", i, paper_count, sf)) 

        # build a record of results
        rec[[i]] <- list(paper_count = paper_count, sf  = sf, url = url)
        Sys.sleep(sleep)                    # give OnePetro a break
    } 
    rec.df <- data.table::rbindlist(rec)    # convert list to dataframe
    df <- cbind(df, rec.df)                 # join the results
    invisible(df)
}

test #1

#paper_count_from_vectors <- function() {}

# provide two different set of keywords to combine as vectors
major  <- c("water injection", "water flooding")
minor  <- c("machine-learning", "intelligent")
lesser <- c("neural network", "SVM", "genetic", "algorithm")

# join_keywords(major, minor, lesser)
# p.df <- join_keywords(major, minor)
p.df <- join_keywords(major, minor, lesser)
p.df

test #2

# provide two different set of keywords to combine as vectors
m  <- c("water injection", "water flooding")
n  <- c("machine-learning", "machine learning", "intelligent")
p  <- c("neural network", "SVM", "genetic")
q  <- c("algorithm")

p.df <- join_keywords(m, n, p, q)
p.df

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