data <- data.frame(org_name = c("PRESUMPTIVELY Streptococcus",
"MODERATE Escherichia coli",
"S. AUREUS POSITIVE",
"CANCELLED Influenza A"))
data <- cleanse_urine_organism_names(data,
column_name = "org_name",
strings_to_remove = c("POSITIVE FOR",
"PRESUMPTIVELY","PRESUMPTIVE",
"PROBABLE", "IDENTIFICATION",
"RESEMBLING", "SEEN",
"MODERATE", "FEW", "BETA",
"METHICILLIN RESISTANT",
"NUTRITIONALLY VARIANT",
"NOT C. PERFRINGENS OR C. SEPTICUM",
"-LACTAMASE POSITIVE",
"-LACTAMASE NEGATIVE",
"VIRAL ANTIGEN",
"CANDIDA INCONSPICUA",
"/POSADASII",
"NOT FUMIGATUS, FLAVUS OR NIGER",
"MRSA POSITIVE", "MRSA NEGATIVE",
"HISTOLYTICA/DISPAR"),
standard_mapping = c(
"NON-FERMENTER" = "STREPTOCOCCUS",
"ABIOTROPHIA/GRANULICATELLA" =
"STREPTOCOCCUS",
"S. AUREUS POSITIVE" =
"STAPHYLOCOCCUS AUREUS",
"ASPERGILLUS FUMIGATUS COMPLEX" =
"ASPERGILLUS FUMIGATUS",
"(CRYPTOSPORIDIUM PARVUM OOCYSTS|
CUNNINGHAMELLA BERTHOLLETIAE|
EPIDERMOPHYTON FLOCCOSUM|
EXOPHIALA JEANSELMEI COMPLEX|
SCEDOSPORIUM|
NEOASCOCHYTA DESMAZIERI|
NEOSCYTALIDIUM DIMIDIATUM|
LOMENTOSPORA|NEUROSPORA|
PERONEUTYPA SCOPARIA|
SPOROTHRIX SCHENCKII COMPLEX|
ZYGOSACCHAROMYCES FERMENTATI)" =
"UNKNOWN FUNGUS"
),
filter_values = c('CANCELLED|VIRUS|SIMPLEX|PARAINFLUENZA|
INFLUENZA A|INFLUENZA B|TICK|
AFB GROWN|GRAM VARIABLE RODS|HYMENOLEPIS'))
Run the code above in your browser using DataLab