This report is automatically generated with the R
package knitr
(version 1.40
)
.
source("R Functions/functions_QA data.R") ### LOAD DATA ### #FIND AND REPLACE (Ctrl+F) 'WORKSHEET' WITH MORE APPROPRIATE NAME (e.g., 'CALFED_data') #CHANGE 'FILENAME' & 'SHEETNAME' WITH ACTUAL NAMES USGSFISH <- readxl::read_excel('Reeval_Impl_Goals_Linkage_Analysis/Data/Fish/USGSFISH.xlsx', sheet='Sheet1', guess_max = 30000) nrow(USGSFISH) #number of rows should match the Excel file (minus the header row)
## [1] 507
### LIST COLUMNS TO BE USED, ADD USER DEFINED COLUMNS, & RENAME COLUMNS TO CEDEN STANDARDS ### #Use 1.READ ME.xlsx, 'ColumnsForR' to list & identify columns that match corresponding CEDEN Standard columns keep_cols <- c('SourceID','SourceRow', 'CitationCode (PUB ID)', 'ProgramName','ParentProjectName','ProjectCode','StationName','StationCode','TargetLatitude','TargetLongitude','SampleDate','CommonName','FinalID','NumberFishPerComp','Analyte','Unit','Result','ResQualCode','MDL','RL','WeightAvg g','TLMin mm','TLMax mm','TLAvgLength mm','SampleID','WBT','ProjectName (report title)','CollectionTime','TissueName (only filet or whole)','MethodName' ) #temp_cols <- c('') #Include columns that do not match CEDEN standards but may be useful (e.g., Unit columns for MDL & RL) #temp_cols are removed before the data is merged with other datasets USGSFISH_new <- USGSFISH %>% select( c(keep_cols) ) %>% #DO NOT CHANGE - selects columns specified above rename( #Rename USGSFISH columns to CEDEN format here: CEDEN 'COLUMNNAME' = USGSFISH 'COLUMNNAME' #DELETE COLUMN NAMES THAT DO NOT HAVE AN EQUIVALENT COLUMN IN THE USGSFISH 'ProjectName' = 'ProjectName (report title)', 'ResultQualCode' = 'ResQualCode', 'TaxonomicName' = 'FinalID', 'SampleTime' = 'CollectionTime', 'TissueName' = 'TissueName (only filet or whole)', 'Method' = 'MethodName', 'CitationCode' = 'CitationCode (PUB ID)' ) %>% mutate( #Create Missing column or modify existing column here: CEDEN COLUMNNAME = 'SPECIFIED VALUE' or FUNCTION #DELTE COLUMN NAMES THAT DO NOT NEED TO BE CHANGED CoordSystem = NA_character_, CompositeRowID = NA_character_, BatchVerification = NA_character_, ComplianceCode = NA_character_, CompositeID = NA_character_, LabSubmissionCode = NA_character_, QACode = NA_character_, ResultComments = NA_character_ ) nrow(USGSFISH_new)
## [1] 507
#str(USGSFISH_new) #just to check data class of different columns - e.g., is Date column in POSIX format? #View(USGSFISH_new) ### FORMAT COLUMN PARAMETERS ### # Standardize WBT (WaterBodyType) Groups - "River/Stream", "Estuary", "Drain/Canal", "Wetland", "Spring", "Slough", # "Pond", "Lake/Reservoir", "Delta", "Forebay/Afterbay", "Not Recorded" # unique(USGSFISH_new$WBT) #Identifies OLDNAMES
## [1] "River" "Creek" "Drain/Canal" "Slough" "Gulch" "Pond" ## [7] "Lake"
#STANDARD CODE TO CHANGE GROUPING NAMES USGSFISH_new <- USGSFISH_new %>% mutate(WBT = recode(WBT, "River" = "River/Stream", "Creek" = "River/Stream", "Gulch" = "River/Stream", "Lake" = "Lake/Reservoir"), #EXAMPLE FOR WHEN "OLDNAME" is 'NA' but we want a NEWNAME - if this example is deleted, also delete the comma after "Not Recorded" above WBT = case_when(is.na(WBT) ~ "Not Recorded", #Use "Not Recorded" when WBT value is NA TRUE ~ WBT) #Keep original WBT value in all other cases ) %>% filter(WBT %are not% c("Lake/Reservoir", "Pond")) #checked and made sure no ponds or lakes where part of a river or the delta unique(USGSFISH_new$WBT) #New naming structure for WBT Groupings
## [1] "River/Stream" "Drain/Canal" "Slough"
# Standardize TissueName Groups - "Fillet" or "Whole Body" # unique(USGSFISH_new$TissueName)
## [1] "Whole fish" "Liver" "Soft tissue" "Fillet" "Whole body"
USGSFISH_new <- USGSFISH_new %>% mutate(TissueName = recode(TissueName, "Whole fish" = "Whole Body", "Whole body" = "Whole Body" ) ) %>% filter(TissueName %in% c('Fillet','Whole Body')) unique(USGSFISH_new$TissueName)
## [1] "Whole Body" "Fillet"
# Standardize Analyte Groups - "Mercury, Total" (we consider Total Mercury and Methylmercury to be approx equal) # unique(USGSFISH_new$Analyte)
## [1] "Mercury, Total" "Monomethylmercury, Total"
USGSFISH_new <- USGSFISH_new %>% mutate( Analyte = recode(Analyte, "Monomethylmercury, Total" = "Mercury, Total" ) ) #Create 'Analyte' column from Analyte & Analyte_part2 columns - then delete Analyte_part2 column## unique(USGSFISH_new$Analyte) #New naming structure for Analyte Groupings
## [1] "Mercury, Total"
# Standardize ResultQualCode Groups - "ND", "DNQ", NA# unique(USGSFISH_new$ResultQualCode) #Identifies OLDNAMES
## [1] NA "="
#Lauren to fix error: attempt to use zero-length variable name - maybe not needed #USGSFISH_new <- USGSFISH_new %>% # mutate(ResultQualCode = recode(ResultQualCode, # "" = NA_character_ #changes empty cells to NA - delete if not needed # )) unique(USGSFISH_new$ResultQualCode) #New naming structure for ResultQualCode Groupings
## [1] NA "="
# Format Result Column to Numeric# # Check column for text - based on text user needs to decide what to do if(!is.numeric(USGSFISH_new$Result)){ old <-USGSFISH_new$Result new <-USGSFISH_new$Result new[grepl('<|[a-df-zA-DF-Z]', new)] <- NA #skip 'e' for exponential notation e.g., "8e-005" cat(paste0("'Result' column should be numeric but some cells contain ", grammaticList(setdiff(old, new)),"\n", ".\nACTIONS TAKEN:\n", "For numeric values with '<': 'ND' put in ResultQualCode column, numeric value moved to MDL column, & made Result blank.\n", "For NA's: 'ND' put in ResultQualCode column, MDL column value converted to mg/Kg, & made Result blank.\n\n")) USGSFISH_new <- USGSFISH_new %>% mutate( # Fixing numeric Result with '<'s MDL = if_else(grepl('<',Result), '.1', MDL), # Only Results with '<' are '<0.1' MDL = if_else(grepl('NA',Result), '.00026', MDL), # Only Results with NA's have MDL of 0.26 ng/g, so need to divide by 1000 to convert to mg/Kg ResultQualCode = if_else(grepl('<|NA',Result), 'ND', ResultQualCode), Result = if_else(grepl('<|NA',Result), NA_character_, Result), Result = as.numeric(Result) ) } else { cat("'Result' column is in numeric format\n")}
## 'Result' column should be numeric but some cells contain <.1 and NA ## . ## ACTIONS TAKEN: ## For numeric values with '<': 'ND' put in ResultQualCode column, numeric value moved to MDL column, & made Result blank. ## For NA's: 'ND' put in ResultQualCode column, MDL column value converted to mg/Kg, & made Result blank.
# Format MDL Column to Numeric# # Check column for text - based on text user needs to decide what to do if(!is.numeric(USGSFISH_new$MDL)){ old <-USGSFISH_new$MDL new <- USGSFISH_new$MDL new[grepl('[a-df-zA-DF-Z]', new)] <- NA #skip 'e' for exponential notation e.g., "8e-005" #Print what text was found and what is being done cat(paste0("'MDL' column should be numeric but some cells contain ", grammaticList(setdiff(old, new)), ".\nACTIONS TAKEN:\n", "The 'ng/g' text dropped and value converted to mg/Kg.\n\n")) USGSFISH_new <- USGSFISH_new %>% mutate( #Do stuff to prep column to be converted to Numeric MDL = as.character(as.numeric(gsub(' ng/g','',MDL))/1000), #drop the ng/g unit, convert to number to convert value to mg/Kg, convert back to character to match column class MDL = as.numeric(new) ) } else { cat("'MDL' column is in numeric format\n")}
## 'MDL' column should be numeric but some cells contain 1.33 ng/g, 1.5 ng/g, 0.26 ng/g, and 0.07 ng/g. ## ACTIONS TAKEN: ## The 'ng/g' text dropped and value converted to mg/Kg.
# Format RL Column to Numeric# # Check column for text - based on text user needs to decide what to do if(!is.numeric(USGSFISH_new$RL)){ if(all(is.na(USGSFISH_new$RL))){ USGSFISH_new <- USGSFISH_new %>% mutate( #Due stuff to prep column to be converted to Numeric RL = as.numeric(new) ) cat("'RL' column is all blanks and was converted to numeric format\n") }else{ old <-USGSFISH_new$RL new <-USGSFISH_new$RL new[grepl('[a-df-zA-DF-Z]', new)] <- NA #skip 'e' for exponential notation e.g., "8e-005" #Print what text was found and what is being done cat(paste0("'RL' column should be numeric but some cells contain ", grammaticList(setdiff(old, new)), ".\nACTIONS TAKEN:\n", "~explain here~.\n")) } }else{ cat("'RL' column is in numeric format\n")}
## 'RL' column is all blanks and was converted to numeric format
# Check if Result, MDL, & RL Columns all equal <NA> or 0 - these rows have no useful information nrow(USGSFISH_new) #Number rows before
## [1] 381
#CODE BELOW REQUIRES USER TROUBLESHOOTING DEPENDING ON AVAILABLE COLUMNS AND SPREADSHEET SPECIFIC CONDITIONS# USGSFISH_new <- USGSFISH_new %>% #Set 0 & negative values as blank mutate(Result = ifelse(Result <= 0, NA_real_, Result), MDL = ifelse(MDL <= 0, NA_real_, MDL), RL = ifelse(RL <= 0, NA_real_, RL)) na_results <- USGSFISH_new %>% #Record rows where Result, MDL, & RL all equal <NA> filter( is.na(Result) & is.na(MDL) & is.na(RL) ) #View(na_results) USGSFISH_new <- anti_join(USGSFISH_new, na_results, by='SourceRow') #returns rows from USGSFISH_new not matching values in no_result nrow(USGSFISH_new) #Number rows after
## [1] 381
# Format Units Column - "mg/Kg ww" or "mg/Kg dw" unique(USGSFISH_new$Unit) #Identifies OLDNAMES
## [1] "mg/kg" "mg/kg; ww"
# If more than 1 unit colmn exists (e.g., for RL and MDL columns) see WQP script for example on merging into 1 column USGSFISH_new <- USGSFISH_new %>% mutate(Unit = recode(Unit, "mg/kg; ww" = "mg/Kg ww", "mg/kg" = "mg/Kg") ) unique(USGSFISH_new$Unit) #New naming structure for Unit Groupings
## [1] "mg/Kg" "mg/Kg ww"
# Format Date and Time Column # - Lauren to fix issue with date. not showing up when time is a column; both don't merge date and time # THE EXAMPLE CODE BELOW ASSUMES DATE AND TIME ARE IN SAME COLUMNS - IF TIME IS IN SEPERATE COLUMN LOOK AT AQ LINKAGE DATA TEMPLATE USGSFISH_new <- USGSFISH_new %>% #rowise() %>% # rowise is very slow - so used sapply to make this a rowise operation mutate( #If SampleDate & CollectioTIme are not in Character format by defualt, turn it into a character class so it exports better SampleDate = ifelse(sapply(SampleDate, is.character), SampleDate, as.character(as.Date(SampleDate))), SampleTime = ifelse(sapply(SampleTime, is.character), SampleTime, format(lubridate::ymd_hms(SampleTime), "%H:%M:%S")), #COMBINE DATE AND TIME INTO SampleDateTime COLUMN SampleDateTime = ifelse(!is.na(SampleTime), paste(SampleDate, SampleTime), paste(SampleDate, '00:00:00')), #FORMAT SampleDateTime COLUMN TO DATE FORMAT SampleDateTime = lubridate::ymd_hms(SampleDateTime) ) ### REMOVE TEMPORARY COLUMNS ### #USGSFISH_new <- USGSFISH_new %>% # select(-one_of(temp_cols)) #Remove temp columns since they are no longer needed #View(USGSFISH_new) ## SAVE FORMATTED DATA AS EXCEL FILE ## writexl::write_xlsx(USGSFISH_new, path='Reeval_Impl_Goals_Linkage_Analysis/Data/Fish/USGSFISH_ceden_format.xlsx') # In excel, to convert SampleDate column to Date format # 1 - Select the date column. # 2 - Go to the Data-tab and choose "Text to Columns". # 3 - On the first screen, leave radio button on "delimited" and click Next. # 4 - Unselect any delimiter boxes (everything blank) and click Next. # 5 - Under column data format choose Date, select YMD # 6 - Click Finish.
The R session information (including the OS info, R version and all packages used):
sessionInfo()
## R version 4.2.2 (2022-10-31 ucrt) ## Platform: x86_64-w64-mingw32/x64 (64-bit) ## Running under: Windows 10 x64 (build 22621) ## ## Matrix products: default ## ## locale: ## [1] LC_COLLATE=English_United States.utf8 LC_CTYPE=English_United States.utf8 ## [3] LC_MONETARY=English_United States.utf8 LC_NUMERIC=C ## [5] LC_TIME=English_United States.utf8 ## ## attached base packages: ## [1] stats graphics grDevices utils datasets methods base ## ## other attached packages: ## [1] lubridate_1.8.0 plotly_4.10.0 readxl_1.4.1 actuar_3.3-0 ## [5] NADA_1.6-1.1 forcats_0.5.2 stringr_1.4.1 dplyr_1.0.9 ## [9] purrr_0.3.4 readr_2.1.2 tidyr_1.2.0 tibble_3.1.8 ## [13] ggplot2_3.3.6 tidyverse_1.3.2 fitdistrplus_1.1-8 survival_3.4-0 ## [17] MASS_7.3-58.1 ## ## loaded via a namespace (and not attached): ## [1] lattice_0.20-45 assertthat_0.2.1 digest_0.6.29 utf8_1.2.2 ## [5] R6_2.5.1 cellranger_1.1.0 backports_1.4.1 reprex_2.0.2 ## [9] evaluate_0.16 highr_0.9 httr_1.4.4 pillar_1.8.1 ## [13] rlang_1.0.5 lazyeval_0.2.2 googlesheets4_1.0.1 rstudioapi_0.14 ## [17] data.table_1.14.2 Matrix_1.5-1 splines_4.2.2 googledrive_2.0.0 ## [21] htmlwidgets_1.5.4 munsell_0.5.0 broom_1.0.1 compiler_4.2.2 ## [25] modelr_0.1.9 xfun_0.32 pkgconfig_2.0.3 htmltools_0.5.3 ## [29] tidyselect_1.1.2 fansi_1.0.3 viridisLite_0.4.1 crayon_1.5.1 ## [33] tzdb_0.3.0 dbplyr_2.2.1 withr_2.5.0 grid_4.2.2 ## [37] jsonlite_1.8.0 gtable_0.3.1 lifecycle_1.0.1 DBI_1.1.3 ## [41] magrittr_2.0.3 scales_1.2.1 writexl_1.4.0 cli_3.3.0 ## [45] stringi_1.7.8 fs_1.5.2 xml2_1.3.3 ellipsis_0.3.2 ## [49] generics_0.1.3 vctrs_0.4.1 expint_0.1-7 tools_4.2.2 ## [53] glue_1.6.2 hms_1.1.2 fastmap_1.1.0 colorspace_2.0-3 ## [57] gargle_1.2.0 rvest_1.0.3 knitr_1.40 haven_2.5.1
Sys.time()
## [1] "2024-01-05 11:25:14 PST"